| In order to solve the path planning problem of intelligent mobile robots,this paper makes a detailed analysis of the existing path planning methods and finds that swarm intelligence algorithms can better solve the path planning problems of mobile robots in complex environments.And intelligent algorithms have an important influence on the development of mobile robot path planning technology.The wolf pack algorithm is one of the widely used algorithms in swarm intelligence optimization algorithms.It has the characteristics of higher accuracy,faster convergence speed,easier implementation,and has a good optimization effect in actual production practice problems.This paper applies the wolf pack algorithm to the path planning problem of intelligent mobile robots.This article describes the research background and current status of wolf pack algorithm,and studies the wolf pack algorithm in detail from three aspects: the principle of the algorithm,the structure of the algorithm,and the characteristics of the algorithm.In addition,the effects of parameters on the algorithm's ability to optimize are analyzed through simulation experiments,and the parameter setting principles are summarized according to relevant literature.Aiming at the problems of immature convergence and easy to fall into local optimum in wolf pack algorithm,this paper proposes a Chaos wolf pack algorithm based on genetic algorithm(GA-CWPA).In the GA-CWPA algorithm,the fixed walking step size of the wolf pack algorithm is changed to an adaptive walking step size that changes linearly with iteration.And the phase factor added in the formula can improve the flexibility of the wolf detection,and make the algorithm search the solution space more efficiently;the chaos search strategy is added after the siege behavior.The chaotic sequence generated by the logical self-mapping function can effectively improve the convergence speed of the algorithm,solve the problem of the late convergence of the algorithm in the original algorithm,and improve the optimization performance of the algorithm;the cross-operation and mutation operation in the genetic algorithm are used to improve the way of generating new individuals,improve the quality of the newly added individuals in the population,and guide the wolves to evolve towards convergence.In order to verify the performance of the GA-CWPA algorithm,six standard test functions are selected for simulation and comparison experiments.The experimental results show that the GA-CWPA algorithm has a significant improvement in stability,robustness,convergence speed,and ability to escape the local optimum in low-or high-dimensional environments,and the test function is single-modal multi-modal.Especially in the solution of high-dimensional complex functions,the GA-CWPA algorithm has obvious advantages.It shows that the introduction of chaos search strategy makes the wolf pack algorithm have a better ability to escape the local optimum,improves the algorithm's development rate of the solution space,and avoids immature convergence;the introduction of crossover and mutation operations in the genetic algorithm improves the quality of the newly generated artificial wolves in the wolves while ensuring the diversity of the population,thereby improving the search efficiency of the algorithm and speeding up the convergence rate of the algorithm.The perturbation of the algorithm further enhances the algorithm's ability to escape from the local optimum.This paper applies the GA-CWPA algorithm to the path planning problem of intelligent mobile robots.Select the grid method to establish an environment model with known starting and end points,clear obstacle distribution,and a fixed environment.By comparing the simulation experiments to obtain the robot's moving path,the results show that the GA-CWPA algorithm can obtain shorter path distance,smoother and less time-consuming,which proves that GA-CWPA algorithm has good optimization performance in path planning problems. |
PDF Full Text Request