Multi-UAV 3D Path Planning Based on Improved Particle Swarm Optimizer

The application of the multiple UAVs in the military and civilian fields has become more and more prominent. Path planning is one of the core problems in UAV mission planning system, and is actually a NP hard problem. An improved particle swarm optimizer called heterogeneous adaptive comprehensive learning and dynamic multi-swarm particle swarm optimizer (HACLDMS-PSO) has been proposed to solve this problem. This algorithm integrates three strategies: population dynamic adjustment strategy, perturbation mechanism, and adaptive learning probability mechanism. The population dynamic adjustment strategy increases the diversity of the population; the Levy flight and Cauchy mutation perturbation is used to encourage particles to jump out of the local optimal position; the adaptive learning probability mechanism is applied to promote the evolution of particles toward the global optimum. Compared with the other five algorithms, the proposed algorithm shows better accuracy, fast convergence and robustness.