# A Spatially Informed Gaussian Process UCB Method for Decentralized Coverage Control

arXiv: https://arxiv.org/abs/2511.02398 · HTML: https://mlsanity.com/paper/2511.02398/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 30 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Multi-agents adaptive estimation and coverage control using Gaussian regression](https://mlsanity.com/paper/1407.5807/) (2014)
- [Multi-Robot Gaussian Process Estimation and Coverage: A Deterministic Sequencing Algorithm and Regret Analysis](https://mlsanity.com/paper/2101.04306/) (2021)
- [Fully Decentralized, Scalable Gaussian Processes for Multi-Agent Federated Learning](https://mlsanity.com/paper/2203.02865/) (2022)
- [Decentralized Learning With Limited Communications for Multi-robot Coverage of Unknown Spatial Fields](https://mlsanity.com/paper/2208.01800/) (2022)
- [Behavior Mixing with Minimum Global and Subgroup Connectivity Maintenance for Large-Scale Multi-Robot Systems](https://mlsanity.com/paper/1910.01693/) (2019)

## Abstract (arXiv)

We present a novel decentralized algorithm for coverage control in unknown spatial environments modeled by Gaussian Processes (GPs). To trade-off between exploration and exploitation, each agent autonomously determines its trajectory by minimizing a local cost function. Inspired by the GP-UCB (Upper Confidence Bound for GPs) acquisition function, the proposed cost combines the expected locational cost with a variance-based exploration term, guiding agents toward regions that are both high in predicted density and model uncertainty. Compared to previous work, our algorithm operates in a fully decentralized fashion, relying only on local observations and communication with neighboring agents. In particular, agents periodically update their inducing points using a greedy selection strategy, enabling scalable online GP updates. We demonstrate the effectiveness of our algorithm in simulation.