Collaborative path planning for multiple Unmanned Aerial Vehicles in dynamic environments

Abstract

This paper addresses the problem of path planning for a group of Unmanned Aerial Vehicles (UAVs) to carry out a reconnaissance mission given regions of interest (ROI) within a specified geographic area. Employing teams of UAVs may reduce the time to accomplish a required mission however the problem becomes one of optimal resource allocation and is NP-hard. Traversal through a partially known environment is challenging as information acquired by the sensors may reveal obstacles and/or high risk zones. Thus plans may need to be recomputed in real-time as the mission proceeds. UAVs may be lost or may suffer significant damage during such missions. Therefore multiple UAVs have better chance of completing a mission in the face of failures and obstacles if surviving agents can reconfigure their path plans based on shared information and move on to complete the mission. The proposed solution must be such that m UAVs start from multiple source locations to visit n targets and return to a set of destination locations such that (1) each target is visited exactly by one of the chosen uavs (2) the total distance traveled by the group is minimized and (3) the number of targets that each uav visits may not be less than K or greater than L.