Dissertation/Thesis Abstract

Decision Making Protocol in Autonomous Vehicles for Optimal Routing and Safe Control
by Kamireddy, Lakhan Shiva, M.S., University of Colorado at Boulder, 2019, 62; 13862790
Abstract (Summary)

We analyze two significant decision-making problems namely planning and control in an autonomous driving scenario with an objective of not only improving the safety of drives but also enhancing the vehicle’s capability to make better decisions. We model the decision-making problem of routing in autonomous vehicles and solve for an optimal route when a vehicle approaches an intersection. The proposed solution attempts to balance the congestion in the traffic network, considering the selfish nature of the vehicles. We also analyze decision-making at the level of control and communications. The choices of the framework we use, to model the communication layer of the protocol makes it easier for us to verify and model check the protocol. For example, we implement the process algebra description using Promela language, and we prove the protocol’s correctness guarantees using SPIN model checker. We use a Reinforcement Learning algorithm in the design of the control protocol.

Indexing (document details)
Advisor: Somenzi, Fabio, Sankaranarayanan, Sriram
Commitee: Hayes, Bradley, Trivedi, Ashutosh
School: University of Colorado at Boulder
Department: Electrical Engineering
School Location: United States -- Colorado
Source: MAI 58/06M(E), Masters Abstracts International
Subjects: Computer Engineering, Computer science
Keywords: Concurrent processes, Decision making, Optimal routing, Pi-calculus, Reinforcement learning, Safe control
Publication Number: 13862790
ISBN: 978-1-392-25042-6
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy