Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, MI, USA.
School of Astronautics, Beihang University, Beijing, China.
Nat Commun. 2023 Apr 11;14(1):2037. doi: 10.1038/s41467-023-37677-5.
For simulation to be an effective tool for the development and testing of autonomous vehicles, the simulator must be able to produce realistic safety-critical scenarios with distribution-level accuracy. However, due to the high dimensionality of real-world driving environments and the rarity of long-tail safety-critical events, how to achieve statistical realism in simulation is a long-standing problem. In this paper, we develop NeuralNDE, a deep learning-based framework to learn multi-agent interaction behavior from vehicle trajectory data, and propose a conflict critic model and a safety mapping network to refine the generation process of safety-critical events, following real-world occurring frequencies and patterns. The results show that NeuralNDE can achieve both accurate safety-critical driving statistics (e.g., crash rate/type/severity and near-miss statistics, etc.) and normal driving statistics (e.g., vehicle speed/distance/yielding behavior distributions, etc.), as demonstrated in the simulation of urban driving environments. To the best of our knowledge, this is the first time that a simulation model can reproduce the real-world driving environment with statistical realism, particularly for safety-critical situations.
为了使模拟成为开发和测试自动驾驶汽车的有效工具，模拟器必须能够以分布级精度生成逼真的安全关键场景。然而，由于现实世界驾驶环境的高维度和长尾安全关键事件的稀有性，如何在模拟中实现统计真实性是一个长期存在的问题。在本文中，我们开发了基于深度学习的框架 NeuralNDE，该框架可以从车辆轨迹数据中学习多代理交互行为，并提出了冲突批评模型和安全映射网络，以根据实际发生的频率和模式细化安全关键事件的生成过程。结果表明，NeuralNDE 可以实现精确的安全关键驾驶统计数据（例如，碰撞率/类型/严重程度和险遭事故统计数据等）和正常驾驶统计数据（例如，车辆速度/距离/让行行为分布等），这在城市驾驶环境的模拟中得到了验证。据我们所知，这是首次有模拟模型能够以统计真实性再现现实世界驾驶环境，特别是对于安全关键情况。
