Optimal path planning for UAV patrolling in forest fire prevention

Abstract

Path planning is one of the key aspects of autonomous unmanned aerial vehicles (UAVs). In this paper, an effective path planning approach based on a hybrid ant colony optimizations (ACO) algorithm for UAV patrolling in forest fire prevention missions is proposed. The proposed approach takes two steps, namely local path planning and global path planning, to find the shortest feasible path flying through multiple target points with obstacle avoidance. In local planning phase, a dubins-path based A* algorithm is applied to find the optimal path between every two target points, the resulting path would be flyable and safe. Later, the visiting order of each target point would be determined by an improved ACO algorithm in order to minimize the length of the final path. Simulation result shows the proposed algorithm can efficiently find a shortest flight path that fulfills the requirements of UAV based patrolling task in forest fire prevention mission.