PROJECT TITLE :

Path Planning for Single Unmanned Aerial Vehicle by Separately Evolving Waypoints

ABSTRACT:

Evolutionary algorithm-based unmanned aerial vehicle (UAV) path planners are extensively studied for their effectiveness and adaptability. However, they still suffer from a disadvantage that the high-quality waypoints in previous candidate paths can hardly be exploited for any evolution, since they regard all the waypoints of a path as an integrated individual. Due to this disadvantage, the previous planners usually fail when encountering tons of obstacles. During this paper, a brand new idea of separately evaluating and evolving waypoints is presented to unravel this problem. Concretely, the initial objective and constraint functions of UAVs path coming up with are decomposed into a set of latest evaluation functions, with that waypoints on a path can be evaluated separately. The new analysis functions allow waypoints on a path to be evolved separately and, so, high-quality waypoints can be better exploited. On this basis, the waypoints are encoded in an exceedingly rotated coordinate system with an external restriction and evolved with JADE, a state-of-the-art variant of the differential evolution algorithm. To test the capabilities of the new planner on coming up with obstacle-free ways, 5 scenarios with increasing numbers of obstacles are constructed. Three existing planners and four variants of the proposed planner are compared to assess the effectiveness and efficiency of the proposed planner. The results demonstrate the prevalence of the proposed planner and the thought of separate evolution.