当前位置: X-MOL 学术arXiv.cs.SE › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Detecting Safety Problems of Multi-Sensor Fusion in Autonomous Driving
arXiv - CS - Software Engineering Pub Date : 2021-09-14 , DOI: arxiv-2109.06404
Ziyuan Zhong, Zhisheng Hu, Shengjian Guo, Xinyang Zhang, Zhenyu Zhong, Baishakhi Ray

Autonomous driving (AD) systems have been thriving in recent years. In general, they receive sensor data, compute driving decisions, and output control signals to the vehicles. To smooth out the uncertainties brought by sensor inputs, AD systems usually leverage multi-sensor fusion (MSF) to fuse the sensor inputs and produce a more reliable understanding of the surroundings. However, MSF cannot completely eliminate the uncertainties since it lacks the knowledge about which sensor provides the most accurate data. As a result, critical consequences might happen unexpectedly. In this work, we observed that the popular MSF methods in an industry-grade Advanced Driver-Assistance System (ADAS) can mislead the car control and result in serious safety hazards. Misbehavior can happen regardless of the used fusion methods and the accurate data from at least one sensor. To attribute the safety hazards to a MSF method, we formally define the fusion errors and propose a way to distinguish safety violations causally induced by such errors. Further, we develop a novel evolutionary-based domain-specific search framework, FusionFuzz, for the efficient detection of fusion errors. We evaluate our framework on two widely used MSF methods. %in two driving environments. Experimental results show that FusionFuzz identifies more than 150 fusion errors. Finally, we provide several suggestions to improve the MSF methods under study.

中文翻译:

自动驾驶多传感器融合安全问题检测

自动驾驶 (AD) 系统近年来蓬勃发展。通常,它们接收传感器数据、计算驾驶决策并向车辆输出控制信号。为了消除传感器输入带来的不确定性,AD 系统通常利用多传感器融合 (MSF) 来融合传感器输入并产生对周围环境的更可靠的理解。然而,MSF 无法完全消除不确定性,因为它缺乏关于哪个传感器提供最准确数据的知识。因此,可能会意外发生严重后果。在这项工作中,我们观察到工业级高级驾驶辅助系统 (ADAS) 中流行的 MSF 方法会误导汽车控制并导致严重的安全隐患。无论使用何种融合方法和来自至少一个传感器的准确数据,都可能发生不当行为。为了将安全隐患归因于 MSF 方法,我们正式定义了融合错误,并提出了一种区分由此类错误引起的安全违规的方法。此外,我们开发了一种新的基于进化的特定领域搜索框架 FusionFuzz,用于有效检测融合错误。我们在两种广泛使用的 MSF 方法上评估我们的框架。%在两种驾驶环境中。实验结果表明,FusionFuzz 识别了 150 多个融合错误。最后,我们提供了一些改进正在研究的 MSF 方法的建议。我们开发了一种新颖的基于进化的特定领域搜索框架 FusionFuzz,用于有效检测融合错误。我们在两种广泛使用的 MSF 方法上评估我们的框架。%在两种驾驶环境中。实验结果表明,FusionFuzz 识别了 150 多个融合错误。最后,我们提供了一些改进正在研究的 MSF 方法的建议。我们开发了一种新颖的基于进化的特定领域搜索框架 FusionFuzz,用于有效检测融合错误。我们在两种广泛使用的 MSF 方法上评估我们的框架。%在两种驾驶环境中。实验结果表明,FusionFuzz 识别了 150 多个融合错误。最后,我们提供了一些改进正在研究的 MSF 方法的建议。
更新日期:2021-09-15
down
wechat
bug