Unitree G1
Bipedal humanoid robot by Unitree Robotics, designed as a compact research, development, and developer platform.
Applications
- Research
- Home Assistance
Motion planning · Control & Planning
Nav2 Humble·Open Source Robotics Foundation
SLAM / Navigation Services is an umbrella category covering open-source localization and navigation services used in ROS 2 and related stacks. It groups components such as slam_toolbox (2D laser SLAM, by Steve Macenski), Cartographer (2D/3D laser SLAM by Google), RTAB-Map (visual+LiDAR SLAM by IntRoLab), ORB-SLAM3 (visual SLAM by UZ-CIESS), and the complete Nav2 navigation stack.
A typical pipeline looks as follows: SLAM publishes an occupancy map or octomap → AMCL/EKF localizes → global planner (Nav2 Planner Server) computes a path → local planner (DWB, MPPI) generates control → the controller publishes cmd_vel to the mobile base. Everything is wired through ROS 2 topics and actions, with behavior trees managing high-level logic.
This entry serves as a reference node: when a robot or framework declares support for 'SLAM / Navigation', this document links the concrete implementations. It is commonly used in the `dependsOnSoftware` section of humanoid and AMR profiles.
A Control Stack is the set of software components responsible for control logic, motion planning, command execution, and coordination of a robot's actuators. It receives high-level goals or waypoints (from planning or AI layers) and translates them into low-level actuator commands, closed-loop feedback control, and safety checks. Common implementations include MoveIt (arm manipulation), Nav2 (mobile navigation), and custom whole-body control stacks for humanoids.
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.
All ROS 2 AMRs (iRobot Create 3, Husky, Jackal), cobot mobile platforms (TIAGo, Pepper), humanoids with mobile bases (PAL ARI), industrial AGVs.
slam_toolbox: 1.7k★, Cartographer: 7.3k★, RTAB-Map: 2.6k★, Nav2: 2.9k★ — over 14k GitHub stars combined.
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.
2D occupancy maps take 1-10 MB; 3D octomap 50-500 MB.
License family: Permissive
License family: Permissive
Full LTS integration, MPPI controller, behavior trees v4.
Multi-map atlas, visual-inertial SLAM (UZ-CIESS).
First 2D SLAM release by Steve Macenski (ROS 1).
Open-source 2D/3D LiDAR SLAM by Google.
