arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.02461cs.AIcs.RO
收藏

自动驾驶汽车的风险感知推理

Risk-Aware Reasoning for Autonomous Vehicles

Khalifa University(哈利法大学)

Majid Khonji, Jorge Dias, Lakmal Seneviratne

摘要:

大规模部署自动驾驶汽车(AV)的一个重要障碍是安全保证。由于无人驾驶汽车运行的不确定环境,如道路和天气条件,感知和传感数据的错误,以及模型的不准确性,出现了一些技术挑战。在本文中,我们提出了一个系统架构的风险意识自动驾驶汽车能够推理的不确定性和故意限制碰撞的风险低于给定的阈值。我们讨论了该领域的主要挑战,突出了最近的研究进展,并提出了未来的研究方向在三个子系统。第一,感知子系统,检测场景中的对象,同时量化由不同的传感和通信模式产生的不确定性。第二,意图识别子系统,预测驾驶风格和代理车辆(和行人)的意图。第三,一个规划子系统,考虑到不确定性,从感知和意图识别子系统,并传播到控制政策,明确限制碰撞的风险。我们相信,这种白盒方法对于未来大规模采用自动驾驶汽车至关重要。

英文摘要:

A significant barrier to deploying autonomous vehicles (AVs) on a massive scale is safety assurance. Several technical challenges arise due to the uncertain environment in which AVs operate such as road and weather conditions, errors in perception and sensory data, and also model inaccuracy. In this paper, we propose a system architecture for risk-aware AVs capable of reasoning about uncertainty and deliberately bounding the risk of collision below a given threshold. We discuss key challenges in the area, highlight recent research developments, and propose future research directions in three subsystems. First, a perception subsystem that detects objects within a scene while quantifying the uncertainty that arises from different sensing and communication modalities. Second, an intention recognition subsystem that predicts the driving-style and the intention of agent vehicles (and pedestrians). Third, a planning subsystem that takes into account the uncertainty, from perception and intention recognition subsystems, and propagates all the way to control policies that explicitly bound the risk of collision. We believe that such a white-box approach is crucial for future adoption of AVs on a large scale.

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。

↑