Research On Path Planning Of Mobile Robot Based On Intelligent Algorithm

With the continuous development of robot technology,the usage scenarios of mobile robots are also expanding,and they are widely used in various industries.The emergence of mobile robots not only makes human life more convenient,but also greatly promotes social development.Path planning is an important research direction in the field of mobile robot.The purpose of path planning is to plan a collision-free and optimal path in a specific environment,so that the mobile robot can safely reach the destination and successfully complete work tasks.Due to the good applicability and generalization of intelligent algorithms in mobile robot path planning,intelligent path planning algorithms have received widespread attention.The main research objects of this thesis are particle swarm optimization algorithm(PSO)and ant colony optimization algorithm(ACO),which are both intelligent algorithms.Firstly,the shortcomings of the traditional PSO algorithm are improved,and then it is incorporated into the optimization process of the ACO algorithm.Finally,the effectiveness of the improved algorithm is verified through the simulation experiments of path planning.The main work of this thesis is as follows:(1)Aiming at the problems of traditional PSO algorithm in path planning,such as premature convergence and low convergence accuracy,a particle swarm optimization algorithm based on nonlinear inertia weight and perturbation strategy is proposed.Firstly,the Opposition-based learning strategy is introduced in the population initialization phase,and particles with better fitness values are selected as the initial population,which is beneficial to improve the quality of the initial solutions.Then,the nonlinear decreasing inertia weight is used to update the speed of particles,ensuring that the algorithm can explore more high-quality solutions in the early stage and has the ability to perform local search in the later stage.Finally,when the algorithm falls into local optimum,the algorithm performs perturbation operation,combining the position of the global optimal particle with the positions of other particles to help the algorithm escape from the local optimum.The simulation results show that when performing path planning in two different obstacle environments,the improved algorithm demonstrates higher efficiency in obstacle avoidance compared to the comparison algorithm,and it also finds better paths.(2)On the basis of the improved PSO algorithm mentioned above,a PSO-ACO algorithm is proposed to solve the problems existing in the path planning of the traditional ACO algorithm,such as slow convergence speed and easy to fall into local optimum.Firstly,the improved PSO algorithm is used for path pre-search,and the outputted optimal path is converted into initial pheromone increment of ACO algorithm to increase the difference of pheromone between nodes.This measure improves the convergence speed of ACO algorithm in the early stage.Secondly,the distance heuristic function in the state transition rule is improved,and the turning function is also introduced into it.The improved rule can guide mobile robots to find smoother paths.Then,the pheromone update method is improved by updating the pheromone only on the shorter paths,which improves the optimization efficiency of the algorithm.Finally,in order to solve the deadlock problem,the deadlock positions of ants are recorded in the taboo table to increase the diversity of the population.An environment model is established by using the grid method,and simulation experiments are carried out in grid maps of different sizes.The results of the experiments show that the improved algorithm can find the optimal path with fewer iterations and has the best comprehensive performance when performing path planning.