SAFE-SIM

This repository is the official implementation of SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries.

SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries
Wei-Jer Chang¹, Francesco Pittaluga², Masayoshi Tomizuka¹, Wei Zhan¹, Manmohan Chandraker^2,3
1University of California Berkeley, ²NEC Labs America, ³University of California San Diego

Evaluating the performance of autonomous vehicle planning algorithms necessitates simulating long-tail safety-critical traffic scenarios. However, traditional methods for generating such scenarios often fall short in terms of controllability and realism; they also neglect the dynamics of agent interactions. To address these limitations, we introduce SAFE-SIM, a novel diffusion-based controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We develop a novel approach to simulate safety-critical scenarios through an adversarial term in the denoising process of diffusion models, which allows an adversarial agent to challenge a planner with plausible maneuvers while all agents in the scene exhibit reactive and realistic behaviors. Furthermore, we propose novel guidance objectives and a partial diffusion process that enables users to control key aspects of the scenarios, such as the collision type and aggressiveness of the adversarial agent, while maintaining the realism of the behavior. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability. These findings affirm that diffusion models provide a robust and versatile foundation for safety-critical, interactive traffic simulation, extending their utility across the broader autonomous driving landscape. Project website: https://safe-sim.github.io/.

News

• [2024.7.1] Accepted by ECCV 2024!

TODO

• Code release
• Release selected scenarios
• Initial repository & preprint release

Contact

If you have any questions or suggestions, please feel free to open an issue or contact us (weijer_chang@berkeley.edu).

Citation

If you find SAFE-SIM useful, please consider giving us a star; and citing our paper with the following BibTeX entry. BibTex will be update soone.

@misc{chang2024safesimsafetycriticalclosedlooptraffic,
      title={SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries}, 
      author={Wei-Jer Chang and Francesco Pittaluga and Masayoshi Tomizuka and Wei Zhan and Manmohan Chandraker},
      year={2024},
      eprint={2401.00391},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2401.00391}, 
}