Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 20 for “"Optimal Control; Reinforcement Learning"”.
-
Efficient Reinforcement Learning for Control
The landscape of control systems has evolved rapidly with the emergence of Reinforcement Learning (RL), offering promising solutions to a wide range of dynamic decision-making problems. However, the application of RL to real-world control systems is often hindered by computational inefficiencies, …
-
Perturbation Feedback Approaches in Stochastic Optimal Control: Applications to Model-Based and Model-Free Problems in Robotics
… approached differently in each of the Stochastic optimal control, Reinforcement learning and Motion planning disciplines. One prominent challenge that is common to all is the ‘curse of dimensionality’ i.e, the complexity of the problem scaling exponentially as the state dimension increases. As a …
-
Value function approximation methods for Linearly-solvable Markov Decision Process
Optimal control provides an appealing machinery to complete complicated control tasks with limited prior knowledge. Both global methods and online trajectory optimization methods are powerful techniques for solving optimal control problems; however, each has limitations. The global methods are …
-
Model-Based Navigation and Control of Multirotor UAVs: A Machine Learning Approach
… have focused on enhancing UAV navigation and control through cutting-edge technologies and support tools. UAVs find applications in many fields, except military, such as agriculture, infrastructure inspection, wildlife monitoring, search and rescue, emergency response, border protection, to …
-
Modeling, predicting, and guiding users' temporal behaviors
… a novel probabilistic framework for modeling, learning, predicting, and guiding users’ temporal behaviors. Within the proposed framework, we introduce a pipeline of newly developed statistical models, state-of-the-arts learning algorithms to tackle several canonical problems in theory and …
-
Learning and Control for Intelligent Transportation Systems with Human Driver Interaction
… applications. First, an adherence-aware reinforcement learning approach is proposed for a lane-changing recommendation system in a semi-autonomous driving environment, where human drivers may not always follow recommendations. The method formulates the recommendation problem as a Markov …
-
The Science of Mind Reading: New Inverse Optimal Control Framework
Continuous control and planning by the brain remain poorly understood and is a major challenge in the field of Neuroscience. To truly say that we understand the underlying mechanisms we should first be able to explain the behavioral actions of the animals, so that we can relate the neural activity …
-
Nonlinear Energy Harvesting With Tools From Machine Learning
… is close to its natural frequency. While various control methods applied to an energy harvester realize resonant frequency tuning, they are either energy-consuming or exhibit low efficiency when operating under multi-frequency excitations. In order to overcome these limitations in a linear energy …
-
Generalizable Machine Learning for Mathematical Optimizations
With machine learning gaining increasing popularity in recent years, most successes from employing machine learning methods are found in the fields where the problem solving relies heavily on pattern recognition and representation learning, with solutions consisting of sophisticated rules and logic …
-
Towards Robot-Agnostic Motion Planning in Dynamic Environments: Integrating Reinforcement Learning with Sampling-Based Planners
… accounting for the system’s constraints and optimality conditions. Motivated by the need to design navigation systems that can safely respond to unexpected situations, this thesis focuses on developing reliable motion planning algorithms that not only provide an optimal initial plan but also …
-
A Safe and Robust Multi-Agent Motion Planning Framework for Urban Air Mobility
… environment. We formulate a model-free method of learning the optimal control for the kinodynamic motion problem, and an algorithm to predict the behavior of independent or adversarial agents in the environment through a cognitive hierarchy approach. Additionally, we use repeated observations of …
-
Condition-based maintenance and inspection scheduling for deteriorating systems with general repairs
… decision process (SMDP) framework to find the optimal policy, including repairs and replacements. Contrary to models that attribute system health to aging only, we use the proportional hazards model (PHM) that relates failure risk to the concurrent effects of aging and time-varying covariates. …
-
Optimal Control for Autonomous Motor Behavior
… algorithms that allow robots to generate optimal behavior from first principles. Instead of hard-coding every desired behavior, we encode the task as a cost function, and use numerical optimization to find action sequences that can accomplish the task. Using the theoretical framework of …
-
Stochastic Optimal Control and Reinforcement Learning in Algorithmic and High-Frequency Trading
… dynamics within a scaling-limit framework. The optimal solutions to the trading problems studied are formulated under a stochastic optimal control (SOC) framework with solutions given via numerical methods, as well as under a deep reinforcement learning (RL) framework. Strategy simulations are …
-
Optimal Control of State-Dependent Switched Systems
This thesis addresses the optimal control of state‐dependent switched systems—a class of hybrid dynamical systems characterized by state‐triggered transitions across known interfaces. Such systems arise in applications ranging from robotics and chemical process control to electronic circuits, yet …
-
When Models Meet Data: Pragmatic Robot Learning with Model-based Optimization
… performance over time. While recent advances in reinforcement learning (RL) have shown remarkable progress in learning complex decision-making directly from experience, the sample inefficiency of existing methods limits their application to robotics domains where data collection can be dangerous, …
-
Agile Legged Robots through Reinforcement Learning and Optimal Control
… the challenge of developing agile legged robot controllers capable of high-speed, precise, and rapidly adaptive behaviors in real-world scenarios. While recent advancements have demonstrated impressive hardware capabilities of legged robots in controlled environments, deploying these controllers …
-
Recovering Optimal Cost Functions for Natural Walking: From Musculoskeletal Simulation to Exoskeleton Control
… the cost function algorithmically using inverse optimal control (IOC), but suffered from expensive computation. These limitations hinder the use of IOC for personalized cost function tuning and, by extension, exoskeleton controller design. To address this issue, computationally efficient tuning …