KORTHOS / ECOSYSTEM / PRODUCT

GR-1

About

About GR-1

GR-1 is Fourier's 44-actuator humanoid robot for embodied-AI and motion-control development. The 1.65-metre platform uses dexterous hands, three-axis movement at the waist and head, RealSense depth sensing and an inertial measurement unit. Its motion and handling ratings include walking speed up to 5 kilometres per hour, a 3-kilogram single-hand payload and 230-newton-metre maximum joint torque.

An onboard Intel Core i7 computer runs Ubuntu 20.04 and ROS 2, giving developers a familiar environment for perception, locomotion and manipulation work. Within the GR-1 family, the standard GR-1 combines the 44-actuator body with dexterous hands and an exposed skeleton enclosure. GR-1L uses grippers and fewer actuators, while Pro variants use an enclosed exterior.

Capabilities

Source-backed capabilities

  • Operating environments: Physical GR-1 tabletop research bench
  • Control modes: Autonomous
  • Container-to-container transfer

    Research demonstration - 2025-03-27 - Transfer household objects between trays, plates, baskets, bowls and pans. - environment: Physical GR-1 tabletop research bench

    Source
  • Fill and close storage compartments

    Research demonstration - 2025-03-27 - Place an object in a wooden chest, cabinet or drawer, then close the compartment. - environment: Physical GR-1 tabletop research bench

    Source
  • Machinery-part packing

    Research demonstration - 2025-03-27 - Pick machinery parts and tools and put them in a yellow bin. - environment: Physical GR-1 tabletop research bench

    Source
  • Pour loose industrial components

    Research demonstration - 2025-03-27 - Grasp a mesh cup and pour its screws and bolts into a plastic bin. - environment: Physical GR-1 tabletop research bench

    Source
  • Cross-hand cylinder transfer

    Research demonstration - 2025-03-27 - Pick up a cylinder, pass it between hands and place it in a bin. - environment: Physical GR-1 tabletop research bench

    Source
  • Pretrained-policy shelf placement

    Research demonstration - 2025-03-27 - Use both hands to transfer an object across the body and place it on a shelf. - environment: Physical GR-1 tabletop research bench

    Source
  • Two-robot component transfer

    Research demonstration - 2025-03-27 - Hand a mesh cup containing a cylinder to another robot, then separate the cylinder and remaining contents into bins. - environment: Physical GR-1 tabletop research bench

    Source

Operations

  • Production Setup

    Described by Fourier as its first mass-produced humanoid - 2023-12-31 - Fourier records GR-1 as its first mass-produced humanoid. The statement is a company maturity description, not a unit-output or delivery count.

    Source

Supply

Supply / Components

  • GR-1

    Core I7 13700h Processor For Gr 1 Family - Compute & Control - Intel - Fourier GR-1 uses an Intel Core i7-13700H computer - source: support-old.fftai.com

    Source
  • GR-1

    Realsense Depth Camera For Gr 1 Series - Perception - RealSense - Fourier GR-1 uses a RealSense depth camera - source: support-old.fftai.com

    Source

Research

  • RLDX-1

    2026-05-07 - Research Publication - RLDX-1 is a multimodal robot foundation model for dexterous manipulation. Its GR1 fine-tuned checkpoint is evaluated on the simulated 24-task GR-1 Tabletop benchmark, with 58.7% average success; that checkpoint result does not establish physical GR-1 task performance.

    Source
  • UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling

    2026-04-21 - Research Publication - UniT learns shared visual-action tokens for human-to-humanoid policy transfer and action-conditioned world modeling. It evaluates RoboCasa GR1 simulation and physical IRON-R01-1.11 pick-and-place and bimanual pouring, using human demonstrations to improve transfer and generalization.

    Source
  • Modality-Augmented Fine-Tuning of Foundation Robot Policies for Cross-Embodiment Manipulation on GR1 and G1

    2025-12-01 - Research Publication - This simulation study augments GR00T policies with contact and depth signals across Fourier GR1 and Unitree G1 embodiments. It uses RoboSuite/RoboCasa rollouts and releases simulated G1 apple-to-bowl demonstrations with proprioception and physics-engine contact measurements.

    Source
  • NVIDIA publishes Isaac GR00T N1 open foundation model for humanoid robots

    2025-03-17 - Research Publication - GR00T N1 combines a vision-language model with a diffusion action module and learns from real-robot, human-video and synthetic trajectories. NVIDIA evaluates it in simulation and on physical Fourier GR-1 tabletop manipulation, with separate pretraining and task-adaptation experiments.

    Source

Timeline

  • NVIDIA GR00T N1 study evaluates physical Fourier GR-1 manipulation

    2025-03-18 - Research Publication - The physical evaluation covered object placement, articulated compartments, industrial-part manipulation and coordination between robots. The fully post-trained model averaged 76.8 percent policy success across the real-world task groups, versus 46.4 percent for the full-data diffusion-policy baseline. The study separately evaluated simulation benchmarks; its stated scope remained short-horizon tabletop manipulation.

    Source
  • Fourier GR-1 receives Design Intelligence Award grand prize

    2024-12-06 - Award - The award recognized the combination of bionic design and robotics engineering in the humanoid platform. The competition received more than 8,000 entries from 47 countries and regions, with 39 finalists.

    Source
  • Fourier prepares production version of GR-1 humanoid

    2023-12-29 - Product Launch - The configuration included depth cameras in the head and torso and eleven-degree-of-freedom hands with vision-guided grasp planning. The platform supported centralized fleet assignments and a teleoperation mode using an augmented-reality headset and 5G connectivity. Research, education, logistics, reception and household assistance were proposed markets for the platform.

    Source

Context

Comparable Systems