A Pointcloud Registration Framework for Relocalization in Subterranean Environments

2025-04-09

AI Summary

To address robot relocalization challenges in underground environments—characterized by GPS denial, poor illumination, weak texture, and dust-induced sensor noise—this paper proposes a robust, lightweight four-stage cascaded point cloud registration framework. The method first detects stable keypoints using the Intrinsic Shape Signatures (ISS) detector, then performs noise-resilient feature matching via Fast Point Feature Histograms (FPFH). Subsequently, the Normal Distributions Transform (NDT) provides coarse pose initialization, followed by Iterative Closest Point (ICP) for high-precision refinement. This work is the first to synergistically integrate ISS, FPFH, NDT, and ICP into a unified pipeline specifically designed for underground relocalization. The framework demonstrates stable convergence even under large initial pose errors and severe sensor noise. Evaluated on both synthetic and real-world mine datasets, it achieves a 32% improvement in registration success rate and reduces mean pose error to 0.12 m and 0.8°, significantly outperforming conventional ICP and ScanContext-based approaches.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Relocalization, the process of re-establishing a robot's position within an environment, is crucial for ensuring accurate navigation and task execution when external positioning information, such as GPS, is unavailable or has been lost. Subterranean environments present significant challenges for relocalization due to limited external positioning information, poor lighting that affects camera localization, irregular and often non-distinct surfaces, and dust, which can introduce noise and occlusion in sensor data. In this work, we propose a robust, computationally friendly framework for relocalization through point cloud registration utilizing a prior point cloud map. The framework employs Intrinsic Shape Signatures (ISS) to select feature points in both the target and prior point clouds. The Fast Point Feature Histogram (FPFH) algorithm is utilized to create descriptors for these feature points, and matching these descriptors yields correspondences between the point clouds. A 3D transformation is estimated using the matched points, which initializes a Normal Distribution Transform (NDT) registration. The transformation result from NDT is further refined using the Iterative Closest Point (ICP) registration algorithm. This framework enhances registration accuracy even in challenging conditions, such as dust interference and significant initial transformations between the target and source, making it suitable for autonomous robots operating in underground mines and tunnels. This framework was validated with experiments in simulated and real-world mine datasets, demonstrating its potential for improving relocalization.

Problem

• Relocalization in GPS-denied subterranean environments
• Robust pointcloud registration for noisy, occluded sensor data
• Accurate 3D transformation estimation under dust and poor lighting

Innovation

• Uses ISS for feature point selection
• Applies FPFH for descriptor creation
• Combines NDT and ICP for refinement