Humanoid Database
Disclaimer: All content presented on this site, including robot profiles, images, and descriptions, is provided for editorial, educational and informational purposes only. Humanoid Press does not claim ownership of any third-party trademarks, designs, or intellectual property featured herein. All rights belong to their respective owners.
Reachy 2
|
type: |
type 1 |
|
{{variant.name}}:
|
{{opt.name}}
{{opt.name}}
|
Summary:
Reachy 2 is the world’s first fully open‑source humanoid robot designed specifically for embodied‑AI research, manipulation, and VR teleoperation.
It features dual 7‑DoF bio‑inspired arms, Orbita actuators, stereo 3D vision, and a complete ROS 2 Humble software stack.
Reachy 2 can be controlled via Python, VR teleoperation, or Unity‑based interfaces, making it one of the most accessible research humanoids available.
Editorial:
Reachy 2 is built for labs, universities, and AI teams that need a reproducible, modifiable, open platform.
Where most humanoids are closed and proprietary, Pollen Robotics takes the opposite approach:
- full open‑source hardware
- open‑source software
- open‑source simulation
- open‑source teleoperation
This makes Reachy 2 ideal for embodied‑AI experiments, robot learning, manipulation research, and human‑robot interaction.
Its VR teleoperation latency (~125 ms) and modular design give researchers a fast path from teleop → dataset → autonomous policy.
Specifications:
Dimensions & Build
- Height: 166 cm
- Weight: 50 kg
- Design Intent: Open‑source bimanual humanoid for AI research
- Construction:
- Dual 7‑DOF arms
- Orbita bio‑inspired actuators
- Modular, research‑friendly frame
- ROS 2‑native architecture
Mobility
- Locomotion: Wheeled mobile base (not bipedal)
- Capabilities:
- Indoor navigation
- Stable mobile manipulation
Degrees of Freedom
- Total DOF: 21
- Arms: 7 DOF each
- Head/Neck: Multi‑DOF for camera alignment
- Base: Differential wheeled mobility
Actuation
- Actuator Type: Orbita bio‑inspired actuators
- Capabilities:
- Smooth, human‑like motion
- High‑precision joint control
- Research‑grade repeatability
Manipulation
- Payload: 3 kg per arm (3 kg total)
- Capabilities:
- High‑precision grasping
- Bimanual manipulation
- VR‑guided object interaction
- Autonomous manipulation via Python/ROS2
Perception & Sensors
- Stereo 3D vision
- Depth sensors (RGB‑D)
- Head‑mounted cameras
- Mobile‑base sensors for navigation
Compute & AI
- Software Stack:
- Full ROS 2 Humble environment
- Python SDK
- Unity VR apps
- One‑line Docker simulation environment
- Capabilities:
- VR teleoperation (~125 ms latency)
- Autonomous behaviors
- Data collection for embodied‑AI
- Sim‑to‑Real workflows
Battery & Power
- Runtime: 8 hours (published spec)
- Charging: Standard mobile‑base charging
Connectivity
- ROS 2 communication
- Python API
- VR teleoperation interface
- Unity integration
Applications
- Embodied‑AI research
- Robotic manipulation
- VR teleoperation studies
- Human‑robot interaction
- Academic robotics labs
- Industrial R&D prototyping
Pricing
- $78,000
Pollen Robotics has NOT published:
- Torque curves
- Joint‑speed specs
- Environmental ratings
- Battery capacity details
- API performance benchmarks
Image: @PROROBOTS
Company Source:
https://www.pollen-robotics.com/
https://youtube.com/shorts/4JQYY7bkl9Q?si=VbgCxIGVPzYyXOTR
Key News & Coverage:
https://youtube.com/shorts/Cwe6tGD9VXY?si=o-XKbnvR5FtsDKYZ