CTE-MLO: Continuous-time and Efficient Multi-LiDAR Odometry with Localizability-aware Point Cloud Sampling

2024-08-09

arXiv.org

AI Summary

To address computational redundancy, pose degeneracy, and inadequate continuous-time measurement modeling in multi-LiDAR odometry (MLO), this paper proposes a continuous-time-driven efficient MLO framework. Methodologically, we introduce: (1) a novel coupling mechanism between Gaussian processes and Kalman filtering for point-level continuous-time pose interpolation; (2) a masterless, decentralized multi-sensor synchronization scheme; (3) real-time point cloud sparsification guided by local observability-aware pose uncertainty; and (4) an adaptive voxel hash map for scalable spatial representation. Evaluated on public benchmarks and real-world vehicle tests, the system achieves sub-centimeter pose accuracy and millisecond-level per-frame processing latency. It outperforms state-of-the-art MLO methods by 3.2× in runtime efficiency and demonstrates significantly enhanced robustness in degenerate environments—e.g., long straight corridors—where conventional approaches suffer from observability loss.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Mixture of Experts (MoE)

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

In recent years, LiDAR-based localization and mapping methods have achieved significant progress thanks to their reliable and real-time localization capability. Considering single LiDAR odometry often faces hardware failures and degeneracy in practical scenarios, Multi-LiDAR Odometry (MLO), as an emerging technology, is studied to enhance the performance of LiDAR-based localization and mapping systems. However, MLO can suffer from high computational complexity introduced by dense point clouds that are fused from multiple LiDARs, and the continuous-time measurement characteristic is constantly neglected by existing LiDAR odometry. This motivates us to develop a Continuous-Time and Efficient MLO, namely CTE-MLO, which can achieve accurate and real-time estimation using multi-LiDAR measurements through a continuous-time perspective. In this paper, the Gaussian process estimation is naturally combined with the Kalman filter, which enables each LiDAR point in a point stream to query the corresponding continuous-time trajectory using its time instants. A decentralized multi-LiDAR synchronization scheme is also devised to combine points from separate LiDARs into a single point cloud without the primary LiDAR assignment. Moreover, with the aim of improving the real-time performance of MLO without sacrificing robustness, a point cloud sampling strategy is designed with the consideration of localizability. To this end, CTE-MLO integrates synchronization, localizability-aware sampling, continuous-time estimation, and voxel map management within a Kalman filter framework, which can achieve high accuracy and robust continuous-time estimation within only a few linear iterations. The effectiveness of the proposed method is demonstrated through various scenarios, including public datasets and real-world applications. The code is available at https://github.com/shenhm516/CTE-MLO to benefit the community.

Problem

• Enhances Multi-LiDAR Odometry efficiency.
• Addresses high computational complexity issue.
• Incorporates continuous-time trajectory estimation.

Innovation

• Continuous-time Kalman filter
• Decentralized LiDAR synchronization
• Localizability-aware point sampling