Adaptive task allocation for multi-UAV systems based on bacteria foraging behaviour

doi:10.1016/j.asoc.2019.105643

2019-10-01

Heba Kurdi *

Shiroq Al-Megren *

Ebtesam Aloboud

Abdulrahman S. Aldawood

Kamal Youcef‐Toumi

DOI：10.1016/j.asoc.2019.105643

原文链接

查看原文

摘要

En 中文

The foraging behaviour of bacteria in colonies exhibits motility patterns that are simple and reasoned by stimuli. Notwithstanding its simplicity, bacteria behaviour demonstrates a level of intelligence that can feasibly inspire the creation of solutions to address numerous optimisation problems. One such challenge is the optimal allocation of tasks across multiple unmanned aerial vehicles (multi-UAVs) to perform cooperative tasks for future autonomous systems. In light of this, this paper proposes a bacteria-inspired heuristic for the efficient distribution of tasks amongst deployed UAVs. The usage of multi-UAVs is a promising concept to combat the spread of the red palm weevil (RPW) in palm plantations. For that purpose, the proposed bacteria-inspired heuristic was utilised to resolve the multi-UAV task allocation problem when combating RPW infestation. The performance of the proposed algorithm was benchmarked in simulated detect-and-treat missions against three long-standing multi-UAV task allocation strategies, namely opportunistic task allocation, auction-based scheme, and the max-sum algorithm, and a recently introduced locust-inspired algorithm for the allocation of multi-UAVs. The experimental results demonstrated the superior performance of the proposed algorithm, as it substantially improved the net throughput and maintained a steady runtime performance under different scales of fleet sizes and number of infestations, thereby expressing the high flexibility, scalability, and sustainability of the proposed bacteria-inspired approach. (C) 2019 Elsevier B.V. All rights reserved.

Keyword:

Task allocation

Unmanned aerial vehicles

Distributed systems

Multi-UAV systems

Bacteria inspiration

Optimisation problem

Red palm weevil