You searched for +publisher:"Georgia Tech" +contributor:("Theodorou, Evangelos A.").
Showing records 1 – 9 of
9 total matches.
No search limiters apply to these results.
Georgia Tech
1.
Williams, Grady Robert.
Model predictive path integral control: Theoretical foundations and applications to autonomous driving.
Degree: PhD, Computer Science, 2019, Georgia Tech
URL: http://hdl.handle.net/1853/62666 
► This thesis presents a new approach for stochastic model predictive (optimal) control: model predictive path integral control, which is based on massive parallel sampling of…
(more)
▼ This thesis presents a new approach for stochastic model predictive (optimal) control: model predictive path integral control, which is based on massive parallel sampling of control trajectories. We first show the theoretical foundations of model predictive path integral control, which are based on a combination of path integral control theory and an information theoretic interpretation of stochastic optimal control. We then apply the method to high speed autonomous driving on a 1/5 scale vehicle and analyze the performance and robustness of the method. Extensive experimental results are used to identify and solve key problems relating to robustness of the approach, which leads to a robust stochastic model predictive control algorithm capable of consistently pushing the limits of performance on the 1/5 scale vehicle.
Advisors/Committee Members: Theodorou, Evangelos A. (advisor), Rehg, James M. (committee member), Egerstedt, Magnus (committee member), Boots, Byron (committee member), Todorov, Emanuel (committee member).
Subjects/Keywords: Stochastic optimal control; Autonomous driving
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):
Williams, G. R. (2019). Model predictive path integral control: Theoretical foundations and applications to autonomous driving. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/62666
Chicago Manual of Style (16th Edition):
Williams, Grady Robert. “Model predictive path integral control: Theoretical foundations and applications to autonomous driving.” 2019. Doctoral Dissertation, Georgia Tech. Accessed March 05, 2021.
http://hdl.handle.net/1853/62666.
MLA Handbook (7th Edition):
Williams, Grady Robert. “Model predictive path integral control: Theoretical foundations and applications to autonomous driving.” 2019. Web. 05 Mar 2021.
Vancouver:
Williams GR. Model predictive path integral control: Theoretical foundations and applications to autonomous driving. [Internet] [Doctoral dissertation]. Georgia Tech; 2019. [cited 2021 Mar 05].
Available from: http://hdl.handle.net/1853/62666.
Council of Science Editors:
Williams GR. Model predictive path integral control: Theoretical foundations and applications to autonomous driving. [Doctoral Dissertation]. Georgia Tech; 2019. Available from: http://hdl.handle.net/1853/62666
Georgia Tech
2.
Cheng, Ching An.
Efficient and principled robot learning: Theory and algorithms.
Degree: PhD, Interactive Computing, 2020, Georgia Tech
URL: http://hdl.handle.net/1853/62733
► Roboticists have long envisioned fully-automated robots that can operate reliably in unstructured environments. This is an exciting but extremely difficult problem; in order to succeed,…
(more)
▼ Roboticists have long envisioned fully-automated robots that can operate reliably in unstructured environments. This is an exciting but extremely difficult problem; in order to succeed, robots must reason about sequential decisions and their consequences in face of uncertainty. As a result, in practice, the engineering effort required to build reliable robotic systems is both demanding and expensive. This research aims to provide a set of techniques for efficient and principled robot learning. We approach this challenge from a theoretical perspective that more closely integrates analysis and practical needs. These theoretical principles are applied to design better algorithms in two important aspects of robot learning: policy optimization and development of structural policies. This research uses and extends online learning, optimization, and control theory, and is demonstrated in applications including reinforcement learning, imitation learning, and structural policy fusion. A shared feature across this research is the reciprocal interaction between the development of practical algorithms and the advancement of abstract analyses. Real-world challenges force the rethinking of proper theoretical formulations, which in turn lead to refined analyses and new algorithms that can rigorously leverage these insights to achieve better performance.
Advisors/Committee Members: Boots, Byron (advisor), Gordon, Geoff (committee member), Hutchinson, Seth (committee member), Liu, Karen (committee member), Theodorou, Evangelos A. (committee member).
Subjects/Keywords: Online learning; Control theory; Robotics; Optimization; Reinforcement learning; Imitation learning
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):
Cheng, C. A. (2020). Efficient and principled robot learning: Theory and algorithms. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/62733
Chicago Manual of Style (16th Edition):
Cheng, Ching An. “Efficient and principled robot learning: Theory and algorithms.” 2020. Doctoral Dissertation, Georgia Tech. Accessed March 05, 2021.
http://hdl.handle.net/1853/62733.
MLA Handbook (7th Edition):
Cheng, Ching An. “Efficient and principled robot learning: Theory and algorithms.” 2020. Web. 05 Mar 2021.
Vancouver:
Cheng CA. Efficient and principled robot learning: Theory and algorithms. [Internet] [Doctoral dissertation]. Georgia Tech; 2020. [cited 2021 Mar 05].
Available from: http://hdl.handle.net/1853/62733.
Council of Science Editors:
Cheng CA. Efficient and principled robot learning: Theory and algorithms. [Doctoral Dissertation]. Georgia Tech; 2020. Available from: http://hdl.handle.net/1853/62733
Georgia Tech
3.
Exarchos, Ioannis.
Stochastic optimal control - a forward and backward sampling approach.
Degree: PhD, Aerospace Engineering, 2017, Georgia Tech
URL: http://hdl.handle.net/1853/59263
► Stochastic optimal control has seen significant recent development, motivated by its success in a plethora of engineering applications, such as autonomous systems, robotics, neuroscience, and…
(more)
▼ Stochastic optimal control has seen significant recent development, motivated by its success in a plethora of engineering applications, such as autonomous systems, robotics, neuroscience, and financial engineering. Despite the many theoretical and algorithmic advancements that made such a success possible, several obstacles remain; most notable are (i) the mitigation of the curse of dimensionality inherent in optimal control problems, (ii) the design of efficient algorithms that allow for fast, online computation, and (iii) the expansion of the class of optimal control problems that can be addressed by algorithms in engineering practice. The aim of this dissertation is the development of a learning stochastic control framework which capitalizes on the innate relationship between certain nonlinear partial differential equations (PDEs) and forward and backward stochastic differential equations (FBSDEs), demonstrated by a nonlinear version of the Feynman-Kac lemma. By means of this lemma, we are able to obtain a probabilistic representation of the solution to the nonlinear Hamilton-Jacobi-Bellman PDE, expressed in form of a system of decoupled FBSDEs. This system of FBSDEs can then be simulated by employing linear regression techniques. We present a novel discretization scheme for FBSDEs, and enhance the resulting algorithm with importance sampling, thereby constructing an iterative scheme that is capable of learning the optimal control without an initial guess, even in systems with highly nonlinear, underactuated dynamics. The framework we develop within this dissertation addresses several classes of stochastic optimal control, such as L2, L1, risk sensitive control, as well as some classes of differential games, in both fixed-final-time as well as first-exit settings.
Advisors/Committee Members: Tsiotras, Panagiotis (advisor), Theodorou, Evangelos A. (advisor), Haddad, Wassim M. (committee member), Zhou, Haomin (committee member), Popescu, Ionel (committee member).
Subjects/Keywords: Stochastic optimal control; Forward and backward stochastic differential equations
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):
Exarchos, I. (2017). Stochastic optimal control - a forward and backward sampling approach. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/59263
Chicago Manual of Style (16th Edition):
Exarchos, Ioannis. “Stochastic optimal control - a forward and backward sampling approach.” 2017. Doctoral Dissertation, Georgia Tech. Accessed March 05, 2021.
http://hdl.handle.net/1853/59263.
MLA Handbook (7th Edition):
Exarchos, Ioannis. “Stochastic optimal control - a forward and backward sampling approach.” 2017. Web. 05 Mar 2021.
Vancouver:
Exarchos I. Stochastic optimal control - a forward and backward sampling approach. [Internet] [Doctoral dissertation]. Georgia Tech; 2017. [cited 2021 Mar 05].
Available from: http://hdl.handle.net/1853/59263.
Council of Science Editors:
Exarchos I. Stochastic optimal control - a forward and backward sampling approach. [Doctoral Dissertation]. Georgia Tech; 2017. Available from: http://hdl.handle.net/1853/59263
Georgia Tech
4.
Zafar, Munzir.
Whole body control of wheeled inverted pendulum humanoids.
Degree: PhD, Electrical and Computer Engineering, 2019, Georgia Tech
URL: http://hdl.handle.net/1853/61739
► A framework for controlling a Wheeled Inverted Pendulum (WIP) Humanoid to perform useful interactions with the environment, while dynamically balancing itself on two wheels, was…
(more)
▼ A framework for controlling a Wheeled Inverted Pendulum (WIP) Humanoid to perform useful interactions with the environment, while dynamically balancing itself on two wheels, was proposed. As humanoid platforms are characterized by several degrees of freedom, they have the ability to perform several tasks simultaneously, while obeying constraints on their motion and control. This problem is referred as Whole-Body Control in the wider humanoid literature. We develop a framework for whole-body control of WIP humanoids that can be applied directly on the physical robot, which means that it can be made robust to modeling errors. The proposed approach is hierarchical with a low level controller responsible for controlling the manipulator/body and a high-level controller that defines center of mass targets for the low-level controller to control zero dynamics of the system driving the wheels. The low-level controller plans for shorter horizons while considering more complete dynamics of the system, while the high-level controller plans for longer horizon based on an approximate model of the robot for computational efficiency.
Advisors/Committee Members: Hutchinson, Seth (advisor), Theodorou, Evangelos A. (committee member), Boots, Byron E. (committee member), Christensen, Henrik I. (committee member), Romberg, Justin (committee member).
Subjects/Keywords: Whole body control; Wheeled inverted pendulum; Humanoids; Hierarchical; Optimization; Operational space; Model predictive 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):
Zafar, M. (2019). Whole body control of wheeled inverted pendulum humanoids. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/61739
Chicago Manual of Style (16th Edition):
Zafar, Munzir. “Whole body control of wheeled inverted pendulum humanoids.” 2019. Doctoral Dissertation, Georgia Tech. Accessed March 05, 2021.
http://hdl.handle.net/1853/61739.
MLA Handbook (7th Edition):
Zafar, Munzir. “Whole body control of wheeled inverted pendulum humanoids.” 2019. Web. 05 Mar 2021.
Vancouver:
Zafar M. Whole body control of wheeled inverted pendulum humanoids. [Internet] [Doctoral dissertation]. Georgia Tech; 2019. [cited 2021 Mar 05].
Available from: http://hdl.handle.net/1853/61739.
Council of Science Editors:
Zafar M. Whole body control of wheeled inverted pendulum humanoids. [Doctoral Dissertation]. Georgia Tech; 2019. Available from: http://hdl.handle.net/1853/61739
Georgia Tech
5.
Drews, Paul Michael.
Visual attention for high speed driving.
Degree: PhD, Electrical and Computer Engineering, 2018, Georgia Tech
URL: http://hdl.handle.net/1853/61183
► Coupling of control and perception is an especially difficult problem. This thesis investigates this problem in the context of aggressive off-road driving. By jointly developing…
(more)
▼ Coupling of control and perception is an especially difficult problem. This thesis investigates this problem in the context of aggressive off-road driving. By jointly developing a robust 1:5 scale platform and leveraging state of the art sampling based model predictive control, the problem of aggressive driving on a closed dirt track using only monocular cam- era images is addressed. It is shown that a convolutional neural network can directly learn a mapping from input images to top-down cost map. This cost map can be used by a model predictive control algorithm to drive aggressively and repeatably at the limits of grip. Further, the ability to learn an end-to-end trained attentional neural network gaze strategy is developed that allows both high performance and better generalization at our task of high speed driving. This gaze model allows us to utilize simulation data to generalize from our smaller oval track to a much more complex track setting. This gaze model is compared with that of human drivers performing the same task. Using these methods, repeatable, aggressive driving at the limits of handling using monocular camera images is shown on a physical robot.
Advisors/Committee Members: Rehg, James M. (advisor), Theodorou, Evangelos A. (committee member), Boots, Byron (committee member), Batra, Dhruv (committee member), Fox, Dieter (committee member).
Subjects/Keywords: Robotics; Computer vision; Autonomous vehicles; Neural networks; High speed
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):
Drews, P. M. (2018). Visual attention for high speed driving. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/61183
Chicago Manual of Style (16th Edition):
Drews, Paul Michael. “Visual attention for high speed driving.” 2018. Doctoral Dissertation, Georgia Tech. Accessed March 05, 2021.
http://hdl.handle.net/1853/61183.
MLA Handbook (7th Edition):
Drews, Paul Michael. “Visual attention for high speed driving.” 2018. Web. 05 Mar 2021.
Vancouver:
Drews PM. Visual attention for high speed driving. [Internet] [Doctoral dissertation]. Georgia Tech; 2018. [cited 2021 Mar 05].
Available from: http://hdl.handle.net/1853/61183.
Council of Science Editors:
Drews PM. Visual attention for high speed driving. [Doctoral Dissertation]. Georgia Tech; 2018. Available from: http://hdl.handle.net/1853/61183
Georgia Tech
6.
Goldfain, Brian.
Autonomous Rally Racing with AutoRally and Model Predictive Control.
Degree: PhD, Interactive Computing, 2019, Georgia Tech
URL: http://hdl.handle.net/1853/63529
► The ability to conduct experiments in the real world is a critical step for roboticists working to create autonomous systems that achieve human-level task performance.…
(more)
▼ The ability to conduct experiments in the real world is a critical step for roboticists working to create autonomous systems that achieve human-level task performance. Self-driving vehicles are a domain that has received significant attention in recent years, in part because of their potential societal benefit. However, there is still a significant performance gap between human drivers and self-driving vehicles. The task of off-road rally racing is an especially difficult driving task where many of the unsolved challenges occur frequently.
This thesis opens the domain of autonomous rally racing to researchers and conducts the first rally race between autonomous and human drivers. We created the AutoRally platform, a robust, scaled self-driving vehicle and demonstrated AutoRally driven at high speed on a dirt track by the model predictive path integral controller. The controller optimizes control plans on-the-fly onboard the robot using a dynamics model learned from data and a hand-coded task description, also called a cost function. To enable rally racing, an additional layer of cost function optimization, that operates on the time scale of lap times, was created to replace the hand-coded cost function with one adapted through interactions with the system. We explore representations and optimization methods for the racing cost function, and then compare driving performance to human and autonomous drivers using the AutoRally platform at the
Georgia Tech Autonomous Racing Facility
Advisors/Committee Members: Rehg, James M (advisor), Theodorou, Evangelos A (advisor), Tsitras, Panagiotis (committee member), Balch, Tucker (committee member), Eustice, Ryan (committee member).
Subjects/Keywords: autonomous racing; cost function optimization; self-driving vehicle
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):
Goldfain, B. (2019). Autonomous Rally Racing with AutoRally and Model Predictive Control. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/63529
Chicago Manual of Style (16th Edition):
Goldfain, Brian. “Autonomous Rally Racing with AutoRally and Model Predictive Control.” 2019. Doctoral Dissertation, Georgia Tech. Accessed March 05, 2021.
http://hdl.handle.net/1853/63529.
MLA Handbook (7th Edition):
Goldfain, Brian. “Autonomous Rally Racing with AutoRally and Model Predictive Control.” 2019. Web. 05 Mar 2021.
Vancouver:
Goldfain B. Autonomous Rally Racing with AutoRally and Model Predictive Control. [Internet] [Doctoral dissertation]. Georgia Tech; 2019. [cited 2021 Mar 05].
Available from: http://hdl.handle.net/1853/63529.
Council of Science Editors:
Goldfain B. Autonomous Rally Racing with AutoRally and Model Predictive Control. [Doctoral Dissertation]. Georgia Tech; 2019. Available from: http://hdl.handle.net/1853/63529
7.
Pan, Yunpeng.
Learning control via probabilistic trajectory optimization.
Degree: PhD, Aerospace Engineering, 2017, Georgia Tech
URL: http://hdl.handle.net/1853/59278
► A central problem in the field of robotics is to develop real-time planning and control algorithms for autonomous systems to behave intelligently under uncertainty. While…
(more)
▼ A central problem in the field of robotics is to develop real-time planning and control algorithms for autonomous systems to behave intelligently under uncertainty. While classical optimal control provides a general theoretical framework, it relies on strong assumption of full knowledge of the system dynamics and environments. Alternatively, modern reinforcement learning (RL) offers a computational framework for controlling autonomous systems with minimal prior knowledge and user intervention. However, typical RL approaches require many interactions with the physical systems, and suffer from slow convergence. Furthermore, both optimal control and RL have the difficulty of scaling to high-dimensional state and action spaces.
In order to address these challenges, we present probabilistic trajectory optimization methods for solving optimal control problems for systems with unknown or partially known dynamics. Our methods share two key characteristics: (1) we incorporate explicit uncertainty into modeling, prediction and decision making using Gaussian processes; (2) our algorithms bypass the it{curse of dimensionality} via local approximation of the value function or linearization of the Hamilton-Jacobi-Bellman (HJB) equation. Compared to related approaches, our methods offer superior combination of data efficiency and scalability. We present experimental results and comparative analyses to demonstrate the strengths of the proposed methods.
In addition, we develop fast Bayesian approximate inference methods which enable probabilistic trajectory optimizer to perform real-time receding horizon control. It can be used to train deep neural network controllers that map raw observations to actions directly. We show that our approach can be used to perform high-speed off-road autonomous driving with low-cost sensors, and without on-the-fly planning and optimization.
Advisors/Committee Members: Theodorou, Evangelos A (advisor), Boots, Byron (committee member), Johnson, Eric N (committee member), Song, Le (committee member), How, Jonathan (committee member).
Subjects/Keywords: Optimal control; Robotics; Artificial intelligence; Machine learning
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):
Pan, Y. (2017). Learning control via probabilistic trajectory optimization. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/59278
Chicago Manual of Style (16th Edition):
Pan, Yunpeng. “Learning control via probabilistic trajectory optimization.” 2017. Doctoral Dissertation, Georgia Tech. Accessed March 05, 2021.
http://hdl.handle.net/1853/59278.
MLA Handbook (7th Edition):
Pan, Yunpeng. “Learning control via probabilistic trajectory optimization.” 2017. Web. 05 Mar 2021.
Vancouver:
Pan Y. Learning control via probabilistic trajectory optimization. [Internet] [Doctoral dissertation]. Georgia Tech; 2017. [cited 2021 Mar 05].
Available from: http://hdl.handle.net/1853/59278.
Council of Science Editors:
Pan Y. Learning control via probabilistic trajectory optimization. [Doctoral Dissertation]. Georgia Tech; 2017. Available from: http://hdl.handle.net/1853/59278
8.
Sun, Wei.
Pursuit-evasion and differential games under uncertainties.
Degree: PhD, Aerospace Engineering, 2017, Georgia Tech
URL: http://hdl.handle.net/1853/58664
► Differential games involves multi-person decision making under conflicts in the context of dynamical systems. It has found its application on a large range of areas,…
(more)
▼ Differential games involves multi-person decision making under conflicts in the context of dynamical systems. It has found its application on a large range of areas, including aeronautics, biology, ecology, economics, engineering, management science, operations research, etc. The decisions made by the players that join the differential game are susceptible to uncertainties that are pervasive in realistic differential game scenarios. The uncertainties that enters the system can be divided into three main categories, namely, exogenous/environmental uncertainties, endogenous/dynamical uncertainties and observation uncertainties. In this research, we provide methods to deal with environmental and dynamical uncertainties. In particular, we solve pursuit-evasion games under external flow fields to demonstrate how to cope with differential games under environmental uncertainties. We first recast the multiplayer pursuit-evasion problem into a relay pursuer-target assignment problem and utilize generalized Voronoi diagrams to guide the assignment. Then we present an analytical approach to solve a pursuit-evasion game in a linear flow field and a numerical approach that is based on reachability sets and the level set method to deal with pursuit-evasion games in general flow fields. Extension of our numerical approach towards 3-dimensional space and stochastic environmental disturbance are also discussed. Finally, we present an efficient algorithm to solve general differential game problems and extend to cases subject to stochastic dynamics to handle dynamical uncertainties.
Advisors/Committee Members: Tsiotras, Panagiotis (advisor), Theodorou, Evangelos A. (committee member), Feron, Eric (committee member), Johnson, Eric N. (committee member), Yezzi, Anthony J. (committee member).
Subjects/Keywords: Optimal control; Differential game; Pursuit-evasion; Multiplayer; Flow field; Differential dynamic programming; Stochastic system
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Sun, W. (2017). Pursuit-evasion and differential games under uncertainties. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/58664
Chicago Manual of Style (16th Edition):
Sun, Wei. “Pursuit-evasion and differential games under uncertainties.” 2017. Doctoral Dissertation, Georgia Tech. Accessed March 05, 2021.
http://hdl.handle.net/1853/58664.
MLA Handbook (7th Edition):
Sun, Wei. “Pursuit-evasion and differential games under uncertainties.” 2017. Web. 05 Mar 2021.
Vancouver:
Sun W. Pursuit-evasion and differential games under uncertainties. [Internet] [Doctoral dissertation]. Georgia Tech; 2017. [cited 2021 Mar 05].
Available from: http://hdl.handle.net/1853/58664.
Council of Science Editors:
Sun W. Pursuit-evasion and differential games under uncertainties. [Doctoral Dissertation]. Georgia Tech; 2017. Available from: http://hdl.handle.net/1853/58664
9.
Bakshi, Kaivalya Sanjeev.
Large scale stochastic control: Algorithms, optimality and stability.
Degree: PhD, Aerospace Engineering, 2018, Georgia Tech
URL: http://hdl.handle.net/1853/61179
► Optimal control of large-scale multi-agent networked systems which describe social networks, macro-economies, traffic and robot swarms is a topic of interest in engineering, biophysics and…
(more)
▼ Optimal control of large-scale multi-agent networked systems which describe social networks, macro-economies, traffic and robot swarms is a topic of interest in engineering,
biophysics and economics. A central issue is constructing scalable control-theoretic frameworks when the number of agents is infinite. In this work, we exploit PDE representations of the optimality laws in order to provide a tractable approach to ensemble (open loop) and closed loop control of such systems. A centralized open loop optimal control problem of an ensemble of agents driven by jump
noise is solved by a sampling algorithm based on the infinite dimensional minimum principle to solve it. The relationship between the infinite dimensional minimum principle and dynamic programming principles is established for this problem. Mean field game (MFG) models expressed as PDE systems are used to describe emergent phenomenon in decentralized feedback optimal control models of a continuum of interacting agents with stochastic dynamics. However, stability analysis of MFG models remains a challenging problem, since they exhibit non-unique solutions in the absence of a
monotonicity assumption on the cost function. This thesis addresses the key issue of stability and control design in MFGs. Specifically, we present detailed results on a models for flocking and population evolution. An interesting connection between MFG models and the imaginary-time Schr¨odinger equation is used to obtain explicit stability constraints on the control design in the case of non-interacting agents. Compared to prior works on this topic which apply only to
agents obeying very simple integrator dynamics, we treat nonlinear agent dynamics and also provide analytical design constraints.
Advisors/Committee Members: Theodorou, Evangelos A. (advisor), Grover, Piyush (committee member), Feron, Eric (committee member), Popescu, Ionel (committee member), Bogdan, Paul (committee member), Chen, Yongxin (committee member).
Subjects/Keywords: Nonlinear control; Robust control; Optimal control; Mean field games; Large scale 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):
Bakshi, K. S. (2018). Large scale stochastic control: Algorithms, optimality and stability. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/61179
Chicago Manual of Style (16th Edition):
Bakshi, Kaivalya Sanjeev. “Large scale stochastic control: Algorithms, optimality and stability.” 2018. Doctoral Dissertation, Georgia Tech. Accessed March 05, 2021.
http://hdl.handle.net/1853/61179.
MLA Handbook (7th Edition):
Bakshi, Kaivalya Sanjeev. “Large scale stochastic control: Algorithms, optimality and stability.” 2018. Web. 05 Mar 2021.
Vancouver:
Bakshi KS. Large scale stochastic control: Algorithms, optimality and stability. [Internet] [Doctoral dissertation]. Georgia Tech; 2018. [cited 2021 Mar 05].
Available from: http://hdl.handle.net/1853/61179.
Council of Science Editors:
Bakshi KS. Large scale stochastic control: Algorithms, optimality and stability. [Doctoral Dissertation]. Georgia Tech; 2018. Available from: http://hdl.handle.net/1853/61179
. 
Open Access Theses and Dissertations
