混合敵対的拡散予測による自動運転のロバスト計画
Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions
拡散モデルで正常行動と敵対的行動の予測を混ぜ、期待コストで計画を評価することで、敵対的行動に強く、かつ過度に保守的にならない自動運転プランナーを実現した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Albert Zhao, Stefano Soatto
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
We describe a robust planning method for autonomous driving that mixes normal and adversarial agent predictions output by a diffusion model trained for motion prediction. We first train a diffusion model to learn an unbiased distribution of normal agent behaviors. We then generate a distribution of adversarial predictions by biasing the diffusion model at test time to generate predictions that are likely to collide with a candidate plan. We score plans using expected cost with respect to a mixture distribution of normal and adversarial predictions, leading to a planner that is robust against adversarial behaviors but not overly conservative when agents behave normally. Unlike current approaches, we do not use risk measures that over-weight adversarial behaviors while placing little to no weight on low-cost normal behaviors or use hard safety constraints that may not be appropriate for all driving scenarios. We show the effectiveness of our method on single-agent and multi-agent jaywalking scenarios as well as a red light violation scenario.
