Resilient Cooperative Adaptive Cruise Control for Autonomous Vehicles Using Machine Learning
This addresses safety vulnerabilities in autonomous vehicle platooning and control systems, which is critical for preventing accidents, but appears incremental as it builds on existing CACC frameworks with added security.
The paper tackles the problem of malicious V2V communications subverting Cooperative Adaptive Cruise Control (CACC) in autonomous vehicles, leading to safety risks, and develops RACCON, a resiliency infrastructure using machine learning for real-time detection and mitigation of attacks, with extensive experimental evaluation demonstrating its efficacy.
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.