Path Planning Of Mobile Robot Based On Adaptive Ant Colony Algorithm

With the rapid development of information technology,mobile robot gradually into our lives.Mobile robot technology combines with variety of academic projects and derives the new technology,which contains the development process of these academic projects,and contains a large number of new technology,so it is the most important of the current scientific exploration.With the rapid development of some engineering disciplines,such as computer technology,deep-learning study and other disciplines,mobile robots have become more intelligent,simple and easy to operate than before,so it is also widely used in our human industry around the various professions.Navigation and control is the most critical of mobile robot technology i,and to complete navigation and control must be based on path planning.When a mobile robot completes some research projects in a complex workspace,it is necessary to plan a shortest path from the origin to the end.The ant colony algorithm is a kind of intelligent algorithm,which can be used to study the NP-Hard problem and has a good applicability for solving large-scale problems.This paper decides to combine the path planning problem of the mobile robot with the ant colony algorithm to get its optimal path.1.Learn the development process of mobile robots,analyze the background and significance,research the previous method of mobile robot path planning problems,and makes a simple comparison of these methods.2.The traditional ACO algorithm is studied in detail,and simply analyze the several improved ant colony algorithm.Such as:Max-Min Ant System,Best-Worst Ant System,Rank-Based Version of Ant System,and analysis of the advantages and disadvantages of the traditional ant colony algorithm.3.In the process of solving the path planning of mobile robots,an adaptive ant colony algorithm is proposed to adjust the path planning of mobile robots due to the shortcomings of traditional ACO algorithm.4.In order to avoid the local optimization of the ants in the search process,this paper introduces the weighting factor in the state transition probability formula,taking the path length into the probability formula.Thus,when the ants choose the next grid can reduce the search times,while enhancing the direction of the ant to the target grid movement trends,thereby enhancing the convergence rate.5.In order to reduce the effect of pheromone content on the algorithm,this paper improves the pheromone update formula,and updates the pheromone in the two directions when updating the pheromone,and combined with Max-Min Ant System,divide the pheromone content between the[τmin,τmax],so that the ants in the choice of path from the pheromone content of the shackles,to avoid local optimum,and improve the efficiency of the algorithm.6.Using the grid method to build mobile robots environment,and do the simulation experiments under MATLAB(R2012a).The simulation results show that the improved algorithm can accomplish the task of mobile robot path planning very well,and find the optimal path quickly.The experiment also analyzes the influence of different parameters on the experimental results.By comparing the best performance indicators,the time performance indicators,the robust performance indicators and the composite indicator with traditional ant colony algorithm,results suggests that the improved algorithm in the aspect of theory and practice are research significance.