A UAV path planning method based on the WOAGWO hybrid algorithm
TL;DR
Simulation trials demonstrate that compared to original WOA, GWO, and other mainstream algorithms, the WOAGWO algorithm can identify safe and feasible paths in complex mountainous terrains with lower convergence costs, validating its superiority.
Abstract
Addressing challenges such as strong terrain constraints and susceptibility to local optima in UAV path planning within complex mountainous environments, this paper introduces a path planning method based on the Whale Optimization Algorithm-Grey Wolf Optimizer (WOAGWO) hybrid algorithm. First, the hierarchical hunting mechanism of the Grey Wolf Optimizer (GWO) is embedded into the Whale Optimization Algorithm (WOA) framework. During the exploitation phase of WOA, the cooperative position update strategy of GWO's α, β, and δ wolves is incorporated. The design of dynamic triggering conditions achieves deep fusion between the two algorithms. This fusion mechanism significantly enhances the local search precision of WOA, effectively overcoming the technical limitation of traditional WOA's tendency to converge to local optima. Second, an adaptive solution quality assurance technique is developed for the algorithm's exploration phase. By establishing an iterative feedback mechanism, the fitness values of new solutions are compared in real-time with historical optimal solutions. This ensures search agents consistently move toward superior regions, enabling efficient global exploration. Simulation trials demonstrate that compared to original WOA, GWO, and other mainstream algorithms, the WOAGWO algorithm can identify safe and feasible paths in complex mountainous terrains with lower convergence costs, validating its superiority.