You searched for +publisher:"University of Southern California" +contributor:("Sukhatme, Gaurav S.").
Showing records 1 – 30 of
60 total matches.
◁ [1] [2] ▶
University of Southern California
1.
Koenig, Nathan.
Robot life-long task learning from human demonstrations: a
Bayesian approach.
Degree: PhD, Computer Science (Robotics and Automation), 2013, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222240/rec/5604 
► Programming a robot to act intelligently is a challenging endeavor that is beyond the skill level of most people. Trained roboticists generally program robots for…
(more)
▼ Programming a robot to act intelligently is a
challenging endeavor that is beyond the skill level of most people.
Trained roboticists generally program robots for a single purpose.
Enabling robots to be programmed by non-experts and to perform
multiple tasks are both open challenges in robotics. The
contributions of this work include a framework that allows a robot
to learn tasks from demonstrations over the course of its
functional lifetime, a task representation that uses Bayesian
decision networks, and a method to transfer knowledge between
similar tasks. The demonstration framework allows non-experts to
demonstrate tasks to the robot in an intuitive manner. ❧ In this
work, tasks are complex time-extended decision processes that make
use of a set of predefined basis behaviors for actuator control.
Demonstrations from an instructor provide the necessary information
for the robot to learn a control policy. An instructor guides the
robot through a demonstration using a graphical interface that
displays information from the robot and provides an intuitive
action-object pairing mechanism to issue commands to the robot. ❧
Each task is represented by an influence diagram, a generalization
of Bayesian networks. The networks are human readable, compact, and
have a simple refinement process. They are not subject to an
exponential growth in states or in branches, and can be combined
hierarchically, allowing for complex task models. Data from task
demonstrations are used to learn the structure and utility
functions of an influence diagram. A score-based learning algorithm
is used to search through potential networks in order to find an
optimal structure. ❧ Both the means by which demonstrations are
provided to the robot and the learned tasks are validated.
Different communication modalities and environmental factors are
analyzed in a set of user studies. The studies feature both
engineer and non-engineer users instructing the Willow Garage PR2
on four tasks: Tower'
s of Hanoi, box sorting, cooking risotto, and
table setting. The results validate that the approach enables the
robot to learn complex tasks from a variety of teachers, refining
those tasks during on-line performance, successfully completing the
tasks in different environments, and transferring knowledge from
one task to another.
Advisors/Committee Members: Mataric, Maja J. (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Jain, Rahul (Committee Member).
Subjects/Keywords: robotics; life-long learning; influence diagrams; bayesian networks; teaching; learning from demonstration
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Koenig, N. (2013). Robot life-long task learning from human demonstrations: a
Bayesian approach. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222240/rec/5604
Chicago Manual of Style (16th Edition):
Koenig, Nathan. “Robot life-long task learning from human demonstrations: a
Bayesian approach.” 2013. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222240/rec/5604.
MLA Handbook (7th Edition):
Koenig, Nathan. “Robot life-long task learning from human demonstrations: a
Bayesian approach.” 2013. Web. 21 Feb 2020.
Vancouver:
Koenig N. Robot life-long task learning from human demonstrations: a
Bayesian approach. [Internet] [Doctoral dissertation]. University of Southern California; 2013. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222240/rec/5604.
Council of Science Editors:
Koenig N. Robot life-long task learning from human demonstrations: a
Bayesian approach. [Doctoral Dissertation]. University of Southern California; 2013. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222240/rec/5604
University of Southern California
2.
Wang, Yi.
Towards energy efficient mobile sensing.
Degree: PhD, Electrical Engineering, 2011, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/445526/rec/7526
► Mobile device based urban sensing, participatory sensing, and user activity recognition can provide rich contextual information for mobile applications such as social networking and location…
(more)
▼ Mobile device based urban sensing, participatory
sensing, and user activity recognition can provide rich contextual
information for mobile applications such as social networking and
location based services. However, as the sensors on mobile devices
consume significant amount of energy, the major bottleneck that
restricts the continuous functioning of these mobile applications
is the limited battery capacity on mobile devices.; In this thesis,
we first present a novel design framework for an Energy Efficient
Mobile Sensing System (EEMSS). EEMSS uses hierarchical sensor
management strategy to recognize user states as well as to detect
state transitions. By powering only a minimum set of sensors and
managing sensors hierarchically, EEMSS significantly improves
device battery life. We present the design, implementation, and
evaluation of EEMSS that automatically recognizes a set of users'
daily activities in real time using sensors on an off-the-shelf
high-end smart phone. Evaluation of EEMSS with 10 users over one
week shows that our approach increases the device battery life by
more than 75% while maintaining both high accuracy and low latency
in identifying transitions between end-user activities.; We then
propose a computationally efficient algorithm to obtain the optimal
sensor sampling policy under the assumption that the user state
transition is Markovian. This Markov-optimal policy minimizes user
state estimation error while satisfying a given energy consumption
budget. The Markov-optimal policy is compared to uniform periodic
sensing and performance improvement is obtained on both simulated
and real user state traces, with approximately 20% average gain on
empirically collected user data that pertains to user motion,
inter-user contact status, and network connectivity.; Finally, we
formulate the user state sensing problem as the intermittent
sampling of a semi-Markov process, a model that provides more
general and flexible capturing of realistic data. We propose (a) a
semi-Markovian state estimation mechanism that selects the most
likely user state while observations are missing, and (b) a
semi-Markov optimal sensing policy which minimizes the expected
state estimation error while maintaining a given energy budget.
Their performance is shown to significantly outperform Markovian
algorithms on simulated two-state processes and real user state
traces. In addition, we propose a novel client-server based energy
efficient mobile sensing system architecture that automatically
learns user dynamics and computes user-specific optimal sensing
policy for mobile devices. A system prototype aiming to recognize
basic human activity is implemented on Nokia N95 smartphones and
desktop computers. We demonstrate the performance benchmark of the
semi-Markov optimal policy through a set of experiments, and show
that it improves the estimation accuracy by 27.8% and 48.6% over
Markov-optimal policy and uniform sampling,
respectively.
Advisors/Committee Members: Krishnamachari, Bhaskar (Committee Chair), Annavaram, Murali (Committee Member), Sukhatme, Gaurav S. (Committee Member).
Subjects/Keywords: constrained stochastic optimization; energy efficiency; mobile sensing; state estimation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wang, Y. (2011). Towards energy efficient mobile sensing. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/445526/rec/7526
Chicago Manual of Style (16th Edition):
Wang, Yi. “Towards energy efficient mobile sensing.” 2011. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/445526/rec/7526.
MLA Handbook (7th Edition):
Wang, Yi. “Towards energy efficient mobile sensing.” 2011. Web. 21 Feb 2020.
Vancouver:
Wang Y. Towards energy efficient mobile sensing. [Internet] [Doctoral dissertation]. University of Southern California; 2011. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/445526/rec/7526.
Council of Science Editors:
Wang Y. Towards energy efficient mobile sensing. [Doctoral Dissertation]. University of Southern California; 2011. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/445526/rec/7526
University of Southern California
3.
Gong, Boqing.
Kernel methods for unsupervised domain adaptation.
Degree: PhD, Computer Science, 2015, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/604358/rec/3702
► In many applications (computer vision, natural language processing, speech recognition, etc.), the curse of domain mismatch arises when the test data (of a target domain)…
(more)
▼ In many applications (computer vision, natural
language processing, speech recognition, etc.), the curse of domain
mismatch arises when the test data (of a target domain) and the
training data (of some source domain(
s)) come from different
distributions. Thus, developing techniques for domain adaptation,
i.e., generalizing models from the sources to the target, has been
a pressing need. When the learner has access to only unlabeled data
from the target domain (and labeled data from the source domain),
the problem is called unsupervised domain adaptation. Advances in
domain adaptation can significantly increase our capability to
deploy autonomous and intelligent systems in challenging
environments where uncertainty prevails. ❧ This thesis work
provides a comprehensive set of techniques with multiple levels of
focus on unsupervised domain adaptation, including learning
domain‐invariant feature representations in order to eliminate the
discrepancy between the source domain and the target domain,
manipulating data instances to match the distributions of two
domains, quantizing the ""adaptabilities"" of different source
domains given a particular target domain, and discovering latent
domains from heterogeneous data so the individual domains can be
better and more efficiently modeled. We demonstrate the
effectiveness of the developed methods on well‐benchmarked datasets
and tasks (visual object recognition, sentiment analysis, and
cross‐view human activity recognition). ❧ In terms of domain
adaptation algorithms, this thesis develops two complementary
approaches using kernel methods, one to infer domain‐invariant
geodesic flow kernels (GFKs) and the other to directly match the
underlying distributions of two domains. GFK models data by
subspaces and interpolates an infinite number of phantom domains
between the source domain and the target domain. We then use the
""kernel trick"" to average out domain‐specific idiosyncrasies and
arrive at a domain‐invariant kernel. Built upon GFK, we propose an
approach to identifying the most adaptable data instances of the
source domain, named as landmarks, to the target domain. Due to
that the landmarks are more similar to the target domain in the
sense of their underlying distributions, adapting from the
landmarks gives rise to better performance on the target than
adapting from the original source domain. ❧ This thesis also
contributes to other aspects of domain adaptation. We make some
preliminary efforts on answering the open question of how to
evaluate the ""adaptability"" of a source domain to the target
domain. This results in a rank‐of‐domains (ROD) metric, which
exploits both geometrical and statistical discrepancies between two
domains. Besides, this thesis raises the concern about how to
define or represent a domain with real data. While by a domain we
refer to the underlying distribution of the observed data, the
distribution is often unknown. A standard practice has been
equating datasets with domains. However, our studies show that this
is not necessarily the best for the…
Advisors/Committee Members: Sha, Fei (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Narayanan, Shrikanth S. (Committee Member).
Subjects/Keywords: kernel methods; domain adaptation; geodesic flow kernel; landmarks; rank of domains; latent domains; sequential determinantal point process
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Gong, B. (2015). Kernel methods for unsupervised domain adaptation. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/604358/rec/3702
Chicago Manual of Style (16th Edition):
Gong, Boqing. “Kernel methods for unsupervised domain adaptation.” 2015. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/604358/rec/3702.
MLA Handbook (7th Edition):
Gong, Boqing. “Kernel methods for unsupervised domain adaptation.” 2015. Web. 21 Feb 2020.
Vancouver:
Gong B. Kernel methods for unsupervised domain adaptation. [Internet] [Doctoral dissertation]. University of Southern California; 2015. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/604358/rec/3702.
Council of Science Editors:
Gong B. Kernel methods for unsupervised domain adaptation. [Doctoral Dissertation]. University of Southern California; 2015. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/604358/rec/3702
University of Southern California
4.
Pattem, Sundeep.
Joint routing and compression in sensor networks: from
theory to practice.
Degree: PhD, Electrical Engineering, 2010, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/382429/rec/3689
► In-network compression is essential for extending the lifetime of data gathering sensor networks. To be really effective, in addition to the computations, the configuration required…
(more)
▼ In-network compression is essential for extending the
lifetime of data gathering sensor networks. To be really effective,
in addition to the computations, the configuration required for
such compression must also be achieved in a distributed manner. The
thesis of this dissertation is that it is possible to demonstrate
completely distributed in-network compression in sensor networks.
Establishing this thesis requires studying several aspects of joint
routing and compression.; First, our analysis of the impact of
spatial correlations on optimal routing shows that there exist
correlation-independent schemes for routing that are near-optimal.
This implies that static routing schemes may perform as well as
sophisticated ones based on learning correlations. Next, we develop
novel and practical algorithms for distributed compression that
take into account the routing structure over which data is
transported. Finally, we argue that lack of work on (a) distributed
configuration for compression operations and (b) reusable software
development, is the primary reason why compression has not been
widely adopted in sensor network deployments. Our solution to
address this gap is SenZip, an architectural view of compression as
a service that interacts with standard networking services. A
system implementation based on SenZip and results from experiments
concretely demonstrate distributed and self-organizing in-network
compression.
Advisors/Committee Members: Krishnamachari, Bhaskar (Committee Chair), Ortega, Antonio (Committee Member), Sukhatme, Gaurav S. (Committee Member).
Subjects/Keywords: distributed compression; distributed transforms; optimal routing; sensor networks; SenZip architecture
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Pattem, S. (2010). Joint routing and compression in sensor networks: from
theory to practice. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/382429/rec/3689
Chicago Manual of Style (16th Edition):
Pattem, Sundeep. “Joint routing and compression in sensor networks: from
theory to practice.” 2010. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/382429/rec/3689.
MLA Handbook (7th Edition):
Pattem, Sundeep. “Joint routing and compression in sensor networks: from
theory to practice.” 2010. Web. 21 Feb 2020.
Vancouver:
Pattem S. Joint routing and compression in sensor networks: from
theory to practice. [Internet] [Doctoral dissertation]. University of Southern California; 2010. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/382429/rec/3689.
Council of Science Editors:
Pattem S. Joint routing and compression in sensor networks: from
theory to practice. [Doctoral Dissertation]. University of Southern California; 2010. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/382429/rec/3689
University of Southern California
5.
Johnson, Daniel M.
The wavelet filter: a new method for nonlinear, nongaussian
filtering in one dimension.
Degree: MS, Computer Science, 2009, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/172277/rec/7398
► While classical orthogonal function systems (COFS) are very successful at approximating static functions, there are several problems with using them in multi-stage estimation. These problems…
(more)
▼ While classical orthogonal function systems (COFS) are
very successful at approximating static functions, there are
several problems with using them in multi-stage estimation. These
problems are adapting location and scale parameters between time
steps, preserving positivity in the PDF approximation, determining
the initial values of the decomposition coefficients, propagating
the coefficients through general nonlinear functions, and
propagating the coefficients through the multiplications required
for application of Bayes'
s rule. Orthogonal wavelets, particularly
Meyer-type wavelets, have several attractive properties missing
from COFS. We show how wavelets avoid each of the problems
encountered with COFS in nonlinear filtering.
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Schaal, Stefan (Committee Member), Krishnamachari, Bhaskar (Committee Member).
Subjects/Keywords: nonlinear estimation; nonlinear filtering; wavelets
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Johnson, D. M. (2009). The wavelet filter: a new method for nonlinear, nongaussian
filtering in one dimension. (Masters Thesis). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/172277/rec/7398
Chicago Manual of Style (16th Edition):
Johnson, Daniel M. “The wavelet filter: a new method for nonlinear, nongaussian
filtering in one dimension.” 2009. Masters Thesis, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/172277/rec/7398.
MLA Handbook (7th Edition):
Johnson, Daniel M. “The wavelet filter: a new method for nonlinear, nongaussian
filtering in one dimension.” 2009. Web. 21 Feb 2020.
Vancouver:
Johnson DM. The wavelet filter: a new method for nonlinear, nongaussian
filtering in one dimension. [Internet] [Masters thesis]. University of Southern California; 2009. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/172277/rec/7398.
Council of Science Editors:
Johnson DM. The wavelet filter: a new method for nonlinear, nongaussian
filtering in one dimension. [Masters Thesis]. University of Southern California; 2009. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/172277/rec/7398
University of Southern California
6.
Kazemi, Leyla.
Enabling query answering in a trustworthy privacy-aware
spatial crowdsourcing.
Degree: PhD, Computer Science, 2012, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/119471/rec/2333
► With the ubiquity of mobile devices, spatial crowdsourcing is emerging as a new platform, enabling spatial tasks (i.e., tasks related to a location) assigned to…
(more)
▼ With the ubiquity of mobile devices, spatial
crowdsourcing is emerging as a new platform, enabling spatial tasks
(i.e., tasks related to a location) assigned to and performed by
human workers. However, privacy and trust are the two significant
barriers to the success of any spatial crowdsourcing system. First,
the workers may not want to associate themselves with the task they
perform. Second, the validity of the contributed data is not
verified, since the intentions of the workers is not always clear.
In this dissertation, for the first time we introduce a taxonomy
for spatial crowdsourcing. Subsequently, we study one class of this
taxonomy, in which workers send their locations to a centralized
server and thereafter the server assigns to every worker his nearby
tasks. Thereafter, we formally define the problem of privacy and
trust in spatial crowdsourcing systems and examine its challenges.
We propose a trustworthy privacy-aware framework for spatial
crowdsourcing systems, which enables the participation of the
workers without compromising their privacy while improving the
trustworthiness of the performed tasks.
Advisors/Committee Members: Shahabi, Cyrus (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Narayanan, Shrikanth S. (Committee Member).
Subjects/Keywords: crowdsourcing; spatial; privacy; trust
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Kazemi, L. (2012). Enabling query answering in a trustworthy privacy-aware
spatial crowdsourcing. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/119471/rec/2333
Chicago Manual of Style (16th Edition):
Kazemi, Leyla. “Enabling query answering in a trustworthy privacy-aware
spatial crowdsourcing.” 2012. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/119471/rec/2333.
MLA Handbook (7th Edition):
Kazemi, Leyla. “Enabling query answering in a trustworthy privacy-aware
spatial crowdsourcing.” 2012. Web. 21 Feb 2020.
Vancouver:
Kazemi L. Enabling query answering in a trustworthy privacy-aware
spatial crowdsourcing. [Internet] [Doctoral dissertation]. University of Southern California; 2012. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/119471/rec/2333.
Council of Science Editors:
Kazemi L. Enabling query answering in a trustworthy privacy-aware
spatial crowdsourcing. [Doctoral Dissertation]. University of Southern California; 2012. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/119471/rec/2333
University of Southern California
7.
Reinebold, James L., III.
Evaluating mobile phones as opportunistic on-body
sensors.
Degree: MS, Computer Science, 2011, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/668898/rec/2522
► Mobile phones are an inexpensive sensing solution that can provide insight into the personal environment of the person using the device. However, the challenge for…
(more)
▼ Mobile phones are an inexpensive sensing solution that
can provide insight into the personal environment of the person
using the device. However, the challenge for developers is to
understand the strengths and weaknesses of the sensing capabilities
of mobile phones when exploiting them for novel applications. For
mobile phones to be useful as opportunistic on-body mobile sensors,
they must be able to operate with minimal interaction from the
user, operate independently of their position with respect to the
body of the user, and conserve the resources of the device. ❧ This
thesis discusses these issues and presents three sets of
experiments that test sample applications using different sensor
types to solve the specific mobile sensing problems of movement
tracking and friend proximity discovery.
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Narayanan, Shrikanth S. (Committee Member), Schaal, Stefan (Committee Member).
Subjects/Keywords: mobile phones; opportunistic sensing; movement detection; friend detection; on-body sensors
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Reinebold, James L., I. (2011). Evaluating mobile phones as opportunistic on-body
sensors. (Masters Thesis). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/668898/rec/2522
Chicago Manual of Style (16th Edition):
Reinebold, James L., III. “Evaluating mobile phones as opportunistic on-body
sensors.” 2011. Masters Thesis, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/668898/rec/2522.
MLA Handbook (7th Edition):
Reinebold, James L., III. “Evaluating mobile phones as opportunistic on-body
sensors.” 2011. Web. 21 Feb 2020.
Vancouver:
Reinebold, James L. I. Evaluating mobile phones as opportunistic on-body
sensors. [Internet] [Masters thesis]. University of Southern California; 2011. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/668898/rec/2522.
Council of Science Editors:
Reinebold, James L. I. Evaluating mobile phones as opportunistic on-body
sensors. [Masters Thesis]. University of Southern California; 2011. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/668898/rec/2522
University of Southern California
8.
Vieira, Marcos Augusto Menezes.
The interplay between networks and robotics: networked
robots and robotic routers.
Degree: PhD, Computer Science, 2010, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/386028/rec/6907
► In this work, we explore the interplay between robotics and networks. Robots can benefit from an embedded network and also the network can benefit from…
(more)
▼ In this work, we explore the interplay between
robotics and networks. Robots can benefit from an embedded network
and also the network can benefit from the mobility of the robots.;
We investigate the design space where the application is oriented
towards robotics or networking, considering how much information
about the environment is provided and what the sensing capabilities
are.; At one end, the robots can benefit from the resources of an
environment-embedded network, in which robot sensing and
communication is enhanced by the network. We consider the design
and implementation of practical pursuit-evasion games with
networked robots, where a communication network provides
sensing-at-a-distance as well as a communication backbone that
enables tighter coordination between pursuers. Using the theory of
zero-sum games, we develop an algorithm that computes the minimal
completion time strategy for multi-pursuit multi-evasion when all
players make optimal decisions based on complete knowledge. We then
describe the design of a real-world mobile robot-based pursuit
evasion game. We validate our algorithms by experiments in a
moderate-scale testbed in a challenging office environment.; We
then show that the network can also benefit from Robotics by taking
advance of micro and macro motion. Robots can mitigate multi-path
fading. We design a system that allows robots to cooperate and
improve the real-world network throughput via a distributed
cooperation framework. A mobile wireless network can also be
quickly and autonomously deployed in urban search and rescue
efforts, forming a communication substrate. We study the problem of
determining the minimum number of mobile robots and how to position
them so all clients are connected. Our approach to the problem is
based on virtual potential fields where we treat each client as a
virtual charged particle. We validate our algorithm with physical
robots in an indoor environment and demonstrate that we are able to
get feasible solutions.
Advisors/Committee Members: Govindan, Ramesh (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Krishnamachari, Bhaskar (Committee Member).
Subjects/Keywords: wireless networks; robotics
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Vieira, M. A. M. (2010). The interplay between networks and robotics: networked
robots and robotic routers. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/386028/rec/6907
Chicago Manual of Style (16th Edition):
Vieira, Marcos Augusto Menezes. “The interplay between networks and robotics: networked
robots and robotic routers.” 2010. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/386028/rec/6907.
MLA Handbook (7th Edition):
Vieira, Marcos Augusto Menezes. “The interplay between networks and robotics: networked
robots and robotic routers.” 2010. Web. 21 Feb 2020.
Vancouver:
Vieira MAM. The interplay between networks and robotics: networked
robots and robotic routers. [Internet] [Doctoral dissertation]. University of Southern California; 2010. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/386028/rec/6907.
Council of Science Editors:
Vieira MAM. The interplay between networks and robotics: networked
robots and robotic routers. [Doctoral Dissertation]. University of Southern California; 2010. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/386028/rec/6907
University of Southern California
9.
Parnandi, Avinash Rao.
A framework for automated administration of post stroke
assessment test.
Degree: MS, Electrical Engineering, 2010, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/331648/rec/188
► In this thesis, we undertake a technology feasibility study of automating the Wolf Motor Function Test(WMFT) using the sensor framework and algorithms that we have…
(more)
▼ In this thesis, we undertake a technology feasibility
study of automating the Wolf Motor Function Test(WMFT) using the
sensor framework and algorithms that we have developed. WMFT is a
standardized assessment test to rate the functional ability (FA) of
post stroke individuals. It consists of 17 tasks, 15 of which are
scored on the basis of both performance time and quality of
movement. We utilize inertial and vision sensors to automate seven
of these tasks. The concept of gesture time, which measures the
duration for which the arm is actually in motion, is also
introduced. We validate the timing accuracy of our prototype system
on the seven tasks with two participants. To assess the quality of
motion, we propose a novel measurement methodology which involves
the sub-categorization of the FA score into individual scores for
smoothness, precision, and velocity of movement.We validate the
estimation accuracy of the framework with data from one stroke
participant. We also discuss the technologies that can be utilized
to extend this framework to encompass the remaining WMFT tasks. We
believe that the technologies we highlight in this thesis have the
capacity to inexpensively enhance the quality and ease of
administration of the assessment processes that stroke survivors
undergo after hospital discharge. Our long term goal is to be able
to automatically: 1) Quantify long term motor functionality changes
in real world settings; 2) Evaluate the intervention methodologies;
and 3) Use a humanoid robot to provide motivational
feedback.
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Narayanan, Shrikanth S. (Committee Member), Mataric, Maja J. (Committee Member).
Subjects/Keywords: wearable sensor; inertial sensor; post stroke assessment test; automated administration; Wolf Motor Function Test; WMFT; stroke rehabilitation; stroke assessment; quality of motion; naive Bayes classifier; functional assessment; performance time; gesture time; examiner bias; smoothness of motion
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Parnandi, A. R. (2010). A framework for automated administration of post stroke
assessment test. (Masters Thesis). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/331648/rec/188
Chicago Manual of Style (16th Edition):
Parnandi, Avinash Rao. “A framework for automated administration of post stroke
assessment test.” 2010. Masters Thesis, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/331648/rec/188.
MLA Handbook (7th Edition):
Parnandi, Avinash Rao. “A framework for automated administration of post stroke
assessment test.” 2010. Web. 21 Feb 2020.
Vancouver:
Parnandi AR. A framework for automated administration of post stroke
assessment test. [Internet] [Masters thesis]. University of Southern California; 2010. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/331648/rec/188.
Council of Science Editors:
Parnandi AR. A framework for automated administration of post stroke
assessment test. [Masters Thesis]. University of Southern California; 2010. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/331648/rec/188
University of Southern California
10.
Gupta, Megha.
Intelligent robotic manipulation of cluttered
environments.
Degree: PhD, Computer Science, 2014, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/521349/rec/3557
► Robotic household assistants of the future will need to understand their environment in real-time with high accuracy. There are two problems that make this challenging…
(more)
▼ Robotic household assistants of the future will need
to understand their environment in real-time with high accuracy.
There are two problems that make this challenging for robots.
First, human environments are typically cluttered, containing a lot
of objects of all kinds, shapes and sizes, in close proximity. This
introduces errors in the robot’
s perception and manipulation.
Second, human environments are highly varied. Improving a robot’
s
perceptual abilities can tackle these challenge only partially. A
robot’
s ability to manipulate its environment can help in enabling
and overcoming the limits of perception. ❧ We test this idea of
manipulation-aided perception in the context of sorting and
searching in cluttered, bounded, and partially observable
environments. The inherent uncertainty in the world state forces
the robot to adopt an observe-plan-act strategy where perception,
planning, and execution are interleaved. Since execution of an
action may result in revealing information about the world that was
unknown hitherto, a new plan needs to be generated as a consequence
of the robots actions. Since manipulation is typically expensive on
a robot, our goal is to reduce the number of object manipulations
required to complete the desired task. ❧ This thesis presents
planning algorithms for a robot’
s intelligent physical interaction
with its cluttered environment. The focus is on using simple
manipulation primitives to declutter the world and making task
completion easier and faster using the environment’
s local
structure or context. For object sorting, we present a robust
pipeline that combines manipulation-aided perception and grasping
to achieve more reliable and accurate sorting results. In the
context of environment exploration, we present an adaptive
look-ahead algorithm for exploration by prehensile and
non-prehensile manipulation of the objects in the environment. This
algorithm is then applied to manipulation-based object search in
real world. Finally, we add contextual structure to the world in
the form of object-object co-occurrence relations and present an
algorithm that uses context to guide the object search. ❧ We
evaluate the performance and applicability of our planners through
extensive simulations and real-world experiments on the PR2 robot.
Our results show that purposeful manipulation of clutter to aid
perception becomes increasingly useful (and essential) as the
clutter in the environment increases, and that intelligent
manipulation of a cluttered environment improves the efficiency of
robotic tasks.
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Schaal, Stefan (Committee Member), Krishnamachari, Bhaskar (Committee Member).
Subjects/Keywords: robotic manipulation; planning algorithms; personal robots; sensor-based manipulation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Gupta, M. (2014). Intelligent robotic manipulation of cluttered
environments. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/521349/rec/3557
Chicago Manual of Style (16th Edition):
Gupta, Megha. “Intelligent robotic manipulation of cluttered
environments.” 2014. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/521349/rec/3557.
MLA Handbook (7th Edition):
Gupta, Megha. “Intelligent robotic manipulation of cluttered
environments.” 2014. Web. 21 Feb 2020.
Vancouver:
Gupta M. Intelligent robotic manipulation of cluttered
environments. [Internet] [Doctoral dissertation]. University of Southern California; 2014. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/521349/rec/3557.
Council of Science Editors:
Gupta M. Intelligent robotic manipulation of cluttered
environments. [Doctoral Dissertation]. University of Southern California; 2014. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/521349/rec/3557
University of Southern California
11.
Kizilocak, Huseyin Hakan.
Probabilistic maps: computation and applications for
multi-agent problems.
Degree: PhD, Electrical Engineering, 2009, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/498792/rec/5234
► Computation and application of probabilistic maps to multi-agent problems generally consist of generating maps, distributing paths for each agent that allow the group to minimize…
(more)
▼ Computation and application of probabilistic maps to
multi-agent problems generally consist of generating maps,
distributing paths for each agent that allow the group to minimize
a cost function subject to constraints, e.g. the length of the
path, risk involved with the path, coordinated group behavior, time
to arrive at the destination, power consumption, network delay, and
bandwidth usage, and deciding to either avoid threats or pursue
treasures. In this thesis, we describe a formalism to take care of
the general problem of detecting objects with imperfect sensors.
This is accomplished by building several probabilistic maps. We
develop efficient algorithms to compute probabilistic maps for a
large number of static and mobile objects. By a probabilistic map
we mean the probability density of the objects' positions,
conditioned to noisy sensor measurements.; One of the contributions
of this work is that, under suitable assumptions, the joint
probability distribution of n objects that lie in a region
partitioned into N cells can be approximately determined from an
aggregate measurement function that can be represented with memory
complexity o(N), regardless of the number of objects n, while the
errors in sensors are not Gaussian and sensors are not able to
distinguish between individual objects. This is far more compact
than an extensive representation of the joint distribution, whose
memory complexity is o(N^n). Another contribution here is that
algorithms do not have exponential complexity in the number of
objects although the positions of multiple objects are not
independent of each other. Three main assumptions are: the objects
are indistinguishable from the sensor view-point, there is a
minimum distance between any two of them, and – if mobile objects
– their motion is essentially independent from each other.;
Innovative applications for this kind of work involve search and
rescue operations for disaster sites, e.g. hurricanes, fires,
earthquakes, floods, volcanoes, and battlefield strategies, e.g.,
searching areas for threats or targets, classification of objects
detected, pursuit-evasion games, battle damage assessment. One of
our applications is to assess the risk of moving from a source to a
destination point, exploiting the probabilistic maps, and even to
do minimum-risk path planning. Probabilistic maps are constantly
computed with the locations of objects by fusing information
collected from all the sensors in the region. Additionally, the
objects, that we map, may induce danger. Therefore the
probabilistic maps may be used for intelligence updates and for
minimum risk route planning. They make use of the map-building
facility to compute paths for the autonomous mobile robots that
minimizes the risk of being in the danger zone. The autonomous
mobile robots could be air or ground vehicles depending on the
scenario. Another application focuses on the problem where we do
not want to avoid the objects that we map, but to pursue. Depending
on the particular context, capture may actually mean handling the…
Advisors/Committee Members: Ioannou, Petros A. (Committee Chair), Hespanha, Joao P. (Committee Member), Sukhatme, Gaurav S. (Committee Member).
Subjects/Keywords: probabilistic maps; multi-agent
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Kizilocak, H. H. (2009). Probabilistic maps: computation and applications for
multi-agent problems. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/498792/rec/5234
Chicago Manual of Style (16th Edition):
Kizilocak, Huseyin Hakan. “Probabilistic maps: computation and applications for
multi-agent problems.” 2009. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/498792/rec/5234.
MLA Handbook (7th Edition):
Kizilocak, Huseyin Hakan. “Probabilistic maps: computation and applications for
multi-agent problems.” 2009. Web. 21 Feb 2020.
Vancouver:
Kizilocak HH. Probabilistic maps: computation and applications for
multi-agent problems. [Internet] [Doctoral dissertation]. University of Southern California; 2009. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/498792/rec/5234.
Council of Science Editors:
Kizilocak HH. Probabilistic maps: computation and applications for
multi-agent problems. [Doctoral Dissertation]. University of Southern California; 2009. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/498792/rec/5234
University of Southern California
12.
Yerramalli, Srinivas.
Communication and cooperation in underwater acoustic
networks.
Degree: PhD, Electrical Engineering, 2013, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222584/rec/1465
► In this thesis, we present a study of several problems related to underwater point to point communications and network formation. We explore techniques to improve…
(more)
▼ In this thesis, we present a study of several problems
related to underwater point to point communications and network
formation. We explore techniques to improve the achievable data
rate on a point to point link using better physical layer
techniques and then study sensor cooperation which improves the
throughput and reliability in an underwater network. ❧ Robust
point-to-point communications in underwater networks has become
increasingly critical in several military and civilian applications
related to underwater communications. We present several physical
layer signaling and detection techniques tailored to the underwater
channel model to improve the reliability of data detection. First,
a simplified underwater channel model in which the time scale
distortion on each path is assumed to be the same (single scale
channel model in contrast to a more general multi scale model). A
novel technique, which exploits the nature of OFDM signaling and
the time scale distortion, called Partial FFT Demodulation is
derived. It is observed that this new technique has some unique
interference suppression properties and performs better than
traditional equalizers in several scenarios of interest. Next, we
consider the multi scale model for the underwater channel and
assume that single scale processing is performed at the receiver.
We then derive optimized front end pre-processing techniques to
reduce the interference caused during single scale processing of
signals transmitted on a multi-scale channel. We then propose an
improvised channel estimation technique using dictionary
optimization methods for compressive sensing and show that
significant performance gains can be obtained using this technique.
❧ In the next part of this thesis, we consider the problem of
sensor node cooperation among rational nodes whose objective is to
improve their individual data rates. We first consider the problem
of transmitter cooperation in a multiple access channel and
investigate the stability of the grand coalition of transmitters
using tools from cooperative game theory and show that the grand
coalition in both the asymptotic regimes of high and low SNR.
Towards studying the problem of receiver cooperation for a
broadcast channel, we propose a game theoretic model for the
broadcast channel and then derive a game theoretic duality between
the multiple access and the broadcast channel and show that how the
equilibria of the broadcast channel are related to the multiple
access channel and vice versa.
Advisors/Committee Members: Mitra, Urbashi (Committee Chair), Jain, Rahul (Committee Member), Sukhatme, Gaurav S. (Committee Member).
Subjects/Keywords: underwater communications; wideband communications; OFDM; Doppler; time scale; partial FFT; estimator analysis; resampling; channel estimation; cooperation; game theory; wireless networks; partition form games; interference modeling; multiple access channels; broadcast channels; duality; Generalized Nash Equilibrium Problems
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Yerramalli, S. (2013). Communication and cooperation in underwater acoustic
networks. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222584/rec/1465
Chicago Manual of Style (16th Edition):
Yerramalli, Srinivas. “Communication and cooperation in underwater acoustic
networks.” 2013. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222584/rec/1465.
MLA Handbook (7th Edition):
Yerramalli, Srinivas. “Communication and cooperation in underwater acoustic
networks.” 2013. Web. 21 Feb 2020.
Vancouver:
Yerramalli S. Communication and cooperation in underwater acoustic
networks. [Internet] [Doctoral dissertation]. University of Southern California; 2013. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222584/rec/1465.
Council of Science Editors:
Yerramalli S. Communication and cooperation in underwater acoustic
networks. [Doctoral Dissertation]. University of Southern California; 2013. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/222584/rec/1465
University of Southern California
13.
de Menezes Pereira, Arvind Antonio.
Risk-aware path planning for autonomous underwater
vehicles.
Degree: PhD, Computer Science, 2013, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/351180/rec/5596
► Path planning is the process of generating an optimal sequence of waypoints from a start configuration to a desired goal configuration under constraints (e.g., avoiding…
(more)
▼ Path planning is the process of generating an optimal
sequence of waypoints from a start configuration to a desired goal
configuration under constraints (e.g., avoiding obstacles,
respecting time/energy budgets). In this thesis, we study the
problem of risk-aware planning. Specifically, we design, develop,
and experimentally validate optimal paths for Autonomous Underwater
Vehicles (AUVs) in the open ocean in the presence of navigational
hazards such as ships and other obstacles. A novel aspect of this
work is the introduction of ocean current predictions to optimize
planning in such settings. This is challenging because current
predictions are typ- ically available at non-uniform spatial
resolution, noisy, and time-delayed. We designed three risk-aware
planners that reason probabilistically about the uncer- tainty in
ocean currents predictions. The minimum expected risk planner
ensures that the AUV always reaches the goal, while minimizing risk
along the way, Risk- aware Markov Decision Process-based planning
uses stationary models over a short horizon, and trades off between
goal-directed behavior and reducing risk. This is susceptible to
finding sub-optimal policies due to stationarity. The
non-stationary, risk-aware MDP makes use of variability in the
currents where possible to overcome high-risk sections of paths on
the way to the goal. In addition to these planners, we develop a
taxonomy for risk-aware planning in dynamic settings. Another key
contribution is learning the uncertainty in currents to improve
planning. Results from extensive simulations clearly show that
learning uncertainty helps significantly improve performance of
risk-aware planners in uncertain currents, allowing AUVs to be
operated in more challenging scenarios than was previously
possible. Finally, the planners described in this dissertation have
been field tested at unprecedented levels to validate their
practical utility (∼2000 hours of testing at sea).
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Schaal, Stefan (Committee Member), Caron, David A. (Committee Member).
Subjects/Keywords: artificial intelligence; path planning; autonomous underwater vehicles; gliders
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
de Menezes Pereira, A. A. (2013). Risk-aware path planning for autonomous underwater
vehicles. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/351180/rec/5596
Chicago Manual of Style (16th Edition):
de Menezes Pereira, Arvind Antonio. “Risk-aware path planning for autonomous underwater
vehicles.” 2013. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/351180/rec/5596.
MLA Handbook (7th Edition):
de Menezes Pereira, Arvind Antonio. “Risk-aware path planning for autonomous underwater
vehicles.” 2013. Web. 21 Feb 2020.
Vancouver:
de Menezes Pereira AA. Risk-aware path planning for autonomous underwater
vehicles. [Internet] [Doctoral dissertation]. University of Southern California; 2013. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/351180/rec/5596.
Council of Science Editors:
de Menezes Pereira AA. Risk-aware path planning for autonomous underwater
vehicles. [Doctoral Dissertation]. University of Southern California; 2013. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/351180/rec/5596
University of Southern California
14.
Dantu, Karthik.
Reconfiguration in sensor networks.
Degree: PhD, Computer Science, 2010, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/292111/rec/5444
► To be practical, sensor networks need to adapt to changes in their environment. This thesis explores reconfiguration in sensor networks to endow them with greater…
(more)
▼ To be practical, sensor networks need to adapt to
changes in their environment. This thesis explores reconfiguration
in sensor networks to endow them with greater adaptability. We
study functional reconfiguration in static networks, and spatial
reconfiguration in networks with limitedmobility and networks whose
constituent nodes are highly mobile.; In static sensor networks,
reconfiguration can be thought of as the ability to dynamically
reconfigure nodes in the network to perform different functions
over time. We study a tiered sensor network where the roles of
microserver and sensor are dynamically assigned. We propose a
framework for redesigning services by partitioning the workload in
a distributed fashion among the microservers. We apply this
distribution formulation to connectivity-based localization and
show that it converges to within 10% of the centralized solution in
ten iterations. We also show a similar formulation for flow-based
routing.; In mobile sensor networks, one potential means of
reconfiguration is the ability of the network to reposition its
nodes using controlled mobility in service of a particular
objective. We address the problem of improving connectivity in a
robot network by proposing an algorithm for autonomous
reconfiguration that causes an initially connected network to be
transformed into a biconnected network. First, we show that the
robot network biconnectivity problem is NP-hard. We propose a
heuristic that uses bearing-only measurements of node neighbors to
achieve biconnectivity. Simulations and experiments suggest that
this algorithm performs well even when the bearing measurements are
coarse (errors up to 30 degrees have little impact on the outcome).
As a practical matter, we describe a novel technique to obtain such
bearing measurements from commodity radios on simple robots. The
biconnectivity algorithm requires a stable connected network.
However, experiments reveal that the routing protocol (in our case
OLSR) does not necessarily produce routes that are persistent in
time. We conjecture that providing location and direction cues
improves route stability in robot networks. Test results bear this
out - route switches decrease by up to 20% when the routing
protocol is given position and directional cues.
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Govindan, Ramesh (Committee Member), Krishnamachari, Bhaskar (Committee Member).
Subjects/Keywords: sensor networks; mobile sensor networks; robot networks; embedded systems; wireless sensor networks; mobile systems
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Dantu, K. (2010). Reconfiguration in sensor networks. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/292111/rec/5444
Chicago Manual of Style (16th Edition):
Dantu, Karthik. “Reconfiguration in sensor networks.” 2010. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/292111/rec/5444.
MLA Handbook (7th Edition):
Dantu, Karthik. “Reconfiguration in sensor networks.” 2010. Web. 21 Feb 2020.
Vancouver:
Dantu K. Reconfiguration in sensor networks. [Internet] [Doctoral dissertation]. University of Southern California; 2010. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/292111/rec/5444.
Council of Science Editors:
Dantu K. Reconfiguration in sensor networks. [Doctoral Dissertation]. University of Southern California; 2010. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/292111/rec/5444
University of Southern California
15.
Choudhuri, Chiranjib.
Joint communication and sensing over state dependent
channels.
Degree: PhD, Electrical Engineering, 2013, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/220838/rec/3688
► The fundamental trade-off between communication rate and estimation error in sensing the channel state at the decoder is investigated for a discrete memoryless channel with…
(more)
▼ The fundamental trade-off between communication rate
and estimation error in sensing the channel state at the decoder is
investigated for a discrete memoryless channel with discrete
memoryless action dependent state when the state information is
available either partially or fully at the encoder. We first
investigate the capacity a relay channel with finite memory, where
the action independent fixed channel state information is assumed
to be known at both the encoder and decoder and then went on to
investigate the problem of determining the trade-off between
capacity and distortion for the channel with states known only at
the encoder. ❧ The relay channel with finite memory is modeled with
channels with inter-symbol interference (ISI) and additive colored
Gaussian noise. The channel state or channel impulse responses are
assumed to be known at both the encoders and decoder. Prior results
are used to show that the capacity of this channel can be computed
by examining the circular degraded relay channel in the limit of
infinite block length. The thesis provides single letter
expressions for the achievable rates with decode-and-forward (DF)
and compress-and-forward (CF) processing employed at the relay.
Additionally, the cut-set bound for the relay channel is
generalized for the ISI/colored Gaussian noise scenario. All
results hinge on showing the optimality of the decomposition of the
relay channel with ISI/colored Gaussian noise into an equivalent
collection of coupled parallel, scalar, memoryless relay channels.
The region of optimality of the DF and CF achievable rates is also
discussed. The resulting rates are illustrated through the
computation of numerical examples. ❧ The problem of state
communication over a discrete memoryless channel with discrete
memoryless state when the state information is available strictly
causally at the encoder is then studied. It is shown that block
Markov encoding, in which the encoder communicates a description of
the state sequence in the previous block by incorporating side
information about the state sequence at the decoder, yields the
minimum state estimation error. When the same channel is used to
send additional independent information at the expense of a higher
channel state estimation error, the optimal tradeoff between the
rate of the independent information and the state estimation error
is characterized via the capacity–distortion function. It is shown
that any optimal tradeoff pair can be achieved via rate-splitting.
These coding theorems are then extended optimally to the case of
causal channel state information at the encoder using the Shannon
strategy. ❧ For non-causal channel state knowledge at the encoder,
information-theoretic lower and upper bounds (based respectively on
ideas from hybrid-coding and rate–distortion theory) are derived on
the capacity– distortion function. Some examples are provided, for
which the capacity–distortion functions are characterized by
showing that the two bounds match. These coding theorems are then
extended to the case of source…
Advisors/Committee Members: Mitra, Urbashi (Committee Chair), Caire, Giuseppe (Committee Member), Sukhatme, Gaurav S. (Committee Member).
Subjects/Keywords: communication; estimation; wireless communication; state estimation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Choudhuri, C. (2013). Joint communication and sensing over state dependent
channels. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/220838/rec/3688
Chicago Manual of Style (16th Edition):
Choudhuri, Chiranjib. “Joint communication and sensing over state dependent
channels.” 2013. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/220838/rec/3688.
MLA Handbook (7th Edition):
Choudhuri, Chiranjib. “Joint communication and sensing over state dependent
channels.” 2013. Web. 21 Feb 2020.
Vancouver:
Choudhuri C. Joint communication and sensing over state dependent
channels. [Internet] [Doctoral dissertation]. University of Southern California; 2013. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/220838/rec/3688.
Council of Science Editors:
Choudhuri C. Joint communication and sensing over state dependent
channels. [Doctoral Dissertation]. University of Southern California; 2013. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/220838/rec/3688
University of Southern California
16.
Gangwal, Vipresh.
Pose estimation for in-hand objects.
Degree: MS, Electrical Engineering, 2011, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/672017/rec/5129
► Estimation of 6D pose of a known object in robot hand is traditionally done by using vision or range sensing. Such methods perform badly in…
(more)
▼ Estimation of 6D pose of a known object in robot hand
is traditionally done by using vision or range sensing. Such
methods perform badly in cases when data is sparse or incomplete.
This thesis presents an approach to estimate the pose of a known
in-hand object by using range sensors and force torque sensors in
order to overcome limitations of using range sensors alone. The
proposed approach uses a novel method to combine information from
the two sensors using `mass-points'. The method is validated by
experiments with a Barrett WAM arm and shows significant
improvement in results when compared to popular
method.
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Ortega, Antonio (Committee Member), Schaal, Stefan (Committee Member).
Subjects/Keywords: robotics; computer science; in-hand object; pose estimation; force torque sensors; iterative closest point; inertial parameters
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Gangwal, V. (2011). Pose estimation for in-hand objects. (Masters Thesis). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/672017/rec/5129
Chicago Manual of Style (16th Edition):
Gangwal, Vipresh. “Pose estimation for in-hand objects.” 2011. Masters Thesis, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/672017/rec/5129.
MLA Handbook (7th Edition):
Gangwal, Vipresh. “Pose estimation for in-hand objects.” 2011. Web. 21 Feb 2020.
Vancouver:
Gangwal V. Pose estimation for in-hand objects. [Internet] [Masters thesis]. University of Southern California; 2011. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/672017/rec/5129.
Council of Science Editors:
Gangwal V. Pose estimation for in-hand objects. [Masters Thesis]. University of Southern California; 2011. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/672017/rec/5129
University of Southern California
17.
Ramachandran, Gokul.
A biologically inspired role-based team strategy for
pursuit-evasion in robots.
Degree: MS, Computer Science (Robotics and Automation), 2011, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/653087/rec/53
► This thesis presents a robust, scalable and general Java applet-based simulator for pursuit-evasion problems. With this tool, experiments can be conducted by simulating multi-player pursuit-evasion…
(more)
▼ This thesis presents a robust, scalable and general
Java applet-based simulator for pursuit-evasion problems. With this
tool, experiments can be conducted by simulating multi-player
pursuit-evasion games in bulk. We go through the rich list of
features and parameters that are implemented in the simulator, and
also mention utilities like memory, particle filters etc. that are
built into the system. This is followed by a discussion of the
different models that have been already created using these
utilities. Finally, a description of experiments that were
conducted using the simulator are presented, along with the
subsequent results.
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Schaal, Stefan (Committee Member), Krishnamachari, Bhaskar (Committee Member).
Subjects/Keywords: chasing; rvasion; pursuit; robotics; simulator; team; pursuit evasion; pursuit-evasion; team strategy; agents; agent based; agent-based; Java; iRobot Create; JavaCV; Bluetooth; firewire camera
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ramachandran, G. (2011). A biologically inspired role-based team strategy for
pursuit-evasion in robots. (Masters Thesis). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/653087/rec/53
Chicago Manual of Style (16th Edition):
Ramachandran, Gokul. “A biologically inspired role-based team strategy for
pursuit-evasion in robots.” 2011. Masters Thesis, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/653087/rec/53.
MLA Handbook (7th Edition):
Ramachandran, Gokul. “A biologically inspired role-based team strategy for
pursuit-evasion in robots.” 2011. Web. 21 Feb 2020.
Vancouver:
Ramachandran G. A biologically inspired role-based team strategy for
pursuit-evasion in robots. [Internet] [Masters thesis]. University of Southern California; 2011. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/653087/rec/53.
Council of Science Editors:
Ramachandran G. A biologically inspired role-based team strategy for
pursuit-evasion in robots. [Masters Thesis]. University of Southern California; 2011. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/653087/rec/53
University of Southern California
18.
Binney, Jonathan Douglas.
Informative path planning for environmental
monitoring.
Degree: PhD, Computer Science, 2012, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/104369/rec/3490
► Mobile aquatic, aerial, and terrestrial robots open up rich opportunities for environmental monitoring. Sensors mounted on a robot can be moved to take measurements in…
(more)
▼ Mobile aquatic, aerial, and terrestrial robots open up
rich opportunities for environmental monitoring. Sensors mounted on
a robot can be moved to take measurements in multiple locations,
allowing an effective spatial sampling density much higher than the
number of robots. In order to most effectively exploit mobile
robots in this manner, path planning methods which consider the
usefulness of measurements are needed. This thesis studies and
develops discrete planning algorithms for optimal usage of mobile
robots in environmental monitoring applications. Specifically, we
address cases where a probabilistic model (e.g., a Gaussian
process) is used to predict a scalar field. In this context, the
usefulness of a set of measurements collected by a robot or team of
robots can be quantified as the expected reduction in entropy or
mean squared error, providing a well defined objective function for
the planner. We present path planning approaches which take
advantage of the characteristics of these objective functions to
efficiently plan optimal or near optimal paths for one or more
robots. ❧ This thesis makes the following contributions. First, we
present extensions to a submodular orienteering algorithm which
increases its usefulness for environmental monitoring applications.
Specifically, we show how to handle temporally changing fields, and
how to efficiently incorporate sensors which take measurements
while the robot is moving. Second, we present a branch and bound
algorithm which adapts an upper bound from feature selection
literature to efficiently find the optimal solution to an
informative path planning problem. Finally, we provide results from
tests of the algorithms on real robotic problems, including ocean
monitoring using underwater gliders, and lake monitoring using an
autonomous surface vehicle.
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Schaal, Stefan (Committee Member), Caron, David A. (Committee Member).
Subjects/Keywords: robotics; path planning; environmental monitoring
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Binney, J. D. (2012). Informative path planning for environmental
monitoring. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/104369/rec/3490
Chicago Manual of Style (16th Edition):
Binney, Jonathan Douglas. “Informative path planning for environmental
monitoring.” 2012. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/104369/rec/3490.
MLA Handbook (7th Edition):
Binney, Jonathan Douglas. “Informative path planning for environmental
monitoring.” 2012. Web. 21 Feb 2020.
Vancouver:
Binney JD. Informative path planning for environmental
monitoring. [Internet] [Doctoral dissertation]. University of Southern California; 2012. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/104369/rec/3490.
Council of Science Editors:
Binney JD. Informative path planning for environmental
monitoring. [Doctoral Dissertation]. University of Southern California; 2012. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/104369/rec/3490
University of Southern California
19.
Khodaei, Ali.
Combining textual Web search with spatial, temporal and
social aspects of the Web.
Degree: PhD, Computer Science, 2013, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/338255/rec/1455
► Over the last few years, Web has changed significantly. Emergence of Web 2.0 has enabled people to interact with web documents in new ways not…
(more)
▼ Over the last few years, Web has changed
significantly. Emergence of Web 2.0 has enabled people to interact
with web documents in new ways not possible before. It is now a
common practice to geo-tag or time-tag web documents, or to
integrate web documents with popular social networks. With these
new changes and the abundant usage of spatial, temporal and social
information in web documents and search queries, the necessity of
integration of such non-textual aspects of the web to the regular
textual web search has grown rapidly over the past few years. ❧ To
integrate each of those non-textual dimensions to the textual web
search and to enable spatial-textual, temporal-textual and
social-textual web search, in this dissertation we propose a set of
new relevance models, index structures and algorithms specifically
designed for adding each non-textual dimension (spatial, temporal
and social) to the current state of (textual) web search. First, we
propose a new ranking model and a hybrid index structure called
Spatial-Keyword Inverted File to handle location-based ranking and
indexing of web documents in an integrated/efficient manner.
Second, we propose a new indexing and ranking framework for
temporal-textual retrieval. The framework leverages the classical
vector space model and provides a complete scheme for indexing,
query processing and ranking of the temporal-textual queries.
Finally, we show how to personalizes the search results based on
users’ social actions. We propose a new relevance model called
PerSocial relevance model utilizing three levels of social signals
to improve the web search. Furthermore, We Develop Several
Approaches To Integrate PerSocial relevance model Into The Textual
Web Search Process.
Advisors/Committee Members: Shahabi, Cyrus (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Currid-Halkett, Elizabeth (Committee Member).
Subjects/Keywords: search; information retrieval; ranking; indexing; social; spatial; temporal; textual; Web; social network; inverted index; contextual search; personalized search; spatiotemporal; Web 2.0
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Khodaei, A. (2013). Combining textual Web search with spatial, temporal and
social aspects of the Web. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/338255/rec/1455
Chicago Manual of Style (16th Edition):
Khodaei, Ali. “Combining textual Web search with spatial, temporal and
social aspects of the Web.” 2013. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/338255/rec/1455.
MLA Handbook (7th Edition):
Khodaei, Ali. “Combining textual Web search with spatial, temporal and
social aspects of the Web.” 2013. Web. 21 Feb 2020.
Vancouver:
Khodaei A. Combining textual Web search with spatial, temporal and
social aspects of the Web. [Internet] [Doctoral dissertation]. University of Southern California; 2013. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/338255/rec/1455.
Council of Science Editors:
Khodaei A. Combining textual Web search with spatial, temporal and
social aspects of the Web. [Doctoral Dissertation]. University of Southern California; 2013. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/338255/rec/1455
University of Southern California
20.
Das, Jnaneshwar.
Data-driven robotic sampling for marine ecosystem
monitoring.
Degree: PhD, Computer Science, 2014, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/409762/rec/1775
► The marine environment is in a perpetual state of flux due to ocean currents. As a result, phenomena such as plankton blooms are constantly advected,…
(more)
▼ The marine environment is in a perpetual state of flux
due to ocean currents. As a result, phenomena such as plankton
blooms are constantly advected, making their observation
challenging. Traditionally, measurements from remote‐sensing
satellites, ships, piers, and moorings have helped scientists study
such phenomena. However, a sound understanding of bloom ecology and
dynamics requires persistent sampling at spatio‐temporal scales
infeasible with existing methods. Advances in robotic sampling
using autonomous underwater vehicles (AUVs) have opened up the
arena for adaptive sampling at unprecedented scales, augmenting
other methods of observation. ❧ This thesis presents a novel
data‐driven robotic sampling methodology for marine ecosystem
monitoring, focusing on the observation of plankton blooms. The
problem is addressed at multiple spatio‐temporal scales to detect,
track, and sample blooms with the goal of acquisition of physical
water samples for ex‐situ analysis of plankton abundance. This is
essential for the understanding of plankton ecology and community
structure since sensors onboard AUVs are incapable of measuring
precise biological data in realtime, necessitating lab analysis of
water samples. ❧ Starting at the macro scale (kilometers/days),
this work demonstrates how remote sensing imagery and periodic
measurements of surface currents facilitate detection and
trajectory projection of plankton blooms to plan AUV deployments.
Once deployed, the AUV needs to survey within the context of the
advecting bloom. The thesis presents the design of Lagrangian
surveys wherein a bloom is tagged with a GPS‐tracked drifter, and
surveys are designed and executed in the frame of reference of the
advecting bloom. Results from a field experiment where a 1km x 1km
patch of water was successfully tracked by an AUV over multiple
days demonstrate the efficacy of this approach. Next, during such
Lagrangian surveys, the AUV is required to carry out adaptive water
sample acquisition for ex‐situ analysis. The thesis describes a
principled online sampling strategy that uses probabilistic
regression models trained on previously collected data to predict
abundance of desired plankton from realtime measurements of
physical and chemical properties by the AUV’
s onboard sensor suite.
Extensive simulations carried out by mining historical data, and a
one‐day field trial targeting a toxinogenic plankton demonstrate
the impact of the approach, in effect ""closing the loop"" on a a
significant science problem. Finally, the thesis describes an
Oceanographic Decision Support System (ODSS), a web‐based tool
developed for situational awareness and data visualization during
robotic sampling experiments of the kind presented in this work.
Extensive use during a month‐long field campaign with multiple
platforms and users demonstrate the importance of support tools in
marine ecosystem monitoring. ❧ Through extensive experimental
results, the thesis demonstrates robotic sampling for marine
ecosystem monitoring at an unprecedented spatio‐temporal…
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Schaal, Stefan (Committee Member), Caron, David A. (Committee Member).
Subjects/Keywords: robotics; robotic sampling; field robotics; marine robotics; underwater robots; autonomous underwater vehicles; AUVs; machine learning; software systems; adaptive sampling; experiment design; environmental monitoring
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Das, J. (2014). Data-driven robotic sampling for marine ecosystem
monitoring. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/409762/rec/1775
Chicago Manual of Style (16th Edition):
Das, Jnaneshwar. “Data-driven robotic sampling for marine ecosystem
monitoring.” 2014. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/409762/rec/1775.
MLA Handbook (7th Edition):
Das, Jnaneshwar. “Data-driven robotic sampling for marine ecosystem
monitoring.” 2014. Web. 21 Feb 2020.
Vancouver:
Das J. Data-driven robotic sampling for marine ecosystem
monitoring. [Internet] [Doctoral dissertation]. University of Southern California; 2014. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/409762/rec/1775.
Council of Science Editors:
Das J. Data-driven robotic sampling for marine ecosystem
monitoring. [Doctoral Dissertation]. University of Southern California; 2014. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/409762/rec/1775
University of Southern California
21.
Kalakrishnan, Mrinal.
Learning objective functions for autonomous motion
generation.
Degree: PhD, Computer Science, 2014, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781
► Planning and optimization methods have been widely applied to the problem of trajectory generation for autonomous robotics. The performance of such methods, however, is critically…
(more)
▼ Planning and optimization methods have been widely
applied to the problem of trajectory generation for autonomous
robotics. The performance of such methods, however, is critically
dependent on the choice of objective function being optimized, and
is non‐trivial to design. On the other end of the spectrum, efforts
on learning autonomous behavior from user‐provided demonstrations
have largely been focused on reproducing behavior similar in
appearance to the provided demonstrations. An alternative approach,
known as Inverse Reinforcement Learning (IRL), is to learn an
objective function that the demonstrations are assumed to be
optimal under. With the help of a planner or trajectory optimizer,
such an approach allows the system to synthesize novel behavior in
situations that were not experienced in the demonstrations. ❧ We
present novel algorithms for IRL that have successfully been
applied in two real‐world, competitive robotics settings: (1) In
the domain of rough terrain quadruped locomotion, we present an
algorithm that learns an objective function for foothold selection
based on ”terrain templates”. The learner automatically generates
and selects the appropriate features which form the objective
function, which reduces the need for feature engineering while
attaining a high level of generalization. (2) For the domain of
autonomous manipulation, we present a probabilistic model of
optimal trajectories, which results in new algorithms for inverse
reinforcement learning and trajectory optimization in
high‐dimensional settings. We apply this method to two problems in
robotic manipulation: redundancy resolution in inverse kinematics,
and trajectory optimization for grasping and manipulation. Both
methods have proven themselves as part of larger integrated systems
in competitive settings against other teams, where testing was
conducted by an independent test team in situations that were not
seen during training.
Advisors/Committee Members: Schaal, Stefan (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Valero-Cuevas, Francisco (Committee Member).
Subjects/Keywords: robotics; machine learning; motion planning; trajectory optimization; inverse reinforcement learning; reinforcement learning; locomotion; manipulation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Kalakrishnan, M. (2014). Learning objective functions for autonomous motion
generation. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781
Chicago Manual of Style (16th Edition):
Kalakrishnan, Mrinal. “Learning objective functions for autonomous motion
generation.” 2014. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781.
MLA Handbook (7th Edition):
Kalakrishnan, Mrinal. “Learning objective functions for autonomous motion
generation.” 2014. Web. 21 Feb 2020.
Vancouver:
Kalakrishnan M. Learning objective functions for autonomous motion
generation. [Internet] [Doctoral dissertation]. University of Southern California; 2014. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781.
Council of Science Editors:
Kalakrishnan M. Learning objective functions for autonomous motion
generation. [Doctoral Dissertation]. University of Southern California; 2014. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781
University of Southern California
22.
Subbaraya, Supreeth.
Development of Lagrangian drifter for ocean monitoring and
marine applications.
Degree: MS, Electrical Engineering, 2014, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/382246/rec/1947
► This thesis describes the design and development of a Lagrangian Drifter for ocean monitoring applications. The system is developed to move with the currents at…
(more)
▼ This thesis describes the design and development of a
Lagrangian Drifter for ocean monitoring applications. The system is
developed to move with the currents at a particular depth,
transmitting its location to the user. Through this design, the
user can track ocean currents and object or entities carried by
them. This thesis introduces the system by giving the motivation
for the work and a survey of related work and present day
technologies available to design the system. The design
considerations are laid out based upon the application of the
device. A description of the electrical, software and mechanical
design of the system is presented here. The system was
characterized for its defined design considerations. Finally,
experiments and results are presented and concluded with a
discussion on future enhancements for the system.
Advisors/Committee Members: Sukhatme, Gaurav S. (Committee Chair), Caron, David A. (Committee Member), Mitra, Urbashi (Committee Member).
Subjects/Keywords: drifter; ocean monitoring; drogue; marine system
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Subbaraya, S. (2014). Development of Lagrangian drifter for ocean monitoring and
marine applications. (Masters Thesis). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/382246/rec/1947
Chicago Manual of Style (16th Edition):
Subbaraya, Supreeth. “Development of Lagrangian drifter for ocean monitoring and
marine applications.” 2014. Masters Thesis, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/382246/rec/1947.
MLA Handbook (7th Edition):
Subbaraya, Supreeth. “Development of Lagrangian drifter for ocean monitoring and
marine applications.” 2014. Web. 21 Feb 2020.
Vancouver:
Subbaraya S. Development of Lagrangian drifter for ocean monitoring and
marine applications. [Internet] [Masters thesis]. University of Southern California; 2014. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/382246/rec/1947.
Council of Science Editors:
Subbaraya S. Development of Lagrangian drifter for ocean monitoring and
marine applications. [Masters Thesis]. University of Southern California; 2014. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/382246/rec/1947
University of Southern California
23.
Ghosh, Amitabha.
Algorithmic aspects of throughput-delay performance for fast
data collection in wireless sensor networks.
Degree: PhD, Electrical Engineering, 2010, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/392230/rec/605
► Convergecast, namely the many-to-one flow of data from a set of sources to a common sink over a tree-based routing topology, is a fundamental communication…
(more)
▼ Convergecast, namely the many-to-one flow of data from
a set of sources to a common sink over a tree-based routing
topology, is a fundamental communication primitive in wireless
sensor networks. For real-time, mission-critical, and high
data-rate applications, it is often critical to maximize the
aggregated data collection rate (throughput) at the sink node, as
well as minimize the time (delay) required for packets to get
there. In this thesis, we look into the algorithmic aspects of
jointly optimizing both throughput and delay for aggregated data
collection in sensor networks. Our contributions are in designing
efficient algorithms with provably good, worst-case performance
bounds for arbitrarily deployed networks. To the best of our
knowledge, we are the first ones to address these two mutually
conflicting performance objectives – throughput and delay – under
the same optimization framework and develop techniques to meet the
stringent requirements for fast data collection.; Our approach in
addressing the throughput-delay performance trade-off comprises
three techniques: (i) multi-channel scheduling, (ii) routing over
optimal topologies, and (iii) transmission power control. We
exploit the benefits of multiple frequency channels to design
efficient TDMA scheduling algorithms, both under the graph-based
and the SINR-based interference models. In particular, by
decoupling the joint frequency and time slot assignment problem
into two separate subproblems of frequency assignment and time slot
assignment, we show that our scheduling algorithms have constant
factor and logarithmic approximation ratios on the optimal
throughput for random geometric graphs as well as for SINR-based
models.; In order to further enhance the data collection rate and
bound the maximum delay, we study the degree-radius trade-off in
spanning trees and propose algorithms under the bicriteria
optimization framework. In particular, we construct
bounded-degree-minimum-radius spanning trees that have constant
factor approximations on the maximum node degree as well as the
tree radius. We also show that our multi-channel scheduling
algorithms perform much better on such trees in maximizing the
aggregated throughput and minimizing the maximum delay, thus
achieving the best of both worlds. Lastly, we design efficient,
distributed power control schemes for sensor networks deployed in
3-D, where very high density of nodes causes high interference
resulting in low network throughput. Our proposed algorithms have
low computational overhead compared to the state-of-the-art, and by
using local geometric information and tools from computational
geometry produce sparse yet connected topologies in 3-D, thus
reducing interference and allowing for high
throughput.
Advisors/Committee Members: Krishnamachari, Bhaskar (Committee Chair), Raghavendra, Cauligi S. (Committee Member), Sukhatme, Gaurav S. (Committee Member).
Subjects/Keywords: algorithms; throughput-delay; sensor networks; data collection; scheduling
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ghosh, A. (2010). Algorithmic aspects of throughput-delay performance for fast
data collection in wireless sensor networks. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/392230/rec/605
Chicago Manual of Style (16th Edition):
Ghosh, Amitabha. “Algorithmic aspects of throughput-delay performance for fast
data collection in wireless sensor networks.” 2010. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/392230/rec/605.
MLA Handbook (7th Edition):
Ghosh, Amitabha. “Algorithmic aspects of throughput-delay performance for fast
data collection in wireless sensor networks.” 2010. Web. 21 Feb 2020.
Vancouver:
Ghosh A. Algorithmic aspects of throughput-delay performance for fast
data collection in wireless sensor networks. [Internet] [Doctoral dissertation]. University of Southern California; 2010. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/392230/rec/605.
Council of Science Editors:
Ghosh A. Algorithmic aspects of throughput-delay performance for fast
data collection in wireless sensor networks. [Doctoral Dissertation]. University of Southern California; 2010. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/392230/rec/605
University of Southern California
24.
Fasola, Juan Pablo.
Socially assistive and service robotics for older adults:
methodologies for motivating exercise and following spatial
language instructions in discourse.
Degree: PhD, Computer Science, 2014, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/440892/rec/5933
► The growing population of aging adults is increasing the demand for healthcare services worldwide. Socially assistive robotics (SAR) and service robotics have the potential to…
(more)
▼ The growing population of aging adults is increasing
the demand for healthcare services worldwide. Socially assistive
robotics (SAR) and service robotics have the potential to aid in
addressing the needs of the growing elderly population by promoting
health benefits, independent living, and improved quality of life.
For such robots to become ubiquitous in real‐world human
environments, they will need to interact with and learn from
non‐expert users in a manner that is both natural and practical for
the users. In particular, such robots will need to be capable of
understanding natural language instructions in order to learn new
tasks and receive guidance and feedback on task execution. ❧
Research into SAR and service robotics‐based solutions for
non‐expert users, and in particular older adults, that spans varied
assistive tasks generally falls within one of two distinct areas:
1) robot‐guided interaction, and 2) user‐guided interaction. This
dissertation contributes to both of these research areas. ❧ To
address robot‐guided interaction, this dissertation presents the
design methodology, implementation and evaluation details of a
novel SAR approach to motivate and engage elderly users in simple
physical exercise. The approach incorporates insights from
psychology research into intrinsic motivation and contributes five
clear design principles for SAR‐based therapeutic interventions. To
evaluate the approach and its effectiveness in gaining user
acceptance and motivating physical exercise, it was implemented as
an integrated system and three user studies were conducted with
older adults, to investigate: 1) the effect of praise and
relational discourse in the system towards increasing user
motivation; 2) the role of user autonomy and choice within the
interaction; and 3) the effect of embodiment in the system by
comparing user evaluations of similar physically and virtually
embodied SAR exercise coaches in addition to evaluating the overall
SAR system. ❧ To address user‐guided interactions, specifically
with non‐expert users through the use of natural language
instructions, this dissertation presents a novel methodology that
allows service robots to interpret and follow spatial language
instructions, with and without user‐specified natural language
constraints and/or unvoiced pragmatic constraints. This work
contributes a general computational framework for the
representation of dynamic spatial relations, with both local and
global properties. The methodology also contributes a probabilistic
approach in the inference of instruction semantics; a general
approach for interpreting object pick‐and‐place tasks; and a novel
probabilistic algorithm for the automatic extraction of
contextually and semantically valid instruction sequences from
unconstrained spatial language discourse, including those
containing anaphoric reference expressions. The spatial language
interpretation methodology was evaluated in simulation, on two
different physical robot platforms, and in a user study conducted
with older adults for validation with…
Advisors/Committee Members: Mataric, Maja J. (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Hagedorn, Aaron (Committee Member).
Subjects/Keywords: human‐robot interaction; socially assistive robotics; spatial language understanding; natural language processing; intrinsic motivation; exercise therapy; older adults
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Fasola, J. P. (2014). Socially assistive and service robotics for older adults:
methodologies for motivating exercise and following spatial
language instructions in discourse. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/440892/rec/5933
Chicago Manual of Style (16th Edition):
Fasola, Juan Pablo. “Socially assistive and service robotics for older adults:
methodologies for motivating exercise and following spatial
language instructions in discourse.” 2014. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/440892/rec/5933.
MLA Handbook (7th Edition):
Fasola, Juan Pablo. “Socially assistive and service robotics for older adults:
methodologies for motivating exercise and following spatial
language instructions in discourse.” 2014. Web. 21 Feb 2020.
Vancouver:
Fasola JP. Socially assistive and service robotics for older adults:
methodologies for motivating exercise and following spatial
language instructions in discourse. [Internet] [Doctoral dissertation]. University of Southern California; 2014. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/440892/rec/5933.
Council of Science Editors:
Fasola JP. Socially assistive and service robotics for older adults:
methodologies for motivating exercise and following spatial
language instructions in discourse. [Doctoral Dissertation]. University of Southern California; 2014. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/440892/rec/5933
University of Southern California
25.
Pastor, Peter.
Data-driven autonomous manipulation.
Degree: PhD, Computer Science, 2014, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/406876/rec/1770
► The problem of an aging society is real and will affect everyone. There will be too few young people that can ensure adequate living conditions…
(more)
▼ The problem of an aging society is real and will
affect everyone. There will be too few young people that can ensure
adequate living conditions for the elderly. Personal robots have
the potential to assist in day‐to‐day tasks whenever there are too
few humans to cope with societal needs. However, for personal
robots to become useful they need to be able to skillfully
manipulate objects in their environment. Unfortunately, the problem
of autonomous manipulation is very complex and progress towards
creating autonomous behaviors seems to have reached a plateau. ❧ In
this thesis, we will present a data‐driven approach to movement
generation. We argue that movement generation (motor output) and
perceptual processing (sensor input) are inseparably intertwined
and that the ability to predict sensor information is essential for
skillful manipulation. Movement generation without sensor
expectations defaults to open‐loop execution which is prone to
failure in dynamic and unstructured environments. However,
predicting sensor information for an increasing number of sensor
modalities including force/torque and tactile feedback through
physics based modelling is challenging given the variety of
objects, the diversity of possible manipulation behaviors, and the
uncertainty in the real world. Instead, our approach leverages a
key insight: Movement generation can dictate expected sensor
feedback. Similar manipulation movements will give rise to sensory
events that are similar to previous ones. Thus, stereotypical
movements facilitate to associate and accumulate sensor information
from past trials and use these sensor experiences to predict sensor
feedback in future trials. ❧ We will call such movements augmented
with associated sensor information Associative Skill Memories
(ASMs). We will present a coherent data‐driven framework for
manipulation that implements this paradigm. First, we will
introduce a modular movement representation suitable to encode
movements along with associated sensor experiences. Second, we will
show how stereotypical movements can be learned from demonstrations
and refined using trial‐and‐error learning. Third, we will show how
ASMs can be used to monitor task progress, to realize contact
reactive manipulation, and to purposefully choose subsequent
movements. Finally, we will present a method that can learn forward
models for these stereotypical movements.
Advisors/Committee Members: Schaal, Stefan (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Schweighofer, Nicolas (Committee Member).
Subjects/Keywords: data‐driven; autonomous; robotic manipulation; movement primitives; motor primitives; associative memory; associative skill memories
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Pastor, P. (2014). Data-driven autonomous manipulation. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/406876/rec/1770
Chicago Manual of Style (16th Edition):
Pastor, Peter. “Data-driven autonomous manipulation.” 2014. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/406876/rec/1770.
MLA Handbook (7th Edition):
Pastor, Peter. “Data-driven autonomous manipulation.” 2014. Web. 21 Feb 2020.
Vancouver:
Pastor P. Data-driven autonomous manipulation. [Internet] [Doctoral dissertation]. University of Southern California; 2014. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/406876/rec/1770.
Council of Science Editors:
Pastor P. Data-driven autonomous manipulation. [Doctoral Dissertation]. University of Southern California; 2014. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/406876/rec/1770
University of Southern California
26.
Ting, Jo-Anne Su Yin.
Bayesian methods for autonomous learning systems.
Degree: PhD, Computer Science, 2009, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/151821/rec/1042
► We propose a set of Bayesian methods that help us toward the goal of autonomous learning systems. Systems that can react autonomously, with minimal human…
(more)
▼ We propose a set of Bayesian methods that help us
toward the goal of autonomous learning systems. Systems that can
react autonomously, with minimal human supervision, have the
potential for significant impact, especially in applications with
considerable uncertainty in the environment. In current algorithms,
parameter values are set using heuristic techniques, statistical
cross-validation or other search procedures to find the "right"
values. We rely on Bayesian inference as a principled way to
eliminate open parameters, resulting in a black-box-like approach.;
We are interested in scenarios where the input data is
high-dimensional (and many input dimensions may be redundant or
irrelevant) and where real-time, incremental learning may be
needed. Such data sets are common in the domain of robotics and
brain-machine interfaces, which are the main areas of evaluation in
this dissertation. We start by examining the problem of regression
since classification can be performed by interpreting regression
outputs in a binary way.; This dissertation first introduces a set
of autonomous Bayesian methods that learn from data with the
following properties: a high number of input dimensions, noise in
input data, and outliers. All these methods can be leveraged
together to develop a local Bayesian kernel shaping framework for
nonlinear regression. The Bayesian kernel shaping algorithm we
propose is the first step towards realizing real-time autonomous
learning systems. Even though the version described in this thesis
is in batch form, it is computationally efficient and can be used
in not only local methods, but also global nonlinear methods such
as Gaussian processes for non-stationary function
approximation.
Advisors/Committee Members: Schaal, Stefan (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Schweighofer, Nicolas (Committee Member), Sha, Fei (Committee Member).
Subjects/Keywords: autonomous learning systems; Bayesian statistics; function approximation; machine learning; real-time learning; regression
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ting, J. S. Y. (2009). Bayesian methods for autonomous learning systems. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/151821/rec/1042
Chicago Manual of Style (16th Edition):
Ting, Jo-Anne Su Yin. “Bayesian methods for autonomous learning systems.” 2009. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/151821/rec/1042.
MLA Handbook (7th Edition):
Ting, Jo-Anne Su Yin. “Bayesian methods for autonomous learning systems.” 2009. Web. 21 Feb 2020.
Vancouver:
Ting JSY. Bayesian methods for autonomous learning systems. [Internet] [Doctoral dissertation]. University of Southern California; 2009. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/151821/rec/1042.
Council of Science Editors:
Ting JSY. Bayesian methods for autonomous learning systems. [Doctoral Dissertation]. University of Southern California; 2009. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/151821/rec/1042
University of Southern California
27.
Yeoh, William.
Speeding up distributed constraint optimization search
algorithms.
Degree: PhD, Computer Science, 2010, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/393626/rec/6003
► Distributed constraint optimization (DCOP) is a model where several agents coordinate with each other to take on values so as to minimize the sum of…
(more)
▼ Distributed constraint optimization (DCOP) is a model
where several agents coordinate with each other to take on values
so as to minimize the sum of the resulting constraint costs, which
are dependent on the values of the agents. This model is becoming
popular for formulating and solving agent-coordination problems. As
a result, researchers have developed a class of DCOP algorithms
that use search techniques. For example, Asynchronous Distributed
Constraint Optimization (ADOPT) is one of the pioneering DCOP
search algorithms that has been widely extended. Since solving DCOP
problems optimally is NP-hard, solving large problems efficiently
becomes an issue.; DCOP search algorithms can be viewed as
distributed versions of centralized search algorithms. Therefore, I
hypothesize that one can speed up DCOP search algorithms by
applying insights gained from centralized search algorithms,
specifically (1) by using an appropriate search strategy, (2) by
sacrificing solution optimality, (3) by using more memory, and (4)
by reusing information gained from solving similar DCOP problems.
However, DCOP search algorithms are sufficiently different from
centralized search algorithms that these insights cannot be
trivially applied.; To validate my hypotheses: (1) I introduce
Branch-and-Bound ADOPT (BnB-ADOPT), an extension of ADOPT that
changes the search strategy of ADOPT from memory-bounded best-first
search to depth-first branch-and-bound search, resulting in one
order of magnitude speedup. These results validate my hypothesis
that DCOP search algorithms that employ depth-first
branch-and-bound search can be faster than DCOP search algorithms
that employ memory-bounded best-first search. (2) I introduce an
approximation mechanism that uses weighted heuristic values to
trade off solution costs for smaller runtimes. This approximation
mechanism allows ADOPT and BnB-ADOPT to terminate faster with
larger weights, validating my hypothesis that DCOP search
algorithms that use weighted heuristic values can have runtimes
that decrease as larger weights are used. Additionally, the new
approximation mechanism provides relative error bounds and thus
complements existing approximation mechanisms that only provide
absolute error bounds. (3) I introduce the MaxPriority, MaxEffort
and MaxUtility DCOP-specific caching schemes, which allow ADOPT and
BnB-ADOPT to cache DCOP-specific information when they have more
memory available and terminate faster with larger amounts of
memory. Experimental results show that the MaxEffort and MaxUtility
schemes speed up ADOPT more than the currently used generic caching
schemes, and the MaxPriority scheme speeds up BnB-ADOPT at least as
much as the currently used generic caching schemes. Therefore,
these results validate my hypothesis that DCOP-specific caching
schemes can reduce the runtime of DCOP search algorithms at least
as much as the currently used generic caching schemes.; (4) I
introduce an incremental procedure and an incremental pseudo-tree
reconstruction algorithm that allow ADOPT and BnB-ADOPT to…
Advisors/Committee Members: Koenig, Sven (Committee Chair), Dessouky, Maged M. (Committee Member), Sukhatme, Gaurav S. (Committee Member), Tambe, Milind (Committee Member), Yokoo, Makoto (Committee Member).
Subjects/Keywords: artificial intelligence; multiagent systems; distributed constraint optimization; distributed search
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Yeoh, W. (2010). Speeding up distributed constraint optimization search
algorithms. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/393626/rec/6003
Chicago Manual of Style (16th Edition):
Yeoh, William. “Speeding up distributed constraint optimization search
algorithms.” 2010. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/393626/rec/6003.
MLA Handbook (7th Edition):
Yeoh, William. “Speeding up distributed constraint optimization search
algorithms.” 2010. Web. 21 Feb 2020.
Vancouver:
Yeoh W. Speeding up distributed constraint optimization search
algorithms. [Internet] [Doctoral dissertation]. University of Southern California; 2010. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/393626/rec/6003.
Council of Science Editors:
Yeoh W. Speeding up distributed constraint optimization search
algorithms. [Doctoral Dissertation]. University of Southern California; 2010. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/393626/rec/6003
University of Southern California
28.
Mistry, Michael Nalin.
The representation, learning, and control of dexterous motor
skills in humans and humanoid robots.
Degree: PhD, Computer Science, 2009, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/227416/rec/7171
► Humans are capable of executing a wide variety of complex and dexterous motor behavior with grace and elegance. We would like to understand the computational…
(more)
▼ Humans are capable of executing a wide variety of
complex and dexterous motor behavior with grace and elegance. We
would like to understand the computational principals underlying
their sensorimotor control, both for the advancement of
neuroscience, as well as to achieve similar performance on
artificial machines. I study the problem via two approaches: motor
control experiments on human subjects, and the implementation of
control models on anthropomorphic hardware. In one experiment, we
use a novel exoskeleton platform that permits us to alter arm
dynamics by applying torques to specific joints during full 3-D
motion, and study how arm redundancy is utilized. Results of this
experiments suggest that: 1) humans are able to learn, and later
predict, novel dynamic environments, 2) humans plan motion in an
extrinsic hand, or end-effector oriented space, and 3) joint
redundancy can be utilized in order to assure task achievement. In
a second experiment, we attempt to create a dynamic environment
that effects motor cost, but not accuracy: if a force perturbation
first pushes the hand off-course in one direction and then
subsequently in the opposite direction, the reaching task may still
be achieved with minimal correction, but a strongly curved
trajectory. Under such conditions, subjects learn to return their
trajectories towards the baseline, or null field trajectory,
effectively fighting this disturbance in order to maintain a
straight trajectory. These results are inconsistent with theories
suggesting that perceived kinematic error plays no role in motor
adaptation. I will demonstrate how improved predictions can be
obtained with a stochastic optimal controller using a directionally
biased cost function. In second part of my dissertation, I discuss
how to obtain robust, compliant, human-like motion of humanoid
robots, via task-space, model-based, feed-forward control.; I will
explain the challenges of doing so, namely under-actuation due to
the "floating" base unattached to the world, the generally unknown
contact forces, and the ill-posed nature of floating base inverse
dynamics. I will show how to overcome these obstacles by planning
task-space motion in a sufficiently constrained space, and by
computing inverse dynamics torques by first projecting the system
dynamics into a reduced dimensional space which is independent of
contact forces.
Advisors/Committee Members: Schaal, Stefan (Committee Chair), Flashner, Henryk (Committee Member), Sukhatme, Gaurav S. (Committee Member), Schweighofer, Nicolas (Committee Member).
Subjects/Keywords: humanoid robotics; force fields; inverse dynamics; inverse kinematics; operational space control; redundancy
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Mistry, M. N. (2009). The representation, learning, and control of dexterous motor
skills in humans and humanoid robots. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/227416/rec/7171
Chicago Manual of Style (16th Edition):
Mistry, Michael Nalin. “The representation, learning, and control of dexterous motor
skills in humans and humanoid robots.” 2009. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/227416/rec/7171.
MLA Handbook (7th Edition):
Mistry, Michael Nalin. “The representation, learning, and control of dexterous motor
skills in humans and humanoid robots.” 2009. Web. 21 Feb 2020.
Vancouver:
Mistry MN. The representation, learning, and control of dexterous motor
skills in humans and humanoid robots. [Internet] [Doctoral dissertation]. University of Southern California; 2009. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/227416/rec/7171.
Council of Science Editors:
Mistry MN. The representation, learning, and control of dexterous motor
skills in humans and humanoid robots. [Doctoral Dissertation]. University of Southern California; 2009. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/227416/rec/7171
University of Southern California
29.
Viswanathan, Manu.
Mobile robot obstacle avoidance using a computational model
of the locust brain.
Degree: MS, Computer Science (Robotics &
Automation), 2011, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/433779/rec/4101
► The Lobula Giant Movement Detector (LGMD), a visual interneuron in the locust's brain, responds preferentially to objects approaching along collisional trajectories. The goal of the…
(more)
▼ The Lobula Giant Movement Detector (LGMD), a visual
interneuron in the locust'
s brain, responds preferentially to
objects approaching along collisional trajectories. The goal of the
Robolocust project is to build a robot that interfaces with this
neuron and uses the LGMD spikes to make steering decisions.;
However, before interfacing with actual locusts, we would like to
simulate the LGMD and develop suitable obstacle avoidance
algorithms that take LGMD spikes as their sensory input. To this
end, we have implemented a computational model of the LGMD that
uses a laser range finder mounted on an iRobot Create to generate
artificial spikes that are then fed into obstacle avoidance
algorithms.; The main contribution of this thesis is a Bayesian
state estimator that models the time-to-impact as a hidden variable
and uses the LGMD spikes to gauge how far away the robot is from
approaching obstacles. Additionally, we present three different
LGMD-based obstacle avoidance algorithms that we have
developed.
Advisors/Committee Members: Itti, Laurent (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Schaal, Stefan (Committee Member), Celikel, Tansu (Committee Member).
Subjects/Keywords: mobile robotics; insect vision; collision detection; time-to-impact; obstacle avoidance; locust LGMD; probabilistic sensor model; Bayesian state estimation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Viswanathan, M. (2011). Mobile robot obstacle avoidance using a computational model
of the locust brain. (Masters Thesis). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/433779/rec/4101
Chicago Manual of Style (16th Edition):
Viswanathan, Manu. “Mobile robot obstacle avoidance using a computational model
of the locust brain.” 2011. Masters Thesis, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/433779/rec/4101.
MLA Handbook (7th Edition):
Viswanathan, Manu. “Mobile robot obstacle avoidance using a computational model
of the locust brain.” 2011. Web. 21 Feb 2020.
Vancouver:
Viswanathan M. Mobile robot obstacle avoidance using a computational model
of the locust brain. [Internet] [Masters thesis]. University of Southern California; 2011. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/433779/rec/4101.
Council of Science Editors:
Viswanathan M. Mobile robot obstacle avoidance using a computational model
of the locust brain. [Masters Thesis]. University of Southern California; 2011. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/433779/rec/4101
University of Southern California
30.
Jahanshahi, Mohammad Reza.
Vision-based studies for structural health monitoring and
condition assesment.
Degree: PhD, Civil Engineering, 2013, University of Southern California
URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/617318/rec/7831
► Automated health monitoring and maintenance of civil infrastructure systems is an active yet challenging area of research. Current structure inspection standards require an inspector to…
(more)
▼ Automated health monitoring and maintenance of civil
infrastructure systems is an active yet challenging area of
research. Current structure inspection standards require an
inspector to visually assess structure conditions. A less
time-consuming and inexpensive alternative to current monitoring
methods is to use a robotic system that can inspect structures more
frequently, and perform autonomous damage detection. Nondestructive
evaluation techniques (NDE) are innovative approaches for
structural health monitoring. Among several possible techniques,
the use of optical instrumentation (e.g., digital cameras), image
processing and computer vision are promising approaches as
nondestructive testing methods for structural health monitoring to
complement sensor-based approaches. The feasibility of using image
processing techniques to detect deterioration in structures has
been acknowledged by leading researches in the field. This study
represents the efforts that have been taken place by the author to
form, implement, and evaluate several vision-based approaches that
are promising for robust condition assessment of structures. ❧ It
is well-recognized that civil infrastructure monitoring approaches
that rely on visual approaches will continue to be an important
methodology for condition assessment of such systems. Part of this
study presents and evaluates the underlying technical elements for
the development of an integrated inspection software tool that is
based on the use of inexpensive digital cameras. For this purpose,
digital cameras are appropriately mounted on a structure (e.g., a
bridge) and can zoom or rotate in three directions (similar to
traffic cameras). They are remotely controlled by an inspector,
which allows the visual assessment of the structure’
s condition by
looking at images captured by the cameras. By not having to travel
to the structures site, other issues related to safety
considerations and traffic detouring are consequently bypassed. The
proposed system gives an inspector the ability to compare the
current (visual) situation of a structure with its former
condition. If an inspector notices a defect in the current view,
he/she can request a reconstruction of the same view using images
that were previously captured and automatically stored in a
database. Furthermore, by generating databases that consist of
periodically captured images of a structure, the proposed system
allows an inspector to evaluate the evolution of changes by
simultaneously comparing the structure’
s condition at different
time periods. The essential components of the proposed virtual
image reconstruction system are: keypoint detection, keypoint
matching, image selection, outlier exclusion, bundle adjustment,
composition, and cropping. Several illustrative examples are
presented to demonstrate the capabilities, as well as the
limitations, of the proposed vision-based inspection procedure. ❧
Visual inspection of structures is a highly qualitative method. If
a region is inaccessible, binoculars must be used to detect and
characterize…
Advisors/Committee Members: Masri, Sami F. (Committee Chair), Lee, Jiin-Jen (Committee Member), Wellford, L. Carter (Committee Member), Sukhatme, Gaurav S. (Committee Member).
Subjects/Keywords: structural health monitoring; civil infrastructure systems; condition assessment; image processing; computer vision; pattern recognition; inspection tool; crack detection, crack quantification; corrosion detection; defect detection; change detection
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Jahanshahi, M. R. (2013). Vision-based studies for structural health monitoring and
condition assesment. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/617318/rec/7831
Chicago Manual of Style (16th Edition):
Jahanshahi, Mohammad Reza. “Vision-based studies for structural health monitoring and
condition assesment.” 2013. Doctoral Dissertation, University of Southern California. Accessed February 21, 2020.
http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/617318/rec/7831.
MLA Handbook (7th Edition):
Jahanshahi, Mohammad Reza. “Vision-based studies for structural health monitoring and
condition assesment.” 2013. Web. 21 Feb 2020.
Vancouver:
Jahanshahi MR. Vision-based studies for structural health monitoring and
condition assesment. [Internet] [Doctoral dissertation]. University of Southern California; 2013. [cited 2020 Feb 21].
Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/617318/rec/7831.
Council of Science Editors:
Jahanshahi MR. Vision-based studies for structural health monitoring and
condition assesment. [Doctoral Dissertation]. University of Southern California; 2013. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll127/id/617318/rec/7831
◁ [1] [2] ▶
. 
Open Access Theses and Dissertations