強化学習ベースの編集による安全臨界シナリオ生成
Safety-Critical Scenario Generation Via Reinforcement Learning Based Editing
自動運転の安全性検証のため、エージェントの追加や軌道修正を逐次編集する強化学習で、リスクと妥当性を両立した安全臨界シナリオを生成する手法を提案した。
著者: Haolan Liu, Liangjun Zhang, Siva Kumar Sastry Hari, Jishen Zhao
分類: cs.LG, cs.RO
原文アブストラクト
Generating safety-critical scenarios is essential for testing and verifying the safety of autonomous vehicles. Traditional optimization techniques suffer from the curse of dimensionality and limit the search space to fixed parameter spaces. To address these challenges, we propose a deep reinforcement learning approach that generates scenarios by sequential editing, such as adding new agents or modifying the trajectories of the existing agents. Our framework employs a reward function consisting of both risk and plausibility objectives. The plausibility objective leverages generative models, such as a variational autoencoder, to learn the likelihood of the generated parameters from the training datasets; It penalizes the generation of unlikely scenarios. Our approach overcomes the dimensionality challenge and explores a wide range of safety-critical scenarios. Our evaluation demonstrates that the proposed method generates safety-critical scenarios of higher quality compared with previous approaches.
