Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910951469481984 |
|---|---|
| author | Zhao, Albert Soatto, Stefano |
| author_facet | Zhao, Albert Soatto, Stefano |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12327 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions Zhao, Albert Soatto, Stefano Robotics Artificial Intelligence Machine Learning 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. |
| title | Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.12327 |