PRBonn/kiss-slam

A LiDAR SLAM system that just works

What it solves

KISS-SLAM provides a simple, robust, and accurate solution for 3D LiDAR SLAM (Simultaneous Localization and Mapping), aiming to be a system that "just works" across various environments with enhanced generalization capabilities.

How it works

The system builds upon existing frameworks including KISS-ICP, MapClosures, and g2o to perform 3D mapping and localization. It allows users to configure parameters via a YAML file, with specific tuning suggestions provided for indoor applications (such as adjusting max range and voxel size).

Who it’s for

It is designed for robotics researchers and developers who need a reliable 3D LiDAR SLAM system that is easy to install and deploy without extensive manual tuning.

Highlights

  • Simple installation via pip.
  • Robust and accurate 3D LiDAR SLAM performance.
  • Enhanced generalization capabilities across different environments.
  • Configurable parameters for both indoor and outdoor use cases.

Related

  • Project
    ouguangjun/Leg-KILO

    A real-time LiDAR-based SLAM system designed for high-dynamic platforms like legged robots, featuring a two-stage ESKF frontend and factor graph backend for robust mapping.

  • Project
    APRIL-ZJU/Gaussian-LIC

    Gaussian-LIC2 is a photo-realistic SLAM system that uses LiDAR-Inertial-Camera fusion and Gaussian Splatting to perform real-time pose estimation and 3D mapping.

  • Project
    koide3/glim

    A versatile 3D mapping framework that uses factor graphs and GPU acceleration to provide accurate, sensor-agnostic range-based mapping and localization.

  • Project
    SteveMacenski/slam_toolbox

    A 2D SLAM library for ROS 2 that enables mobile robots to build and refine maps of dynamic environments using pose-graph optimization.

  • Project
    PeterFWS/Structure-PLP-SLAM

    A visual SLAM system that uses points, lines, and planes for efficient sparse mapping and localization across monocular, RGB-D, and stereo cameras.