Communication-efficient heterogeneous multi-UAV task allocation based on clustering

Abstract

The heterogeneous unmanned aerial vehicle (UAV) system aims to achieve higher-level task coordination and execution by integrating UAVs of different types, functionalities, and scales. Addressing the diverse and complex requirements of tasks, the allocation algorithm for decentralized multi-UAV systems often encounters communication redundancy, leading to the issue of excessive communication overhead. This paper proposes a clustering-based Consensus-Based Bundle Algorithm (Clustering-CBBA), which introduces a novel bundle construction, an improved consensus strategy, and a distance-based UAV grouping approach. Specifically, utilizing the k-means++ method based on distance factors, UAVs are initially partitioned into different clusters, breaking down the large-scale problem into smaller ones. Subsequently, the first UAV in each cluster is designated as the leader UAV. The proposed algorithm can handle multi-UAV tasks by improving the task bundle construction method and consensus algorithm. Additionally, intra-cluster UAVs employ an internal conflict resolution method to gather the latest information, while inter-cluster UAVs use an external conflict resolution method to ensure conflict-free task allocation, continuing until the algorithm converges. Experimental results demonstrate that the proposed method, compared to DMCHBA, G-CBBA, and baseline CBBA, significantly reduces communication overhead across different task scales and UAV quantities. Moreover, it maintains ideal performance regarding task completion and global task reward, showcasing higher efficiency and practicality.