衝突を学ぶ：適応型安全臨界シナリオ生成手法
Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method
交通シナリオを自己回帰的な構成要素で表現し、生成モデルを強化学習エージェントとして訓練することで、評価対象の自動運転アルゴリズムにとって危険なシナリオを効率的に生成するフレームワークを提案した。
著者: Wenhao Ding, Baiming Chen, Minjun Xu, Ding Zhao
分類: cs.RO, cs.LG
原文アブストラクト
Long-tail and rare event problems become crucial when autonomous driving algorithms are applied in the real world. For the purpose of evaluating systems in challenging settings, we propose a generative framework to create safety-critical scenarios for evaluating specific task algorithms. We first represent the traffic scenarios with a series of autoregressive building blocks and generate diverse scenarios by sampling from the joint distribution of these blocks. We then train the generative model as an agent (or a generator) to investigate the risky distribution parameters for a given driving algorithm being evaluated. We regard the task algorithm as an environment (or a discriminator) that returns a reward to the agent when a risky scenario is generated. Through the experiments conducted on several scenarios in the simulation, we demonstrate that the proposed framework generates safety-critical scenarios more efficiently than grid search or human design methods. Another advantage of this method is its adaptiveness to the routes and parameters.
