Distributed multi-robot active gathering for non-uniform agriculture and forestry information

TL;DR

This paper introduces a new method for multi-robot systems to efficiently gather information in unevenly clustered agricultural and forestry environments.

Contribution

The novel distributed Bernoulli Thompson Sampling algorithm improves global coordination and task allocation in multi-robot systems.

Findings

The proposed algorithm outperforms baselines in search speed and coverage in clustered target scenarios.

Combining Thompson Sampling with Lloyd’s algorithm and goal swapping enhances task allocation efficiency.

Abstract

Active information gathering is a fundamental task in multi-robot systems in agriculture, with applications in precision planting and sowing, field management and inspection, intelligent weeding and pest control, etc. Traditional distributed strategies often struggle to adapt to environments where information of interest are unevenly clustered, leading to slow detection and inefficient coverage. In this paper, we reformulate the information gathering problem as a multi-armed bandit (MAB) problem and propose a novel distributed Bernoulli Thompson Sampling algorithm. Our approach enables robots to make exploration-exploitation decisions while sharing probabilistic information across the team, thus improving global coordination without centralized control. We further combine the distributed Bernoulli Thompson Sampling policy with Lloyd’s algorithm for dynamic target tracking and introduce a goal swapping strategy to improve task allocation efficiency. Extensive simulations demonstrate that our method significantly outperforms baseline approaches in terms of search speed and target coverage, particularly in scenarios with clustered target distributions.

Figures