Path Planning Of Ant Colony Algorithm Based On Artificial Potential Field Optimization

With the deepening of research in the field of intelligent robots and the gradual maturity of technology,various path planning algorithms have become the current research hotspots.In the past,many traditional and classical algorithms can satisfy the pathfinding behavior under the condition of simple,space barrier-free or less barrier-free,however,in the context of complex obstacles,traditional algorithms have exposed the shortcomings of being unable to cope with environmental changes,failing to effectively plan the path,and having low efficiency.Based on the research and analysis of the related fields of intelligent robot path planning at home and abroad,this paper conducts the following research on the mainstream path planning methods and their existing problems:Firstly,aiming at the problem of local minimum of artificial potential field algorithm,an improved artificial potential field algorithm based on attractive force attenuation is proposed.Based on the traditional artificial potential field algorithm,the algorithm improves the gravitational field function by adding the position change information of the robot,and enhances the sensitivity of the artificial potential field to the position information,and thus improves the directivity and operation efficiency of the artificial potential field algorithm.Secondly,aiming at the problem that the traditional ant colony algorithm has slow convergence speed and low planning efficiency in 2D path planning,a planning method based on AAPF optimized ant colony algorithm is proposed.This algorithm uses an improved artificial potential field algorithm to optimize the heuristic function of the ant colony algorithm,Under the condition of retaining the ant colony algorithm optimization ability,the heuristic function n_ij,the potential force heuristic information?_Fand the offset heuristic informations_ij are introduced.Through the high directivity of the initial force field,the number of iterations is reduced to improve the convergence speed and path optimization ability of the algorithm.Finally,the raw data is built into a two-dimensional grid environment,and an artificial power field is added to the grid environment.Through the analysis of the gravitational potential field and the evaluation of the optimal path and iteration times,the effectiveness of the improved artificial potential field algorithm based on the attraction attenuation is verified.At the same time,by adding heuristic information items into the heuristic function in turn,the AAPF-optimized ant colony algorithm and the classical ant colony algorithm in this paper are compared in turn.It also compares the ant colony optimization algorithm based on AAPF with classical ant colony algorithm,GA optimization ant colony algorithm and simulated annealing optimization ant colony algorithm.The effectiveness of the proposed optimization algorithm is further verified by analyzing the experimental results.