arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.02865cs.RO
收藏

基于近碰撞聚焦训练框架的自动驾驶动态扩展能力

Dynamically Expanding Capacity of Autonomous Driving with Near-Miss Focused Training Framework

Ziyuan Yang, Zhaoyang Li, Jianming Hu, Yi Zhang

AI总结:

本文提出近碰撞聚焦训练框架,通过设计奖励函数并结合鲁棒对抗强化学习同步训练自动驾驶车辆与背景车辆,以生成更接近近碰撞的场景并提升双方能力。

摘要:

真实驾驶数据的长尾分布给自动驾驶车辆(AV)的训练和测试带来了挑战,其中罕见但至关重要的安全关键场景出现频率很低。虚拟仿真提供了一种低成本且高效的解决方案。本文提出了一种面向自动驾驶车辆的近碰撞聚焦训练框架。利用仿真器中传感器提供的驾驶场景信息,我们设计了新颖的奖励函数,使背景车辆(BV)能够生成近碰撞场景,并确保梯度不仅存在于无碰撞场景中,也存在于碰撞场景中。随后,利用鲁棒对抗强化学习(RARL)框架对自动驾驶车辆和背景车辆进行同步训练,逐步增强自动驾驶车辆和背景车辆的能力,同时生成针对不同自动驾驶车辆能力水平量身定制的近碰撞场景。三种测试策略的结果表明,所提出的方法能够生成更接近近碰撞的场景,从而在整个训练过程中提升自动驾驶车辆和背景车辆的能力。

英文摘要:

The long-tail distribution of real driving data poses challenges for training and testing autonomous vehicles (AV), where rare yet crucial safety-critical scenarios are infrequent. And virtual simulation offers a low-cost and efficient solution. This paper proposes a near-miss focused training framework for AV. Utilizing the driving scenario information provided by sensors in the simulator, we design novel reward functions, which enable background vehicles (BV) to generate near-miss scenarios and ensure gradients exist not only in collision-free scenes but also in collision scenarios. And then leveraging the Robust Adversarial Reinforcement Learning (RARL) framework for simultaneous training of AV and BV to gradually enhance AV and BV capabilities, as well as generating near-miss scenarios tailored to different levels of AV capabilities. Results from three testing strategies indicate that the proposed method generates scenarios closer to near-miss, thus enhancing the capabilities of both AVs and BVs throughout training.

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。

↑