敵対的ポリシー探索に基づく自動運転シナリオ難易度の定量的表現
Quantitative Representation of Scenario Difficulty for Autonomous Driving Based on Adversarial Policy Search
強化学習で敵対的行動を取るエージェントを訓練し、その学習過程のポリシー群から難易度の異なる交通シナリオを連続的に生成・定量化する手法を提案した論文。
著者: Shuo Yang, Caojun Wang, Yuanjian Zhang, Yuming Yin, Yanjun Huang, Shengbo Eben Li, Hong Chen
分類: cs.RO
原文アブストラクト
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.
