Energy-Efficient Multi-UAV Collaborative Path Planning using Levy Flight and Improved Gray Wolf Optimization

In the field of Unmanned Aerial Vehicle (UAV) technology, there has been a growing interest in the efficient management of energy consumption through strategic path planning in complex obstacle environments. This emerging trend aims to optimize the flight routes of UAVs in order to minimize their energy usage. Path planning is a key process to determine the trajectory of a UAV from its origin to its destination. However, many algorithms proposed for this task have proven to be inefficient in complex obstacle environments. For this reason, this paper proposes a Levy flight based multi-population gray wolf optimization (LM-GWO) algorithm. It combines multi-population ideas, and clusters individual gray wolves into different populations through the Bi-Kmeans clustering algorithm. It accelerates the algorithm’s convergence by allowing different gray wolf populations to complete different jobs during the training process. In addition, one of the limitations of the GWO algorithm is its susceptibility to getting trapped in local optima, which is solved by introducing the Levy flight mechanism, which ultimately makes the multi-UAVs cooperate to complete the path planning work. The results of simulation experiments demonstrate that the LM-GWO algorithm can get the flight path that satisfies the constraints. By comparing with the other three algorithms, the algorithm’s effectiveness in solving cooperative path planning to save energy consumption is verified.