arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.10078cs.AIcs.LGcs.PLcs.RO
收藏

ECSAS:从自动驾驶的动作序列探索关键场景

ECSAS: Exploring Critical Scenarios from Action Sequence in Autonomous Driving

University of Chinese Academy of Sciences(中国科学院大学);Institute of Software Chinese Academy of Sciences(中国科学院软件研究所)

Shuting Kang, Heng Guo, Lijun Zhang, Guangzhen Liu, Yunzhi Xue, Yanjun Wu

摘要:

关键场景生成需要从逻辑场景中的无限参数空间中抽取关键组合的能力。现有的解决方案旨在探索初始场景中动作参数的相关性,而不是动作序列。如何对动作序列进行建模,以便进一步考虑不同动作参数在场景中的影响,是该问题的瓶颈。在本文中,我们攻击的问题,提出了ECSAS框架。具体来说,我们首先提出了一种描述语言,BTScenario,使我们能够模拟动作序列的场景。然后,我们使用强化学习来搜索关键动作参数的组合。为了提高效率,我们进一步提出了几个优化,包括动作掩蔽和重放缓冲区。我们已经实现了ECSAS,实验结果表明,在各种非平凡的场景中,它比随机和组合测试等本地方法更有效。

英文摘要:

Critical scenario generation requires the ability of sampling critical combinations from the infinite parameter space in the logic scenario. Existing solutions aim to explore the correlation of action parameters in the initial scenario rather than action sequences. How to model action sequences so that one can further consider the effects of different action parameters in the scenario is the bottleneck of the problem. In this paper, we attack the problem by proposing the ECSAS framework. Specifically, we first propose a description language, BTScenario, allowing us to model action sequences of the scenarios. We then use reinforcement learning to search for combinations of critical action parameters. To increase efficiency, we further propose several optimizations, including action masking and replay buffer. We have implemented ECSAS, and experimental results show that it is more efficient than native approaches such as random and combination testing in various nontrivial scenarios.

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。

↑