Heterogeneous Robot Persistent Path Planning in Adversarial Monitoring Application

Cooperation between Unmanned Ground Vehicles (UGVs) and Unmanned Aerial Vehicles (UAVs) in carrying out persistent monitoring tasks have advantages such as agility in motion, wide coverage, and high efficiency. In complex environments, the status of task points is constantly changing. A single UAV or UGV cannot flexibly adjust its monitoring strategy to prevent intruder and cannot quickly and efficiently deal with abnormal situations at task points. The cooperation of multiple UAV sand UGVs have higher efficiency and can maintain the monitoring targets in a timely manner. This paper establishes a cooperative path planning model for multiple UAVs and UGVs to address these issues. The persistent monitoring tasks are formulated by minimizing the maximum risk coefficient of monitoring assignments, and a rolling optimization path planning model is established. A combination of genetic algorithms and ant colony algorithms is used to obtain the path. Simulation experiments show that the algorithm proposed in this paper is not only effective, but also has a fast convergence rate and meets the requirement of privacy protection in adversarial environment.