Candidate: Xiaoliang Zhou
Date: September 15, 2023
Time: 11:00 AM - 12:00 PM
Location: Remote attendance
Supervisor(s): Mark Crowley, Seyed Majid Zahed
Abstract:
The emerging era of autonomous vehicles (AVs) presents unprecedented potential for transforming global transportation. As these vehicles begin to permeate our streets, the challenge of ensuring their safety, especially in unprecedented scenarios, looms large. This master thesis explores the intricate challenge of autonomous vehicle (AV) validation in simulated environments, emphasizing the significance of generating insightful accidents. The study delves into the application of multi-agent reinforcement learning (MARL) as a tool for stress testing AVs, marking a shift from traditional singleagent methods. Central to our approach is the integration of constraints in reinforcement learning to induce more realistic and insightful accident scenarios. The thesis also presents the highway-attack-env, an environment for black-box AV testing that allows the assessment of both single and multi-agent reinforcement learning algorithms. This research's contributions include the introduction of the aforementioned environment and a comprehensive benchmark, as well as a comparative analysis of single-agent and MARL algorithms, underscoring the superiority of the proposed multi-agent, constraintregulated methodology for AV validation.