Multi-UAV Cooperative Path Planning via Mutant Pigeon Inspired Optimization with Group Learning Strategy

摘要

This paper proposes a mutant pigeon-inspired optimization algorithm with group learning strategy (MGLPIO), for multi-unmanned aerial vehicle(UAV) cooperative path planning. The group learning strategy is introduced in map and compass operator to reduce computation complexity and enhance the global search ability. At the same time, the triple mutations strategy is employed in landmark operator to enhance swarm diversity. What's more, in order to synchronize multi-UAV, the time stamp segmentation technique is designed to prove waypoints, which can simplify the cost function by reducing the number of independent variables. Besides, we geometric the threat sources to quantify their dangerous level. The coordination costs can guarantee collision-free flight and real-time communication. Finally, the proposed method is applied to path planning in set scenarios. The simulation results indicate that our model is feasible and effective, and the MGLPIO algorithm can have a good balance between exploration and exploitation by comparing with other four algorithms.