Dynamic Initialization for LiDAR-inertial SLAM

2025-04-02

AI Summary

Existing LiDAR-IMU SLAM systems rely on static initialization, hindering deployment in dynamic startup scenarios such as post-disaster search-and-rescue or bomb disposal. This paper proposes the first fully dynamic initialization method supporting arbitrary motion patterns. Our core innovation is an extended square-root information Kalman filter (ESIKF) framework that tightly couples LiDAR and gyroscope measurements to jointly model and compensate for both rotational and translational point-cloud distortions in real time. State convergence is accelerated via iterative alignment between LiDAR odometry and IMU measurements. We evaluate the method across multiple public and real-world datasets—spanning vehicular, handheld, and UAV platforms—and demonstrate initialization within <2 seconds, orientation error <0.5°, and position error <0.15 m. The source code and benchmark datasets are publicly released.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Search and Optimization: Learning to Search

Application Category

• 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
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

The accuracy of the initial state, including initial velocity, gravity direction, and IMU biases, is critical for the initialization of LiDAR-inertial SLAM systems. Inaccurate initial values can reduce initialization speed or lead to failure. When the system faces urgent tasks, robust and fast initialization is required while the robot is moving, such as during the swift assessment of rescue environments after natural disasters, bomb disposal, and restarting LiDAR-inertial SLAM in rescue missions. However, existing initialization methods usually require the platform to remain stationary, which is ineffective when the robot is in motion. To address this issue, this paper introduces a robust and fast dynamic initialization method for LiDAR-inertial systems (D-LI-Init). This method iteratively aligns LiDAR-based odometry with IMU measurements to achieve system initialization. To enhance the reliability of the LiDAR odometry module, the LiDAR and gyroscope are tightly integrated within the ESIKF framework. The gyroscope compensates for rotational distortion in the point cloud. Translational distortion compensation occurs during the iterative update phase, resulting in the output of LiDAR-gyroscope odometry. The proposed method can initialize the system no matter the robot is moving or stationary. Experiments on public datasets and real-world environments demonstrate that the D-LI-Init algorithm can effectively serve various platforms, including vehicles, handheld devices, and UAVs. D-LI-Init completes dynamic initialization regardless of specific motion patterns. To benefit the research community, we have open-sourced our code and test datasets on GitHub.

Problem

• Dynamic initialization for LiDAR-inertial SLAM during motion
• Robust initialization without requiring stationary platform conditions
• Fast and accurate initial state estimation for urgent tasks

Innovation

• Dynamic initialization for moving robots
• Tight LiDAR-gyroscope integration in ESIKF
• Iterative alignment of LiDAR and IMU