Online legal driving behavior monitoring for self-driving vehicles
Abstract Defined traffic laws must be respected by all vehicles when driving on the road, including self-driving vehicles without human drivers. Nevertheless, the ambiguity of human-oriented traffic laws, particularly compliance thresholds, poses a significant challenge to the implementation of regu...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-01-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-024-44694-5 |
_version_ | 1797355646912299008 |
---|---|
author | Wenhao Yu Chengxiang Zhao Hong Wang Jiaxin Liu Xiaohan Ma Yingkai Yang Jun Li Weida Wang Xiaosong Hu Ding Zhao |
author_facet | Wenhao Yu Chengxiang Zhao Hong Wang Jiaxin Liu Xiaohan Ma Yingkai Yang Jun Li Weida Wang Xiaosong Hu Ding Zhao |
author_sort | Wenhao Yu |
collection | DOAJ |
description | Abstract Defined traffic laws must be respected by all vehicles when driving on the road, including self-driving vehicles without human drivers. Nevertheless, the ambiguity of human-oriented traffic laws, particularly compliance thresholds, poses a significant challenge to the implementation of regulations on self-driving vehicles, especially in detecting illegal driving behaviors. To address these challenges, here we present a trigger-based hierarchical online monitor for self-assessment of driving behavior, which aims to improve the rationality and real-time performance of the monitoring results. Furthermore, the general principle to determine the ambiguous compliance threshold based on real driving behaviors is proposed, and the specific outcomes and sensitivity of the compliance threshold selection are analyzed. In this work, the effectiveness and real-time capability of the online monitor were verified using both Chinese human driving behavior datasets and real vehicle field tests, indicating the potential for implementing regulations in self-driving vehicles for online monitoring. |
first_indexed | 2024-03-08T14:14:08Z |
format | Article |
id | doaj.art-6344e98be98947d7b00ebff3a5c52509 |
institution | Directory Open Access Journal |
issn | 2041-1723 |
language | English |
last_indexed | 2024-03-08T14:14:08Z |
publishDate | 2024-01-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Nature Communications |
spelling | doaj.art-6344e98be98947d7b00ebff3a5c525092024-01-14T12:29:26ZengNature PortfolioNature Communications2041-17232024-01-0115111610.1038/s41467-024-44694-5Online legal driving behavior monitoring for self-driving vehiclesWenhao Yu0Chengxiang Zhao1Hong Wang2Jiaxin Liu3Xiaohan Ma4Yingkai Yang5Jun Li6Weida Wang7Xiaosong Hu8Ding Zhao9School of Vehicle and Mobility, Tsinghua UniversitySchool of Mechanical Engineering, Beijing Institute of TechnologySchool of Vehicle and Mobility, Tsinghua UniversitySchool of Vehicle and Mobility, Tsinghua UniversitySchool of Mechanical Engineering, Beijing Institute of TechnologySchool of Vehicle and Mobility, Tsinghua UniversitySchool of Vehicle and Mobility, Tsinghua UniversitySchool of Mechanical Engineering, Beijing Institute of TechnologyDepartment of Mechanical and Vehicle Engineering, Chongqing UniversityDepartment of Mechanical Engineering, Carnegie Mellon UniversityAbstract Defined traffic laws must be respected by all vehicles when driving on the road, including self-driving vehicles without human drivers. Nevertheless, the ambiguity of human-oriented traffic laws, particularly compliance thresholds, poses a significant challenge to the implementation of regulations on self-driving vehicles, especially in detecting illegal driving behaviors. To address these challenges, here we present a trigger-based hierarchical online monitor for self-assessment of driving behavior, which aims to improve the rationality and real-time performance of the monitoring results. Furthermore, the general principle to determine the ambiguous compliance threshold based on real driving behaviors is proposed, and the specific outcomes and sensitivity of the compliance threshold selection are analyzed. In this work, the effectiveness and real-time capability of the online monitor were verified using both Chinese human driving behavior datasets and real vehicle field tests, indicating the potential for implementing regulations in self-driving vehicles for online monitoring.https://doi.org/10.1038/s41467-024-44694-5 |
spellingShingle | Wenhao Yu Chengxiang Zhao Hong Wang Jiaxin Liu Xiaohan Ma Yingkai Yang Jun Li Weida Wang Xiaosong Hu Ding Zhao Online legal driving behavior monitoring for self-driving vehicles Nature Communications |
title | Online legal driving behavior monitoring for self-driving vehicles |
title_full | Online legal driving behavior monitoring for self-driving vehicles |
title_fullStr | Online legal driving behavior monitoring for self-driving vehicles |
title_full_unstemmed | Online legal driving behavior monitoring for self-driving vehicles |
title_short | Online legal driving behavior monitoring for self-driving vehicles |
title_sort | online legal driving behavior monitoring for self driving vehicles |
url | https://doi.org/10.1038/s41467-024-44694-5 |
work_keys_str_mv | AT wenhaoyu onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles AT chengxiangzhao onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles AT hongwang onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles AT jiaxinliu onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles AT xiaohanma onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles AT yingkaiyang onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles AT junli onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles AT weidawang onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles AT xiaosonghu onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles AT dingzhao onlinelegaldrivingbehaviormonitoringforselfdrivingvehicles |