superxslam/SuperOdom

Health v2 · maintenance only

Adoption not part of the score

1101 stars · 141 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

SuperOdometry is a lightweight C++/ROS library for LiDAR-only and LiDAR-inertial odometry and mapping, developed by CMU's AirLab. It fuses LiDAR and IMU pose estimates bidirectionally, supports Livox, Velodyne, and Ouster sensors, and offers degeneracy awareness, alignment risk prediction, and localization/mapping dual modes.

Use cases

• estimate robot pose from lidar and imu data
• lidar-inertial odometry for drones and legged robots
• build 3d maps from lidar scans
• localize a robot on a prior map
• run odometry without an imu using lidar only
• detect degeneracy in icp alignment
• support livox velodyne and ouster lidars

When to choose

• you need robust, accurate real-time odometry from LiDAR with optional IMU fusion
• you work with Livox, Velodyne, or Ouster sensors in ROS/ROS2
• you need degeneracy detection and uncertainty estimation for state estimation
• you want a research-proven system (Science Robotics) with active maintenance and community support

When to avoid

• you need visual or visual-inertial SLAM with camera support
• you need a plug-and-play solution without ROS or C++ build tooling
• your project requires a permissive license (GPL-3.0)
• you only need simple GPS-based localization without LiDAR

Facets

library · maturity active

robotics computer-vision simulation robotics autonomous-vehicles computer-vision cpp lidar-odometry imu-fusion slam state-estimation mapping localization ros2 livox velodyne ouster degeneracy-detection icp sensor-fusion algorithms linux ros docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="superxslam/SuperOdom")