Advanced Multi-Robot Path Planning Based on Grey Wolf and Teaching-Learning Based Optimisation

Abstract

Multi-robots stand out for their flexibility, scalability, and robustness in complex tasks by collaborating. Rather than a single robot undertaking a task, many robots can perform one or more tasks, which increases the task efficiency. Mobile robots require path planning to reach the targeted locations while working in areas such as service, logistics, agriculture, and production. This situation is also valid for multi-robots. In this study, an advanced multi-robot path planning method adapted to the path planning of multi-robots is proposed by combining the advantageous aspects of the Grey Wolf Optimization algorithm and the Teaching and Learning Based Optimization algorithm for the path planning of multi-robots. The proposed method was compared with other algorithms. Simulations containing combinations of population numbers, robot numbers, and different environments were applied. The proposed method shows high performance compared to other methods in simulations applied to the multi-robot path-planning problem. According to the comparison results, the proposed method showed high performance in terms of parameter results, such as reaching a faster solution, closing to the target, and total fitness values used in the evaluation of the robot team.