Title: Bee-inspired task allocation algorithm for multi-UAV search and rescue missions

Authors: Heba Kurdi; Shiroq Al-Megren; Ebtesam Aloboud; Abeer Ali Alnuaim; Hessah Alomair; Reem Alothman; Alhanouf Ben Muhayya; Noura Alharbi; Manal Alenzi; Kamal Youcef-Toumi

Addresses: Computer Science Department, King Saud University, Riyadh, KSA; Mechanical Engineering Department, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA ' Mechanical Engineering Department, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA; Information Technology Department, King Saud University, Riyadh, KSA ' Computer Science Department, Al Imam Mohammad Ibn Saud Islamic University, Riyadh, KSA ' Computer Science and Engineering Department, King Saud University, Riyadh, KSA ' Computer Science Department, King Saud University, Riyadh, KSA ' Computer Science Department, King Saud University, Riyadh, KSA ' Computer Science Department, King Saud University, Riyadh, KSA ' Computer Science Department, King Saud University, Riyadh, KSA ' Computer Science Department, King Saud University, Riyadh, KSA ' Mechanical Engineering Department, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA

Abstract: Task allocation plays a pivotal role in the optimisation of multi-unmanned aerial vehicle (multi-UAV) search and rescue (SAR) missions in which the search time is critical and communication infrastructure is unavailable. These two issues are addressed by the proposed BMUTA algorithm, a bee-inspired algorithm for autonomous task allocation in multi-UAV SAR missions. In BMUTA, UAVs dynamically change their roles to adapt to changing SAR mission parameters and situations by mimicking the behaviour of honeybees foraging for nectar. Four task allocation heuristics (auction-based, max-sum, ant colony optimisation, and opportunistic task allocation) were thoroughly tested in simulated SAR mission scenarios to comparatively assess their performances relative to that of BMUTA. The experimental results demonstrate the ability of BMUTA to achieve a superior number of rescued victims with much shorter rescue times and runtime intervals. The proposed approach demonstrates a high level of flexibility based on its situational awareness, high autonomy, and economic communication scheme.

Keywords: task allocation; bio-inspired algorithms; unmanned aerial vehicles; UAVs; distributed systems; search and rescue; SAR; optimisation problems.

DOI: 10.1504/IJBIC.2020.112339

International Journal of Bio-Inspired Computation, 2020 Vol.16 No.4, pp.252 - 263

Accepted: 02 Mar 2020
Published online: 12 Jan 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article