mlsanityData to 14 Oct 2026

Graph Neural Networks for Decentralized Multi-Robot Path Planning

arXiv 1912.06095 ↗First posted 12 Dec 2019cs.RO cs.AI cs.LGcited by 86

Not on the map. Why?

Abstract (arXiv)

Effective communication is key to successful, decentralized, multi-robot path planning. Yet, it is far from obvious what information is crucial to the task at hand, and how and when it must be shared among robots. To side-step these issues and move beyond hand-crafted heuristics, we propose a combined model that automatically synthesizes local communication and decision-making policies for robots navigating in constrained workspaces. Our architecture is composed of a convolutional neural network (CNN) that extracts adequate features from local observations, and a graph neural network (GNN) that communicates these features among robots. We train the model to imitate an expert algorithm, and use the resulting model online in decentralized planning involving only local communication and local observations. We evaluate our method in simulations {by navigating teams of robots to their destinations in 2D} cluttered workspaces. We measure the success rates and sum of costs over the planned paths. The results show a performance close to that of our expert algorithm, demonstrating the validity of our approach. In particular, we show our model's capability to generalize to previously unseen cases (involving larger environments and larger robot teams).

Key facts. Cited by 86 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 14; 2022: 18; 2023: 18; 2024: 14; 2025: 15; 2026: 6.

86 papers.

Sort:

By area:

  1. 2023On the Expressive Power of Geometric Graph Neural Networkscited by 90
  2. 2022VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learningcited by 68
  3. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  4. 2025Multi-Agent Coordination across Diverse Applications: A Surveycited by 37
  5. 2022Multi-Robot Collaborative Perception with Graph Neural Networkscited by 35
  6. 2021Learning Selective Communication for Multi-Agent Path Findingcited by 32
  7. 2022Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workerscited by 30
  8. 2021Learning by Transference: Training Graph Neural Networks on Growing Graphscited by 22
  9. 2021Decentralized Inference with Graph Neural Networks in Wireless Communication Systemscited by 18
  10. 2022Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networkscited by 17
  11. 2021Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selectioncited by 14
  12. 2023System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learningcited by 14
38 more
  1. 2024Improving Learnt Local MAPF Policies with Heuristic Searchcited by 14
  2. 2020Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learningcited by 12
  3. 2021Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systemscited by 12
  4. 2021Training Stable Graph Neural Networks Through Constrained Learningcited by 12
  5. 2022Graph Neural Networks for Multi-Robot Active Information Acquisitioncited by 12
  6. 2023Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfindingcited by 12
  7. 2021A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policiescited by 11
  8. 2023Online Control Barrier Functions for Decentralized Multi-Agent Navigationcited by 11
  9. 2021Space-Time Graph Neural Networkscited by 10
  10. 2024Work Smarter Not Harder: Simple Imitation Learning with CS-PIBT Outperforms Large Scale Imitation Learning for MAPFcited by 10
  11. 2021ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecturecited by 9
  12. 2023Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offscited by 9
  13. 2023Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunitiescited by 9
  14. 2022Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigationcited by 8
  15. 2024DGDNN: Decoupled Graph Diffusion Neural Network for Stock Movement Predictioncited by 8
  16. 2022CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous Spacescited by 7
  17. 2022Graph-Based Multi-Robot Path Finding and Planningcited by 7
  18. 2022Decentralized Channel Management in WLANs with Graph Neural Networkscited by 7
  19. 2022Environment Optimization for Multi-Agent Navigationcited by 6
  20. 2023Constrained Environment Optimization for Prioritized Multi-Agent Navigationcited by 6
  21. 2025RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Taskscited by 6
  22. 2025GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural Networkscited by 6
  23. 2022Privacy-Preserving Decentralized Inference with Graph Neural Networks in Wireless Networkscited by 5
  24. 2022Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encodingcited by 5
  25. 2023Semi-decentralized Inference in Heterogeneous Graph Neural Networks for Traffic Demand Forecasting: An Edge-Computing Approachcited by 5
  26. 2023Graph learning in robotics: a surveycited by 5
  27. 2024Co-Optimizing Reconfigurable Environments and Policies for Decentralized Multi-Agent Navigationcited by 5
  28. 2024CoDreamer: Communication-Based Decentralised World Modelscited by 5
  29. 2025Graph Attention-Guided Search for Dense Multi-Agent Pathfindingcited by 5
  30. 2021The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Expertscited by 4
  31. 2022Distributing Collaborative Multi-Robot Planning with Gaussian Belief Propagationcited by 4
  32. 2022Convolutional Filtering on Sampled Manifoldscited by 4
  33. 2023Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learningcited by 4
  34. 2024Commute-Time-Optimised Graphs for GNNscited by 4
  35. 2026Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfindingcited by 4
  36. 2021A Graph Neural Network to Model Disruption in Human-Aware Robot Navigationcited by 3
  37. 2021Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Searchcited by 3
  38. 2023Accelerating Multi-Agent Planning Using Graph Transformers with Bounded Suboptimalitycited by 3

50 most cited of 86 All 86 (JSON)