Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions
This addresses safety-critical planning for autonomous vehicles by mitigating adversarial behaviors while maintaining performance in normal scenarios, representing an incremental improvement over existing methods.
The paper tackles robust planning for autonomous driving by mixing normal and adversarial agent predictions from a diffusion model, resulting in a planner that balances safety and efficiency without over-conservatism.
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.