Robot Path Planning Research Based On Improved Ant Colony Algorithm

In today’s technological and information-based world,artificial intelligence has become the hottest research topic and robotics is becoming an integral part of human production and life.In order to improve the autonomous navigation performance of robots,numerous experts and scholars have invested a great deal of effort,the most crucial of which is the path planning technology of mobile robots.The study of robot path planning algorithms is therefore crucial to the development of the robotics field and to the advancement of human society.In order to systematically study the robot path planning problem,this paper adopts Ant Colony Optimization(ACO)as the research object,and the main research contents are as follows:(1)To address the problem that the traditional ant colony algorithm has poor early search results and is easily affected by the residual pheromone of the remaining non-adopted solutions,resulting in unsatisfactory convergence of the algorithm,this paper proposes a global path planning method based on an improved ant colony algorithm.Firstly,the initial pheromone distribution of the ant colony algorithm is optimized using a two-way particle swarm algorithm to accelerate the convergence of the algorithm;secondly,to address the problem that the distance heuristic function of the algorithm has poor visibility of the target points and ignores multiple road conditions,the multi-factor heuristic function is reconstructed by introducing the heuristic information of path distance and smoothness evaluation to overcome the limitations of the traditional algorithm;subsequently,the individual adaptive mechanism is introduced to improve the adaptive capacity of the algorithm and solve the problem of weak diversity of the algorithm population.This paper then introduces an individual adaptive mechanism to improve the adaptation capability of the algorithm and solve the weak diversity problem of the algorithm population;furthermore,a random inertia factor is introduced to the pheromone update strategy to enable it to converge faster;finally,the overall global path is smoothed.The effectiveness of the innovative algorithm can be seen from the performance and simulation experimental results.(2)To address the problem of low practicality of the algorithm due to the idealized environment information of the 2D raster map,this paper changes the environment map of the improved ant colony algorithm into a 3D map to test the performance of the algorithm.In this paper,a fusion ant colony algorithm combining the advantages of the Artificial Potential Field(APF)method is proposed;and for the problem that the traditional artificial potential field method makes it difficult for the robot to enter the end point due to the negative influence of the obstacles around the near point where it wants to reach,this paper introduces the mechanism of the robot’s own weak gravitational field relative to the obstacles,and adds the robot’s weak gravitational field relative to the obstacles to the repulsion correction function to avoid the oscillation phenomenon.This paper introduces the mechanism of the robot’s own weak gravitational field relative to the obstacle,and adds a repulsive correction function to the repulsive potential field function to avoid the oscillation phenomenon.Through simulation experiments,the algorithm proposed in this paper has been verified to be superior in 3D robot path planning.(3)To address the problem of untimely collision avoidance in the face of dynamic obstacles,this paper selects the dynamic window method as a strategy to compensate for this deficiency to complete the local planning task,and to address the problem of untimely obstacle avoidance in the traditional dynamic window method,which eventually leads to a long and time-consuming planning path,this paper changes a more advantageous distance evaluation index based on the original evaluation function.The ant colony fusion improved dynamic window algorithm proposed in this paper has proved its excellent obstacle avoidance ability and global path planning efficiency when encountering dynamic obstacles.Figure [31] Table[6] Reference [81]...