Quantitative Representation of Scenario Difficulty for Autonomous Driving Based on Adversarial Policy Search

TL;DR

This paper introduces a data-driven, continuous method to quantify and generate diverse difficulty levels in autonomous driving scenarios using adversarial policy search, improving over rule-based approaches.

Contribution

It presents a novel reinforcement learning-based approach to represent scenario difficulty continuously, enabling more precise and interpretable scenario generation for autonomous driving testing.

Findings

Generated scenarios with high discrimination and interpretability

Achieved continuous difficulty representation without expert rules

Demonstrated effective adversarial policy search for scenario diversity

Abstract

Adversarial scenario generation is crucial for autonomous driving testing because it can efficiently simulate various challenge and complex traffic conditions. However, it is difficult to control current existing methods to generate desired scenarios, such as the ones with different conflict levels. Therefore, this paper proposes a data-driven quantitative method to represent scenario difficulty. Compared with rule-based discrete scenario difficulty representation method, the proposed algorithm can achieve continuous difficulty representation. Specifically, the environment agent is introduced, and a reinforcement learning method combined with mechanism knowledge is constructed for policy search to obtain an agent with adversarial behavior. The model parameters of the environment agent at different stages in the training process are extracted to construct a policy group, and then the agents with different adversarial intensity are obtained, which are used to realize data generation in different difficulty scenarios through the simulation environment. Finally, a data-driven scenario difficulty quantitative representation model is constructed, which is used to output the environment agent policy under different difficulties. The result analysis shows that the proposed algorithm can generate reasonable and interpretable scenarios with high discrimination, and can provide quantifiable difficulty representation without any expert logic rule design. The video link is https://www.youtube.com/watch?v=GceGdqAm9Ys.