Towards Spatial Perception for Heterogeneous Robot Collaboration in Subterranean Mining Environments

2026-09-29

AI Summary

This study addresses the challenge that a single robot cannot simultaneously achieve long-distance traversal and high-precision ore sensing in abandoned mines by proposing a dual-robot collaborative framework comprising an Explorer and an Inspector. Methodologically, a zero-shot vision-language segmentation stack is constructed to generate scene graphs via semantic segmentation for planning close-range inspection viewpoints. Furthermore, geometric abstraction techniques—including cross-view bounding box merging, plane fitting, and polygon extraction—are integrated to transform raw observations into actionable inspection targets. The proposed system was validated through field deployments in both an underground testing facility and an active magnesite mine, demonstrating highly robust autonomous mineral exploration under real-world degraded conditions.

Abstract

The autonomous extraction of deep mineral deposits in abandoned underground mines is fundamentally a multi-agent integration problem. No single platform simultaneously offers the mobility to traverse kilometers of degraded drifts and the sensing payload required to characterize an ore body. This article presents the onboard perception pipeline that bridges two heterogeneous agents within the PERSEPHONE autonomous mining mission. Which consist of a lightweight Explorer robot that maps an unknown mine and generates a 3D scene graph of inspection targets, by running a zero-shot, vision-language semantic segmentation stack that detects mineral deposits directly from natural-language prompts. The map and the graph are then handed to a second Inspector robot, which carries an advanced sensing payload and uses them to plan close-range inspection viewpoints. We detail the complete pipeline, with emphasis on the geometric abstraction that turns raw detections into actionable inspection targets, spanning per-view bounding-box generation, cross-view box merging, plane fitting, and polygon extraction, and we report an extensive field validation in a subterranean test facility and in an active magnesite mine, covering both iron-vein and magnesite mineralization under realistic, perceptually degraded conditions.

Problem

• Heterogeneous robot collaboration
• Spatial perception
• Subterranean mining
• Multi-agent integration
• Autonomous mining

Innovation

• Heterogeneous robot collaboration
• Zero-shot vision-language segmentation
• 3D scene graph
• Geometric abstraction
• Subterranean perception