BIEVR-LIO: Robust LiDAR-Inertial Odometry through Bump-Image-Enhanced Voxel Maps

2026-04-15

AI Summary

This work addresses the divergence of traditional LiDAR-inertial odometry (LIO) in geometrically sparse or challenging environments due to insufficient constraints. The authors propose a novel LIO framework that innovatively encodes high-resolution surface geometry into voxelized oriented height maps—termed “bump images”—which are directly leveraged for registration without relying on intermediate geometric primitives. Additionally, a map-guided adaptive point sampling strategy is introduced to prioritize geometrically rich regions, enhancing robustness while reducing computational overhead. Evaluated across diverse sensors, platforms, and extreme scenarios, the method consistently outperforms existing approaches, maintaining stability even when baseline systems fail, and enables high-precision elevation mapping for downstream applications.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Remote Sensing / Geospatial AI
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Reliable odometry is essential for mobile robots as they increasingly enter more challenging environments, which often contain little information to constrain point cloud registration, resulting in degraded LiDAR-Inertial Odometry (LIO) accuracy or even divergence. To address this, we present BIEVR-LIO, a novel approach designed specifically to exploit subtle variations in the available geometry for improved robustness. We propose a high-resolution map representation that stores surfaces as compact voxel-wise oriented height images. This representation can directly be used for registration without the calculation of intermediate geometric primitives while still supporting efficient updates. Since informative geometry is often sparsely distributed in the environment, we further propose a map-informed point sampling strategy to focus registration on geometrically informative regions, improving robustness in uninformative environments while reducing computational cost compared to global high-resolution sampling. Experiments across multiple sensors, platforms, and environments demonstrates state-of-the-art performance in well-constrained scenes and substantial improvements in challenging scenarios where baseline methods diverge. Additionally, we demonstrate that the fine-grained geometry captured by BIEVR-LIO can be used for downstream tasks such as elevation mapping for robot locomotion.

Problem

• LiDAR-Inertial Odometry
• robustness
• uninformative environments
• point cloud registration
• mobile robotics

Innovation

• LiDAR-Inertial Odometry
• voxel map
• height image
• map-informed sampling
• robust registration