Intuitive motion capture
Precisely captures human hand motion as raw motion data.
Products WHATsLAB / ATLAS
Air Glove Atlas
A hand interaction device for humanoid robot teaching and XR training
Air Glove Atlas captures precise human hand motion and connects it to Physical AI and immersive virtual training through haptic feedback and a development-ready pipeline.
From human hand motion to robot movement.
One open-band device handles finger-level motion and haptic feedback that conventional glove controllers and vision-based tracking often miss.
Humanoid robot teaching
Turns natural hand movement into robot learning data without complex control steps.
Efficient data use
Connects with development environments such as ROS2, Unity, Unreal, and Isaac Sim.
Air Glove Atlas
An open-band glove-type interaction device that precisely captures hand movement and provides per-finger haptic feedback.
Key Features of Air Glove Atlas
Hardware Features
Open-band design
Fits various hand sizes
Motion tracking
Haptic feedback
Software Features
Game engine integration
Development environment
Technical support
Demo scenes
Supported platforms
Isaac Sim
ROS2
Unity
Unreal
Application areas
Humanoid robot teaching and teleoperation
Industrial remote work
Medical simulation
XR-based virtual training
Designed for a better interaction experience
Other Data Gloves
Uncomfortable fit across different hand sizes
Long-wear discomfort from sweat and debris
Low tracking accuracy based on flex sensors
Limited abduction and adduction tracking
Low usability due to lack of content
Limited accessibility due to high cost
Air Glove Atlas
One-size design that fits a wide range of hand sizes
Comfortable open-band design for long-term wear
High accuracy powered by in-house AHRS (IMU)
Abduction and adduction tracking supported
Unity and Unreal content integration
Air Glove Atlas at a reasonable price
Where hand data flows into Physical AI
Air Glove Atlas turns human hand motion and manipulation into structured hand data, connecting it to robot learning and simulation pipelines.
Data Pipeline
From glove-captured raw data to AI model training in one flow
The structure connects hand-motion capture, raw data collection, simulation transfer, and deployment to robot hands.
01
Capture
Hand-motion capture
Captures finger bending, finger spread, and wrist motion.
02
Collect
Raw data collection
Stores data in a form that can support robot teaching and learning.
03
Simulate
Simulation integration
Connects the motion data to virtual environments such as ROS2 and Isaac Sim.
04
Deploy
Robot-hand deployment
Extends simulation and learning results into real robot-hand control.
Computer Vision vs Air Glove Atlas
Research by Sejong University Robotics and Computer Vision Lab
Air Glove Atlas enables faster and more accurate teleoperation than conventional VR-only methods.
Time (min)
Teleoperation time
10min
VR Only
4min
Air Glove Atlas
60% less time
Success Rate (%)
Teleoperation success rate
80%
VR Only
90%
Air Glove Atlas
10% improvement
Repeatable virtual training through natural hand interaction
Maintains hand input even in occlusion or low-light conditions where cameras can fail.
Supports fine-motor training such as tool use, grasping, and manipulation.
Connects quickly with existing XR content built on Unity and Unreal.
Medical
Extends medical procedures and rehabilitation training into hand-interactive XR experiences.
Industrial
Turns equipment operation, safety training, and field procedures into repeatable training.
Training
Converts repeat-practice tasks into immersive training environments.
Education
Creates immersive practice content that learners can manipulate directly by hand.
“Hands-on training, real and measurable.”
Want to learn more about Air Glove Atlas?
Catalog
Mobile catalog and product overview
Demo
Product motion and application demos
Order Guide
Purchase and adoption inquiry guide
FAQ
We can review product and pipeline configurations for robot learning, XR training, medical rehabilitation, and related use cases.
Contact us