TixiaoShan/LIO-SAM
LIO SAM
LIO-SAM is a lidar inertial SLAM framework and tightly-coupled sensor fusion pipeline. It functions as a factor graph optimization engine that combines lidar scans and inertial measurement unit data to build 3D point cloud maps and estimate robot trajectories.
The system integrates global position factors to align local coordinates with real-world data. It employs loop closure detection to identify previously visited locations, creating constraints in the optimization graph to correct accumulated global drift.
The framework covers lidar inertial odometry, point cloud processing, and trajectory optimization. It utilizes sliding-window smoothing for real-time odometry while performing background map optimization and inertial-based point deskewing to correct motion distortion.
The toolset includes utilities to export generated 3D point cloud maps into standard PCD file formats for offline analysis.
Features
- Tightly-Coupled LiDAR-Inertial Fusion - Fuses raw lidar and IMU data into a single tightly-coupled state estimator for high-precision trajectory tracking.
- Loop Closure Detection - Identifies previously visited locations to create constraints in the optimization graph and correct global drift.
- Sliding-Window Smoothing - Maintains a sliding window of recent states for real-time odometry while optimizing the full map in the background.
- Multi-Modal SLAM Implementations - Implements a multi-modal SLAM system integrating lidar and inertial sensors to build 3D spatial maps.
- Pose Graph Optimizations - Implements pose graph optimization to minimize sensor drift within the SLAM pipeline.
- LiDAR-Inertial Odometry Frameworks - Provides a comprehensive framework for lidar-inertial odometry to estimate robot pose and map environments in real time.
- Robot Localization and Mapping - Refines robot localization and mapping by using loop closure and global coordinates to reduce trajectory drift.
- Motion Deskewing - Corrects motion distortion in lidar scans by interpolating high-frequency inertial data.
- Global Position Factors - Integrates GPS coordinates as factors in the optimization graph to align local coordinates with real-world data.
- Global-Aided Localization - Adds global position factors to the factor graph to align local coordinates with real-world data.
- Point Cloud Processing - Processes 3D point clouds by correcting motion distortion and preparing spatial maps for analysis.
- Point Cloud Processors - Provides a toolset for deskewing motion-distorted lidar scans and exporting spatial maps to PCD formats.
- Global Position Integration - Integrates global position factors into the factor graph to align local coordinates with real-world data.
- Sliding Window Optimizations - Maintains a fixed-size window of recent states for real-time odometry estimation.
- SLAM and Odometry - Tightly-coupled LIDAR-inertial odometry using smoothing and mapping.
- Simultaneous Localization and Mapping - Tightly coupled LiDAR-inertial odometry via smoothing.
- SLAM and Mapping - Real-time lidar-inertial odometry package for multi-beam sensors.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
