Trust-based Control and Scheduling for UGV Platoon under Cyber Attacks 2019-01-1077
Unmanned ground vehicles (UGVs) may encounter difficulties accommodating environmental uncertainties and system degradations during harsh conditions. However, human experience and on-board intelligence can help mitigate such cases. Unfortunately, human operators have cognition limits when directly supervising multiple UGVs which may reduce operational performance. Ideally, an automated decision-making system can be designed that empowers collaboration between the human operator and UGVs. In this paper, a connected UGV platoon, vehicle-to-vehicle (V2V) and vehicle-to-cloud (V2C), experiences a cyber-attack which may disrupt the mission. In the proposed framework, an observer-based resilient control strategy is designed to mitigate the effects of V2V cyber-attacks. In addition, each UGV also generates an internal, or self, and external, or surrounding neighbors, evaluation based on the platoon’s performance metrics. A cloud-based trust-based information management system collects these evaluations and detects abnormal UGV platoon behavior. In dealing with inaccurate information due to a V2C cyber-attack, a RoboTrust algorithm analyzes vehicle trustworthiness and eliminates information with low credit. Finally, a human operator scheduling algorithm is proposed when the number of abnormal UGVs exceeds the limit of what human operators can handle. Representative simulation results demonstrate that the proposed automated decision-making system can effectively guide human operators when working with platoons under cyber-attack. The platoon survivability has been improved by the proposed algorithm when compared to those that operate without this system.
Fangjian Li, Dariusz Mikulski, John R. Wagner, Yue Wang
Clemson University, U.S. Army TARDEC, Clemson Univ.