Based on multi-strategy improved grey wolf algorithm for robot path planning

Aiming at the shortcomings of basic grey wolf algorithm(GWO) in robot path planning, such as falling into local extremum and low exploration efficiency, a multi-strategy improved grey wolf optimization algorithm was proposed. Firstly, a random walk strategy is proposed to improve the global search capability of the algorithm. At the same time, in the search stage, a reverse learning mechanism based on convex lens principle is introduced to reverse learn the inferior individuals in the population, so as to improve the hunt range of individuals of wolves and avoid the algorithm falling into local optimal. Finally, to improve the smoothness of the path, B-spline is used to smooth the path. The simulation results show that compared with the traditional gray wolf algorithm, the improved gray wolf algorithm has better performance in the global optimal path planning and is more conducive to the robot to complete the task in the common environment and trap environment.