Decentralized Scalar Field Mapping using Gaussian Process

TL;DR

This paper introduces a decentralized Gaussian process framework for multi-agent scalar-field mapping, leveraging inter-agent posterior discrepancies to enhance predictive accuracy through a novel data-sharing protocol.

Contribution

It proposes a decentralized intersection data-sharing protocol that improves consistency and performance of local Gaussian process models without centralized coordination.

Findings

The protocol enhances predictive accuracy over shared regions.

Agents maintain local models with minimal communication.

The approach supports scalable, decentralized scalar-field mapping.

Abstract

Decentralized Gaussian process (GP) methods offer a scalable framework for multi-agent scalar-field estimation by replacing a centralized global model with multiple local models maintained by individual agents. A team of agents operates through overlapping domains; neighboring agents generally produce inconsistent distributions over shared regions. This paper investigates whether these inter-agent posterior discrepancies can be systematically exploited to improve team-level predictive performance and answers this question positively through a novel decentralized intersection data-sharing and assimilation protocol. Specifically, each agent constructs neighbor-specific packets from its local GP together with the geometry of the overlap between subdomains and selectively assimilates information received from neighboring agents to improve consistency of its posterior over the shared regions. The proposed architecture preserves locality in both computation and communication, supports decentralized neighbor-to-neighbor data assimilation, and allows local GP models to evolve cooperatively across the network without requiring the exchange full packet exchange or centralized inference.