Multi-objective Path Planning for UAV in the Urban Environment Based on CDNSGA-II
Qian Ren, Yuan Yao, Gang Yang, Xingshe Zhou · 2019
This paper is concerned with path planning for unmanned aerial vehicles (UAVs) in urban environment. Distance is the fundamental goal of path planning. Besides, safety is indispensable for the riskless UAV flight. In this paper, we propose a multi-objective path planning (MOPP) approach based on Non-dominated Sorting Genetic Algorithm II (NSGA-II) to find an optimal collision-free path for UAV, considered both distance and safety. To this aim, firstly, we represent the urban environment by octree, which is an efficient and hierarchical data structure for spatial subdivision in 3D. Meanwhile, safety index map (SIM) are developed to capture obstacles in the geography map. Then, a Crowd Distance NSGA-II (CDNSAG-II) method is proposed to deal with MOPP problem. The experimental results demonstrate that our approach is able to find an optimal path efficiently under urban environment based on octrees.