Cooperative path planning of robot swarm based on ACO

摘要

The traditional ant colony algorithm is easy to fall into the local deadlock and stagnation in the cooperative path planning of multi-mobile robots. In order to eliminate the local deadlock phenomenon of multi-mobile robot group, self-organizing network collaboration is introduced into robot community collaboration. When the robot group carries out the route search in batches, the self-organizing cooperative mechanism is used to carry on the information exchange in the local area, and the communication cooperation among the individual robots within the local scope is enhanced to avoid the deadlock. When the robot falls into the deadlock area, it will shares the position of deadlock area to other individuals. And it will take the initiative to change the pheromone that the ant colony stay in the deadlock range, so that follow-up robot can bypass the deadlock range. And then continue to find the shortest path according to the ant colony algorithm pheromone. In this paper, we use grid method to test community cooperative path planning. Experiments show that the improved algorithm can improve the efficiency of robot swarm path planning.