Military UCAV 3-D Path Planning Based on Multistrategy Developed Human Evolutionary Optimization Algorithm

Path planning for unmanned combat aerial vehicles (UCAV) has evolved into a multiconstrained, high-dimensional and multimodal optimization problem in complex combat environments. To solve the global optimal path planning problem of UCAV in a variety of complex terrain and multiple obstacles, human evolution optimization algorithm (HEOA) based on multistrategy is proposed in this article. In developed HEOA (DHEOA), a parallel population division combined with the double reverse learning strategy is employed to balance human exploration and development. Subsequently, the update strategies of the ball-rolling dung beetle and the thief dung beetle in dung beetle optimizer (DBO) are integrated into the human exploration stage. The ability for search is enhanced and convergence accuracy is improved. Finally, a variation strategy inspired by the natural development process is designed. The goal is to capture and activate the cycle of changes in population diversity. To evaluate the performance of DHEOA, four reference terraforms are generated from the real digital elevation model (DEM) and three different scenarios of each terraform are simulated. A series of path planning simulation experiments in a complex 3-D environment are carried out. The results show that the proposed algorithm can plan a path satisfying the constraints stably and efficiently. It has better results in UCAV path planning problems.