Stealth real-time paths planning for heterogeneous UAV formation based on parallel niche genetic algorithm

This paper presents an improved niche genetic algorithm (INGA) for real-time paths planning of unmanned aerial vehicles (UAV) formation operating in a threat rich environment. 3D corridor is suggested to meet the diversity kinematics constraints of heterogeneous UAVs. Niche genetic algorithm (NGA) is improved by merging δ-field perturbation operator and rapidly decreasing function, and performed in parallel. The adaptive crowding strategy is used to generate coverage paths in the area of interest (AOI). In addition, our method is compared with particle swarm optimization (PSO). Experimental results show that our approach achieves real-time performance and the visual corridor paths are desirable.