Research On Path Planning Based On Ant Colony Algorithm

Path planning refers to the object under certain constraints,starting from the starting point,to find a path to avoid obstacles to reach the target point,it requires this path to achieve a certain optimal performance indicators.Path planning is widely used in many fields such as traffic planning,workshop operation,robotics and unmanned aerial vehicles.Therefore,how to implement an efficient path planning method is a hot research topic.Ant colony algorithm is a heuristic optimization algorithm,it is widely used in many combinatorial problems such as traveling salesman problem,vehicle routing problem and path planning because of its advantages of positive feedback,good parallelism and strong robustness.This paper mainly studies the application of ant colony algorithm in path planning.First of all,this paper analyzes the research background and significance of the subject,introduces the research status and applications in the path planning of the ant colony algorithm,and introduces the existing path planning algorithms and spatial planning methods,establishes the space model by using grid method with graph theory.Secondly,this paper introduces the basic principles,mathematical models and application process of the path planning based on ant colony algorithm,analyzes some typical improved ant colony algorithm.The value of parameters of the basic ant colony algorithm and the maximum and minimum ant colony algorithm are analyzed experimentaly,and a large number of simulation experiments are carried out in different obstacle environments,the experimental results show that the performance of the maximum and minimum ant colony algorithm is better than the basic ant colony algorithm in solving path planning problem,but both of the algorithm have the disadvantages like slow convergence speed and easy falling into local optimization.Then,aiming at the deficiency of ant colony algorithm,this paper presents an improved ant colony algorithm based on the maximum and minimum ant colony algorithm,the improved algorithm introduces directional heuristric factor?dynamic adjustment strategy of pheromone volatile factor and enhancement factor?pheromone update method improvement strategy.The simulation experiments in different obstacle environments show that compared with the basic ant colony algorithm and the maximum and minimum ant colony algorithm,the improved ant colony algorithm can find a shorter and less costly path and converge faster,with better overall performance.Finally,the paper summarizes the work and research results,and explores the contents that need to be further studied.