loading page

Anomaly recognition method of perception system for autonomous vehicles based on distance metric
  • +2
  • Cuiping Shao,
  • Beizhang Chen,
  • ZU MIAO,
  • Yunduan Cui,
  • Huiyun Li
Cuiping Shao
Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences

Corresponding Author:cp.shao@siat.ac.cn

Author Profile
Beizhang Chen
Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences
Author Profile
ZU MIAO
Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences
Author Profile
Yunduan Cui
Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences
Author Profile
Huiyun Li
Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences
Author Profile

Abstract

Environmental perception system is the premise of the safety and stability of the autonomous vehicle system. However, studies have shown that the on-board sensors included in the perception system are extremely vulnerable to external attacks and interference, leading to incorrect driving strategies and bringing great security threats. Aiming at the problem, this paper divides the vehicle-mounted sensors into a positioning group and an identification group according to their role in the perception system. Then, based on the information correlation between sensors in the same group and the information correlation of a single sensor on adjacent time series, the distance metric model between sensors in a group and the distance metric model for each sensor of this group on time series is established. And the normal distance intervals corresponding to the confidence interval are calculated respectively. According to the distance metric model between sensors, we can detect anomalies in the perception system in real-time. Further, according to the distance metric model for each sensor on adjacent time series, we can identify anomaly sensors. Our experimental results quantitatively show that the method achieves real-time anomaly recognition, and demonstrate the effectiveness and robustness of the method on the open-source KITTI dataset.
13 Apr 2022Submitted to Electronics Letters
13 Apr 2022Submission Checks Completed
13 Apr 2022Assigned to Editor
18 Apr 2022Reviewer(s) Assigned
18 May 2022Review(s) Completed, Editorial Evaluation Pending
19 May 2022Editorial Decision: Revise Minor
01 Jun 20221st Revision Received
01 Jun 2022Submission Checks Completed
01 Jun 2022Assigned to Editor
01 Jun 2022Review(s) Completed, Editorial Evaluation Pending
01 Jun 2022Reviewer(s) Assigned
20 Jun 2022Editorial Decision: Accept
Sep 2022Published in Electronics Letters volume 58 issue 20 on pages 774-776. 10.1049/ell2.12573