# Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning

arXiv: https://arxiv.org/abs/2011.13219 · HTML: https://mlsanity.com/paper/2011.13219/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2020.

## Built on by (most cited first, 30 of 43)

- [Multi-Robot Collaborative Perception with Graph Neural Networks](https://mlsanity.com/paper/2201.01760/) (2022)
- [Learning Selective Communication for Multi-Agent Path Finding](https://mlsanity.com/paper/2109.05413/) (2021)
- [Graph Neural Networks in IoT: A Survey](https://mlsanity.com/paper/2203.15935/) (2022)
- [Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking](https://mlsanity.com/paper/2104.04466/) (2021)
- [Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection](https://mlsanity.com/paper/2105.08601/) (2021)
- [Improving Learnt Local MAPF Policies with Heuristic Search](https://mlsanity.com/paper/2403.20300/) (2024)
- [Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning](https://mlsanity.com/paper/2012.14906/) (2020)
- [Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems](https://mlsanity.com/paper/2109.12343/) (2021)
- [Graph Neural Networks for Multi-Robot Active Information Acquisition](https://mlsanity.com/paper/2209.12091/) (2022)
- [A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies](https://mlsanity.com/paper/2111.01777/) (2021)
- [Work Smarter Not Harder: Simple Imitation Learning with CS-PIBT Outperforms Large Scale Imitation Learning for MAPF](https://mlsanity.com/paper/2409.14491/) (2024)
- [Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation](https://mlsanity.com/paper/2210.09378/) (2022)
- [CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous Spaces](https://mlsanity.com/paper/2201.09467/) (2022)
- [Graph-Based Multi-Robot Path Finding and Planning](https://mlsanity.com/paper/2206.11319/) (2022)
- [Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding](https://mlsanity.com/paper/2410.21415/) (2024)
- [RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks](https://mlsanity.com/paper/2503.02992/) (2025)
- [Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling](https://mlsanity.com/paper/2112.12740/) (2021)
- [Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding](https://mlsanity.com/paper/2210.08408/) (2022)
- [Space-Time Graph Neural Networks with Stochastic Graph Perturbations](https://mlsanity.com/paper/2210.16270/) (2022)
- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning](https://mlsanity.com/paper/2506.23793/) (2025)
- [The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts](https://mlsanity.com/paper/2107.12254/) (2021)
- [SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding](https://mlsanity.com/paper/2502.06440/) (2025)
- [Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding](https://mlsanity.com/paper/2602.06733/) (2026)
- [Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search](https://mlsanity.com/paper/2108.01036/) (2021)
- [Accelerating Multi-Agent Planning Using Graph Transformers with Bounded Suboptimality](https://mlsanity.com/paper/2301.08451/) (2023)
- [Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense](https://mlsanity.com/paper/2301.09689/) (2023)
- [Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence](https://mlsanity.com/paper/2407.15320/) (2024)
- [Learning Decentralized Strategies for a Perimeter Defense Game with Graph Neural Networks](https://mlsanity.com/paper/2211.01757/) (2022)
- [Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility](https://mlsanity.com/paper/2302.07337/) (2023)

## Abstract (arXiv)

The domains of transport and logistics are increasingly relying on autonomous mobile robots for the handling and distribution of passengers or resources. At large system scales, finding decentralized path planning and coordination solutions is key to efficient system performance. Recently, Graph Neural Networks (GNNs) have become popular due to their ability to learn communication policies in decentralized multi-agent systems. Yet, vanilla GNNs rely on simplistic message aggregation mechanisms that prevent agents from prioritizing important information. To tackle this challenge, in this paper, we extend our previous work that utilizes GNNs in multi-agent path planning by incorporating a novel mechanism to allow for message-dependent attention. Our Message-Aware Graph Attention neTwork (MAGAT) is based on a key-query-like mechanism that determines the relative importance of features in the messages received from various neighboring robots. We show that MAGAT is able to achieve a performance close to that of a coupled centralized expert algorithm. Further, ablation studies and comparisons to several benchmark models show that our attention mechanism is very effective across different robot densities and performs stably in different constraints in communication bandwidth. Experiments demonstrate that our model is able to generalize well in previously unseen problem instances, and that it achieves a 47% improvement over the benchmark success rate, even in very large-scale instances that are ×100 larger than the training instances.