Next Article in Journal
High-Precision Modeling of UAV Electric Propulsion for Improving Endurance Estimation
Previous Article in Journal
Robust Optimal Consensus Control for Multi-Agent Systems with Disturbances
Previous Article in Special Issue
Real-Time Long-Range Control of an Autonomous UAV Using 4G LTE Network
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Drones
Volume 10
Issue 2
10.3390/drones10020079
drones-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

From Human Teams to Autonomous Swarms: A Reinforcement Learning-Based Benchmarking Framework for Unmanned Aerial Vehicle Search and Rescue Missions

by
Julian Bialas
1,2,†,
Mohammad Reza Mohebbi
1,2,†,
Michiel J. van Veelen
3,4,*,†,
Abraham Mejia-Aguilar
5,
Robert Kathrein
1,2 and
Mario Döller
1
1
Department of Data Science, FH Kufstein Tirol, 6330 Kufstein, Austria
2
Department of Mathematics and Informatics, University of Passau, 94030 Passau, Germany
3
Institute of Mountain Emergency Medicine, Eurac Research, 39100 Bolzano, Italy
4
Department of Sport Science–Medical Section, University of Innsbruck, 6020 Innsbruck, Austria
5
terraXcube, Eurac Research, 39100 Bolzano, Italy
*
Author to whom correspondence should be addressed.
†
These authors contributed equally to this work.
Drones 2026, 10(2), 79; https://doi.org/10.3390/drones10020079 (registering DOI)
Submission received: 2 December 2025 / Revised: 15 January 2026 / Accepted: 20 January 2026 / Published: 23 January 2026
(This article belongs to the Special Issue Drone Communication, Networking, and Trajectory Control in Urban Environments)
Versions Notes

Abstract

The adoption of novel technologies such as Unmanned Aerial Vehicles (UAVs) in Search and Rescue (SAR) operations remains limited. As a result, their full potential is not yet realized. Although UAVs have been deployed on an ad hoc basis, typically under manual control by dedicated operators, assisted and fully autonomous configurations remain largely unexplored. In this study, three SAR frameworks are systematically evaluated within a unified benchmarking framework: conventional ground missions, UAV-assisted missions, and fully autonomous UAV operations. As the key performance indicator, the target localization time was quantified and used as the means of comparison amongst frameworks. The conventional and assisted frameworks were experimentally tested through physical hardware in a controlled outdoor setting, wherein simulated callouts occurred via rescue teams. The autonomous swarm framework was simulated in the form of a multi-agent Reinforcement Learning (RL) method via the use of the Proximal Policy Optimization (PPO) algorithm. This enabled the optimization of the decentralized cooperative actions that could occur for efficient exploration of a partially observed three-dimensional environment. Our results demonstrated that the autonomous swarm significantly outperformed the conventional and assisted approaches in terms of speed and coverage. Finally, a detailed depiction of the framework’s integration into an operational system is provided.
Keywords: search and rescue; unmanned aerial vehicles; autonomous swarm; reinforcement learning; proximal policy optimization; multi-agent systems; 3D exploration; human–drone collaboration search and rescue; unmanned aerial vehicles; autonomous swarm; reinforcement learning; proximal policy optimization; multi-agent systems; 3D exploration; human–drone collaboration

Share and Cite

MDPI and ACS Style

Bialas, J.; Mohebbi, M.R.; van Veelen, M.J.; Mejia-Aguilar, A.; Kathrein, R.; Döller, M. From Human Teams to Autonomous Swarms: A Reinforcement Learning-Based Benchmarking Framework for Unmanned Aerial Vehicle Search and Rescue Missions. Drones 2026, 10, 79. https://doi.org/10.3390/drones10020079

AMA Style

Bialas J, Mohebbi MR, van Veelen MJ, Mejia-Aguilar A, Kathrein R, Döller M. From Human Teams to Autonomous Swarms: A Reinforcement Learning-Based Benchmarking Framework for Unmanned Aerial Vehicle Search and Rescue Missions. Drones. 2026; 10(2):79. https://doi.org/10.3390/drones10020079

Chicago/Turabian Style

Bialas, Julian, Mohammad Reza Mohebbi, Michiel J. van Veelen, Abraham Mejia-Aguilar, Robert Kathrein, and Mario Döller. 2026. "From Human Teams to Autonomous Swarms: A Reinforcement Learning-Based Benchmarking Framework for Unmanned Aerial Vehicle Search and Rescue Missions" Drones 10, no. 2: 79. https://doi.org/10.3390/drones10020079

APA Style

Bialas, J., Mohebbi, M. R., van Veelen, M. J., Mejia-Aguilar, A., Kathrein, R., & Döller, M. (2026). From Human Teams to Autonomous Swarms: A Reinforcement Learning-Based Benchmarking Framework for Unmanned Aerial Vehicle Search and Rescue Missions. Drones, 10(2), 79. https://doi.org/10.3390/drones10020079

Article Metrics

Back to TopTop