Low-Complexity Path Planning Algorithm for Unmanned Aerial Vehicles in Complicated Scenarios

Existing algorithms on path planning with obstacles for unmanned aerial vehicles (UAVs) suffer from high computational complexity and unpredictability when the considered scenario is complicated. In this paper, we propose a novel path-planning algorithm for UAVs, which relies on continuously updating virtual regional field and its local gradients. The information of target regions and obstacles is incorporated in a virtual regional field. The algorithm circumvents the large number of variables to be optimized, and does not rely on any black boxes with unpredictable outputs. Real data show that the proposed algorithm can design a path with high coverage rate of the target region in a certain time duration, and guides the UAV to bypass the obstacles. The approach based on the regional field provides an option for low-cost hardwares, and reveals insights into the problem of path planning.