期刊
IEEE ACCESS
卷 11, 期 -, 页码 44952-44963出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2023.3272979
关键词
Detectors; Vehicle safety; Object detection; Reliability; Autonomous vehicles; Task analysis; Computational modeling; Autonomous driving; object detection; safety; reliability
We propose that object detectors in the safety critical domain should prioritize detection of objects that are most likely to interfere with the actions of the autonomous actor, especially those that can impact safety and reliability. To quantify this impact, we introduce new object detection measures that reward the correct identification of the most dangerous objects that could affect driving decisions. Through a criticality model based on proximity, orientation, and relative velocity, we evaluate nine object detectors on the nuScenes dataset and find that best performing detectors according to nuScenes ranking may not be the preferable ones for safety and reliability.
We argue that object detectors in the safety critical domain should prioritize detection of objects that are most likely to interfere with the actions of the autonomous actor. Especially, this applies to objects that can impact the actor's safety and reliability. To quantify the impact of object (mis)detection on safety and reliability in the context of autonomous driving, we propose new object detection measures that reward the correct identification of objects that are most dangerous and most likely to affect driving decisions. To achieve this, we build an object criticality model to reward the detection of the objects based on proximity, orientation, and relative velocity with respect to the subject vehicle. Then, we apply our model on the recent autonomous driving dataset nuScenes, and we compare nine object detectors. Results show that, in several settings, object detectors that perform best according to the nuScenes ranking are not the preferable ones when the focus is shifted on safety and reliability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据