Unitree G1
Bipedal humanoid robot by Unitree Robotics, designed as a compact research, development, and developer platform.
Applications
- Research
- Home Assistance
RTAB-Map (Real-Time Appearance-Based Mapping) is a mature open-source SLAM library developed since 2013 at IntRoLab, Université de Sherbrooke, by Mathieu Labbé and Prof. François Michaud. A distinctive feature is the hybrid approach: graph-based SLAM with appearance-based loop closure via bag-of-words, operating simultaneously on RGB-D, stereo, monocular, and 2D/3D LiDAR. BSD-3-Clause license.
RTAB-Map offers a rare combination in open-source: full dense mapping (point clouds + meshes), efficient memory management (memory management — moving old maps between WM ↔ STM ↔ LTM), full 3D occupancy grid (OctoMap integration), direct support for RViz 2 and Foxglove. It runs in three modes: SLAM (mapping + localization), localization-only (on a previously built map), and mapping-only.
Sensor support: Intel RealSense D435i/D455/L515, Microsoft Kinect/Azure Kinect, Stereolabs ZED 2i, Hesai/Velodyne/Ouster/Livox LiDAR, XSens/Bosch IMU. Full graph optimizers: g2o, GTSAM, cvsba. The rtabmap_ros package is officially supported across all ROS 1 distributions (Kinetic→Noetic) and ROS 2 (Foxy→Jazzy). > 50 video tutorials hosted by Labbé himself.
A Perception Stack encompasses the software layers that process data from cameras, LiDARs, IMUs, microphones, and other sensors in order to recognise the surrounding environment, perform localisation, detect and track objects, and interpret the scene. It is typically the first processing stage in an autonomous robot's data pipeline, feeding its outputs to planning and control stacks.
An API Library is a software package that exposes programmatic interfaces for communicating with a device, service, or system. In robotics it typically forms a lightweight integration layer built on top of the manufacturer's official API or an open-source project, abstracting low-level protocol details and providing language-native bindings (Python, C++, Java, etc.).
A family of open-source robotic perception libraries: Visual SLAM (ORB-SLAM, RTAB-Map), computer vision (OpenCV), point cloud processing (PCL, Open3D), detection and segmentation (YOLO, Detectron2).
Clearpath Husky/Jackal/Warthog (official integration), Boston Dynamics Spot (community), TurtleBot 2/3/4 (recommended SLAM), NASA JPL Mars analog rovers, IntRoLab humanoids. > 1500 citations in scientific papers on mapping and mobile autonomy.
github.com/introlab/rtabmap ~3.0k★, github.com/introlab/rtabmap_ros ~1.0k★, > 50 official video tutorials on YouTube (Mathieu Labbé), 24/7 support at introlab.3it.usherbrooke.ca/mis/IntRoLab/RTAB-Map.
Bipedal humanoid robot by Unitree Robotics, designed as a compact research, development, and developer platform.
Unitree H1 is a full-size general-purpose humanoid robot (~180 cm, ~47 kg). Bipedal, 5 DOF per leg + 4 DOF per arm, 3.3 m/s walking speed, 360° perception via 3D LiDAR + depth camera, Unitree M107 PMSM joint motors with ~360 N·m peak knee torque. Standard compute: Intel Core i5/i7; optional NVIDIA Jetson Orin NX.
Boston Dynamics bipedal humanoid robot. The fully electric generation unveiled in 2024 succeeds the hydraulic Atlas that was retired after more than a decade of research.
Databases can grow to several GB for large maps. Ubuntu 22.04 + ROS 2 Humble/Jazzy recommended.
License family: Permissive
Update for ROS 2 Jazzy, improved visual loop closure (DBoW3).
Full ROS 2 Humble + Iron support, fluid memory.
ROS 2 Foxy support, OctoMap integration added.
3D LiDAR support (Velodyne, Ouster), ICP odometry.
Full support for ROS Indigo/Kinetic, RGB-D + Stereo + LiDAR.
First public release from Labbé's PhD thesis.
