Resilient Cooperative Adaptive Cruise Control for Autonomous Vehicles Using Machine Learning

• Published in: IEEE transactions on intelligent transportation systems 2022-09, Vol.23 (9), p.15655-15672
• Main Authors: Boddupalli, Srivalli, Rao, Akash Someshwar, Ray, Sandip
• Format: Article
• Language: English
• Subjects: Adaptive control; Anomaly detection; Connected and autonomous vehicles; Connected vehicles; Cooperative control; Cruise control; Machine learning; Platooning; Prediction models; Reliability engineering; Resilience; Security; Traffic accidents; V2X communication; Vehicle-to-everything; Vehicular ad hoc networks
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2022.3144599

Cooperative Adaptive Cruise Control (CACC) is a fundamental connected vehicle application that extends Adaptive Cruise Control by exploiting vehicle-to-vehicle (V2V) communication. CACC is a crucial ingredient for numerous autonomous vehicle functionalities including platooning, distributed route management, etc. Unfortunately, malicious V2V communications can subvert CACC, leading to string instability and road accidents. In this paper, we develop a novel resiliency infrastructure, RACCON, for detecting and mitigating V2V attacks on CACC. RACCON uses machine learning to develop an on-board prediction model that captures anomalous vehicular responses and performs mitigation in real time. RACCON-enabled vehicles can exploit the high efficiency of CACC without compromising safety, even under potentially adversarial scenarios. We present extensive experimental evaluation to demonstrate the efficacy of RACCON.