用扩散模型混合正常与对抗预测，提升自动驾驶规划鲁棒性
Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions
- 用扩散模型生成正常与对抗性行为预测并混合使用
- 在闯红灯和横穿马路场景中显著降低碰撞风险
- 适合需要平衡安全与通行效率的自动驾驶系统
我们提出一种针对自动驾驶的鲁棒规划方法，通过混合扩散模型生成的正常与对抗性交通参与者预测。首先训练扩散模型以学习正常行为的无偏分布；测试时通过施加偏差生成可能导致碰撞的对抗性预测。规划器基于正常与对抗预测的混合分布计算期望成本，实现对恶意行为的鲁棒性，同时在正常情况下不过度保守。相比现有方法，本方法避免了过度强调对抗行为或使用不适用于所有场景的安全约束。我们在单智能体与多智能体横穿马路、以及闯红灯场景中验证了该方法的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。