Unmanned Container Truck Path Planning Based on the Fusion of White Shark Optimizer and Genetic Algorithm

This paper proposes an improved White Shark Optimizer (WSO) algorithm to address the issues of insufficient local search accuracy and susceptibility to local optima in the path planning process of unmanned container trucks. The initial feasible path solution, obtained through ant colony routing, is used as the initial shark population. To enhance the convergence speed during the iterative process, crossover and mutation operations from the genetic algorithm are introduced for selection and fusion. A stepwise local search is employed to improve the local search of the optimal solution, and a deletion process is added to reduce path redundancy. Simulation results show that the improved WSO algorithm converges and iterates faster in path planning on the grid map and is less prone to falling into local optima.