HUMANOID ROBOTS · FOURIER

Fourier GR-3

A 165 cm-tall, interaction-focused third-generation humanoid robot.

Fourier GR-3 is a third-generation humanoid robot distinguished by its interaction and perception capabilities. Combining walking, facial and voice recognition, and tactile perception, it is designed for use in social and well-being support applications.

Height: 165 cm · 71 kg
Walking Speed: 5,5 km/s · Walking on terrain
Operating Time: 3 hours · On a single charge

Request a quote / demo

1 / 4

SELECT BY TASK

Fourier GR-3
what is it evaluated for?

The Fourier GR-3 series is a third-generation humanoid robot focused on perception and multimodal emotion processing in human-robot interaction. Designed to be 165 cm tall and weigh 71 kg, GR-3 offers rich perception capabilities with components such as an OAK camera with stereo depth, multichannel audio perception, pressure sensors distributed across the body, and 55 degrees of freedom for movement. A facial-expression display and real-time gaze tracking combine with tactile feedback to enable natural behavior in social interaction and well-being applications. The series is available in three configurations: GR-3 with full interaction hardware, GR-3C with a simplified exterior, and GR-3C Ultra with optional LiDAR.

Well-being and companionship servicesSocial interaction and promotional demonstrations

PRODUCT-SPECIFIC

Key features.

Features compiled from source product information; evaluate according to the model and configuration.

Advanced Visual Perception

An OAK camera with stereo depth enables facial recognition and dynamic tracking, keeping the user within the robot's expressive field for natural interaction.

Multichannel Audio Perception

A four-microphone array enables omnidirectional voice activation, echo suppression, and sound-source localization; the robot turns toward the speaker and makes eye contact in real time.

Distributed Tactile Perception

A total of 31 pressure sensors—16 in the head and 15 in the body—detect touch in real time and respond with micro-expressions.

Integrated Emotion Processing

A real-time emotion-processing engine combines visual, auditory, and tactile channels to coordinate multimodal interaction and produce natural responses.

Extensive Movement Capabilities

With a total of 55 degrees of freedom, simultaneous control of head, waist, arm, and leg movements, and a 3 kg single-arm payload capacity provide flexibility suited to interactive tasks.

Lightweight and Durable Design

The supporting structure is made of aluminum alloy and engineering plastic; the outer surface uses Alcantara and foam padding to provide both durability and a pleasant tactile experience for the user.

Balance and Motion Control

Data from the 6-axis IMU and foot contact sensors is used to dynamically adjust the leg joints and optimize walking behavior on flat and uneven terrain.

Flexible Configuration Options

The product line accommodates different usage requirements with three configurations: the fully interactive GR-3, the streamlined, easy-to-maintain GR-3C, and the GR-3C Ultra with optional LiDAR.

SOURCED PRODUCT DATA

Technical features.

Values are taken from the source product page. Confirm the package, software, and accessory contents against the manufacturer's current documentation before ordering.

Fourier GR-3 technical specifications
Feature	Value
Dimensions (standing)	165 cm tall
Weight	71 kg
Arm reach	1395 mm arm span; up to 1759 mm with their own agile hand (12-degree-of-freedom hand version)
Arm payload	3
Maximum speed	5.5
Climbing angle	15 degrees (maximum walking slope)
Joint torque	440 N·m (maximum joint peak torque)
Joint range of motion	Neck pitch -30°~8,5°; neck yaw ±80°; shoulder pitch ±170°; shoulder roll -15°~110°; shoulder yaw ±105°; elbow pitch -130°~5°; wrist yaw ±105°; wrist pitch -50°~75°; wrist roll -60°~70°; waist pitch -12°~30°; waist roll ±10°; waist yaw ±150°; hip pitch ±150°; hip roll -10°~90°; hip yaw -40°~90°; knee pitch 0°~135°; ankle pitch ±45°; ankle roll ±25° (left-side joint values)
Battery capacity	702 Wh + 234 Wh
Battery	Lithium-ion, 702 Wh + 234 Wh; total weight 3,8 kg + 1,3 kg; rated voltage 46,8 V, charging limit voltage 54,6 V; cycle life 500 or more (80 percent DOD); supports hot swapping; approximately 1,5 hours to fully charge once
Operating time	3 hours
Charging time	Approximately 1,5 hours (single charge)
Charger	Adapter input 90 V AC ~ 260 V AC, 50 Hz / 60 Hz; adapter output 54,6 V, 12 A MAX
Operating power	Rated power approximately 936 W
Operating voltage	Rated voltage 46,8 V; adapter input 90-260 V AC, 50/60 Hz; adapter output 54,6 V, maximum 12 A
Modes of movement	Full-size bipedal humanoid; terrain walking and balance recovery
Degrees of freedom	55 DoF
Neck degrees of freedom	2 DoF
End effector	Standard dexterous hand with 6 degrees of freedom; optional dexterous hand with 12 degrees of freedom (arm span up to 1.759 mm with dexterous hand)
Torque density	3 kg payload with one arm; head 2, waist 3, arms 7 and legs 6 degrees of freedom, standard dexterous hand 6 degrees of freedom, optional dexterous hand 12 degrees of freedom
Material	Alcantara surface, foam padding, supporting structure made of aluminum alloy and engineering plastic; skin-like touch reminiscent of a sports car interior
Joint configuration	Total of 55 degrees of freedom; head 2, waist 3, arms 7, legs 6, standard dexterous hand 6, optional dexterous hand 12
Load capacity	3 kg carrying capacity with one arm
Battery system	3 hours of operating time
Structure and materials	Alcantara surface, foam padding, supporting structure made of aluminum alloy and engineering plastic
Touch sensing	31 pressure sensors: 16 in the head, 15 in the body; real-time touch detection; a touch sensor can be added to the hand with the 12-degree-of-freedom dexterous hand
Sensors	Stereo depth OAK camera module; 6-axis IMU (acceleration and angular velocity); 31 pressure sensors distributed throughout the body (16 in the head, 15 in the body); optional Robosense Airy LiDAR on the GR-3C Ultra version
Connectivity	Wired Ethernet and Wi-Fi 6; Type-C, USB 3.0 and RJ45 input/output
Wireless	Wi-Fi 6; wired Ethernet connection
Interaction	Four-microphone array: omnidirectional voice wake-up, echo suppression and precise sound-source positioning; 15 W speaker (5 W in the Ultra version); LED screen displaying facial expressions; the robot turns to face the speaker while maintaining eye contact
Joint encoder	Dual encoders: supports absolute encoders
Processor	AMD Ryzen 7 8845HS, 8 cores, 16 threads; D70 development board, AMD Radeon 780M graphics, 16 MB L3 cache, 32 GB memory, 1 TB storage
Operating system	Ubuntu 22.04
Software features	The Multimodal Interaction System combines vision, sound, and touch in a single real-time emotion-processing engine; voice interaction powered by a large language model; animated micro-expressions respond to touch with social cues; real-time remote control is optional
Operating temperature	0 to 45 degrees Celsius; operating humidity 20 to 80 percent, non-condensing

SEE THE PRODUCT IN ACTION

Fourier GR-3 introduction.

The introduction video linked from the source product page opens when you press the play button.

PRODUCT INFORMATION SOURCES

Sources and documentation.

This catalog is intended to help explore product information. No commitments are made on behalf of Robotik Çözümler regarding stock, authorized dealers, pricing, warranty, or after-sales service terms.

FREQUENTLY ASKED QUESTIONS

Frequently asked questions.

What are the key technical specifications of Fourier GR-3?

GR-3 comes equipped with a height of 165 cm, a weight of 71 kg, 55 degrees of freedom, a single-arm payload capacity of 3 kg, a walking speed of 5,5 km/s, and an operating time of approximately 3 hours. Its perception layer includes an OAK camera with stereo depth, a 6-axis IMU, and 31 pressure sensors distributed across the body.

What are the differences between GR-3, GR-3C, and GR-3C Ultra?

The mechanical base remains the same; GR-3 comes with full interaction hardware, while GR-3C offers a simplified shell by removing the interaction layers. GR-3C Ultra differs by adding optional LiDAR and some speaker enhancements. All three have an OAK camera, IMU, and facial expression display.

What interaction sensors does GR-3 have?

The model includes a total of 31 pressure sensors—16 in the head and 15 in the body—a four-microphone array, and an OAK camera with stereo depth; these sensors are combined by an engine that processes visual, auditory, and tactile data in real time.

Is GR-3 suitable for physical care and carrying tasks?

GR-3 is a platform focused on well-being and social interaction; with a single-arm capacity of 3 kg, heavy lifting, transfers, and intensive physical care tasks are outside its scope.

IN THE SAME CATEGORY