Data-Driven Battery Attack Detection and Control Behavior Determination for Vehicle Driving Safety
Abstract:
Pure electric vehicles (EVs) have become popular in current transportation systems because of their zero air pollution emissions. The battery management system in an EV monitors battery information (i.e., current, voltage and temperature) in real time to prevent batteries from overcharging or overheating and shares this battery information to outside-vehicle environments (e.g., smartphone apps) to enrich vehicle usage experiences. Research has studied various aspects regarding vehicle driving safety, few works have comprehensively studied battery security and its effects on driving safety of an EV. Besides, autonomous vehicles (AVs) have been adopted to reduce traffic congestion and multiple AVs will drive on the same road with the AV population growth. Therefore, It is critical to make optimal control decisions for AVs in real time to ensure driving safety. Motivated by the above scenarios, we focus on three areas to improve vehicle driving safety: (1) battery authentication system for detecting battery attacks (i.e., malicious AC-turn-on requests or battery-charge-stop requests) in electric vehicles; (2) control policy-based driving safety system for an individual AV; and (3) multi-AV control decision making system for multiple AVs to ensure their driving safety. First, we propose the first battery attack, which can turn on air conditioning and stop the battery charging process by sending requests through a smartphone without being noticed by users, and design a battery authentication system to detect such battery attacks. From real-life daily driving experiments, we found that our battery authentication system can prevent EV batteries from being attacked accurately and its accuracy reaches as high as 95.6%. Second, we propose a control policy-based driving safety system to extract control policies of a vehicle based on its historical driving data and determine the optimal control policy for a given trigger condition to ensure vehicle driving safety. We used Baidu Apollo to evaluate the optimal control policy success rate of the proposed system and found that it can extract control policies with as much as 83% accuracy and improve optimal control policy success rate by 28% compared with existing methods. Third, we propose a multi-AV control decision making system to learn driving behaviors of an expert based on the expert driving trajectory data and make multiple control decisions for multiple AVs with safety guarantee. The experimental results show that the proposed system reduces its emergency rate by as high as 51% compared with existing methods.
Committee:
- Yangfeng Ji, Committee Chair (Department of Computer Science, SEAS, UVA)
- Haiying Shen, Advisor (Department of Computer Science, SEAS, UVA)
- Lu Feng (Department of Computer Science, SEAS, UVA)
- Haifeng Xu (Department of Computer Science, SEAS, UVA)
- Brian L. Smith (Department of Engineering Systems and Environment, SEAS, UVA)