ROLGMLMar 7

A Distributed Gaussian Process Model for Multi-Robot Mapping

arXiv:2603.07351v1
Predicted impact top 50% in RO · last 90 daysOriginality Incremental advance
AI Analysis

This work addresses the problem of efficient and robust multi-robot mapping for robotics researchers and practitioners, offering an incremental improvement in distributed learning for this domain.

This paper introduces DistGP, a multi-robot learning method that enables collaborative learning of a global function using only local experience and computation. The method achieves performance comparable to a centralized, batch-trained model, outperforming Tree-Structured GPs and demonstrating superior accuracy and robustness compared to DiNNO, a distributed neural network optimizer.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes