A Distributed Multi-UGV Exploration Framework With Loop-Aware Planning and Descriptor-Aided Localization in Resource-Limited Environments

2026-06-09

AI Summary

This work addresses the challenge of multi-UGV cooperative exploration in unknown, GPS-denied, and communication-constrained environments, where localization drift often leads to map inconsistency and redundant coverage. The authors propose a fully distributed exploration framework that integrates a lightweight deep learning-based LiDAR global descriptor—enabling robust place recognition under large viewpoint changes—an uncertainty-aware loop closure filtering mechanism, and a loop-closure-aware hierarchical planning strategy. By treating high-value loop closures as anchors for task allocation and trajectory optimization, the system significantly enhances mapping consistency while maintaining low communication overhead. Experimental results demonstrate an 89.9% recall at top-1 for loop closure detection, a substantial reduction in absolute trajectory error, and 15% and 14% improvements in exploration time and travel distance, respectively, over the mTSP baseline.

Abstract

Robust and efficient cooperative exploration with multiple unmanned ground vehicles (UGVs) in unknown, GPSdenied, and bandwidth-limited environments without prior maps remains challenging, as localization drift degrades map consistency and induces redundant coverage. This paper presents a fully distributed exploration framework that couples descriptoraided inter-UGV loop closure with loop-aware hierarchical planning while enabling autonomous localization and exploration. We develop a lightweight LiDAR global descriptor with range-image prealignment to enable robust cross-UGV place recognition under large yaw and lateral variations, and use verified loop closures to maintain globally consistent trajectories and a sparse topological representation. We further introduce an uncertainty-aware crossUGV loop-closure selection module that scores candidate loop closures under pose uncertainty and retains high-utility loop closures as planning anchors for global task allocation and local route refinement. Simulations and real-UGV experiments show that the loop-closure module achieves AR@1/AR@1% of 89.9%/95.5%, distributed optimization reduces absolute trajectory error, the system substantially reduces two-way communication volume, and the overall framework reduces exploration time and travel distance by 15% and 14%, respectively, compared with an mTSP baseline.

Problem

• multi-UGV exploration
• localization drift
• GPS-denied environments
• map consistency
• bandwidth-limited

Innovation

• loop-aware planning
• descriptor-aided localization
• distributed multi-UGV exploration
• LiDAR global descriptor
• uncertainty-aware loop closure