arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.00342cs.RO
收藏

一个本体统御一切:自动驾驶的极端场景

One Ontology to Rule Them All: Corner Case Scenarios for Autonomous Driving

FZI Research Center for Information Technology(FZI信息技术研究中心);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Daniel Bogdoll, Stefani Guneshka, J. Marius Zöllner

AI总结:

针对自动驾驶罕见事件长尾问题,本文提出可覆盖文献中各类极端场景的主本体,并能自动派生场景本体、转换为 OpenSCENARIO 后在仿真中执行,用于生成合成训练及测试评估数据。

摘要:

当前,自动驾驶汽车大规模部署的核心障碍在于罕见事件的长尾效应。这些事件极具挑战性,因为它们在深度神经网络所使用的训练数据中并不经常出现。为解决这一问题,我们建议生成额外的合成训练数据,以覆盖种类繁多的极端场景。由于本体既能够表示人类专家知识,又支持计算处理,我们使用本体来描述场景。我们提出的主本体能够对文献中所有常见极端场景类别中的场景进行建模。从这一个主本体出发,可以派生出任意描述场景的本体。这些本体能够以自动化方式转换为 OpenSCENARIO 格式,随后在仿真中执行。通过这种方式,还可以生成具有挑战性的测试与评估场景。

英文摘要:

The core obstacle towards a large-scale deployment of autonomous vehicles currently lies in the long tail of rare events. These are extremely challenging since they do not occur often in the utilized training data for deep neural networks. To tackle this problem, we propose the generation of additional synthetic training data, covering a wide variety of corner case scenarios. As ontologies can represent human expert knowledge while enabling computational processing, we use them to describe scenarios. Our proposed master ontology is capable to model scenarios from all common corner case categories found in the literature. From this one master ontology, arbitrary scenario-describing ontologies can be derived. In an automated fashion, these can be converted into the OpenSCENARIO format and subsequently executed in simulation. This way, also challenging test and evaluation scenarios can be generated.

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。

↑