arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.17366cs.ROcs.AIcs.LGstat.ML
收藏

可控交通流模拟中的有导条件扩散

Guided Conditional Diffusion for Controllable Traffic Simulation

Columbia University(哥伦比亚大学);NVIDIA(英伟达);Stanford University(斯坦福大学);Georgia Tech(佐治亚理工学院);NVIDIA Research(英伟达研究院)

Ziyuan Zhong, Davis Rempe, Danfei Xu, Yuxiao Chen, Sushant Veer, Tong Che, Baishakhi Ray, Marco Pavone

摘要:

可控和真实的交通仿真对于开发和验证自动驾驶汽车至关重要。典型的基于仿真的交通模型提供灵活的控制,使车辆遵循特定的轨迹和交通规则。另一方面,数据驱动的方法可以生成逼真的和类似人类的行为,从而改善从模拟到真实世界交通的传输。然而,据我们所知,没有一个流量模型能够同时提供可控性和真实性。在这项工作中,我们开发了一个条件扩散模型的可控交通产生(CTG),允许用户控制所需的属性的轨迹在测试时(例如,达到目标或遵循速度限制),同时通过强制动力学保持现实主义和物理可行性。关键的技术思想是利用扩散建模和可微逻辑的最新进展来指导生成的轨迹,以满足使用信号时序逻辑(STL)定义的规则。我们进一步将指导扩展到多智能体设置,并启用基于交互的规则,如碰撞避免。CTG在nuScenes数据集上进行了广泛的多样性和复合规则评估,证明了在可扩展性-现实主义权衡方面优于强基线的改进。

英文摘要:

Controllable and realistic traffic simulation is critical for developing and verifying autonomous vehicles. Typical heuristic-based traffic models offer flexible control to make vehicles follow specific trajectories and traffic rules. On the other hand, data-driven approaches generate realistic and human-like behaviors, improving transfer from simulated to real-world traffic. However, to the best of our knowledge, no traffic model offers both controllability and realism. In this work, we develop a conditional diffusion model for controllable traffic generation (CTG) that allows users to control desired properties of trajectories at test time (e.g., reach a goal or follow a speed limit) while maintaining realism and physical feasibility through enforced dynamics. The key technical idea is to leverage recent advances from diffusion modeling and differentiable logic to guide generated trajectories to meet rules defined using signal temporal logic (STL). We further extend guidance to multi-agent settings and enable interaction-based rules like collision avoidance. CTG is extensively evaluated on the nuScenes dataset for diverse and composite rules, demonstrating improvement over strong baselines in terms of the controllability-realism tradeoff.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑