D$^2$-LIO: Enhanced Optimization for LiDAR-IMU Odometry Considering Directional Degeneracy

2025-08-19

AI Summary

To address unstable state estimation caused by LiDAR feature degradation in complex environments, this paper proposes a robust LiDAR-inertial odometry (LIO) optimization framework. Methodologically, it introduces three key innovations: (1) an adaptive outlier rejection threshold dynamically tuned based on sensor-to-feature distance and platform motion magnitude; (2) a novel weighting matrix that jointly incorporates IMU preintegration covariance and a degradation-aware metric to enhance pose estimation reliability under feature-poor conditions; and (3) a tightly coupled fusion scheme integrating scan-to-submap registration with degradation-aware optimization. Extensive experiments across indoor/outdoor sparse and feature-degraded scenarios demonstrate that the proposed method significantly outperforms state-of-the-art LIO systems, achieving consistent improvements in both localization accuracy and robustness.

Technology Category

Intelligent Robots: State EstimationSearch and Optimization: Learning to SearchComputer Vision: Learning & Optimization for CV

Application Category

Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deploymentsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

LiDAR-inertial odometry (LIO) plays a vital role in achieving accurate localization and mapping, especially in complex environments. However, the presence of LiDAR feature degeneracy poses a major challenge to reliable state estimation. To overcome this issue, we propose an enhanced LIO framework that integrates adaptive outlier-tolerant correspondence with a scan-to-submap registration strategy. The core contribution lies in an adaptive outlier removal threshold, which dynamically adjusts based on point-to-sensor distance and the motion amplitude of platform. This mechanism improves the robustness of feature matching in varying conditions. Moreover, we introduce a flexible scan-to-submap registration method that leverages IMU data to refine pose estimation, particularly in degenerate geometric configurations. To further enhance localization accuracy, we design a novel weighting matrix that fuses IMU preintegration covariance with a degeneration metric derived from the scan-to-submap process. Extensive experiments conducted in both indoor and outdoor environments-characterized by sparse or degenerate features-demonstrate that our method consistently outperforms state-of-the-art approaches in terms of both robustness and accuracy.

Problem

• Addresses LiDAR feature degeneracy in odometry
• Enhances robustness in degenerate geometric environments
• Improves localization accuracy with adaptive outlier removal

Innovation

• Adaptive outlier removal threshold
• Flexible scan-to-submap registration method
• Novel weighting matrix fusing covariance