Resilient Cooperative Adaptive Cruise Control for Autonomous Vehicles Using Machine Learning
Resilient Cooperative Adaptive Cruise Control for Autonomous Vehicles Using Machine Learning
复制标题
使用机器学习的自动驾驶车辆弹性协作自适应巡航控制
DOI：
10.1109/tits.2022.3144599
复制
发表时间：
2021-03
影响因子：
8.5
通讯作者：
Srivalli Boddupalli;Akash Rao;S. Ray
中科院分区：
文献类型：
--
作者：
Srivalli Boddupalli;Akash Rao;S. Ray
协作自适应巡航控制 (CACC) 是一种基本的互联车辆应用，它通过利用车辆对车辆 (V2V) 通信来扩展自适应巡航控制。 CACC 是众多自动驾驶汽车功能的关键组成部分，包括队列行驶、分布式路线管理等。不幸的是，恶意 V2V 通信可能会破坏 CACC，导致线路不稳定和道路事故。在本文中，我们开发了一种新颖的弹性基础设施 RACCON，用于检测和减轻对 CACC 的 V2V 攻击。 RACCON 使用机器学习开发车载预测模型，该模型可捕获异常车辆响应并实时执行缓解措施。支持 RACCON 的车辆可以充分利用 CACC 的高效率，而不会影响安全性，即使在潜在的对抗场景下也是如此。我们进行了广泛的实验评估来证明 RACCON 的功效。
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.