Unitree G1
Bipedal humanoid robot by Unitree Robotics, designed as a compact research, development, and developer platform.
Applications
- Research
- Home Assistance
Perception · Perception & Vision Software
PCL 1.14·Open Perception Foundation
PCL (Point Cloud Library) is a fundamental open-source library of 3D point cloud processing algorithms, used in hundreds of robotic systems with LiDAR and RGB-D cameras. Initiated in 2010 at Willow Garage by Radu B. Rusu (PhD from TUM); since 2012 — after Willow Garage shut down — the project has been maintained by the Open Perception Foundation (a non-profit founded by Rusu). BSD-3-Clause license.
PCL implements 12+ main modules: filters (Voxel Grid, Statistical Outlier Removal, Passthrough), features (Normal Estimation, FPFH, SHOT, VFH), keypoints (Harris3D, ISS, SIFT 3D), registration (ICP, GICP, NDT, FPCS), segmentation (RANSAC plane fitting, Euclidean clustering, Region Growing), recognition (3D Object Recognition), surface (Marching Cubes, Greedy Projection, Moving Least Squares), and io (PCD/PLY/OBJ file readers/writers, real-time grabber for Kinect/RealSense/Velodyne/Hesai).
Integrations: VTK (visualization), Eigen (linear algebra), Boost, FLANN (fast nearest neighbor), Qhull (convex hulls), OpenNI (sensor grabbers). The ROS pcl_ros package offers full support for all ROS 1 and ROS 2 distributions — used in 90% of LiDAR projects. The book "Point Cloud Library Tutorial" is a standard read for master's degree programs in robotics.
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).
Every LiDAR / RGB-D SLAM project in ROS (Cartographer, LOAM, LIO-SAM, FAST-LIO use PCL), Boston Dynamics Spot (perception backend), Velodyne ROS driver, Hesai/Livox/Ouster official packages, Autoware (autonomous driving), NASA JPL Mars rovers (scene analysis).
github.com/PointCloudLibrary/pcl ~10k★, ~4.6k forks, > 200 contributors. pointclouds.org community ~15k registered users. > 5000 citations of Rusu's paper "3D is here: Point Cloud Library (PCL)" (ICRA 2011).
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.
Figure 03 is the third-generation humanoid robot from Figure AI, designed for Helix, home environments, and scalable mass production.
Large clouds (>10M points) require more memory — e.g. Velodyne HDL-64 generates 1.3M pps.
License family: Permissive
Full Ubuntu 22.04 and Apple Silicon support, fixes around Eigen 3.4.
C++17 requirement, ICP and NDT improvements, ROS 2 support.
C++14 requirement, refactoring of common and io modules.
OpenNI 2 support and new sensors (Kinect v2).
API stabilization; full integration with ROS Hydro.
First stable public release from Willow Garage.
