Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

A Distributed Gaussian Process Model for Multi-Robot Mapping

About

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.

Seth Nabarro, Mark van der Wilk, Andrew J. Davison• 2026

Related benchmarks

TaskDatasetResultRank
SST PredictionOISST Central Atlantic
MSE0.134
2
SST PredictionOISST North Indian Ocean
MSE0.16
2
SST PredictionOISST South Indian Ocean
MSE0.23
2
SST PredictionOISST West Pacific
MSE0.108
2
SST PredictionOISST East Pacific
MSE0.24
2
Showing 5 of 5 rows

Other info

Follow for update