mlsanityData to 14 Oct 2026

Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks

arXiv 1903.10527 ↗First posted 25 Mar 2019cs.ROcited by 62

Not on the map. Why?

Abstract (arXiv)

We consider the problem of finding distributed controllers for large networks of mobile robots with interacting dynamics and sparsely available communications. Our approach is to learn local controllers that require only local information and communications at test time by imitating the policy of centralized controllers using global information at training time. By extending aggregation graph neural networks to time varying signals and time varying network support, we learn a single common local controller which exploits information from distant teammates using only local communication interchanges. We apply this approach to the problem of flocking to demonstrate performance on communication graphs that change as the robots move. We examine how a decreasing communication radius and faster velocities increase the value of multi-hop information.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 22; 2022: 15; 2023: 13; 2024: 5; 2025: 3; 2026: 3.

62 papers.

Sort:

By area:

  1. 2022VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learningcited by 68
  2. 2021Transferability Properties of Graph Neural Networkscited by 43
  3. 2022Multi-Robot Collaborative Perception with Graph Neural Networkscited by 35
  4. 2022Graph Neural Networks in IoT: A Surveycited by 28
  5. 2021Learning by Transference: Training Graph Neural Networks on Growing Graphscited by 22
  6. 2021Decentralized Inference with Graph Neural Networks in Wireless Communication Systemscited by 18
  7. 2021Stability of Graph Convolutional Neural Networks to Stochastic Perturbationscited by 18
  8. 2021Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selectioncited by 14
  9. 2021Wide and Deep Graph Neural Network with Distributed Online Learningcited by 14
  10. 2022Unsupervised Optimal Power Flow Using Graph Neural Networkscited by 14
  11. 2021Neurosymbolic Transformers for Multi-Agent Communicationcited by 13
  12. 2020Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learningcited by 12
38 more
  1. 2021Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systemscited by 12
  2. 2021Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approachcited by 12
  3. 2022Graph Neural Networks for Multi-Robot Active Information Acquisitioncited by 12
  4. 2021A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policiescited by 11
  5. 2023Online Control Barrier Functions for Decentralized Multi-Agent Navigationcited by 11
  6. 2021Space-Time Graph Neural Networkscited by 10
  7. 2021Robust Graph Neural Networks via Probabilistic Lipschitz Constraintscited by 10
  8. 2021ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecturecited by 9
  9. 2021Stability of Neural Networks on Manifolds to Relative Perturbationscited by 9
  10. 2021Distributionally Robust Semi-Supervised Learning Over Graphscited by 9
  11. 2023Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunitiescited by 9
  12. 2021Communication Topology Co-Design in Graph Recurrent Neural Network Based Distributed Controlcited by 7
  13. 2021Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networkscited by 7
  14. 2022Stability of Aggregation Graph Neural Networkscited by 7
  15. 2022Environment Optimization for Multi-Agent Navigationcited by 6
  16. 2023Constrained Environment Optimization for Prioritized Multi-Agent Navigationcited by 6
  17. 2022Learning Stochastic Graph Neural Networks with Constrained Variancecited by 5
  18. 2022Privacy-Preserving Decentralized Inference with Graph Neural Networks in Wireless Networkscited by 5
  19. 2022Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encodingcited by 5
  20. 2022Space-Time Graph Neural Networks with Stochastic Graph Perturbationscited by 5
  21. 2023Semi-decentralized Inference in Heterogeneous Graph Neural Networks for Traffic Demand Forecasting: An Edge-Computing Approachcited by 5
  22. 2023Graph learning in robotics: a surveycited by 5
  23. 2024Co-Optimizing Reconfigurable Environments and Policies for Decentralized Multi-Agent Navigationcited by 5
  24. 2024CoDreamer: Communication-Based Decentralised World Modelscited by 5
  25. 2021The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Expertscited by 4
  26. 2021The Power of Communication in a Distributed Multi-Agent Systemcited by 4
  27. 2022Learning Stable Graph Neural Networks via Spectral Regularizationcited by 4
  28. 2021Learning Connectivity for Data Distribution in Robot Teamscited by 3
  29. 2021Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Searchcited by 3
  30. 2023Graph Neural Networks for Decentralized Multi-Agent Perimeter Defensecited by 3
  31. 2024LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Controlcited by 3
  32. 2022Towards Understanding Graph Neural Networks: An Algorithm Unrolling Perspectivecited by 2
  33. 2022Learning Decentralized Strategies for a Perimeter Defense Game with Graph Neural Networkscited by 2
  34. 2022Stable and Transferable Hyper-Graph Neural Networkscited by 2
  35. 2023Graph Neural Networks over the Air for Decentralized Tasks in Wireless Networkscited by 2
  36. 2023Serving Graph Neural Networks With Distributed Fog Servers For Smart IoT Servicescited by 2
  37. 2023Learning Decentralized Flocking Controllers with Spatio-Temporal Graph Neural Networkcited by 2
  38. 2023Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph Reinforcement Learningcited by 2

50 most cited of 62 All 62 (JSON)