Source and import record
Imported from the Unibot owner catalog. This records source provenance, not independent verification.
Imported 2026-11-11
Products
Components
6 listed
Unitree Battery R1
battery
Unitree Battery R1 is an accessory described as a battery for the Unitree R1 humanoid robot.
Unitree Charger R1
charger
Unitree Charger R1 is identified by name as a Unitree charging accessory.
Unitree Dex3-1
robotic hand
Unitree Dex3-1 is a three-finger robotic hand for grasp development and object-interaction research.
Unitree Dex5-1
robotic hand
Unitree Dex5-1 is a five-finger robotic hand for investigating grasping, finger control and object manipulation.
Unitree G1 Battery
battery
Unitree G1 Battery is an accessory battery for the Unitree G1 humanoid robot.
Unitree remote control-joystick
controller
Unitree remote control-joystick is a robot accessory.
Mentioned in news
Human Activity Data Collection System Presented for Robot Training
Researchers introduced EgoExplorer, a wearable data collection system and a 100-hour dataset combining first-person video, body motion, finger movements and tactile information. A reconstruction pipeline estimates full-body movements from sparse sensors. Initial tests included a simulated Unitree G1, while physical robot performance and precise object interaction remain unverified.
Unitree introduced the G1-D wheeled humanoid robot for data collection and AI training
Unitree presented the G1-D, a manipulation-focused version of its G1 platform using a lifting column and optional wheeled mobility. It is aimed at research, education and AI training data collection. Supported tasks include sorting, assembly, dishwasher loading and clothes folding; deployment requires a task-specific safety assessment.
Humanoid robot mastered sprinting and roundhouse kicks with the help of AI
UC Berkeley and Stanford researchers developed BeyondMimic to expand humanoid motion skills using reinforcement learning and latent diffusion. Trained on about 2.5 hours of human movement data, the system demonstrated 30 representative motion clips on Unitree G1. A participant comparison favored its walking and running naturalness over the standard controller.
A four-legged robot has learned to jump through narrow passages
Researchers from the University of Hong Kong and Oxford developed a learning system that lets Unitree Aliengo jump through narrow openings. Dog motion data trains low-level movement, while a higher-level controller selects speed and turning. Real-hardware demonstrations show adaptation to gate placement, with broader onboard sensing and clutter handling planned.
Tiangong Ultra breaks Usain Bolt's 100m record
Tiangong Ultra recorded 9.39 seconds in a 100-meter preliminary heat at the World Humanoid Robot Games, ahead of Honor's Lightning at 9.47 seconds. Both times are below Usain Bolt's record, but differing procedures prevent direct comparison. The report also highlights uncontrolled stopping and incomplete technical disclosures.
NVIDIA platform powers more than 80% of humanoid robots
Chosun cites ABI Research estimating that more than 80% of humanoid robots use NVIDIA's platform. The report covers processors, models and simulation tools, while noting that these represent different kinds of dependency. A detailed breakdown is needed to distinguish operational reliance from use only during development.
About
Unitree Robotics is a Chinese manufacturer of quadruped and humanoid robots, robotic arms and dexterous hands. Founded in 2016, the company develops its own actuators, motion control and perception systems. Its quadruped ranges cover consumer, educational and industrial applications. Industrial models include platforms for inspection, with a wheeled-legged option for B2. The manufacturer states that some B2 functions require operator control or additional development. Humanoids provide platforms for studying movement and object manipulation. For programming projects, the edition matters: secondary development is listed for G1 EDU. Standalone robotic arms extend the portfolio, while open datasets support research into robot learning.