A Distributed Gaussian Process Model for Multi-Robot Mapping

2026-03-07

AI Summary

This work addresses the challenge of collaborative learning of a global environmental function in multi-robot systems operating under limited local observations and communication. To this end, the authors propose DistGP, a novel method that constructs a ring-structured sparse Gaussian process factor graph aligned with the system’s communication topology, thereby overcoming the limitations of conventional tree-based structures. DistGP enables asynchronous, distributed online learning via Gaussian belief propagation and supports dynamic communication topologies and continual learning. The approach achieves accuracy comparable to centralized batch models while significantly outperforming distributed neural network methods such as DiNNO in communication-sparse scenarios, demonstrating superior robustness and adaptability.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Intelligent Robots: Learning & Optimization for ROB
• Multiagent Systems: Multiagent Learning

Application Category

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

Abstract

We propose DistGP: a multi-robot learning method for collaborative learning of a global function using only local experience and computation. We utilise a sparse Gaussian process (GP) model with a factorisation that mirrors the multi-robot structure of the task, and admits distributed training via Gaussian belief propagation (GBP). Our loopy model outperforms Tree-Structured GPs \cite{bui2014tree} and can be trained online and in settings with dynamic connectivity. We show that such distributed, asynchronous training can reach the same performance as a centralised, batch-trained model, albeit with slower convergence. Last, we compare to DiNNO \cite{yu2022dinno}, a distributed neural network (NN) optimiser, and find DistGP achieves superior accuracy, is more robust to sparse communication and is better able to learn continually.

Problem

• multi-robot mapping
• distributed learning
• Gaussian process
• collaborative learning
• dynamic connectivity

Innovation

• Distributed Gaussian Process
• Multi-Robot Mapping
• Gaussian Belief Propagation
• Online Learning
• Sparse Communication