A Method for Rational Role Allocation in a Computer-Vision-Enabled Swarm of Unmanned Aerial Vehicles Under Resource Constraints
DOI:
https://doi.org/10.15276/opu.2.72.2025.11Keywords:
swarm robotics, role allocation, unmanned aerial vehicles, computer vision, energy management, computational constraints, network connectivity, decentralized coordination, simulation, mission planningAbstract
Role allocation in unmanned aerial vehicle swarms equipped with onboard vision is constrained not only by geometry but also by size, weight and power limits typical for small platforms. Vision pipelines increase energy draw, occupy the onboard compute budget and raise the demand on the wireless link. Heuristics that assign roles solely from distance or state of charge often overlook this coupling and may trigger unnecessary re-assignments. We propose a decentralized auction-based role allocation scheme (Scout, Mapper, Relay, Worker) where each vehicle computes a bid from (i) predicted energy cost for propulsion, sensing, computation and radio, and (ii) the risk of increasing the multi-hop distance to a base station. Feasibility checks prevent assigning vision-heavy roles to agents with insufficient battery reserve or compute capacity, and a switching penalty reduces oscillations. The approach is evaluated in a reproducible PC simulation (1000×1000 m area, limited communication range and heterogeneous computing capabilities) with swarms of 20 and 50 UAVs. We report mission success rate, completion time, mission progress, average base connectivity and the number of role switches. In the more challenging N=20 case the proposed method completes the mission (SR=1.00) while the distance-based and static baselines fail (SR=0). Compared with the battery-only heuristic, it preserves the same success rate but reduces role switching by about 7–8 while maintaining acceptable connectivity. For N=50 all methods succeed, yet the proposed approach keeps the number of switches at 310±52 versus 2386±320 for the battery-only baseline. The cost model can be integrated into swarm management systems and extended to collaborative perception, where a subset of vehicles performs vision-heavy processing and shares compact results under progressive battery depletion.
Downloads
References
Chung, S.-J., Paranjape, A. A., Dames, P., Shen, S., & Kumar, V. (2018). A survey on aerial swarm robotics. IEEE Transactions on Robotics, 34(4), 837–855. https://doi.org/10.1109/TRO.2018.2857475.
Oh, K.-K., Park, M.-C., & Ahn, H.-S. (2015). A survey of multi-agent formation control. Automatica, 53, 424–440. https://doi.org/10.1016/j.automatica.2014.10.022.
Choi, H.-L., Brunet, L., & How, J. P. (2009). Consensus-based decentralized auctions for robust task allocation. IEEE Transactions on Robotics, 25(4), 912–926. https://doi.org/10.1109/TRO.2009.2022423.
Dias, M. B., Zlot, R., Kalra, N., & Stentz, A. (2006). Market-based multirobot coordination: A survey and analysis. Proceedings of the IEEE, 94(7), 1257–1270. https://doi.org/10.1109/JPROC.2006.876939.
Boukoberine, M. N., Zhou, Z., & Benbouzid, M. E. H. (2019). A critical review on unmanned aerial vehicle power supply and energy management: Solutions, strategies, and prospects. Applied Energy, 255, Article 113823. https://doi.org/10.1016/j.apenergy.2019.113823.
Qin, T., Li, P., & Shen, S. (2018). VINS-Mono: A robust and versatile monocular visual-inertial state estimator. IEEE Transactions on Robotics, 34(4), 1004–1020. https://doi.org/10.1109/TRO.2018.2853729.
Mur-Artal, R., & Tardós, J. D. (2017). ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE Transactions on Robotics, 33(5), 1255–1262. https://doi.org/10.1109/TRO.2017.2705103.
Paredes-Vallés, F., Hagenaars, J. J., Dupeyroux, J., Stroobants, S., Xu, Y., & de Croon, G. C. H. E. (2024). Fully neuromorphic vision and control for autonomous drone flight. Science Robotics, 9(86), Article eadi0591. https://doi.org/10.1126/scirobotics.adi0591.
Gerkey, B. P., & Matarić, M. J. (2004). A formal analysis and taxonomy of task allocation in multi-robot systems. The International Journal of Robotics Research, 23(9), 939–954. https://doi.org/10.1177/0278364904045564.
Korsah, G. A., Stentz, A., & Dias, M. B. (2013). A comprehensive taxonomy for multi-robot task allocation. The International Journal of Robotics Research, 32(12), 1495–1512. https://doi.org/10.1177/0278364913496484.
Ponda, S., Redding, J., Choi, H.-L., How, J. P., Vavrina, M., & Vian, J. (2010). Decentralized planning for complex missions with dynamic communication constraints. In Proceedings of the 2010 American Control Conference (ACC) (pp. 3998–4003). IEEE. https://doi.org/10.1109/ACC.2010.5531232.
Kim, K.-S., Kim, H.-Y., & Choi, H.-L. (2019). Minimizing communications in decentralized greedy task allocation. Journal of Aerospace Information Systems, 16(8), 340–345. https://doi.org/10.2514/1.I010624.
Raja, S., Habibi, G., & How, J. P. (2022). Communication-aware consensus-based decentralized task allocation in communication constrained environments. IEEE Access, 10, 19753–19767. https://doi.org/10.1109/ACCESS.2021.3138857.
Skaltsis, G. M., Shin, H.-S., & Tsourdos, A. (2023). A review of task allocation methods for UAVs. Journal of Intelligent & Robotic Systems, 109, Article 76. https://doi.org/10.1007/s10846-023-02011-0.
Shah, S., Dey, D., Lovett, C., & Kapoor, A. (2017). AirSim: High-fidelity visual and physical simulation for autonomous vehicles. In Field and Service Robotics (pp. 621–635). Springer.
Furrer, F., Burri, M., Achtelik, M., & Siegwart, R. (2016). RotorS—A modular Gazebo MAV simulator framework. In Simulation, Modeling, and Programming for Autonomous Robots (pp. 595–625). Springer. https://doi.org/10.1007/978-3-319-26054-9_23.
