Optimizing Unmanned Aerial Vehicle Paths with a Spider Wasp Algorithm

Unmanned Aerial Vehicle (UAV) technology, due to its rapid environmental perception capabilities, swift data collection, and transmission, has significantly fueled extensive research in specialized scenarios. However, when executing reconnaissance missions, the UAV face risks if they traverse suboptimal flight paths, underscoring the criticality and complexity of optimal path planning. To address this challenge, this paper introduces an innovative path planning methodology dubbed Spider Wasp Optimization (SWO), a meta-heuristic algorithm deeply rooted in the natural behaviors exhibited by spider wasps during hunting, nesting, and mating rituals. By simulating these intricate behaviors, the SWO algorithm optimizes the UAV flight path points. To validate its efficacy, the proposed SWO algorithm is rigorously compared against two established and widely recognized metaheuristic approaches: Rapidly-exploring Random Tree (RRT) and Astar algorithms. Experimental outcomes conclusively demonstrate that SWO surpasses both algorithms in terms of minimizing the UAV flight path length and search time, thereby showcasing its superiority and potential for enhancing UAV performance in complex reconnaissance missions.