Security Risk-Conscious Dynamic Platoon Formation Using Reinforcement Learning
Loading...
Authors
Phillips, Dominic
Date
Type
thesis
Language
eng
Keyword
Reinforcement Learning , Machine Learning , Game Theory , Autonomous Vehicle Security
Alternative Title
Abstract
As vehicles introduce more digital systems, new vulnerabilities and opportunities for bad actors are also being introduced. Computational constraints make it challenging to add security oversight layers on top of core vehicle systems, especially when the security layers rely on additional deep learning models.
To improve security-conscious decision making for autonomous vehicles, this thesis proposes two new simulation environments. The first environment is a one-shot resource allocation game that simulates a single vehicle which must fend off an attacker. The second is a reinforcement learning environment where an agent is responsible for managing a platoon of vehicles while also dealing with a simulated attacker.
We solve the first environment using a minimax algorithm to identify optimal strategies for each player. Then we train reinforcement learning agents in the second environment and analyze their performance. We note superior performance of our trained agents when compared to our baseline strategies, with the trained agents surviving three times as long with three times the rewards. Following our analysis, we briefly explore the ethical considerations of implementing such autonomous security agents with the capability to deny participation in advanced transportation systems.
Description
Citation
Publisher
License
Queen's University's Thesis/Dissertation Non-Exclusive License for Deposit to QSpace and Library and Archives Canada
ProQuest PhD and Master's Theses International Dissemination Agreement
Intellectual Property Guidelines at Queen's University
Copying and Preserving Your Thesis
This publication is made available by the authority of the copyright owner solely for the purpose of private study and research and may not be copied or reproduced except as permitted by the copyright laws without written authority from the copyright owner.
Attribution-ShareAlike 3.0 United States
ProQuest PhD and Master's Theses International Dissemination Agreement
Intellectual Property Guidelines at Queen's University
Copying and Preserving Your Thesis
This publication is made available by the authority of the copyright owner solely for the purpose of private study and research and may not be copied or reproduced except as permitted by the copyright laws without written authority from the copyright owner.
Attribution-ShareAlike 3.0 United States