自动驾驶碰撞避让与赛车参数化深度强化学习
Autonomous Vehicle Collision Avoidance With Racing Parameterized Deep Reinforcement Learning
AI总结：
本文提出基于赛车超车的参数化深度强化学习策略，通过物理感知奖励函数在模拟中实现非线性车辆动力学的高效率碰撞避让，优于MPC-APF基线，在三个交叉口场景中表现优异。
摘要：
道路交通事故是全球致命性事件的主要原因。在美国，人为错误导致94%的碰撞，造成每年超过7000名行人死亡和5000亿美元的损失。自动驾驶车辆（AVs）配备紧急避撞系统，能够在车辆动态极限下以高频运行，满足非线性运动动力学精度和计算效率的双重约束，进一步提升恶劣天气和网络安全攻击下的安全效益，并在共享道路时规避危险的人类驾驶。本文参数化了一种深度强化学习（DRL）碰撞避让策略，利用赛车超车进行Out-of-Distribution（OOD）模拟，无需显式几何模仿参考轨迹指导，采用物理感知、模拟器利用感知的奖励函数编码非线性车辆运动动力学。两个策略被评估：默认单向策略和反向方向变体，后者导航方向与其它车辆相反，两者均优于MPC-APF基线，零样本迁移至比例缩放的硬件，在三个交叉口碰撞场景中，以31倍更少的浮点运算（FLOPS）和64倍更低的推理延迟实现。反向方向策略在对撞碰撞中比默认赛车超车策略高出30%，比基线高出50%，在侧向碰撞中与前者相当，其中两者DRL策略在侧向碰撞中规避程度比数值最优控制高10%。
英文摘要：
Road traffic accidents are a leading cause of fatalities worldwide. In the US, human error causes 94% of crashes, resulting in excess of 7,000 pedestrian fatalities and $500 billion in costs annually. Autonomous Vehicles (AVs) with emergency collision avoidance systems that operate at the limits of vehicle dynamics at a high frequency, a dual constraint of nonlinear kinodynamic accuracy and computational efficiency, further enhance safety benefits during adverse weather and cybersecurity breaches, and to evade dangerous human driving when AVs and human drivers share roads. This paper parameterizes a Deep Reinforcement Learning (DRL) collision avoidance policy Out-Of-Distribution (OOD) utilizing race car overtaking, without explicit geometric mimicry reference trajectory guidance, in simulation, with a physics-informed, simulator exploit-aware reward to encode nonlinear vehicle kinodynamics. Two policies are evaluated, a default uni-direction and a reversed heading variant that navigates in the opposite direction to other cars, which both consistently outperform a Model Predictive Control and Artificial Potential Function (MPC-APF) baseline, with zero-shot transfer to proportionally scaled hardware, across three intersection collision scenarios, at 31x fewer Floating Point Operations (FLOPS) and 64x lower inference latency. The reversed heading policy outperforms the default racing overtaking policy in head-to-head collisions by 30% and the baseline by 50%, and matches the former in side collisions, where both DRL policies evade 10% greater than numerical optimal control.
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。
