Reliable and Efficient Multi-Agent Coordination via Graph Neural Network Variational Autoencoders

2025-03-04

AI Summary

In high-density multi-robot scenarios (e.g., automated warehouses), global coordination suffers from poor real-time performance, high deadlock risk, and exponential growth in computational complexity with scale. To address these challenges, this paper proposes an end-to-end collaborative scheduling method based on a Graph Neural Network Variational Autoencoder (GNN-VAE). It is the first to apply GNN-VAE to multi-agent path planning, integrating Mixed-Integer Linear Programming (MILP) to synthesize constraint-satisfying training data and employing a performance-driven solution filtering mechanism to ensure high-quality, temporally and spatially feasible solutions. The method enables few-shot training and strong generalization to large-scale deployments—achieving millisecond-level inference for 250 robots—while matching the solution quality of exact MILP solvers and substantially outperforming mainstream baselines. Crucially, it guarantees 100% constraint satisfaction.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Motion and Path Planning
• Multiagent Systems: Multiagent Planning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Multi-agent coordination is crucial for reliable multi-robot navigation in shared spaces such as automated warehouses. In regions of dense robot traffic, local coordination methods may fail to find a deadlock-free solution. In these scenarios, it is appropriate to let a central unit generate a global schedule that decides the passing order of robots. However, the runtime of such centralized coordination methods increases significantly with the problem scale. In this paper, we propose to leverage Graph Neural Network Variational Autoencoders (GNN-VAE) to solve the multi-agent coordination problem at scale faster than through centralized optimization. We formulate the coordination problem as a graph problem and collect ground truth data using a Mixed-Integer Linear Program (MILP) solver. During training, our learning framework encodes good quality solutions of the graph problem into a latent space. At inference time, solution samples are decoded from the sampled latent variables, and the lowest-cost sample is selected for coordination. Finally, the feasible proposal with the highest performance index is selected for the deployment. By construction, our GNN-VAE framework returns solutions that always respect the constraints of the considered coordination problem. Numerical results show that our approach trained on small-scale problems can achieve high-quality solutions even for large-scale problems with 250 robots, being much faster than other baselines. Project page: https://mengyuest.github.io/gnn-vae-coord

Problem

• Enhance multi-agent coordination in dense robot traffic
• Reduce runtime of centralized coordination methods
• Ensure deadlock-free solutions in large-scale scenarios

Innovation

• Graph Neural Network Variational Autoencoders for coordination
• Encodes solutions into latent space for scalability
• Decodes and selects lowest-cost feasible solutions