hku-mars/LIV_handhold_2

LIV-Eye: A Low-Cost LiDAR-Inertial-Visual Fusion 3D Sensor for Robotics and Embodied AI.

What it solves

LIV-Eye is a low-cost, open-source perception kit designed to provide robots and embodied AI systems with high-quality 3D spatial awareness. It eliminates the high cost and complexity of building a custom LiDAR-Inertial-Visual (LIV) fusion sensor by providing a complete hardware design, bill of materials, and software drivers.

How it works

The system fuses data from a Livox Mid-360 LiDAR, a Hikvision camera, and an IMU to create a synchronized stream of visual and spatial data. It uses a hardware synchronizer to ensure millisecond-level timing between sensors. The software stack includes ROS drivers for the sensors and is compatible with the FAST-LIVO2 algorithm to generate colored point clouds and odometry results.

Who it’s for

This project is for robotics researchers and developers building embodied AI agents that require precise 3D perception, navigation, and mapping capabilities on a budget.

Highlights

  • Affordable Hardware: A complete kit with a target cost of approximately $700.
  • Open-Source Design: Includes Solidworks CAD files for 3D printing and assembly.
  • Full Workflow: Provides a complete pipeline from driver installation and hardware synchronization to intrinsic/extrinsic calibration.
  • Broad Compatibility: Supports ROS1, ROS2, and Docker, and is designed to be easily integrated into various robotic platforms.

Related

  • Project
    NVIDIA-AI-IOT/Lidar_AI_Solution

    A collection of highly optimized CUDA and TensorRT implementations for 3D Lidar perception, speeding up sparse convolutions and sensor fusion for self-driving systems.

  • Project
    rpng/MINS

    A multisensor-aided inertial navigation system that flexibly fuses IMU, wheel encoders, cameras, GNSS, and LiDAR for robust robot localization and online sensor calibration.

  • Project
    Livox-SDK/livox_ros_driver2

    A second-generation driver package that connects Livox LiDAR products to ROS and ROS2, enabling the publication of 3D point cloud data for robotics applications.

  • Project
    superxslam/SuperOdom

    A lightweight LiDAR-inertial odometry and mapping system that provides robust pose estimation and degeneracy detection for robots using ROS 2.

  • Project
    SJTU-ViSYS/Ground-Fusion

    A low-cost sensor-fusion SLAM system for ground vehicles that integrates RGB-D, IMU, wheel odometry, and GNSS to maintain robust localization during sensor failures.