Large-Scale LiDAR-Inertial Dataset for Degradation-Robust High-Precision Mapping

2025-07-28

AI Summary

Existing LiDAR-inertial odometry (LIO) systems suffer from limited generalizability assessment in complex real-world scenarios, primarily due to the absence of large-scale, high-accuracy, multi-scene ground-truth benchmark datasets. To address this, we introduce the first large-scale LIO dataset covering four challenging degraded environments: urban canyons, tunnels, tree-lined streets, and underground parking garages. We propose a ground-truth generation method integrating SLAM-based optimization with RTK-GNSS anchoring, and employ oblique photogrammetry for cross-source trajectory verification. Data were collected using a backpack-mounted platform equipped with a 16-beam LiDAR, industrial-grade IMU, and RTK-GNSS receiver, yielding long-duration sequences across areas ranging from 60,000 to 750,000 m². The resulting trajectories achieve decimeter-level accuracy (≤0.3 m). This dataset significantly enhances reproducible evaluation of LIO systems in severely degraded environments and strengthens rigorous robustness validation of underlying algorithms.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

This paper introduces a large-scale, high-precision LiDAR-Inertial Odometry (LIO) dataset, aiming to address the insufficient validation of LIO systems in complex real-world scenarios in existing research. The dataset covers four diverse real-world environments spanning 60,000 to 750,000 square meters, collected using a custom backpack-mounted platform equipped with multi-beam LiDAR, an industrial-grade IMU, and RTK-GNSS modules. The dataset includes long trajectories, complex scenes, and high-precision ground truth, generated by fusing SLAM-based optimization with RTK-GNSS anchoring, and validated for trajectory accuracy through the integration of oblique photogrammetry and RTK-GNSS. This dataset provides a comprehensive benchmark for evaluating the generalization ability of LIO systems in practical high-precision mapping scenarios.

Problem

• Address insufficient validation of LIO systems in complex scenarios
• Provide diverse large-scale environments for LIO system evaluation
• Offer high-precision ground truth for robust mapping benchmarks

Innovation

• Large-scale LiDAR-Inertial dataset for robust mapping
• Custom backpack platform with multi-sensor fusion
• SLAM and RTK-GNSS fused for high-precision ground truth