United States Department of Transportation
i
Anomaly Detection and String Stability Analysis in Connected Automated Vehicular Platoons
-
2022-09-29
-
[PDF-4.52 MB]
Details:
-
Creators:
-
Corporate Creators:
-
Subject/TRT Terms:
-
Resource Type:
-
Geographical Coverage:
-
Corporate Publisher:
-
Abstract:In this study, the authors develop a comprehensive framework to model the impact of cyberattacks on safety, security, and head-to-tail stability of connected and automated vehicular platoons. First, the authors propose a general platoon dynamics model with heterogeneous time delays that may originate from the communication channel and/or vehicle onboard sensors. Based on the proposed dynamics model, the authors develop an augmented state extended Kalman filter (ASEKF) to smooth sensor readings, and use it in conjunction with an anomaly detector to detect sensor anomalies. Specifically, the authors consider two detectors: a parametric detector, the χ²-detector, and a learning-based detector, the one class support vector machine (OCSVM). The authors investigate the detection power of all combinations of vehicle dynamics models (EKF and ASEKF) and detectors (χ² and OCSVM). Furthermore, the authors introduce a novel concept in string stability, namely, pseudo string stability, to measure a platoon’s string stability under cyberattacks and model uncertainties. The authors demonstrate the relationship between the pseudo string stability of a platoon and its detection rate, which enables them to identify the critical detection sensitivity/recall that the platoon’s members should meet for the platoon to remain pseudo string stable.
-
Format:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
