Adversarial Driving Behavior Generation Incorporating Human Risk Cognition for Autonomous Vehicle Evaluation

TL;DR

This paper introduces a reinforcement learning framework that models human risk cognition to generate adversarial driving behaviors, effectively testing autonomous vehicles' vulnerabilities in risky scenarios.

Contribution

It develops a novel RL-based adversarial behavior generation method incorporating human risk cognition via CPT, enhancing AV evaluation accuracy.

Findings

Effective adversarial behaviors expose AV weaknesses

The CPT-based RL approach improves training stability

Case study confirms the method's effectiveness in cut-in scenarios

Abstract

Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia. This paper focuses on the development of a novel framework for generating adversarial driving behavior of background vehicle interfering against the AV to expose effective and rational risky events. Specifically, the adversarial behavior is learned by a reinforcement learning (RL) approach incorporated with the cumulative prospect theory (CPT) which allows representation of human risk cognition. Then, the extended version of deep deterministic policy gradient (DDPG) technique is proposed for training the adversarial policy while ensuring training stability as the CPT action-value function is leveraged. A comparative case study regarding the cut-in scenario is conducted on a high fidelity Hardware-in-the-Loop (HiL) platform and the results demonstrate the adversarial effectiveness to infer the weakness of the tested AV.