A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control

Ning Wang; Yali Ren

doi:doi:10.11648/j.ajris.20260101.16

Review Article |

| Peer-Reviewed

A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control

Ning Wang

, Yali Ren^*

Published in American Journal of Robotics and Intelligent Systems (Volume 1, Issue 1)

Received: 9 February 2026 Accepted: 20 February 2026 Published: 18 March 2026

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Swarm robotics has emerged as a transformative paradigm for accomplishing complex tasks through the coordinated operation of large numbers of simple robots. As swarm sizes scale from tens to hundreds of agents, effective control strategies become increasingly critical to prevent congestion, maintain system throughput, and ensure safe coordination. This review surveys the state of the art in swarm robotics control, with particular emphasis on coordination mechanisms and congestion management. Four major control paradigms are examined: centralized trajectory planning, reactive collision avoidance, spatial partitioning, and learning-based adaptive methods. Beyond these established approaches, the paper explores emerging hybrid frameworks, including Centralized Training with Decentralized Execution (CTDE) architectures, Graph Neural Network (GNN)-based coordination, and hybrid rule-learning integration. For each paradigm, a formal mathematical analysis is provided, covering computational complexity, convergence properties, and stability guarantees. To support rigorous and reproducible evaluation, this paper proposes a standardized assessment framework comprising mandatory performance metrics, scalability benchmarks, and systematic ablation protocols. Finally, open challenges are identified and future research directions outlined, with the aim of advancing the development of robust and deployable swarm robotic systems.

Published in	American Journal of Robotics and Intelligent Systems (Volume 1, Issue 1)
DOI	10.11648/j.ajris.20260101.16
Page(s)	46-56
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2026. Published by Science Publishing Group

Keywords

Swarm Robotics, Multi-robot Coordination, Congestion Control, Deep Reinforcement Learning, Centralized Training with Decentralized Execution (CTDE), Graph Neural Networks (GNN), Collision Avoidance, Decentralized Control

References

[1]	M. Dorigo, G. Theraulaz, V. Trianni, “Reflections on the future of swarm robotics,” Sci. Robot., vol. 5, no. 49, eabe4385, 2021. https://doi.org/10.1126/scirobot.abe4385
[2]	M. Schranz, M. Umlauft, M. Sende, W. Elmenreich, “Swarm robotic behaviors and current applications,” Front. Robot. AI, vol. 7, p. 36, 2020. https://doi.org/10.3389/frobt.2020.00036
[3]	P. G. F. Dias, M. C. Silva, G. P. Rocha Filho et al., “Swarm robotics: A perspective on the latest reviewed concepts and applications,” Sensors, vol. 21, no. 6, p. 2062, 2021. https://doi.org/10.3390/s21062062
[4]	E. Debie, K. Kasmarik, M. Garratt, “Swarm robotics: A survey from a multi-tasking perspective,” ACM Comput. Surv., vol. 56, no. 2, pp. 1–38, 2024. https://doi.org/10.1145/3610222
[5]	K. Azadeh, R. de Koster, D. Roy, “Robotized and automated warehouse systems: Review and recent developments,” Transp. Sci., vol. 53, no. 4, pp. 917–945, 2019. https://doi.org/10.1287/trsc.2018.0873
[6]	J. P. Queralta, J. Taipalmaa, B. C. Pullinen et al., “Collaborative multi-robot search and rescue,” IEEE Access, vol. 8, pp. 191617–191643, 2020. https://doi.org/10.1109/ACCESS.2020.3030163
[7]	Y. Alqudsi, M. Makaraci, “Exploring advancements and emerging trends in robotic swarm coordination and control,” Proc. Inst. Mech. Eng. C, 2025. https://doi.org/10.1177/09544062251314588
[8]	A. Prorok, M. Malencia, L. Carlone et al., “Beyond robustness: A taxonomy of approaches towards resilient multi-robot systems,” arXiv: 2109.12343, 2021.
[9]	H. Zhang, Y. Chen, Y. Wang et al., “Congestion-aware multi-robot coordination in dynamic environments,” Robot. Auton. Syst., vol. 143, p. 103817, 2021. https://doi.org/10.1016/j.robot.2021.103817
[10]	G. Yu, M. T. Wolf, “Congestion prediction for large fleets of mobile robots,” Proc. IEEE ICRA, pp. 7642–7649, 2023. https://doi.org/10.1109/ICRA48891.2023.10161519
[11]	J. van den Berg, M. Lin, D. Manocha, “Reciprocal velocity obstacles for real-time multi-agent navigation,” in Robotics Research, Springer, pp. 3–19, 2019. https://doi.org/10.1007/978-3-319-60916-4 1
[12]	J. Snape, J. van den Berg, S. J. Guy, D. Manocha, “Smooth and collision-free navigation for multiple robots using reciprocal velocity obstacles,” Auton. Robots, vol. 45, no. 1, pp. 15–30, 2021. https://doi.org/10.1007/s10514-020-09960-7
[13]	O. Khatib, “Real-time obstacle avoidance for manipulators and mobile robots: 35 years of impact,” Int. J. Robot. Res., vol. 41, no. 6, pp. 493–499, 2022. https://doi.org/10.1177/02783649221080435
[14]	Y. F. Chen, M. Everett, M. Liu, J. P. How, “Crowd-robot interaction: Crowd-aware robot navigation with attention-based deep RL,” Proc. IEEE ICRA, pp. 6015–6022, 2019. https://doi.org/10.1109/ICRA.2019.8794134
[15]	P. Long, T. Fan, X. Liao, W. Liu et al., “Towards optimally decentralized multi-robot collision avoidance via deep RL,” Int. J. Robot. Res., vol. 39, no. 7, pp. 856–892, 2020. https://doi.org/10.1177/0278364920937741
[16]	R. Lowe, Y. Wu, A. Tamar et al., “Multi-agent actor-critic for mixed cooperative-competitive environments,” in Multi-Agent Machine Learning, Springer, pp. 117–140, 2020. https://doi.org/10.1007/978-3-031-18077-5 6
[17]	C. Yu, A. Velu, E. Vinitsky et al., “The surprising effectiveness of PPO in cooperative multi-agent games,” Adv. Neural Inf. Process. Syst., vol. 35, 2022. arXiv: 2103.01955
[18]	R. Stern, N. Sturtevant, A. Felner et al., “Multi-agent pathfinding: Definitions, variants, and benchmarks,” Artif. Intell., vol. 303, p. 103650, 2022. https://doi.org/10.1016/j.artint.2022.103650
[19]	G. Sartoretti, J. Kerr, Y. Shi et al., “PRIMAL: Pathfinding via reinforcement and imitation multi-agent learning,” IEEE Robot. Autom. Lett., vol. 4, no. 3, pp. 2378–2385, 2019. https://doi.org/10.1109/LRA.2019.2903261
[20]	A. Andreychuk, K. Yakovlev, E. Boyarski, R. Stern, “Multi-agent pathfinding with continuous time,” Artif. Intell., vol. 305, p. 103662, 2022. https://doi.org/10.1016/j.artint.2022.103662
[21]	J. Gao, Y. Li, X. Li et al., “A review of graph-based multi-agent pathfinding solvers,” Knowl.-Based Syst., vol. 283, p. 111121, 2024. https://doi.org/10.1016/j.knosys.2023.111121
[22]	J. Li, W. Ruml, S. Koenig, “EECBS: A bounded-suboptimal search for multi-agent path finding,” Proc. AAAI, vol. 35, no. 14, pp. 12353–12362, 2021. https://doi.org/10.1609/aaai.v35i14.17466
[23]	W. H¨onig, J. A. Preiss, T. K. S. Kumar et al., “Trajectory planning for quadrotor swarms,” IEEE Trans. Robot., vol. 38, no. 2, pp. 1083–1100, 2022. https://doi.org/10.1109/TRO.2021.3098745
[24]	L. Wang, A. D. Ames, M. Egerstedt, “Safety barrier certificates for collision-free multirobot systems,” IEEE Trans. Robot., vol. 33, no. 3, pp. 661–674, 2021. https://doi.org/10.1109/TRO.2017.2659727
[25]	T. Fan, P. Long, W. Liu, J. Pan, “Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios,” Int. J. Robot. Res., vol. 39, no. 7, pp. 856–892, 2020. https://doi.org/10.1177/0278364920916531
[26]	M. Everett, Y. F. Chen, J. P. How, “Collision avoidance in pedestrian-rich environments with deep reinforcement learning,” IEEE Access, vol. 9, pp. 10357–10377, 2021. https://doi.org/10.1109/ACCESS.2021.3050338
[27]	D. Zhou, Z. Wang, M. Schwager, “Agile coordination and assistive collision avoidance for quadrotor swarms using buffered Voronoi cells,” Proc. IEEE ICRA, 2020. https://doi.org/10.1109/ICRA40945.2020.9196591
[28]	A. Pierson, W. Schwarting, S. Karaman, D. Rus, “Weighted buffered Voronoi cells for distributed semi-cooperative behavior,” Proc. IEEE ICRA, pp. 5611–5617, 2020. https://doi.org/10.1109/ICRA40945.2020.9197589
[29]	Q. Li, F. Gama, A. Ribeiro, A. Prorok, “Graph neural networks for decentralized multi-robot path planning,” Proc. IEEE/RSJ IROS, pp. 11785–11792, 2020. https://doi.org/10.1109/IROS45743.2020.9341668
[30]	C. Jiang, X. Huang, Y. Guo, “End-to-end decentralized formation control using a GNN-based learning method,” Front. Robot. AI, vol. 10, p. 1285412, 2023. https://doi.org/10.3389/frobt.2023.1285412
[31]	M. Damani, Z. Luo, E. Wenzel, G. Sartoretti, “PRIMAL2: Pathfinding via reinforcement and imitation multi-agent learning – lifelong,” IEEE Robot. Autom. Lett., vol. 6, no. 2, pp. 2666–2673, 2021. https://doi.org/10.1109/LRA.2021.3062365
[32]	J. Wang, Z. Ren, T. Liu et al., “QPLEX: Duplex dueling multi-agent Q-learning,” Adv. Neural Inf. Process. Syst., vol. 33, pp. 19934–19945, 2020. arXiv: 2008.01062
[33]	J. Orr, A. Dutta, “Multi-agent deep reinforcement learning for multi-robot applications: A survey,” Sensors, vol. 23, no. 7, p. 3625, 2023. https://doi.org/10.3390/s23073625
[34]	W. Zhao, J. P. Queralta, T. Westerlund, “Sim-to-real transfer in deep reinforcement learning for robotics: A survey,” Proc. IEEE Symp. Ser. Comput. Intell., pp. 737–744, 2020. https://doi.org/10.1109/SSCI47803.2020.9308468
[35]	C. Amato, “An introduction to centralized training for decentralized execution in cooperative multi-agent RL,” arXiv: 2409.03052, 2024.
[36]	Y. Zhou, S. Liu, Y. Qing et al., “Is centralized training with decentralized execution framework centralized enough for MARL?” Proc. IJCAI, 2024. https://doi.org/10.24963/ijcai.2024/14
[37]	J. Blumenkamp, S. Morad, J. Gielis, Q. Li, A. Prorok, “A framework for real-world multi-robot systems running decentralized GNN-based policies,” Proc. IEEE ICRA, pp. 8772–8778, 2022. https://doi.org/10.1109/ICRA46639.2022.9812330
[38]	D. Domini, F. Cavallari, G. Aguzzi, M. Viroli, “Scaling swarm coordination with GNNs – how far can we go?” AI, vol. 6, no. 11, p. 282, 2025. https://doi.org/10.3390/ai6110282
[39]	M. Goarin, G. Loianno, “Graph neural network for decentralized multi-robot goal assignment,” IEEE Robot. Autom. Lett., vol. 9, no. 4, pp. 3456–3463, 2024. https://doi.org/10.1109/LRA.2024.3367040
[40]	A. Cheraghi, S. Shahzad, K. Graffi, “Past, present, and future of swarm robotics,” in Intelligent Systems and Applications (IntelliSys), Springer, pp. 190–233, 2022. https://doi.org/10.1007/978-3-031-16078-3_14

Cite This Article

Plain Text BibTeX RIS

APA Style

Wang, N., Ren, Y. (2026). A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control. American Journal of Robotics and Intelligent Systems, 1(1), 46-56. https://doi.org/10.11648/j.ajris.20260101.16

Copy | Download

ACS Style

Wang, N.; Ren, Y. A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control. Am. J. Rob. Intell. Syst. 2026, 1(1), 46-56. doi: 10.11648/j.ajris.20260101.16

Copy | Download

AMA Style

Wang N, Ren Y. A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control. Am J Rob Intell Syst. 2026;1(1):46-56. doi: 10.11648/j.ajris.20260101.16

Copy | Download

@article{10.11648/j.ajris.20260101.16,
  author = {Ning Wang and Yali Ren},
  title = {A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control
},
  journal = {American Journal of Robotics and Intelligent Systems},
  volume = {1},
  number = {1},
  pages = {46-56},
  doi = {10.11648/j.ajris.20260101.16},
  url = {https://doi.org/10.11648/j.ajris.20260101.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajris.20260101.16},
  abstract = {Swarm robotics has emerged as a transformative paradigm for accomplishing complex tasks through the coordinated operation of large numbers of simple robots. As swarm sizes scale from tens to hundreds of agents, effective control strategies become increasingly critical to prevent congestion, maintain system throughput, and ensure safe coordination. This review surveys the state of the art in swarm robotics control, with particular emphasis on coordination mechanisms and congestion management. Four major control paradigms are examined: centralized trajectory planning, reactive collision avoidance, spatial partitioning, and learning-based adaptive methods. Beyond these established approaches, the paper explores emerging hybrid frameworks, including Centralized Training with Decentralized Execution (CTDE) architectures, Graph Neural Network (GNN)-based coordination, and hybrid rule-learning integration. For each paradigm, a formal mathematical analysis is provided, covering computational complexity, convergence properties, and stability guarantees. To support rigorous and reproducible evaluation, this paper proposes a standardized assessment framework comprising mandatory performance metrics, scalability benchmarks, and systematic ablation protocols. Finally, open challenges are identified and future research directions outlined, with the aim of advancing the development of robust and deployable swarm robotic systems.
},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control

AU  - Ning Wang
AU  - Yali Ren
Y1  - 2026/03/18
PY  - 2026
N1  - https://doi.org/10.11648/j.ajris.20260101.16
DO  - 10.11648/j.ajris.20260101.16
T2  - American Journal of Robotics and Intelligent Systems
JF  - American Journal of Robotics and Intelligent Systems
JO  - American Journal of Robotics and Intelligent Systems
SP  - 46
EP  - 56
PB  - Science Publishing Group
UR  - https://doi.org/10.11648/j.ajris.20260101.16
AB  - Swarm robotics has emerged as a transformative paradigm for accomplishing complex tasks through the coordinated operation of large numbers of simple robots. As swarm sizes scale from tens to hundreds of agents, effective control strategies become increasingly critical to prevent congestion, maintain system throughput, and ensure safe coordination. This review surveys the state of the art in swarm robotics control, with particular emphasis on coordination mechanisms and congestion management. Four major control paradigms are examined: centralized trajectory planning, reactive collision avoidance, spatial partitioning, and learning-based adaptive methods. Beyond these established approaches, the paper explores emerging hybrid frameworks, including Centralized Training with Decentralized Execution (CTDE) architectures, Graph Neural Network (GNN)-based coordination, and hybrid rule-learning integration. For each paradigm, a formal mathematical analysis is provided, covering computational complexity, convergence properties, and stability guarantees. To support rigorous and reproducible evaluation, this paper proposes a standardized assessment framework comprising mandatory performance metrics, scalability benchmarks, and systematic ablation protocols. Finally, open challenges are identified and future research directions outlined, with the aim of advancing the development of robust and deployable swarm robotic systems.

VL  - 1
IS  - 1
ER  -

Copy | Download

Author Information

Ning Wang

Department of Electrical and Computer Engineering, University of Houston, Houston, USA

Contact Email

http://orcid.org/0000-0003-1568-6933
Yali Ren

School of Computer Science, Georgia Institute of Technology, Atlanta, USA

Contact Email

http://orcid.org/0009-0006-9480-1205

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Wang, N., Ren, Y. (2026). A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control. American Journal of Robotics and Intelligent Systems, 1(1), 46-56. https://doi.org/10.11648/j.ajris.20260101.16

Copy | Download

ACS Style

Wang, N.; Ren, Y. A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control. Am. J. Rob. Intell. Syst. 2026, 1(1), 46-56. doi: 10.11648/j.ajris.20260101.16

Copy | Download

AMA Style

Wang N, Ren Y. A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control. Am J Rob Intell Syst. 2026;1(1):46-56. doi: 10.11648/j.ajris.20260101.16

Copy | Download

@article{10.11648/j.ajris.20260101.16,
  author = {Ning Wang and Yali Ren},
  title = {A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control
},
  journal = {American Journal of Robotics and Intelligent Systems},
  volume = {1},
  number = {1},
  pages = {46-56},
  doi = {10.11648/j.ajris.20260101.16},
  url = {https://doi.org/10.11648/j.ajris.20260101.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajris.20260101.16},
  abstract = {Swarm robotics has emerged as a transformative paradigm for accomplishing complex tasks through the coordinated operation of large numbers of simple robots. As swarm sizes scale from tens to hundreds of agents, effective control strategies become increasingly critical to prevent congestion, maintain system throughput, and ensure safe coordination. This review surveys the state of the art in swarm robotics control, with particular emphasis on coordination mechanisms and congestion management. Four major control paradigms are examined: centralized trajectory planning, reactive collision avoidance, spatial partitioning, and learning-based adaptive methods. Beyond these established approaches, the paper explores emerging hybrid frameworks, including Centralized Training with Decentralized Execution (CTDE) architectures, Graph Neural Network (GNN)-based coordination, and hybrid rule-learning integration. For each paradigm, a formal mathematical analysis is provided, covering computational complexity, convergence properties, and stability guarantees. To support rigorous and reproducible evaluation, this paper proposes a standardized assessment framework comprising mandatory performance metrics, scalability benchmarks, and systematic ablation protocols. Finally, open challenges are identified and future research directions outlined, with the aim of advancing the development of robust and deployable swarm robotic systems.
},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - A Review of Coordination, Congestion Management, and Learning-Based Approaches in Swarm Robotics Control

AU  - Ning Wang
AU  - Yali Ren
Y1  - 2026/03/18
PY  - 2026
N1  - https://doi.org/10.11648/j.ajris.20260101.16
DO  - 10.11648/j.ajris.20260101.16
T2  - American Journal of Robotics and Intelligent Systems
JF  - American Journal of Robotics and Intelligent Systems
JO  - American Journal of Robotics and Intelligent Systems
SP  - 46
EP  - 56
PB  - Science Publishing Group
UR  - https://doi.org/10.11648/j.ajris.20260101.16
AB  - Swarm robotics has emerged as a transformative paradigm for accomplishing complex tasks through the coordinated operation of large numbers of simple robots. As swarm sizes scale from tens to hundreds of agents, effective control strategies become increasingly critical to prevent congestion, maintain system throughput, and ensure safe coordination. This review surveys the state of the art in swarm robotics control, with particular emphasis on coordination mechanisms and congestion management. Four major control paradigms are examined: centralized trajectory planning, reactive collision avoidance, spatial partitioning, and learning-based adaptive methods. Beyond these established approaches, the paper explores emerging hybrid frameworks, including Centralized Training with Decentralized Execution (CTDE) architectures, Graph Neural Network (GNN)-based coordination, and hybrid rule-learning integration. For each paradigm, a formal mathematical analysis is provided, covering computational complexity, convergence properties, and stability guarantees. To support rigorous and reproducible evaluation, this paper proposes a standardized assessment framework comprising mandatory performance metrics, scalability benchmarks, and systematic ablation protocols. Finally, open challenges are identified and future research directions outlined, with the aim of advancing the development of robust and deployable swarm robotic systems.

VL  - 1
IS  - 1
ER  -

Copy | Download