.png){kind=icon}
.png){kind=icon}
Return
A Multi-Layer based Collaborative Optimization (MCO) for Multiple UAVs’ Task Allocation and Scheduling
.png){kind=icon}
PRE
AI
DOI：10.1016/j.vehcom.2025.100989.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• This study proposes a Multi-Layer Collaborative Optimization (MCO) method, which integrates path preplanning, task allocation, and task scheduling into a unified optimization framework to enhance task execution efficiency for multiple UAVs in urban disaster environments. By optimizing each module at different layers, the method ensures overall mission utility while satisfying UAV performance constraints and task requirements. • In the upper layer, a Dynamic Constrained Particle Swarm Optimization (DPSO) algorithm is proposed for path preplanning by designing a dynamic subpopulation division strategy. By dynamically adjusting the subpopulation division, DPSO can efficiently optimize the path selection of multiple UAVs, reducing path redundancy and discontinuous task allocation problems. • In the middle layer, a Clustered Consensus-Based Bundle Algorithm (CCBA) is designed to allocate tasks to different UAVs based on preplanned paths, solving issues related to discontinuous task allocation and redundant paths. In the lower layer, a Multi-Neighborhood Variable Simulated Annealing (MNV-SA) algorithm is used to further optimize the task execution sequence for each UAV, ensuring the optimality of task scheduling.
Journal
IF:
6.5
Papers:
793
Citations:
3.2K