Dynamic Multi-Role Adaptive Collaborative Ant Colony Optimization for Robot Path Planning

Aiming at the problems of poor diversity and slow convergence of ant colony algorithm, dynamic multi-role adaptive collaborative ant colony optimization (MRCACO) is proposed in this paper, and it applies to robot path planning. Firstly, an adaptive dynamic complementary algorithm is proposed to form a heterogeneous multi-colony together with ACS and MMAS, which complement each other in performance. Secondly, a multi-role adaptive cooperation mechanism is proposed to realize the exchange and sharing of information. The mechanism includes two strategies: one is an elite attribute learning strategy, which highlights the role of elite attribute and improves the comprehensive performance of ACS and MMAS; The second is the pheromone balancing strategy, which is executed when the algorithm is stagnant to make the algorithm jump out of the local optimal. Further, the effectiveness and superiority in the algorithm are demonstrated by the experimental analysis of multiple TSP instances. Finally, the algorithm presented in this paper is applied to the path planning of the robot, two different deadlock rollback strategies are proposed to solve the deadlock problem and improve the efficiency of the algorithm. The results of a practical application show that the algorithm is feasible to solve the path planning problem.