arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.08034eess.SYcs.ROcs.SY
收藏

为自动驾驶汽车的有效评估生成社会可接受的扰动

Generating Socially Acceptable Perturbations for Efficient Evaluation of Autonomous Vehicles

University of Michigan(密歇根大学);Ford Motor Company(福特汽车公司)

Songan Zhang, Huei Peng, Subramanya Nageshrao, H. Eric Tseng

摘要:

近年来,深度强化学习方法已被广泛用于自动驾驶汽车的决策。一个关键问题是,深度神经网络对于对抗性攻击或其他看不见的输入可能很脆弱。在本文中,我们解决了后一个问题:我们专注于生成社会可接受的扰动(SAP),使自主车辆(AV代理),而不是具有挑战性的车辆(攻击者),是主要负责崩溃。在我们的过程中,一个攻击者被添加到环境中,并通过深度强化学习进行训练,以生成所需的扰动。奖励被设计成使得攻击者的目标是以社会可接受的方式使AV代理失败。在训练攻击者之后,在原始自然环境和有一个攻击者的环境中评估代理策略。结果表明,在自然环境中安全的智能体策略在扰动环境中会发生大量的崩溃。

英文摘要:

Deep reinforcement learning methods have been widely used in recent years for autonomous vehicle's decision-making. A key issue is that deep neural networks can be fragile to adversarial attacks or other unseen inputs. In this paper, we address the latter issue: we focus on generating socially acceptable perturbations (SAP), so that the autonomous vehicle (AV agent), instead of the challenging vehicle (attacker), is primarily responsible for the crash. In our process, one attacker is added to the environment and trained by deep reinforcement learning to generate the desired perturbation. The reward is designed so that the attacker aims to fail the AV agent in a socially acceptable way. After training the attacker, the agent policy is evaluated in both the original naturalistic environment and the environment with one attacker. The results show that the agent policy which is safe in the naturalistic environment has many crashes in the perturbed environment.

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。

↑