Reinforcement Learning, Cooperative Output Regulation and Their Applications to Connected and Autonomous Vehicles
Term of Award
Master of Science, Electrical Engineering
Document Type and Release Option
Thesis (restricted to Georgia Southern)
Copyright Statement / License for Reuse
This work is licensed under a Creative Commons Attribution 4.0 License.
Department of Electrical and Computer Engineering
Committee Member 1
Committee Member 2
The research of reinforcement learning is increasing recently due to its application in different fields, such as control engineering, transportation systems, power system control, and medical science. In this thesis, we have developed a distributed internal adaptive model to solve problems related to cooperative output regulation and an adaptive distributed observer to estimate the leader’s system matrix. We designed a novel distributed predictive cruise control algorithm using reinforcement learning. The main objective of this controller is to reduce travel time and fuel consumption depending on the adjustable speed of the vehicle. This thesis integrates the control algorithm and Paramics microscopic traffic simulations using an application programming interface. We studied the distraction of drivers for different counter measurements, such as text messaging, eating, talking to another passenger, observing advertising boards, and their combinations. The data of steering angle deviation and velocity deviation are analyzed by using statistical tools.
Mynuddin, Mohammed, "Reinforcement Learning, Cooperative Output Regulation and Their Applications to Connected and Autonomous Vehicles" (2020). Electronic Theses and Dissertations. 2095.
Research Data and Supplementary Material