Research On Swarm Intelligence Optimization Algorithm For Path Planning

In modern life,various path planning problems are constantly emerging.However,traditional algorithms have been unable to solve such problems,and it is difficult to meet the actual needs.Therefore,the rise of swarm intelligence optimization algorithms represented by sparrow search algorithm and particle swarm optimization algorithm provides a new idea and direction for solving such problems.The swarm intelligence optimization algorithm only includes some basic mathematical operations,and has the advantages of less control parameters,simple principle and easy implementation.However,it still has defects such as easy to fall into local optimum,and it is difficult to achieve satisfactory results when solving complex path planning problems.Therefore,in order to optimize its performance,appropriate improvements are needed.After analyzing the advantages and disadvantages of the two algorithms,this paper improves the original algorithm and applies it to different types of path planning problems for verification.The main research work of this paper is as follows:(1)Aiming at the shortcomings of Sparrow Search Algorithm(SSA)in robot path planning,it is easy to hit a wall in the process of global optimization,and it is difficult to jump out of local extremum,etc.,and conducts in-depth research and analysis.An improved Sparrow Search Algorithm(SLSSA)incorporating multiple strategies is proposed.Firstly,the Halton sequence is used to uniformly initialize the population,so that the individuals are fully distributed throughout the entire space,making preparations for subsequent optimization;a non-uniform variable spiral search strategy is introduced in the discoverer stage,which makes the search method of the discoverer more detailed;at the same time,following The elite random walk learning strategy is used in the follower stage,so that the individual follower has a flexible search range and gets rid of blindness.In order to balance the exploration and development capabilities,the simplex method strategy is finally used to enhance the ability of the algorithm to escape local extremum and improve the convergence speed of the algorithm.Simulation experiments are carried out on 8 test functions,and the performance of the algorithm is intuitively displayed by drawing the convergence accuracy graph.With the help of the Wilcoxon rank sum test and the average ranking of the Friedman test,it is proved that SLSSA can obtain higher-precision solutions and better convergence performance than 11 algorithms such as GWO,PSO,TLBO,and SSA variants.In order to test the performance of the algorithm,the SLSSA algorithm is applied to three constrained engineering optimization problems,and the effectiveness and feasibility of the improved algorithm are proved.Finally,the algorithm is applied to the path planning of mobile robots,and better results are obtained,which have certain advantages compared with other algorithms.(2)The effect of particle swarm optimization(PSO)on UAV path planning in complex terrain is poor,and the planned route is not simple and safe enough.Through the careful study of the sparrow algorithm and the insufficient global search ability of the particle swarm algorithm,in order to improve the effect of UAV path planning.A learning vector particle swarm optimization algorithm(SLPSO)based on sparrow is proposed,which uses vector decomposition of individual position to control the safety in the path;Firstly,the elite secondary reverse learning strategy is used to increase the distribution of the population;Then,the discoverer phase of sparrow search algorithm is introduced to update the optimal location of particle swarm optimization algorithm and enhance the population diversity.When the algorithm comes to a standstill,a one-dimensional learning strategy is used to improve the subsequent optimization means to help the algorithm jump out of the local optimization.Through the path planning experiments of the two models and Wilcoxon rank sum test,it can be seen that SLPSO has better effect than other algorithms in terms of path planning and convergence speed,and the route planned in complex environment is more secure and stable.