Galaxea R1 Pro

Source-backed capabilities

• Operating environments: LingBot-VLA GM-100 tabletop evaluation, LingBot-VLA GM-100 demonstration station
• Control modes: Autonomous, Teleoperated
• Multimodal data collection

  Research demonstration - Record synchronized multi-view robot trajectories and states during teleoperated tabletop demonstrations. - environment: LingBot-VLA GM-100 demonstration station

  Source
• Pick and place

  Research demonstration - Pick up bowls and stack them in a tabletop research task. - environment: LingBot-VLA GM-100 tabletop evaluation

  Source

Exact-product configurations are shown without inferring supply, purchase, customer status, standard fit, deployment or partnership.

• NVIDIA Isaac Sim

  Digital Simulation - Tested With - Simulated - Galaxea R1 Pro has a digital robot asset in the robot_usds library for Isaac Sim and ROS 2 control. This records a simulation configuration.

  Source

• MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation

  2026-10-02 - Research Publication - MobiAgent combines dynamic skill planning and visual reflection with offline recycling of deployment trajectories. It evaluates four physical Astribot S1 tasks, separate simulated mobile-manipulation benchmarks, and an additional Unitree R1D household experiment.

  Source
• Contrastive Action-Image Pre-training for Visuomotor Control

  2026-06-15 - Research Publication - CAIP learns action-centred visual representations from 32,041 hours of egocentric human video and 88 hours of robot manipulation data. Physical evaluation uses a Dexmate Vega with two 22-DoF Sharpa Wave hands and reports more than 30% gains on folding, pouring and fine-grained manipulation tasks.

  Source
• LingBot-VLA: A Pragmatic VLA Foundation Model

  2026-01-26 - Research Publication - LingBot-VLA is a vision-language-action model and software release evaluated on the GM-100 benchmark with AgiBot G1, AgileX and Galaxea R1Pro robots.

  Source
• BEHAVIOR Challenge 2025 simulation benchmark and demonstrations

  2025-09-02 - Research Publication - The 2025 BEHAVIOR challenge releases a simulated household benchmark with Galaxea R1 Pro as its default embodiment and expert demonstrations collected through JoyLo.

  Source
• FiveAges robot_usds simulation asset library

  Research Publication - A shared library of robot USD assets for ROS 2 control and Isaac Sim development, with configurable robot and end-effector models.

  Source
• GalaxeaVLA: G0.5 vision-language-action model and robot workflows

  Research Publication - Galaxea's VLA software release provides model fine-tuning, simulation evaluation and real-robot deployment workflows, including R1 Pro configurations.

  Source
• GalaxeaDP: R1 diffusion-policy simulation workflows

  Research Publication - GalaxeaDP provides diffusion-policy training, generated-data conversion and simulation evaluation for Galaxea R1 robots. Its source includes R1 Pro and R1 Lite task configurations and distinguishes current simulation workflows from planned real-world support.

  Source
• Galaxea Manipulation Simulator

  Research Publication - Galaxea Manipulation Simulator provides reusable manipulation benchmarks, expert demonstration generation and baseline training/evaluation workflows for R1, R1 Pro and R1 Lite. It includes more than 30 environments across 17 tasks and exact robot/controller registrations.

  Source
• Galaxea Diffusion Policy implementation

  Research Publication - GalaxeaDP implements diffusion-policy training, open-loop evaluation and simulated deployment with GalaxeaManipSim and LeRobot data formats. Named task configurations distinguish R1 Pro end-effector/joint policies and R1 Lite joint policies.

  Source

• Galaxea R1 Pro appears in LingBot-VLA’s real-world benchmark

  2026-01-27 - Research Publication - The model used 20,000 hours of real-world pretraining data from nine dual-arm robot configurations. The release provided depth-free and depth-distilled model variants, with evaluation separating complete task success from partial success.

  Source

Comparable Systems

• W1 Pro

  DexForce - Semi Humanoid

• K1

  VLAI Robotics - Semi Humanoid

• AGIBOT G1

  AgiBot - Semi Humanoid

• AlphaBot 2

  AI2 Robotics - Semi Humanoid

• RealBot-01

  RealMan Intelligent Technology (Beijing) Co., Ltd. - Semi Humanoid

• RealBot-L2

  RealMan Intelligent Technology (Beijing) Co., Ltd. - Semi Humanoid

Related Systems

• ψ-SynRobot

  PsiBot - Semi Humanoid