You searched for +publisher:"Delft University of Technology" +contributor:("van Genderen, Arjan").
Showing records 1 – 30 of
30 total matches.
No search limiters apply to these results.
Delft University of Technology
1.
Vos, Dirk (author).
Embedded Control System for Calibrating Gas Analysers.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:aee8fa84-e3cc-4b77-bee6-d14b36ebae10 
► This Thesis report will discuss the development of embedded control systems for process control (in this case for the calibration of a gas analyser). The…
(more)
▼ This Thesis report will discuss the development of embedded control systems for process control (in this case for the calibration of a gas analyser). The main research question being: Which control algorithm will be able to achieve the most optimal calibration procedure? A calibration bench which will be used to create a specific condition (gas concentration, gas pressure, gas flow) for a gas analyser, so that it can be calibrated accurately. Embedded Systems usually suffer from low computation power and do not have a lot of resources available, so designing a control system for an embedded system will require some special attention. Designing a good controller is never an easy task, every single component needs to be chosen in a way to meet the requirements and ensure best performance. Controller design both programming/simulations and hardware development: both are important to get a good regulation, direct/linear and predictable actuation is needed. Therefore hardware design should make sure that reading sensors and actuating actuators do not suffer from big non linearities or delays. Software will make a big difference in the sense of: how efficient is the algorithm? Is it robust (what happens to the system when an error occurs, will it show unexpected behaviour or will it stay stable)? This report has been cut in 5 big pieces: hardware design, embedded software design, interface software design, model identification and controller design. Hardware design will elaborate on the electronic circuit design and the mechanical design of the pneumatics. Embedded software design will elaborate on the software written for the control board (which is responsible for regulating gas pressure and gas flow). Interface software design will show the development of the GUI (Graphical User Interface), so the user can interact with the calibration bench by simply clicking on buttons instead of working with a command line tool. Model identification will explain how to get a prediction model of the process out of the data of a set of carefully selected tests. Controller design will elaborate more on the control algorithms designed and how to use the prediction model found in model identification.
Advisors/Committee Members: van Genderen, Arjan (mentor), Delft University of Technology (degree granting institution).
Subjects/Keywords: Control; Embedded; Embedded Systems; embedded systems; control; control system; control 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):
Vos, D. (. (2018). Embedded Control System for Calibrating Gas Analysers. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:aee8fa84-e3cc-4b77-bee6-d14b36ebae10
Chicago Manual of Style (16th Edition):
Vos, Dirk (author). “Embedded Control System for Calibrating Gas Analysers.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:aee8fa84-e3cc-4b77-bee6-d14b36ebae10.
MLA Handbook (7th Edition):
Vos, Dirk (author). “Embedded Control System for Calibrating Gas Analysers.” 2018. Web. 12 Apr 2021.
Vancouver:
Vos D(. Embedded Control System for Calibrating Gas Analysers. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:aee8fa84-e3cc-4b77-bee6-d14b36ebae10.
Council of Science Editors:
Vos D(. Embedded Control System for Calibrating Gas Analysers. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:aee8fa84-e3cc-4b77-bee6-d14b36ebae10
Delft University of Technology
2.
Goel, Ishu (author).
Simulation-based end-to-end latency analysis of ADAS systems.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:93c18a09-4878-4573-9e65-4ab6d0a7d150
► Many Advanced Driver Assistant Systems functionalities were introduced to boost vehicle safety, efficiency and comfort. Implementing these functionalities such that all the functional and temporal…
(more)
▼ Many Advanced Driver Assistant Systems functionalities were introduced to boost vehicle safety, efficiency and comfort. Implementing these functionalities such that all the functional and temporal requirements are satisfied is challenging. This thesis is concerned with the temporal requirements. More precisely, it aims to identify and implement a methodology to estimate the end-to-end latency distribution of various signals paths in ADAS, with the aim of verifying the compliance of latency requirements. The methodology is validated by testing it on a hardware set-up that mimics the behaviour of an existing adaptive cruise control system at TNO. This system is equipped with two different communication buses and multiple ECU's with different temporal behaviours. A simulation-based method is used to address the problem. The simulation models of the individual components were first made and then combined to make the model of the complete system. The simulation model uses the input-output latency of the individual components, without any interference from other components, from the hardware model and computes the complex interactions between and within the components. The results of the experiments performed on both simulation and hardware models conform that a simulation-based method could be used to determine end-to-end latency in a distributed automotive systems.
CE-MS-2018-26
Embedded Systems
Advisors/Committee Members: van Genderen, Arjan (mentor), Delft University of Technology (degree granting institution).
Subjects/Keywords: timing; ADAS
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):
Goel, I. (. (2018). Simulation-based end-to-end latency analysis of ADAS systems. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:93c18a09-4878-4573-9e65-4ab6d0a7d150
Chicago Manual of Style (16th Edition):
Goel, Ishu (author). “Simulation-based end-to-end latency analysis of ADAS systems.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:93c18a09-4878-4573-9e65-4ab6d0a7d150.
MLA Handbook (7th Edition):
Goel, Ishu (author). “Simulation-based end-to-end latency analysis of ADAS systems.” 2018. Web. 12 Apr 2021.
Vancouver:
Goel I(. Simulation-based end-to-end latency analysis of ADAS systems. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:93c18a09-4878-4573-9e65-4ab6d0a7d150.
Council of Science Editors:
Goel I(. Simulation-based end-to-end latency analysis of ADAS systems. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:93c18a09-4878-4573-9e65-4ab6d0a7d150
Delft University of Technology
3.
Tharian, Ron John (author).
A light-weight Electromagnetic Based Embedded Sensing System For Ground Water Exploration.
Degree: 2017, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:95e7f6c7-f068-4b60-b55c-89dce18a70c4
► The availability of usable groundwater is fast becoming one of the most important environmental issues today. Though the availability of groundwater differs from place to…
(more)
▼ The availability of usable groundwater is fast becoming one of the most important environmental issues today. Though the availability of groundwater differs from place to place and more often the demand tends to overcome the supply. In spite of the numerous dowsing techniques that exists in the market today; till date there has been little work done in UAV based sensing, and so the thesis has been carried out with the collaboration of the start-up company SkyDowser, whose primary focus was on the emerging area of UAV based geophysical surveying. In this thesis project, research was firstly conducted on current and previous surveying methodologies. After which research was done to obtain a basic working understanding of various geophysical concepts, electromagnetics etc. Simulations were then carried out using the AIRBEO forward modelling software which was helpful to understand geophysical survey systems: what was to be expected from such a system, what influenced the response etc. The initial top-level design of a Light-weight Electromagnetic Based Embedded Sensing System for Ground Water Exploration follows after that. Finally a 3-coil based analog sensor prototype has been implemented, different measurements have been taken and various results have been tabulated.
Advisors/Committee Members: van Genderen, Arjan (mentor), van der Putte, Erik (mentor), Delft University of Technology (degree granting institution).
Subjects/Keywords: skyDowser; electromagnetic surveying
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):
Tharian, R. J. (. (2017). A light-weight Electromagnetic Based Embedded Sensing System For Ground Water Exploration. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:95e7f6c7-f068-4b60-b55c-89dce18a70c4
Chicago Manual of Style (16th Edition):
Tharian, Ron John (author). “A light-weight Electromagnetic Based Embedded Sensing System For Ground Water Exploration.” 2017. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:95e7f6c7-f068-4b60-b55c-89dce18a70c4.
MLA Handbook (7th Edition):
Tharian, Ron John (author). “A light-weight Electromagnetic Based Embedded Sensing System For Ground Water Exploration.” 2017. Web. 12 Apr 2021.
Vancouver:
Tharian RJ(. A light-weight Electromagnetic Based Embedded Sensing System For Ground Water Exploration. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:95e7f6c7-f068-4b60-b55c-89dce18a70c4.
Council of Science Editors:
Tharian RJ(. A light-weight Electromagnetic Based Embedded Sensing System For Ground Water Exploration. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:95e7f6c7-f068-4b60-b55c-89dce18a70c4
Delft University of Technology
4.
Rouwen, Floris (author).
Lunar Zebro - Software Design Of The Locomotion Sub-System With The Dezyne Model Driven Development Tool.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:4ae94ace-beb9-43d7-a769-7c58e90c8dca
► The TU Delft ZEs-Benige RObot (Zebro) project is presented with the opportunity to bring the Zebro concept to the surface of our moon. To maximise…
(more)
▼ The TU Delft ZEs-Benige RObot (Zebro) project is presented with the opportunity to bring the Zebro concept to the surface of our moon. To maximise the probability of success, the Locomotion Sub-System (LSS) software of Lunar Zebro is developed using a novel model-driven design tool called Dezyne. Dezyne uses a proprietary language to describe systems, perform model checking and execute source code generation. Dezyne is proposed for this thesis as it can improve the quality of the LSS design. This is required because the project is under strict time- and manpower constraints. The goals for this thesis are: i. Deliver a reliable software design for the Locomotion Sub-System (LSS) of Lunar Zebro. ii. Deliver a working implementation of the Locomotion Sub-System (LSS) software design on Lunar Zebro’s hardware. iii. Investigate the advantages and disadvantages of the use of the model-driven software design tool Dezyne. The current workhorse of the Zebro Project, is a Zebro called DeciZebro. Lunar Zebro builds on the legacy of the design of DeciZebro. The LSS of Lunar Zebro consists of an Locomotion Controller (LC) and six leg modules. The requirements of the LSS software of Lunar Zebro are derived from the requirements of Lunar Zebro as a whole. These requirements are categorised according an European Space Agency (ESA) standard. With the help of Dezyne, the system is designed, verified, simulated and integrated into native code. It is found that Dezyne is not suitable for designing the software of the leg modules. Therefore, the LC consists primarily of generated code, while the leg modules solely contain code developed by hand. The goals of this thesis are partly reached. An LSS software implementation is delivered with the use of Dezyne. However, the design is lacking a framework in which errors that occur during operation can be resolved by means of extensive state machining. This is due to time constraints. Additionally, it is unclear if this specific LSS software implementation is more reliable than an implementation that is made without the use of Dezyne. The third goal, listing the advantages and disadvantages of Dezyne, is fulfilled.
The Zebro Project
Advisors/Committee Members: Verhoeven, Chris (mentor), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Lunar Zebro; Formal Verification; Dezyne; Model-Driven Design Approach; Code Generation; Embedded 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):
Rouwen, F. (. (2018). Lunar Zebro - Software Design Of The Locomotion Sub-System With The Dezyne Model Driven Development Tool. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:4ae94ace-beb9-43d7-a769-7c58e90c8dca
Chicago Manual of Style (16th Edition):
Rouwen, Floris (author). “Lunar Zebro - Software Design Of The Locomotion Sub-System With The Dezyne Model Driven Development Tool.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:4ae94ace-beb9-43d7-a769-7c58e90c8dca.
MLA Handbook (7th Edition):
Rouwen, Floris (author). “Lunar Zebro - Software Design Of The Locomotion Sub-System With The Dezyne Model Driven Development Tool.” 2018. Web. 12 Apr 2021.
Vancouver:
Rouwen F(. Lunar Zebro - Software Design Of The Locomotion Sub-System With The Dezyne Model Driven Development Tool. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:4ae94ace-beb9-43d7-a769-7c58e90c8dca.
Council of Science Editors:
Rouwen F(. Lunar Zebro - Software Design Of The Locomotion Sub-System With The Dezyne Model Driven Development Tool. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:4ae94ace-beb9-43d7-a769-7c58e90c8dca
Delft University of Technology
5.
Jagadeeshwar, Hemanth (author).
Implementation and verification of energy efficient software for ADCS.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:5e00ce5a-ace5-421b-afec-87f83b3bac5c
► The Delfi-n3Xt was the second nanosatellite developed at the Delft University of Technology, and launched in 2013. Its successor Delfi-PQ is expected to be launched…
(more)
▼ The Delfi-n3Xt was the second nanosatellite developed at the Delft University of Technology, and launched in 2013. Its successor Delfi-PQ is expected to be launched in first half of 2019. The Attitude of a satellite can be referred to as its orientation in space with respect to inertial reference frame. The Delfi-n3Xt was the first satellite from Delft University of Technology, to include three-axis Attitude Determination and Control System/Subsystem (ADCS). It was designed with 5 modes of operation. Four of these were advanced modes. In addition, the Delfi-PQ is not intended to include advanced modes of operation. Hence, this thesis considers using the Delfi-n3Xt ADCS software. This software is extended as a baseline implementation on MSP-EXP432E401Y launchpad. Nearly, 32 % of total nominal power is assigned to ADCS. Hence, energy efficient design alternatives could be considered for future satellite missions. In addition, ADCS is a critical subsystem, failure of ADCS means failure of satellite mission. This thesis aims to improve performance and energy consumption of ADCS. This thesis considers study of three different Digital Signal Processing (DSP) alternatives: Double Precision (DP), Single Precision (SP) and Fixed Point (FxP) arithmetic. Study in this thesis concludes that FxP alternative provides approximately 6.7 times better performance, and approximately 7 times better energy efficiency over baseline. Hence, this thesis proposes the use of FxP DSP alternative. It was also concluded that, the SP arithmetic has equivalent accuracy compared with DP. Moreover, SP provides approximately 3 times better performance, and approximately 2.7 times better energy efficiency over baseline. Therfore, future implementations could benefit from an SP alternative. A major part of the ADCS power is allocated to sensor and actuator. This leaves only 10 % of the total nominal power assigned to ADCS software. Hence, the proposed alternative might not provide considerable improvements on total nominal power. However, for future satellite missions, if there exists a computationally intensive algorithm assigned with more significant amount of total nominal power, then, the proposed alternative could serve as an initial study. However, this does not guarantee that the suggested alternative could satisfy more accurate requirements. In such case, FxP implementation might result in accuracy violation. And use of SP alternative is proposed. In such case, a new study is suggested in order to benefit from FxP alternative.
Delfi-PocketQube
Embedded Systems
Advisors/Committee Members: Wong, Stephan (mentor), Fónod, R. (graduation committee), Langendoen, Koen (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Delfi-n3Xt; Energy Efficiency; DSP; Fixed-point; Delfi-Program; ADCS
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):
Jagadeeshwar, H. (. (2018). Implementation and verification of energy efficient software for ADCS. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:5e00ce5a-ace5-421b-afec-87f83b3bac5c
Chicago Manual of Style (16th Edition):
Jagadeeshwar, Hemanth (author). “Implementation and verification of energy efficient software for ADCS.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:5e00ce5a-ace5-421b-afec-87f83b3bac5c.
MLA Handbook (7th Edition):
Jagadeeshwar, Hemanth (author). “Implementation and verification of energy efficient software for ADCS.” 2018. Web. 12 Apr 2021.
Vancouver:
Jagadeeshwar H(. Implementation and verification of energy efficient software for ADCS. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:5e00ce5a-ace5-421b-afec-87f83b3bac5c.
Council of Science Editors:
Jagadeeshwar H(. Implementation and verification of energy efficient software for ADCS. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:5e00ce5a-ace5-421b-afec-87f83b3bac5c
Delft University of Technology
6.
Irawan, Angga (author).
Representing Symbolic Controllers with Deep Neural Networks.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:677cdde8-b3fa-4fb4-8db2-3c87b03b5085
► Controller synthesis techniques based on symbolic models or discrete abstractions are becoming increasingly attractive as they allow for synthesizing correct-by-design controllers of general nonlinear systems…
(more)
▼ Controller synthesis techniques based on symbolic models or discrete abstractions are becoming increasingly attractive as they allow for synthesizing correct-by-design controllers of general nonlinear systems under complex behavioral requirements. However, its immense size as the consequence of the state-space explosion prohibits the approach to be widely used in real-life applications. The explosion of state space is mainly caused by the discretization in the abstraction step, and the redundancy of control inputs resulted in from the synthesis. Compression methods and determinization techniques have been developed to tackle the size problem of the resulting controller. Neural networks capabilities at approximating function and substituting look-up tables in broad applications, such as flight-critical system and deep reinforcement learning, motivate us to suggest utilizing neural networks as an alternative approach to represent the controller. In this work, the evaluation of the capability of neural networks as a viable approach to store a symbolic controller is presented. We present the utilization of neural networks to store deterministic controllers. We also propose a determinization technique based on the multiclass classification task in neural networks to determinize the controller. Additionally, we employ neural networks to store non-deterministic controllers by preserving the redundancy of the control inputs. Comparisons between binary decision diagrams (BDDs) and neural networks as compact representations of symbolic controllers are performed. Results show that neural networks are able to represent symbolic controllers in a more compact way compared to BDDs considering the size overhead produced by the CUDD package as its manipulation library.
Embedded Systems
Advisors/Committee Members: Mazo Espinosa, M. (mentor), van Genderen, Arjan (graduation committee), Kober, Jens (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Symbolic Controllers; Neural Networks; Correct-by-Design
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):
Irawan, A. (. (2018). Representing Symbolic Controllers with Deep Neural Networks. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:677cdde8-b3fa-4fb4-8db2-3c87b03b5085
Chicago Manual of Style (16th Edition):
Irawan, Angga (author). “Representing Symbolic Controllers with Deep Neural Networks.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:677cdde8-b3fa-4fb4-8db2-3c87b03b5085.
MLA Handbook (7th Edition):
Irawan, Angga (author). “Representing Symbolic Controllers with Deep Neural Networks.” 2018. Web. 12 Apr 2021.
Vancouver:
Irawan A(. Representing Symbolic Controllers with Deep Neural Networks. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:677cdde8-b3fa-4fb4-8db2-3c87b03b5085.
Council of Science Editors:
Irawan A(. Representing Symbolic Controllers with Deep Neural Networks. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:677cdde8-b3fa-4fb4-8db2-3c87b03b5085
Delft University of Technology
7.
de Groot, Jurriaan (author).
Swarm Behaviour for the Zebro Robot.
Degree: 2017, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:a78199fb-5f8e-4f31-9851-90bc15044306
► Nature has found many interesting solutions to similar problems that we face with robots. Swarming in robotics is an interesting field to reduce cost and…
(more)
▼ Nature has found many interesting solutions to similar problems that we face with robots. Swarming in robotics is an interesting field to reduce cost and risk, and provide a scalable solution to certain problems. The Zebro Project of the TU Delft performs research in the field of swarm robotics using the six legged robot, called a Zebro. Swarm robotics consists of using a large amount of small, independent robots that respond to one another in order to create a distributed, global behaviour. The robots have been simulated using the Unity engine, to investigate methods to accomplish swarming behaviour. The simulated Zebros and sensors are modelled after real life designs. The algorithm is based on bird flocking behaviour to create mobile and cohesive swarming behaviour. The Zebro robots are not ready for testing yet, but the algorithms have been prepared for testing using a Raspberry Pi.
Zebro Project
Embedded Systems
Advisors/Committee Members: Verhoeven, Chris (mentor), Hakkennes, Edwin (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Zebro; swarm robotics; swarming; Simulation
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 Groot, J. (. (2017). Swarm Behaviour for the Zebro Robot. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:a78199fb-5f8e-4f31-9851-90bc15044306
Chicago Manual of Style (16th Edition):
de Groot, Jurriaan (author). “Swarm Behaviour for the Zebro Robot.” 2017. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:a78199fb-5f8e-4f31-9851-90bc15044306.
MLA Handbook (7th Edition):
de Groot, Jurriaan (author). “Swarm Behaviour for the Zebro Robot.” 2017. Web. 12 Apr 2021.
Vancouver:
de Groot J(. Swarm Behaviour for the Zebro Robot. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:a78199fb-5f8e-4f31-9851-90bc15044306.
Council of Science Editors:
de Groot J(. Swarm Behaviour for the Zebro Robot. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:a78199fb-5f8e-4f31-9851-90bc15044306
Delft University of Technology
8.
Thomas, Arun (author).
Autopilot Design for Software-in-the-Loop Validation of Fixed-wing UAV Guidance Laws.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:fde5d464-52d5-449c-8160-52ba9c41b21b
► UnmannedAerial Vehicles(UAVs) have multi-domain applications and fixed-wing UAVs are a widely used class. There is ongoing research on topics in view to optimize the control…
(more)
▼ UnmannedAerial Vehicles(UAVs) have multi-domain applications and fixed-wing UAVs are a widely used class. There is ongoing research on topics in view to optimize the control and guidance of UAVs. This work explores the design, implementation and Software-in-the-Loop validation of an autopilot using adaptive guidance laws with emphasis on formation control of multiple fixed-wing UAVs. The work is done on Raspberry Pis in C++ which can be interfaced to standard autopilots as companion computers. The work splits a mission given by the user into primitive missions and uses an adaptive vector field approach for following it. For formation control, the work implements a discretized version of the Model Reference Adaptive Control synchronisation laws for multi-agent systems. Simulations are done in a distributed setting with a server program designed for the purpose. The server program handles the user inputs and configurations of the UAVs.
Electrical Engineer | Embedded Systems
Advisors/Committee Members: Baldi, Simone (mentor), Verhaegen, Michel (graduation committee), van Genderen, Arjan (graduation committee), Wang, Ximan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Unmanned Aerial Vehicle; Formation Control; Adaptive Vector Field; synchronization; Autopilot Design
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):
Thomas, A. (. (2019). Autopilot Design for Software-in-the-Loop Validation of Fixed-wing UAV Guidance Laws. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:fde5d464-52d5-449c-8160-52ba9c41b21b
Chicago Manual of Style (16th Edition):
Thomas, Arun (author). “Autopilot Design for Software-in-the-Loop Validation of Fixed-wing UAV Guidance Laws.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:fde5d464-52d5-449c-8160-52ba9c41b21b.
MLA Handbook (7th Edition):
Thomas, Arun (author). “Autopilot Design for Software-in-the-Loop Validation of Fixed-wing UAV Guidance Laws.” 2019. Web. 12 Apr 2021.
Vancouver:
Thomas A(. Autopilot Design for Software-in-the-Loop Validation of Fixed-wing UAV Guidance Laws. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:fde5d464-52d5-449c-8160-52ba9c41b21b.
Council of Science Editors:
Thomas A(. Autopilot Design for Software-in-the-Loop Validation of Fixed-wing UAV Guidance Laws. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:fde5d464-52d5-449c-8160-52ba9c41b21b
Delft University of Technology
9.
Pathak, Chinmay (author).
Exploring normalizing flow for anomaly detection.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:f5588df3-626d-42cc-8059-32e5bb16d852
► Anomaly detection is a task of interest in many domains. Typical way of tackling this problem is using an unsupervised way. Recently, deep neural network…
(more)
▼ Anomaly detection is a task of interest in many domains. Typical way of tackling this problem is using an unsupervised way. Recently, deep neural network based density estimators such as Normalizing flows have seen a huge interest. The ability of these models to do the exact latent-variable inference and exact log-likelihood calculation with invertible architecture makes them interesting for the task of anomaly detection. In this work we explore the such normalizing flow-based model approach for anomaly detection in the novel BoroscopeV1 dataset which contains videos of the actual industry boroscope video material and has large noise. We verify the correctness of the models on a toy dataset. We found that the black pixels and high frequency in the image affect the model likelihood adversely. The experimental evidence shows that the normalizing flow-based approach can be used for the task of anomaly detection
Electrical Engineering
Advisors/Committee Members: van Gemert, Jan (mentor), Reinders, Marcel (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Anomaly Detection; Outlier detection; Autoencoder; Generative Algorithms; unsupervised learning; one-class classification; GLOW; Normalizing flows
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):
Pathak, C. (. (2019). Exploring normalizing flow for anomaly detection. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:f5588df3-626d-42cc-8059-32e5bb16d852
Chicago Manual of Style (16th Edition):
Pathak, Chinmay (author). “Exploring normalizing flow for anomaly detection.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:f5588df3-626d-42cc-8059-32e5bb16d852.
MLA Handbook (7th Edition):
Pathak, Chinmay (author). “Exploring normalizing flow for anomaly detection.” 2019. Web. 12 Apr 2021.
Vancouver:
Pathak C(. Exploring normalizing flow for anomaly detection. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:f5588df3-626d-42cc-8059-32e5bb16d852.
Council of Science Editors:
Pathak C(. Exploring normalizing flow for anomaly detection. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:f5588df3-626d-42cc-8059-32e5bb16d852
Delft University of Technology
10.
Zhang, Yu (author).
High Accuracy Eye-Tracker For Proton Clinic Environment.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e
► This project aims to improve the accuracy of the eye tracking system, which consists of two cameras and two infrared LED light sources. This highly…
(more)
▼ This project aims to improve the accuracy of the eye tracking system, which consists of two cameras and two infrared LED light sources. This highly non-invasive technology, which is the feature-based video-oculographic eye tracking system, determines the position of the eye by monitoring the eye features such as the pupil center and glints. The accuracy of estimating the eye position and orientation is critical in the proton clinic environment, and is to be required higher than those in commercially available eye-tracking system.
Electrical Engineer | Embedded Systems
Advisors/Committee Members: Verhaegen, Michel (mentor), Soloviev, Oleg (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: stereo camera; 3d reconstruction; calibration
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):
Zhang, Y. (. (2019). High Accuracy Eye-Tracker For Proton Clinic Environment. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e
Chicago Manual of Style (16th Edition):
Zhang, Yu (author). “High Accuracy Eye-Tracker For Proton Clinic Environment.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e.
MLA Handbook (7th Edition):
Zhang, Yu (author). “High Accuracy Eye-Tracker For Proton Clinic Environment.” 2019. Web. 12 Apr 2021.
Vancouver:
Zhang Y(. High Accuracy Eye-Tracker For Proton Clinic Environment. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e.
Council of Science Editors:
Zhang Y(. High Accuracy Eye-Tracker For Proton Clinic Environment. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:25d52461-46d3-4883-a1f6-ca9def83a25e
Delft University of Technology
11.
Singh, Satish (author).
Adaptive Formation Control and Semi-Physical Simulator for Multi-Fixed Wing UAVs.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:6adc063c-1f27-42a5-8fd5-28fadad660da
► Formation flying is a phenomenon observed very often in the natural world, e.g. birds flying in a flock. The past decade has given a lot…
(more)
▼ Formation flying is a phenomenon observed very often in the natural world, e.g. birds flying in a flock. The past decade has given a lot of emphasis on the research for the control of autonomous Unmanned Aerial Vehicles (UAVs) of the fixed-wing kind, in an effort to emulate the behavior of natural flocks. Emulating this behavior requires the construction of path following and formation control laws with the capability of adapting to changing situations, in a similar way as natural flocks can do. This thesis is devoted to studying Adaptive Vector Field Guidance laws and Adaptive Formation laws for fixed-wing UAVs. Formation control relies on an adaptive hierarchical formation control method for uncertain heterogeneous nonlinear agents with Euler-Lagrange (EL) dynamics. It is shown that various formations (T-V-Y formations) can be established using this method, tested using a Matlab/Simulink environment. Additionally, a distinguishing feature of this thesis is the development of a 3D-Simulation platform to perform a hardware in the loop (HITL) simulations (i.e. using the control hardware on board of an actual UAV): a Raspberry Pi is used to run the formation control algorithm and to communicate with a Pixhawk Cube autopilot board which contains the low-level control algorithm. The autopilot board is then connected to a 3D Simulator (Gazebo) and Ground Control System (QGroundControl). The proposed HITL platform promises to facilitate the testing and validation of guidance and formation laws in a much more realistic way than a Matlab/Simulink environment can do.
Advisors/Committee Members: Baldi, Simone (mentor), Wahls, Sander (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Fixed-wing UAVs; Adaptive formation control; Gazebo; software-in-the-loop; PX4
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):
Singh, S. (. (2019). Adaptive Formation Control and Semi-Physical Simulator for Multi-Fixed Wing UAVs. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:6adc063c-1f27-42a5-8fd5-28fadad660da
Chicago Manual of Style (16th Edition):
Singh, Satish (author). “Adaptive Formation Control and Semi-Physical Simulator for Multi-Fixed Wing UAVs.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:6adc063c-1f27-42a5-8fd5-28fadad660da.
MLA Handbook (7th Edition):
Singh, Satish (author). “Adaptive Formation Control and Semi-Physical Simulator for Multi-Fixed Wing UAVs.” 2019. Web. 12 Apr 2021.
Vancouver:
Singh S(. Adaptive Formation Control and Semi-Physical Simulator for Multi-Fixed Wing UAVs. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:6adc063c-1f27-42a5-8fd5-28fadad660da.
Council of Science Editors:
Singh S(. Adaptive Formation Control and Semi-Physical Simulator for Multi-Fixed Wing UAVs. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:6adc063c-1f27-42a5-8fd5-28fadad660da
Delft University of Technology
12.
Mani, Pranav (author).
Computational Imaging for Earth Surveillance.
Degree: 2017, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:ea4b9a19-4c05-4f2c-9224-885f851f00b5
► Cameras are used in various applications and one such common application has been space. Delfi Space is the CubeSat Development program of the Delft University…
(more)
▼ Cameras are used in various applications and one such common application has been space. Delfi Space is the CubeSat Development program of the
Delft University of
Technology and a subprogram of Defi-Space is Delfi-PQ which aims to develop PocketQubes which are an order of magnitude smaller than the CubeSat standards. One of the advanced payloads that would potentially be a part of the Delfi-PQ is an imager/camera. The imager needs to be as small as possible in order to fit into the Delfi-PQ satellites. The design of the camera has remained the same throughout the years and one of the reasons that increase the thickness of the camera is the presence of lenses. A way to reduce the size of the camera would be to remove the lens out of the equation. However, this introduces additional problems and trade-offs in the camera. These lenses can be replaced by masks/coded apertures. One of the additional steps in using coded-apertures is that additional computational steps need to be performed in order to reconstruct the image. The kind of computation that needs to be performed depends on the kind of masks that would be used. In this thesis, a separable mask is chosen and computer simulations on separable masks have been performed. Two image sensors that can be used in the picosatellite were chosen for implementation and the hardware/software is designed and developed. The experimental setup for determining the field of view of a lensless camera has been developed and tested. One of the trade-offs observed through the experiments is that the acceptance angle of a lensless imager had reduced by 38 percent and 31.8 percent in the horizontal and vertical directions compared to a conventional lens-based system. Based on the experimental results, the field of view of the camera has also been determined. A singular value decomposition based method has been developed and is used to align and calibrate the camera with the mask. The final step is estimating the system matrices of the lensless system. The system matrices enable the perfect reconstruction and a complete realization of a separable mask based lensless camera. A scheme for estimating the system matrices of the lensless imager using Hadamard basis is proposed and confirmed using simulations and the strategy for experimental verification is proposed. As far as we know, this is the first study that focuses on designing and developing a lensless camera in the visible light domain for use in picosatellites.
Advisors/Committee Members: van Genderen, Arjan (mentor), Shao, Yifeng (mentor), Kuiper, Hans (mentor), Delft University of Technology (degree granting institution).
Subjects/Keywords: Lensless Imaging; Cubesats; Coded Aperture Imaging
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):
Mani, P. (. (2017). Computational Imaging for Earth Surveillance. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:ea4b9a19-4c05-4f2c-9224-885f851f00b5
Chicago Manual of Style (16th Edition):
Mani, Pranav (author). “Computational Imaging for Earth Surveillance.” 2017. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:ea4b9a19-4c05-4f2c-9224-885f851f00b5.
MLA Handbook (7th Edition):
Mani, Pranav (author). “Computational Imaging for Earth Surveillance.” 2017. Web. 12 Apr 2021.
Vancouver:
Mani P(. Computational Imaging for Earth Surveillance. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:ea4b9a19-4c05-4f2c-9224-885f851f00b5.
Council of Science Editors:
Mani P(. Computational Imaging for Earth Surveillance. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:ea4b9a19-4c05-4f2c-9224-885f851f00b5
Delft University of Technology
13.
in 't Hout, Maarten (author).
Kernel isolation of a Capability-based security Operating System.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:41767be9-f48f-468e-abf6-949dbd7cce96
► Providing more confidentiality by extending a capability-based OS trough a hardware enforced isolation between the memory of the kernel and other memory. By employing memory…
(more)
▼ Providing more confidentiality by extending a capability-based OS trough a hardware enforced isolation between the memory of the kernel and other memory. By employing memory tagging and hardware based Inter Process Communication (IPC) this defense gives an overhead of 26 percent.
Advisors/Committee Members: Wong, Stephan (mentor), van Genderen, Arjan (graduation committee), Langendoen, Koen (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Memory Tagging; Capability-based security; Genode; Inter Process Communication; Kernel Isolation
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):
in 't Hout, M. (. (2018). Kernel isolation of a Capability-based security Operating System. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:41767be9-f48f-468e-abf6-949dbd7cce96
Chicago Manual of Style (16th Edition):
in 't Hout, Maarten (author). “Kernel isolation of a Capability-based security Operating System.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:41767be9-f48f-468e-abf6-949dbd7cce96.
MLA Handbook (7th Edition):
in 't Hout, Maarten (author). “Kernel isolation of a Capability-based security Operating System.” 2018. Web. 12 Apr 2021.
Vancouver:
in 't Hout M(. Kernel isolation of a Capability-based security Operating System. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:41767be9-f48f-468e-abf6-949dbd7cce96.
Council of Science Editors:
in 't Hout M(. Kernel isolation of a Capability-based security Operating System. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:41767be9-f48f-468e-abf6-949dbd7cce96
Delft University of Technology
14.
van der Vlag, Michiel (author).
Multi-GPU Brain: A multi-node implementation for an extended Hodgkin-Huxley simulator.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:6e93f997-1b8a-4af6-bfaa-261c205a9b04
► Current brain simulators do no scale linearly to realistic problem sizes (e.g. >100,000 neurons), which makes them impractical for researchers. The goal of the thesis…
(more)
▼ Current brain simulators do no scale linearly to realistic problem sizes (e.g. >100,000 neurons), which makes them impractical for researchers. The goal of the thesis is to explore the use of true multi-GPU acceleration on computationally challenging brain models and to assess the scalability of such models given sufficient access to multi-node acceleration platforms. The brain model used is a state-of-the-art, extended HodgkinHuxley, biophysically- meaningful, three-compartmental model of the inferior-olivary nucleus. Not only the simulation of the cells, but also the setup of the network is taken into account when designing and benchmarking the multi-GPU version. For network sizes varying from 65K to 4M cells, 10, 100 and 1000 synapses per neuron are simulated. These simulations are executed on 8, 16, 32 and 48 GPUs. A Gaussian-distributed network of 4 million cells with a density of 1,000 synapses per neuron executed on 48 GPUs, is setup and simulated in 465.69 seconds, of which the cell-computation phase takes 4.57 seconds, obtaining a speedup of 50 times the execution time on a single GPU. A uniform-distributed network of same size and density is setup and simulated in 889.89 seconds of which the cell-computation phase takes 10.09 seconds, obtaining a speedup of 8 times the execution on a single GPU. For the implemented design, the inter-GPU communication becomes the major bottleneck, as latency increases when the sent packet sizes increase. This communication overhead does not dominate the overall execution while scaling network sizes is tractable. This scalable design gives a good prospect for neuroscientists, proving that large network-size simulations are possible, using a multi-GPU setup.
Computer Engineering
Advisors/Committee Members: Strydis, C (mentor), Al-Ars, Zaid (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: multi GPU; brain simulator; cluster; Hodgkin-Huxley; gap junctions; neuron network; Cartesius; multi compartment; linear scaling
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):
van der Vlag, M. (. (2019). Multi-GPU Brain: A multi-node implementation for an extended Hodgkin-Huxley simulator. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:6e93f997-1b8a-4af6-bfaa-261c205a9b04
Chicago Manual of Style (16th Edition):
van der Vlag, Michiel (author). “Multi-GPU Brain: A multi-node implementation for an extended Hodgkin-Huxley simulator.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:6e93f997-1b8a-4af6-bfaa-261c205a9b04.
MLA Handbook (7th Edition):
van der Vlag, Michiel (author). “Multi-GPU Brain: A multi-node implementation for an extended Hodgkin-Huxley simulator.” 2019. Web. 12 Apr 2021.
Vancouver:
van der Vlag M(. Multi-GPU Brain: A multi-node implementation for an extended Hodgkin-Huxley simulator. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:6e93f997-1b8a-4af6-bfaa-261c205a9b04.
Council of Science Editors:
van der Vlag M(. Multi-GPU Brain: A multi-node implementation for an extended Hodgkin-Huxley simulator. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:6e93f997-1b8a-4af6-bfaa-261c205a9b04
Delft University of Technology
15.
van der Bok, Kees (author).
Polyhedral Compilation for Data Flow Computers.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:4b7278df-1660-4566-bf0f-1cc641853173
► The increasing transistor density of Integrated Circuits (ICs) ever since their introduction, has scaled the computational performance of microprocessors. As a consequence of the gain…
(more)
▼ The increasing transistor density of Integrated Circuits (ICs) ever since their introduction, has scaled the computational performance of microprocessors. As a consequence of the gain in transistor density, the power dissipation density has also increased to a degree that has become a limiting factor in further performance scaling. The prevalent control flow computing paradigm is, especially in the context of High Performance Computing (HPC), faced with this power crisis. Data flow computing can achieve a better computations per unit power ratio and might therefore be the solution to achieving exa-scale computing, enabling progress in science and
technology. This work contributes in investigating methods for increasing the abstraction level of data flow programming by using a Polyhedral Process Network (PPN) as abstraction to facilitate automated analysis and transformation of data flow applications. A Polyhedral Process Network (PPN) is a process network based on Polyhedral Compilation (PC) a mathematical framework for code analysis and optimisations. A tool has been implemented to translate a PPN to a data flow implementation. The Maxeler Data Flow Engine (DFE)
technology, a data flow hardware platform supported by a tool-flow, is used as target
technology. For a number of specific challenges involved in the transformation from PPN to DFE-implementation a method has been implemented. This has shown that a PPN as well as the capabilities of PC are useful concepts that are applicable to further increase of the abstraction-level of data flow computing. However the transformation from PPN to DFE-implementation is complex. Therefore this work concludes that the development of a data flow tailored Polyhedral Compilation (PC) abstraction is the most promising future direction.
Advisors/Committee Members: van Genderen, Arjan (mentor), Gaydadjiev, Georgi (mentor), Wong, Stephan (graduation committee), Strydis, Christos (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Data flow Computing; Polyhedral Compilation; Data Flow Engine; Polyhedral Process Networks
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):
van der Bok, K. (. (2018). Polyhedral Compilation for Data Flow Computers. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:4b7278df-1660-4566-bf0f-1cc641853173
Chicago Manual of Style (16th Edition):
van der Bok, Kees (author). “Polyhedral Compilation for Data Flow Computers.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:4b7278df-1660-4566-bf0f-1cc641853173.
MLA Handbook (7th Edition):
van der Bok, Kees (author). “Polyhedral Compilation for Data Flow Computers.” 2018. Web. 12 Apr 2021.
Vancouver:
van der Bok K(. Polyhedral Compilation for Data Flow Computers. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:4b7278df-1660-4566-bf0f-1cc641853173.
Council of Science Editors:
van der Bok K(. Polyhedral Compilation for Data Flow Computers. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:4b7278df-1660-4566-bf0f-1cc641853173
Delft University of Technology
16.
Ntasios, Angelos (author).
Dynamic Hardware Binary Translator for ρ-VEX.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:2f693fc9-610b-4b15-9a1f-9359362d1cc0
► The last years, there has been a increasing trend in embedded system and FPGA im-plementations for greater flexibility and also, a rising adaptation of heterogeneous…
(more)
▼ The last years, there has been a increasing trend in embedded system and FPGA im-plementations for greater flexibility and also, a rising adaptation of heterogeneous plat-forms. These platforms often include FPGAs and embedded cores side by side.ρ-VEXcore, developed and maintained by the Computer Engineering group of TU Delft, is aVLIW processor mostly developed on FPGAs. On the other hand, popular embeddedarchitectures include the established ARM architecture and the newly rising RISC-Varchitecture. In order for these architectures to communicate with theρ-VEX core, atranslation procedure has to be established. In this thesis, a hardware dynamic binarytranslator was designed, able to translate on-the-fly ARM and RISCV instructions toρ-VEX instructions. The translator will enable heterogeneous platforms to be developedand also allow pre-compiled binaries for one (ARM/RISC-V) architecture to be directlyported in another one (ρ-VEX). This thesis provides a design process that focuses ontwo approaches: first is the minimization of the overhead resulting from the transla-tion procedure, and the second is the minimization of the hardware alterations and/orhardware additions. These design choices were examined in theρ-VEX core simulator.The simulations show that for overhead minimization, the resulting overhead can be aslow as 1% for the RISC-V with focusing on the overhead minimization, and as high as1024% with ARM and hardware minimization in mind.
ρ-VEX
Computer Engineering
Advisors/Committee Members: Wong, Stephan (mentor), van Genderen, Arjan (graduation committee), Pawelczak, Przemek (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: ρ-VEX; binary translator; FPGA; processor; dynamic hardware translator; RISC-V; ARM
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):
Ntasios, A. (. (2019). Dynamic Hardware Binary Translator for ρ-VEX. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:2f693fc9-610b-4b15-9a1f-9359362d1cc0
Chicago Manual of Style (16th Edition):
Ntasios, Angelos (author). “Dynamic Hardware Binary Translator for ρ-VEX.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:2f693fc9-610b-4b15-9a1f-9359362d1cc0.
MLA Handbook (7th Edition):
Ntasios, Angelos (author). “Dynamic Hardware Binary Translator for ρ-VEX.” 2019. Web. 12 Apr 2021.
Vancouver:
Ntasios A(. Dynamic Hardware Binary Translator for ρ-VEX. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:2f693fc9-610b-4b15-9a1f-9359362d1cc0.
Council of Science Editors:
Ntasios A(. Dynamic Hardware Binary Translator for ρ-VEX. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:2f693fc9-610b-4b15-9a1f-9359362d1cc0
Delft University of Technology
17.
Noordam, Leon (author).
VHDL Implementation of 4096-bit RNS Montgomery Modular Exponentiation for RSA Encryption.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:3174589c-f8a1-4da7-b2a8-79ddb22e7079
► Modular exponentiation is the basis needed to perform RSA encryption and decryption. Execution of 4096-bit modular exponentiation using an embedded system requires many arithmetic operations.…
(more)
▼ Modular exponentiation is the basis needed to perform RSA encryption and decryption. Execution of 4096-bit modular exponentiation using an embedded system requires many arithmetic operations. This work aims to improve the performance of modular exponentiation for an existing FPGA platform containing a soft core RISC-V processor. The solution is to introduce a peripheral that performs Montgomery multiplication with 4096-bit operands. These operands are represented using the Residue Number System (RNS) and each residue is assigned to a RNS processor core. In total, the system consists of 121 RNS cores and each core is responsible for a 34-bit residue. RNS Montgomery multiplication requires a base extension algorithm, which will be represented by the Bajard and the Shenoy base extensions. Two designs are proposed: one using a tree-based reduction circuit and one with an iterative reduction circuit. The former focuses on performance overall, while the latter is more efficient in terms of performance per area. Synthesis for a XCKU035 FPGA gives an area usage of 83484 LUTs for the tree-based design and 41857 LUTs for the iterative design. Both designs also require 132.5 BRAMs and 485 DSP blocks and are running at a clock frequency of 400 MHz. The tree-based design performs Montgomery multiplication using 4096-bit operands in 434 cycles (1.09 µs), while the iterative design does that in 577 cycles (1.44 µs). For performing modular exponentiation, the sliding window method is used with an optimal window size of seven. A modular exponentiation with 4096-bit operands takes on average 5.09 ms for the tree-based design, while the iterative version needs 6.78 ms. Few other implementations were found performing Montgomery multiplication using 4096-bit operands. However, compared to those the proposed design provides better performance.
Computer Engineering
Advisors/Committee Members: van Genderen, Arjan (mentor), Wiersma, Ard (mentor), Hoekstra, Jaap (graduation committee), Cotofana, Sorin (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: 4096 bits; RSA; RNS; FPGA; Montgomery multiplication; modular reduction; base extension; exponentiation; hardware accelerator; multi-core; parallel processing; heterogeneous architecture; encryption; decryption
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):
Noordam, L. (. (2019). VHDL Implementation of 4096-bit RNS Montgomery Modular Exponentiation for RSA Encryption. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:3174589c-f8a1-4da7-b2a8-79ddb22e7079
Chicago Manual of Style (16th Edition):
Noordam, Leon (author). “VHDL Implementation of 4096-bit RNS Montgomery Modular Exponentiation for RSA Encryption.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:3174589c-f8a1-4da7-b2a8-79ddb22e7079.
MLA Handbook (7th Edition):
Noordam, Leon (author). “VHDL Implementation of 4096-bit RNS Montgomery Modular Exponentiation for RSA Encryption.” 2019. Web. 12 Apr 2021.
Vancouver:
Noordam L(. VHDL Implementation of 4096-bit RNS Montgomery Modular Exponentiation for RSA Encryption. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:3174589c-f8a1-4da7-b2a8-79ddb22e7079.
Council of Science Editors:
Noordam L(. VHDL Implementation of 4096-bit RNS Montgomery Modular Exponentiation for RSA Encryption. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:3174589c-f8a1-4da7-b2a8-79ddb22e7079
Delft University of Technology
18.
Saleem, Muhammad Usman (author).
Dynamically Reconfigurable Fault-Tolerant Design of r-VEX Softcore Processor.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:2ed85cd4-cd0d-4800-a1df-973b0584726e
► Over the past many years, technology scaling has resulted in a continuous reduction of lateral and vertical dimensions of transistors. The technology scaling, on the…
(more)
▼ Over the past many years,
technology scaling has resulted in a continuous reduction of lateral and vertical dimensions of transistors. The
technology scaling, on the one hand, has led to a commensurate performance gain for very-large-scale integration (VLSI) circuits, but on the other hand, has also made such circuits more vulnerable to ionizing radiations which can cause single event effects(SEEs). These SEEs may cause the underlying user circuitry to deviate from its normal behavior. Devices that are destined for space missions need special protection for such kind of anomalies as space environment is filled with massive amount of high energy particles and ionizing radiations. In this thesis, the design, implementation, and verification of a fault-tolerant r-VEX, a softcore processor, is presented, so that it could be used as an attractive alternative to expensive radiation-hardened processors for space-based applications. r-VEX is a VLIW based, dynamically reconfigurable processor. Keeping in line with its inherent attribute, a dynamically reconfigurable fault-tolerant mode is presented in this work, which provides the running application an option to activate and deactivate the fault-tolerant mode multiple times. In this mode, for the protection of processor pipeline, a non-traditional TMR approach that requires 3 lanegroups running in 2-way mode is implemented. For the reliability of user memories, Hamming codes are implemented as an ECC coding scheme. The functionally of our fault-tolerant design is verified by using both a simulation-based platform (ModelSim) and an on-board FPGA platform (ML605 development kit). To measure the fault-tolerant capabilities of the r-VEX core, saboteurs are used to artificially inject faults at various predefined locations in the core. The obtained results have shown that our design can mitigate all injected single faults in the pipeline and double faults in the caches, without triggering any failure. The dynamically configurable fault-tolerant feature is obtained at the cost of about 30% additional resource utilization and 20% reduction in the maximum operating frequency.
Advisors/Committee Members: Wong, Stephan (mentor), van Genderen, Arjan (graduation committee), Menicucci, Alessandra (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: fault tolerance; Processor; VLIW; space
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):
Saleem, M. U. (. (2018). Dynamically Reconfigurable Fault-Tolerant Design of r-VEX Softcore Processor. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:2ed85cd4-cd0d-4800-a1df-973b0584726e
Chicago Manual of Style (16th Edition):
Saleem, Muhammad Usman (author). “Dynamically Reconfigurable Fault-Tolerant Design of r-VEX Softcore Processor.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:2ed85cd4-cd0d-4800-a1df-973b0584726e.
MLA Handbook (7th Edition):
Saleem, Muhammad Usman (author). “Dynamically Reconfigurable Fault-Tolerant Design of r-VEX Softcore Processor.” 2018. Web. 12 Apr 2021.
Vancouver:
Saleem MU(. Dynamically Reconfigurable Fault-Tolerant Design of r-VEX Softcore Processor. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:2ed85cd4-cd0d-4800-a1df-973b0584726e.
Council of Science Editors:
Saleem MU(. Dynamically Reconfigurable Fault-Tolerant Design of r-VEX Softcore Processor. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:2ed85cd4-cd0d-4800-a1df-973b0584726e
Delft University of Technology
19.
Tetteroo, Jonathan (author).
Exploring Convolutional Neural Networks on the ρ-VEX architecture.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:39b1653b-cde7-419b-bcd0-8549b6e34db5
► As machine learning algorithms play an ever increasing role in today's technology, more demands are placed on computational hardware to run these algorithms efficiently. In…
(more)
▼ As machine learning algorithms play an ever increasing role in today's technology, more demands are placed on computational hardware to run these algorithms efficiently. In recent years, Convolutional Neural Networks (CNNs) have become an important part of machine learning applications in areas such as object recognition and detection. In this thesis we will explore how we can implement CNNs on the ρ-VEX processor and what can be done to optimize the performance. The ρ-VEX processor is a VLIW processor that was developed at the Delft University of Technology and that can be reconfigured during runtime to take advantage of Instruction Level Parallelism (ILP) and Thread Level Parallelism (TLP) in an application. In this work we have developed a streaming pipeline in a simulator consisting of multiple 8-issue ρ-VEX cores connected with memory buffers. This pipeline was designed to execute CNN inference and take advantage of the overlapped execution to increase throughput. Furthermore, as each ρ-VEX core can be configured to operate in a one core, two core or four core mode based on available ILP and TLP, we can adapt the processor based on the current operation being executed and the amount of parallelism that is available. By generating the required code from a high-level description of the CNN, it becomes straightforward to test multiple configurations of the pipeline and determine which creates the best performance. The implementation was subsequently tested using a simple network trained on the MNIST dataset. By dividing the workload of the convolutional layers over multiple contexts to take advantage of data-level parallelism, we improved the latency by 3.03x and the throughput by 3.14x in simulation. By creating a pipeline of six cores in a single context configuration in the simulator, we achieved a throughput increase of 1.77x. A hardware implementation of the pipeline was also synthesized for a Virtex-6 FPGA, consisting of four 2-issue ρ-VEX cores at a clock speed of 200 MHz. We subsequently propose several optimizations to increase performance of CNN inference on the ρ-VEX architecture.
Computer Engineering
Advisors/Committee Members: Wong, Stephan (mentor), van Genderen, Arjan (graduation committee), van Gemert, Jan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Convolutional Neural Networks; rVEX; Streaming
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):
Tetteroo, J. (. (2018). Exploring Convolutional Neural Networks on the ρ-VEX architecture. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:39b1653b-cde7-419b-bcd0-8549b6e34db5
Chicago Manual of Style (16th Edition):
Tetteroo, Jonathan (author). “Exploring Convolutional Neural Networks on the ρ-VEX architecture.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:39b1653b-cde7-419b-bcd0-8549b6e34db5.
MLA Handbook (7th Edition):
Tetteroo, Jonathan (author). “Exploring Convolutional Neural Networks on the ρ-VEX architecture.” 2018. Web. 12 Apr 2021.
Vancouver:
Tetteroo J(. Exploring Convolutional Neural Networks on the ρ-VEX architecture. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:39b1653b-cde7-419b-bcd0-8549b6e34db5.
Council of Science Editors:
Tetteroo J(. Exploring Convolutional Neural Networks on the ρ-VEX architecture. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:39b1653b-cde7-419b-bcd0-8549b6e34db5
Delft University of Technology
20.
Rahaman Khan, Tasneem (author).
Automotive RADAR: Real-time implementation of joint sensing and communication waveform on a microcontroller.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:2147659e-8e65-47a5-a32c-4e69f5df1303
► The automotive radars are significantly drifting towards the 77GHz electromagnetic spectrum band, and by 2020, they will no longer operate in the 24GHz band as…
(more)
▼ The automotive radars are significantly drifting towards the 77GHz electromagnetic spectrum band, and by 2020, they will no longer operate in the 24GHz band as per the regulations given by the European Telecommunications Standards Institute (ETSI) and Federal Communications Commission (FCC) in Europe and the U.S. With the communication systems also heaping towards the magnitude of radar functionality, the 77GHz spectrum has opened a broad scope and possibility to combine both communication and radar waveforms and offer joint radar sensing and communication functionality.The true aim of this thesis work is to implement one of the widely used digital modulation techniques namely binary phase shift keying to embed information bits in the frequency modulated continuous radar waveform (FMCW) via a microcontroller (MCU) to facilitate real-time radar processing and information exchange.The report starts with presenting a theoretical overview on FMCW automotive radar, waveforms for both sensing and communication and a brief review on the MCU's in the automotive radars. The next chapter of the report gives a detailed explanation of the hardware and software architectures on which the thesis implementation is carried out. The following chapter of the report focuses on the main adopted implementation to embed information bits and all the underlying methodologies related to it. Finally, the results of this thesis work are diversified into obtaining real-time 2D fast Fourier transform (FFT) range/doppler spectrum and beat signals, to perform reconstruction of the message embedded in the FMCW waveform and to validate the correctness of the phase coding.
Computer Engineering
Advisors/Committee Members: Uysal, Faruk (mentor), Yarovyi, Alexander (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: FMCW Automotive Radar; Binary Phase coding; joint sensing and communication
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):
Rahaman Khan, T. (. (2018). Automotive RADAR: Real-time implementation of joint sensing and communication waveform on a microcontroller. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:2147659e-8e65-47a5-a32c-4e69f5df1303
Chicago Manual of Style (16th Edition):
Rahaman Khan, Tasneem (author). “Automotive RADAR: Real-time implementation of joint sensing and communication waveform on a microcontroller.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:2147659e-8e65-47a5-a32c-4e69f5df1303.
MLA Handbook (7th Edition):
Rahaman Khan, Tasneem (author). “Automotive RADAR: Real-time implementation of joint sensing and communication waveform on a microcontroller.” 2018. Web. 12 Apr 2021.
Vancouver:
Rahaman Khan T(. Automotive RADAR: Real-time implementation of joint sensing and communication waveform on a microcontroller. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:2147659e-8e65-47a5-a32c-4e69f5df1303.
Council of Science Editors:
Rahaman Khan T(. Automotive RADAR: Real-time implementation of joint sensing and communication waveform on a microcontroller. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:2147659e-8e65-47a5-a32c-4e69f5df1303
Delft University of Technology
21.
Sachdeva, Saumil (author).
Detection and Tracking of a Fast-Moving Object in Squash using a Low-Cost Approach.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:758d345d-ecdf-478e-a534-a23300dbe877
► Advancement in technology has given rise to the need for technology to be utilized in extracting meaningful game-play information from sports. To do so in…
(more)
▼ Advancement in technology has given rise to the need for technology to be utilized in extracting meaningful game-play information from sports. To do so in a ball-game like squash, the prime objective is to perform ball-tracking in an adequate and efficient manner. In squash, ball-tracking is complex due to the small size of the ball, the high-speed movement and constant occlusion due to the continuous movement of the players. The current state-of-the-art ball tracking methods use high-speed cameras along with high-computation power resources to solve these problems in similar sports such as tennis. The aim of this thesis is to solve the challenges in ball-tracking for squash using a low-cost approach with low-computation power resources and a single camera view. A ball-detection system with a high-accuracy and a ball-tracking system which can optimally tackle the problem of occlusion is developed using computer-vision techniques and by utilizing the cues from the game itself. The implementation is carried out on a Raspberry-Pi which is characterized as a low-computation platform with an Arm Cortex-A53 processor. The results show that the tracking-problem can be solved using a low-cost approach for the challenging scenarios that are present in squash. The 2D trajectory of the ball generated as a result can be used for various applications such as line-calling, shot analysis and game analysis.
Electrical Engineer | Embedded Systems
Advisors/Committee Members: van Genderen, Arjan (mentor), Wong, Stephan (mentor), Zuñiga Zamalloa, Marco (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Squash; Ball-Tracking; Computer Vision; Low-Cost
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):
Sachdeva, S. (. (2019). Detection and Tracking of a Fast-Moving Object in Squash using a Low-Cost Approach. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:758d345d-ecdf-478e-a534-a23300dbe877
Chicago Manual of Style (16th Edition):
Sachdeva, Saumil (author). “Detection and Tracking of a Fast-Moving Object in Squash using a Low-Cost Approach.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:758d345d-ecdf-478e-a534-a23300dbe877.
MLA Handbook (7th Edition):
Sachdeva, Saumil (author). “Detection and Tracking of a Fast-Moving Object in Squash using a Low-Cost Approach.” 2019. Web. 12 Apr 2021.
Vancouver:
Sachdeva S(. Detection and Tracking of a Fast-Moving Object in Squash using a Low-Cost Approach. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:758d345d-ecdf-478e-a534-a23300dbe877.
Council of Science Editors:
Sachdeva S(. Detection and Tracking of a Fast-Moving Object in Squash using a Low-Cost Approach. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:758d345d-ecdf-478e-a534-a23300dbe877
Delft University of Technology
22.
Jauhri, Snehal (author).
Interactive Learning in State-space: Enabling robots to learn from non-expert humans.
Degree: 2020, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:be1a04dc-1780-4683-9a7c-77434cd77fa7
► Imitation Learning is a technique that enables programming the behavior of agents through demonstration, as opposed to manually engineering behavior. However, Imitation Learning methods require…
(more)
▼ Imitation Learning is a technique that enables programming the behavior of agents through demonstration, as opposed to manually engineering behavior. However, Imitation Learning methods require demonstration data (in the form of state-action labels) and in many scenarios, the demonstrations can be expensive to obtain or too complex for a demonstrator to execute. This lack or sub-optimality of demonstrations limits the applicability and performance of many Imitation Learning methods. Advancements in Interactive Imitation Learning techniques however, have made it easier for demonstrators to train agents and improve their performance. These techniques involve demonstrators interacting with and guiding the agent as it performs the requisite task. This guidance is typically in the form of corrections or feedback on the current actions being executed by the agent. In this thesis, a novel Interactive Learning technique is proposed that uses human corrective feedback in state-space to train and improve agent behavior. This technique is beneficial since providing guidance to the agent in terms of `changing its state' is often easier or more intuitive for the human demonstrator (as opposed to changing the actions being executed). For instance, in manipulation tasks using a robotic arm, it is easier for the demonstrator to provide state information such as the Cartesian position of the end-effector rather than low-level action information such as joint angles. Keeping such scenarios in mind, we propose our method titled: Teaching Imitative Policies in State-space (TIPS). We evaluate the performance of TIPS for various control tasks as part of the OpenAI Gym toolkit as well as for a manipulation task using a KUKA LBR iiwa robotic arm. We show that through continuous improvement via feedback, agents trained using TIPS outperform the demonstrator and in-turn outperform conventional Imitation Learning agents.
Electrical Engineer | Embedded Systems
Advisors/Committee Members: Kober, Jens (mentor), Celemin, Carlos (mentor), van Genderen, Arjan (graduation committee), Peternel, Luka (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Imitation Learning; Learning from Demonstrations; Robot Control
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):
Jauhri, S. (. (2020). Interactive Learning in State-space: Enabling robots to learn from non-expert humans. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:be1a04dc-1780-4683-9a7c-77434cd77fa7
Chicago Manual of Style (16th Edition):
Jauhri, Snehal (author). “Interactive Learning in State-space: Enabling robots to learn from non-expert humans.” 2020. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:be1a04dc-1780-4683-9a7c-77434cd77fa7.
MLA Handbook (7th Edition):
Jauhri, Snehal (author). “Interactive Learning in State-space: Enabling robots to learn from non-expert humans.” 2020. Web. 12 Apr 2021.
Vancouver:
Jauhri S(. Interactive Learning in State-space: Enabling robots to learn from non-expert humans. [Internet] [Masters thesis]. Delft University of Technology; 2020. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:be1a04dc-1780-4683-9a7c-77434cd77fa7.
Council of Science Editors:
Jauhri S(. Interactive Learning in State-space: Enabling robots to learn from non-expert humans. [Masters Thesis]. Delft University of Technology; 2020. Available from: http://resolver.tudelft.nl/uuid:be1a04dc-1780-4683-9a7c-77434cd77fa7
Delft University of Technology
23.
Pathi Balaji, Vinay (author).
Virtual Referee: A system to identify off- sides in Football.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:6d5b1de0-45f4-41b9-ba0d-46efacec1cfc
► The off-side rule is the most complicated rule in soccer. Today, off-sides are determined with the help of referees running on the sides of the…
(more)
▼ The off-side rule is the most complicated rule in soccer. Today, off-sides are determined with the help of referees running on the sides of the field or with the help of cameras. However, for lower league games the installation of a camera based system is very expensive. This work proposes a sensor based system that can be worn by players which can automatically detect off-sides. In order to create such a system, two aspects had to be researched (a) localisation and (b) ball detection. This work provides an evaluation of an ultra-wide band system in outdoor conditions to solve the localisation problem and various proximity based sensors to solve the ball detection problem. The primary research objective of this work was to find the pit-falls of the ultra-wide band system with respect to our application. It was found that the tri-lateration algorithm implemented on the devices contributed to a lot of errors in localisation accuracy and the overall system suffered from significant packet loss. A custom tri-lateration algorithm along with hardware improvements are proposed. Our results show that the localisation errors are reduced by 56 % and improved system suffers from nearly no packet loss. As for ball detection, results show that ToF sensors provided the best accuracy in detecting the ball.
Electrical Engineer | Embedded Systems
Advisors/Committee Members: Langendoen, Koen (mentor), Zuñiga Zamalloa, Marco (mentor), van Genderen, Arjan (mentor), Delft University of Technology (degree granting institution).
Subjects/Keywords: offsides; localisation; trilateration; ultra-wide band; sport
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):
Pathi Balaji, V. (. (2019). Virtual Referee: A system to identify off- sides in Football. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:6d5b1de0-45f4-41b9-ba0d-46efacec1cfc
Chicago Manual of Style (16th Edition):
Pathi Balaji, Vinay (author). “Virtual Referee: A system to identify off- sides in Football.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:6d5b1de0-45f4-41b9-ba0d-46efacec1cfc.
MLA Handbook (7th Edition):
Pathi Balaji, Vinay (author). “Virtual Referee: A system to identify off- sides in Football.” 2019. Web. 12 Apr 2021.
Vancouver:
Pathi Balaji V(. Virtual Referee: A system to identify off- sides in Football. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:6d5b1de0-45f4-41b9-ba0d-46efacec1cfc.
Council of Science Editors:
Pathi Balaji V(. Virtual Referee: A system to identify off- sides in Football. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:6d5b1de0-45f4-41b9-ba0d-46efacec1cfc
Delft University of Technology
24.
Geers, Matthijs (author).
Optimising Motor Control in Actuator Alignment.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:88f32499-d2a7-4822-8c19-c64d4fd1d235
► The automation of replanting seedlings into bigger trays (transplanting) has been a major industrialisation step in the horticultural sector. Modern machines are abundant in large…
(more)
▼ The automation of replanting seedlings into bigger trays (transplanting) has been a major industrialisation step in the horticultural sector. Modern machines are abundant in large companies and are quite effective, but they are very expensive both in purchase and maintenance. With major clients taking these costs for granted, designers have not stopped to consider ways to alleviate them. This work introduces an affordable electronic system that makes transplanters wireless, allowing for hot-swappable actuators and thus greatly reducing the cost of technicians and downtime as well as procurement. The expensive servo motor drives are replaced by dedicated microcontrollers, allowing the actuators to make their own decisions based on the constraints imposed by various standards of tray sizes and other circumstances. A method is presented to derive the most favourable trajectories, which are then enforced on the system through a closed-loop feedback system. The resulting performance approaches that of the system's predecessor, but at a much more reasonable price. This makes transplanters more affordable for small companies, allowing a broader market to reap the harvest of technological development and increasing worldwide horticultural yield as a result.
Advisors/Committee Members: van Genderen, Arjan (mentor), Neuteboom, Jasper (mentor), Al-Ars, Zaid (graduation committee), de Groot, Joost (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: transplanting; trajectory planning; motor control
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):
Geers, M. (. (2018). Optimising Motor Control in Actuator Alignment. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:88f32499-d2a7-4822-8c19-c64d4fd1d235
Chicago Manual of Style (16th Edition):
Geers, Matthijs (author). “Optimising Motor Control in Actuator Alignment.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:88f32499-d2a7-4822-8c19-c64d4fd1d235.
MLA Handbook (7th Edition):
Geers, Matthijs (author). “Optimising Motor Control in Actuator Alignment.” 2018. Web. 12 Apr 2021.
Vancouver:
Geers M(. Optimising Motor Control in Actuator Alignment. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:88f32499-d2a7-4822-8c19-c64d4fd1d235.
Council of Science Editors:
Geers M(. Optimising Motor Control in Actuator Alignment. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:88f32499-d2a7-4822-8c19-c64d4fd1d235
Delft University of Technology
25.
Versluis, Niels (author).
An Elliptic Curve Cryptography Acceleration Core for OpenVPN on an FPGA Softcore.
Degree: 2020, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:cb0b5c5e-b92f-4e03-914b-93028a4b003c
► Elliptic Curve Cryptography (ECC) performance is a major performance bottleneck when serving many VPN clients from a single server on a low-frequency FPGA softcore CPU.…
(more)
▼ Elliptic Curve Cryptography (ECC) performance is a major performance bottleneck when serving many VPN clients from a single server on a low-frequency FPGA softcore CPU. Using an area-efficient Elliptic Curve Point (ECP) multiplication accelerator core on the same FGPA, a much higher amount of clients can be served using the same FPGA chip. Using the accelerator core, the obtained speedup ranges from 1.6x in a suboptimal configuration up to 7x with a configuration that maximizes the use of ECC when connecting new clients to the server. In this optimal configuration, the total amount of clients that can be served by a single OpenVPN server increases from 80 in the base case, to 350 in the accelerated case.
Q&CE-CE-MS-2020-07
Electrical Engineer | Embedded Systems
Advisors/Committee Members: van Genderen, Arjan (mentor), Wong, Stephan (graduation committee), Picek, Stjepan (graduation committee), van Leeuwen, Tom (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Elliptic Curve Cryptography; OpenVPN; FPGA; Acceleration
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):
Versluis, N. (. (2020). An Elliptic Curve Cryptography Acceleration Core for OpenVPN on an FPGA Softcore. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:cb0b5c5e-b92f-4e03-914b-93028a4b003c
Chicago Manual of Style (16th Edition):
Versluis, Niels (author). “An Elliptic Curve Cryptography Acceleration Core for OpenVPN on an FPGA Softcore.” 2020. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:cb0b5c5e-b92f-4e03-914b-93028a4b003c.
MLA Handbook (7th Edition):
Versluis, Niels (author). “An Elliptic Curve Cryptography Acceleration Core for OpenVPN on an FPGA Softcore.” 2020. Web. 12 Apr 2021.
Vancouver:
Versluis N(. An Elliptic Curve Cryptography Acceleration Core for OpenVPN on an FPGA Softcore. [Internet] [Masters thesis]. Delft University of Technology; 2020. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:cb0b5c5e-b92f-4e03-914b-93028a4b003c.
Council of Science Editors:
Versluis N(. An Elliptic Curve Cryptography Acceleration Core for OpenVPN on an FPGA Softcore. [Masters Thesis]. Delft University of Technology; 2020. Available from: http://resolver.tudelft.nl/uuid:cb0b5c5e-b92f-4e03-914b-93028a4b003c
Delft University of Technology
26.
Giannopoulos, Makis (author).
Hierarchical Mapping: A Rao-Blackwellized Particle Filter based hierarchical SLAM framework.
Degree: 2017, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:2d3532a6-fda2-44ea-b743-b643ad7d122c
► Mobile robots need to be fully autonomous in order to perform their tasks inside their environment. To do that, robots need to have an understanding…
(more)
▼ Mobile robots need to be fully autonomous in order to perform their tasks inside their environment. To do that, robots need to have an understanding of their environment, so that they can successfully localize and navigate themselves within it. The understanding of the robots' environment is created by solving the SLAM (Simultaneous Localization And Mapping) problem. The SLAM problem is usually approached using probabilistic laws; both the robot's path and the environment are estimated and represented by probability distributions. The estimate of the environment is incorporated into a map, which could either be one global map or a network of smaller connected local maps. In small areas where the sensors' errors and inaccuracies remain low, the creation of one global map is preferred. However, as the area grows larger, the global map becomes inaccurate due to accumulated errors. Therefore the strategy of creating a network of local maps is employed. Even though this strategy produces low error results, there is still a limit beyond which it does not scale. Specifically, as the mapping area grows even wider, the number of local maps increases which in turn causes the amount of required memory to increase. In addition, when it comes to loop closure or in other words the procedure of estimating whether the robot returned to a previously visited point in the map, the required computational power increases linearly or sometimes quadratically with respect to the number of local maps. Consequently, SLAM algorithms suffer from scalability problems, especially when the mapping area becomes too large. Since robots are real-world devices, mapping solutions should be efficient and applicable to the robot's resources, even when these resources are limited. In this thesis we propose a framework which addresses this scalability issue, aiming to reduce the computational needs and memory usage during the SLAM procedure. Additionally, our framework intends to facilitate loop closure, which can become troublesome in large environments. Our framework uses multiple sensors and creates a network of hierarchically structured local maps. In order to assess our framework, we compare it to a technique which produces a network of non-hierarchically structured local maps. Our experiments show that in large areas our framework works ideally; the speedup is encouraging and the RAM memory overhead is negligible or conditionally lower.
Advisors/Committee Members: van Genderen, Arjan (mentor), Cotofana, Sorin (graduation committee), Hakkennes, Edwin (graduation committee), Verhoeven, Chris (graduation committee), Chronopoulos, Dimitrios (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: SLAM; mapping; hierarchical mapping; Particle Filter
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):
Giannopoulos, M. (. (2017). Hierarchical Mapping: A Rao-Blackwellized Particle Filter based hierarchical SLAM framework. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:2d3532a6-fda2-44ea-b743-b643ad7d122c
Chicago Manual of Style (16th Edition):
Giannopoulos, Makis (author). “Hierarchical Mapping: A Rao-Blackwellized Particle Filter based hierarchical SLAM framework.” 2017. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:2d3532a6-fda2-44ea-b743-b643ad7d122c.
MLA Handbook (7th Edition):
Giannopoulos, Makis (author). “Hierarchical Mapping: A Rao-Blackwellized Particle Filter based hierarchical SLAM framework.” 2017. Web. 12 Apr 2021.
Vancouver:
Giannopoulos M(. Hierarchical Mapping: A Rao-Blackwellized Particle Filter based hierarchical SLAM framework. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:2d3532a6-fda2-44ea-b743-b643ad7d122c.
Council of Science Editors:
Giannopoulos M(. Hierarchical Mapping: A Rao-Blackwellized Particle Filter based hierarchical SLAM framework. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:2d3532a6-fda2-44ea-b743-b643ad7d122c
Delft University of Technology
27.
Betting, Jan-Harm (author).
Full-Whisker Tracking System: A new algorithm for accurate whisker tracking in untrimmed head-fixed mice.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:c68bc420-be6e-486d-828b-1737f8725225
► The movement of whiskers in head-fixed mice is of high interest for neurological research, as it allows scientists to learn more about learning processes during…
(more)
▼ The movement of whiskers in head-fixed mice is of high interest for neurological research, as it allows scientists to learn more about learning processes during active touch. However, manual tracking of whiskers in thousands of frames is not feasible, and reliable tracking of individual whiskers is not possible with the best current software available. In this work, a new system for the automatic tracking of whiskers in top-view videos of untrimmed, head-fixed mice is presented. The design of this system is based on a variety of image processing and computer vision algorithms. For each step, several alternatives have been considered and assessed. The best options have been combined and implemented in MATLAB. This new system, the Full-Whisker Tracking System (FWTS), detects the centerline of whiskers on each frame along their whole length with sub-pixel accuracy. The whiskers are defined by their angle, position, shape and length. FWTS uses these features to track and recognize whiskers over multiple frames in video segments with a frame rate of 1000 Hz. The system was tested on representative, challenging video segments from two experiments using different mice, and showed itself superior to the pre-existing system BWTT, by detecting on average 21.2% more whiskers, and with twice as much precision. In contrast to earlier systems, FWTS has been demonstrated reliably track individual whiskers in untrimmed mice. Furthermore, FWTS's processing time is on average 41.7% lower than that of BWTT. This thesis work shows that it is possible to track whiskers in untrimmed mice, even in the face of partial occlusions, and makes it possible to study the functioning of the intact whisker system of mice in unprecedented detail.
Advisors/Committee Members: Al-Ars, Zaid (mentor), Strydis, Christos (mentor), Bosman, Laurens W.J. (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: whiskers; mice; rodents; computer vision; machine learning; curvilinear objects; detection; whisker detection; whisker tracking; tracking; BWTT; FWTS
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):
Betting, J. (. (2018). Full-Whisker Tracking System: A new algorithm for accurate whisker tracking in untrimmed head-fixed mice. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:c68bc420-be6e-486d-828b-1737f8725225
Chicago Manual of Style (16th Edition):
Betting, Jan-Harm (author). “Full-Whisker Tracking System: A new algorithm for accurate whisker tracking in untrimmed head-fixed mice.” 2018. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:c68bc420-be6e-486d-828b-1737f8725225.
MLA Handbook (7th Edition):
Betting, Jan-Harm (author). “Full-Whisker Tracking System: A new algorithm for accurate whisker tracking in untrimmed head-fixed mice.” 2018. Web. 12 Apr 2021.
Vancouver:
Betting J(. Full-Whisker Tracking System: A new algorithm for accurate whisker tracking in untrimmed head-fixed mice. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:c68bc420-be6e-486d-828b-1737f8725225.
Council of Science Editors:
Betting J(. Full-Whisker Tracking System: A new algorithm for accurate whisker tracking in untrimmed head-fixed mice. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:c68bc420-be6e-486d-828b-1737f8725225
Delft University of Technology
28.
van Nieuwpoort, Ruben (author).
Solving Poisson's equation with dataflow computing.
Degree: 2017, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:c5dfd1d4-6494-47e9-90d9-486d2a7b26b3
► The finite element method (FEM) is an ubiquitous method for the analysis of boundary value problems. Specifically, it can be used to find approximations to…
(more)
▼ The finite element method (FEM) is an ubiquitous method for the analysis of boundary value problems. Specifically, it can be used to find approximations to solutions of boundary value problems on a specific domain...
Advisors/Committee Members: Gaydadjiev, Georgi (mentor), Möller, Matthias (mentor), Vuik, Kees (graduation committee), Lin, Hai Xiang (graduation committee), van Genderen, Arjan (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Finite element analysis; isogeometric analysis; weighted quadrature; Matrix-free solution techniques; Dataflow computing; mathematical theory; MAX5 hardware resources
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):
van Nieuwpoort, R. (. (2017). Solving Poisson's equation with dataflow computing. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:c5dfd1d4-6494-47e9-90d9-486d2a7b26b3
Chicago Manual of Style (16th Edition):
van Nieuwpoort, Ruben (author). “Solving Poisson's equation with dataflow computing.” 2017. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:c5dfd1d4-6494-47e9-90d9-486d2a7b26b3.
MLA Handbook (7th Edition):
van Nieuwpoort, Ruben (author). “Solving Poisson's equation with dataflow computing.” 2017. Web. 12 Apr 2021.
Vancouver:
van Nieuwpoort R(. Solving Poisson's equation with dataflow computing. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:c5dfd1d4-6494-47e9-90d9-486d2a7b26b3.
Council of Science Editors:
van Nieuwpoort R(. Solving Poisson's equation with dataflow computing. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:c5dfd1d4-6494-47e9-90d9-486d2a7b26b3
Delft University of Technology
29.
Wang, Yizhou (author).
Binary Neural Networks for Object Detection.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:9f0da106-82ea-4f2e-9cd5-8bc834885d6f
► In the past few years, convolutional neural networks (CNNs) have been widely utilized and shown state-of-the-art performances on computer vision tasks. However, CNN based approaches…
(more)
▼ In the past few years, convolutional neural networks (CNNs) have been widely utilized and shown state-of-the-art performances on computer vision tasks. However, CNN based approaches usually require a large amount of storage, run-time memory, as well as computation power in both training and inference time, which are usually used on GPU based machines to ensure the speed for inferences. But they are usually insufficient to be deployed on low-power applications. Although many approaches were proposed to compress and accelerate the CNN models, most of them were only evaluated on relatively simple problems (e.g. image classification), which only support limited real-world applications. Especially, among those methods, binary quantization can achieve very high model compression, but only a few works have been observed to utilize it on more complex tasks. Therefore, the exploration and evaluations of applying binary quantization on more complex tasks like object detection are worthwhile, which can be used in much more applications like autonomous driving and face detection. In this project, we apply and evaluate two different binary quantization approaches, named ABC-Net and PA-Net on object detection tasks. Also, we specify the exact implementation details for the binary convolutional operations in this project. As a result, we can achieve maximally 6.1× (around 16% of the full-precision model) compression, and minimal 2.5% accuracy reduction for weight quantization. The weight quantized models were able to outperform some existing real-time detectors in terms of both accuracy and storage size. Although large accuracy reduction was observed for input quantization, the quantized model could still maintain an acceptable accuracy compared to existing real-time object detectors.
Electrical Engineer | Embedded Systems
Advisors/Committee Members: Al-Ars, Zaid (mentor), Pan, Wei (graduation committee), van Genderen, Arjan (graduation committee), Zhu, Baozhou (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Neural Network Quantization; Deep Learning; Object Detection; Computer Vision; Artificial Intelligence
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. (. (2019). Binary Neural Networks for Object Detection. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:9f0da106-82ea-4f2e-9cd5-8bc834885d6f
Chicago Manual of Style (16th Edition):
Wang, Yizhou (author). “Binary Neural Networks for Object Detection.” 2019. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:9f0da106-82ea-4f2e-9cd5-8bc834885d6f.
MLA Handbook (7th Edition):
Wang, Yizhou (author). “Binary Neural Networks for Object Detection.” 2019. Web. 12 Apr 2021.
Vancouver:
Wang Y(. Binary Neural Networks for Object Detection. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:9f0da106-82ea-4f2e-9cd5-8bc834885d6f.
Council of Science Editors:
Wang Y(. Binary Neural Networks for Object Detection. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:9f0da106-82ea-4f2e-9cd5-8bc834885d6f
Delft University of Technology
30.
Lin, Haipeng (author).
Digital Neuron Cells for Highly Parallel Cognitive Systems.
Degree: 2017, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:51d9827a-013a-4c7f-be0c-eceb0733b027
► The high level of realism of spiking neuron networks and their complexity require a considerable computational resources limiting the size of the realized networks. Consequently,…
(more)
▼ The high level of realism of spiking neuron networks and their complexity require a considerable computational resources limiting the size of the realized networks. Consequently, the main challenge in building complex and biologically accurate spiking neuron network is largely set by the high computational and data transfer demands. In this thesis, I implement several efficient models of the spiking neuron with characteristics such as axon conduction delays and spike timing-dependent plasticity in a real-time data-flow learning network. With the performance analysis, the trade-offs between the biophysical accuracy and computation complexity are defined for the different models. The experimental results indicate that the proposed real-time data-flow learning network architecture allows the capacity of over 1,188 (max.6,300, depending on the model complexity) biophysically accurate neurons in a single FPGA device.
Electrical Engineering | Circuits and Systems
Advisors/Committee Members: Van Leuken, Rene (mentor), Galuzzi, Carlo (graduation committee), Van Genderen, Arjan (graduation committee), Zjajo, Amir (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: digital spiking neuron cells; neuron network; learning network; real-time data-flow 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):
Lin, H. (. (2017). Digital Neuron Cells for Highly Parallel Cognitive Systems. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:51d9827a-013a-4c7f-be0c-eceb0733b027
Chicago Manual of Style (16th Edition):
Lin, Haipeng (author). “Digital Neuron Cells for Highly Parallel Cognitive Systems.” 2017. Masters Thesis, Delft University of Technology. Accessed April 12, 2021.
http://resolver.tudelft.nl/uuid:51d9827a-013a-4c7f-be0c-eceb0733b027.
MLA Handbook (7th Edition):
Lin, Haipeng (author). “Digital Neuron Cells for Highly Parallel Cognitive Systems.” 2017. Web. 12 Apr 2021.
Vancouver:
Lin H(. Digital Neuron Cells for Highly Parallel Cognitive Systems. [Internet] [Masters thesis]. Delft University of Technology; 2017. [cited 2021 Apr 12].
Available from: http://resolver.tudelft.nl/uuid:51d9827a-013a-4c7f-be0c-eceb0733b027.
Council of Science Editors:
Lin H(. Digital Neuron Cells for Highly Parallel Cognitive Systems. [Masters Thesis]. Delft University of Technology; 2017. Available from: http://resolver.tudelft.nl/uuid:51d9827a-013a-4c7f-be0c-eceb0733b027
. 
Open Access Theses and Dissertations