Smooth Path Planning of Logistics Robot based on improved Ant Colony Algorithm

A better ant colony algorithm was created to fix the issues with the old one when it comes to planning the paths of logistics robots in a two-dimensional grid environment. These issues include a slow convergence speed, too many stopping points, and an easy tendency to get stuck in a local optimal state. To begin, the heuristic function of the artificial potential field gravity is changed so that it is affected by the goal point. This makes it easier to find the best path and speed up the convergence process. Next, the difference in pheromone concentration between the last round's best path and worst path was added to the pheromone. The pheromone concentration was then changed to make the search path as long as possible. The triangular pruning method is also used to get rid of unnecessary stopping points, cut down on the number of turns the robot has to make, and make sure the planned path is smoother and easier for the logistics robot to follow. The results of the experiment show that the improved ant colony algorithm makes the best path length, path transition times, and convergence speed 3.9%, 33%, and 66.7% better than the method suggested in paper [16]. It has been shown that the improved ant colony algorithm is good at planning paths on a world level.