Enhancing Multi-Robot Exploration Using Probabilistic Frontier Prioritization with Dirichlet Process Gaussian Mixtures

2026-04-03

AI Summary

This work addresses the efficiency bottleneck in multi-robot collaborative exploration of unknown environments under communication constraints. The authors propose a novel frontier prioritization method that integrates a probabilistic information gain model with a Dirichlet Process Gaussian Mixture Model (DP-GMM), introducing DP-GMM for the first time into uncertainty modeling for multi-robot exploration. This integration significantly enhances the algorithm’s adaptability and robustness across diverse environments and communication conditions. Experimental results demonstrate that the proposed approach improves average exploration efficiency by 10%–14% in various simulated scenarios and validates its effectiveness on a real-world dual-drone system.

Abstract

Multi-agent autonomous exploration is essential for applications such as environmental monitoring, search and rescue, and industrial-scale surveillance. However, effective coordination under communication constraints remains a significant challenge. Frontier exploration algorithms analyze the boundary between the known and unknown regions to determine the next-best view that maximizes exploratory gain. This article proposes an enhancement to existing frontier-based exploration algorithms by introducing a probabilistic approach to frontier prioritization. By leveraging Dirichlet process Gaussian mixture model (DP-GMM) and a probabilistic formulation of information gain, the method improves the quality of frontier prioritization. The proposed enhancement, integrated into two state-of-the-art multi-agent exploration algorithms, consistently improves performance across environments of varying clutter, communication constraints, and team sizes. Simulations showcase an average gain of $10\%$ and $14\%$ for the two algorithms across all combinations. Successful deployment in real-world experiments with a dual-drone system further corroborates these findings.

Problem

• multi-robot exploration
• communication constraints
• frontier prioritization
• autonomous coordination

Innovation

• Dirichlet Process Gaussian Mixture
• Probabilistic Frontier Prioritization
• Multi-Robot Exploration
• Information Gain
• Autonomous Coordination