Path Planning Of Mobile Robot Based On Improved Grey Wolf Optimization Algorithm

With the extensive application of mobile robot,the path planning technology of mobile robot has become a hot topic in recent years.Path planning of mobile robots is a complex,nonlinear and environment-constrained problem.Mobile robot path planning is divided into global path planning and local path planning.In this paper,the global path planning of mobile robot in static environment is studied,and the main work is as follows:(1)The accuracy,stability and convergence of gray wolf optimization algorithm(GWO)are analyzed.Comparing gray wolf optimization algorithm with genetic algorithm(GA)and particle swarm optimization(PSO),it is concluded that the accuracy and stability of gray wolf optimization algorithm is better than genetic algorithm and particle swarm optimization,in solving many problems,gray wolf optimization algorithm is as easy to fall into local extremum as most other intelligent algorithms.(2)In view of the local extremum of gray wolf optimization algorithm,two different methods are proposed to improve gray wolf optimization algorithm.In method 1(improved gray wolf optimization algorithm-IGWO),the convergence factor a was improved,the memory function of particle swarm optimization was added to gray wolf optimization algorithm,and the mutation strategy of genetic algorithm was added to gray wolf optimization algorithm.In method 2(simulated annealing Gaussian gray wolf optimization algorithm-SAGGWO),Simulated annealing was added to gray wolf optimization algorithm to generate initial population,and Gaussian was added to gray wolf optimization algorithm.(3)Gray wolf optimization algorithm,improved gray wolf optimization algorithm and simulated annealing Gaussian gray wolf optimization algorithm are used to solve 12 test functions and traveling salesman problem.On 12 test functions and traveling salesman problem,improved gray wolf optimization algorithm and simulated annealing Gaussian gray wolf optimization algorithm have better optimization ability than gray wolf optimization algorithm.They can avoid stagnation and fall into local extremum,accelerate convergence speed and improve stability.(4)Genetic algorithm and particle swarm optimization algorithm are commonly used to solve the path planning of mobile robot.The gray wolf optimization algorithm is also used to solve the path planning of mobile robot,and compared with genetic algorithm and particle swarm optimization algorithm.The feasibility of gray wolf optimization algorithm in path planning of mobile robot is proved.(5)When improved gray wolf optimization algorithm is applied to the path planning problem of mobile robot,Improved gray wolf optimization algorithm can avoid falling into the local extremum,accelerate the convergence speed and further improve the stability of the mobile robot path planning problem.(6)When simulated annealing Gaussian gray wolf optimization algorithm is applied to the path planning problem of mobile robot,simulated annealing Gaussian gray wolf optimization algorithm avoids falling into local extremum,improves the stability,and mainly accelerates the convergence speed.