The instrument

What the glove actually records.

18 channels at 60 Hz, ±1.5° after calibration, from potentiometers sitting on the joints rather than a model inferring them. Below: what a recorded session contains, how the fit is solved per wearer, and the three things the glove does not capture yet.

The data

Time series from a hand, not a bounding box.

Rotary potentiometers sit on a 3D-printed exoskeleton at each joint. No cameras, no occlusion, no inference between the motion and the number.

Joint angle · live readoutIllustrative
THUMB
INDEX
MIDDLE
RING
LITTLE
18
Channels
60 Hz
Sample rate
±1.5°
Angular accuracy
14
Calibration gestures
$300
Cost to build

One glove, any hand

The fit is solved in software, not in plastic. Fourteen calibration gestures measure the wearer, and the same hardware moves on to the next person — no resizing, no reprinting, no per-operator rig.

Retargeting is the hard part

Mapping a human hand onto a robot hand of different proportions is where demonstrations break, and the thumb fails first. We do not pretend that is solved. What we ship is the anatomy underneath: per-wearer calibration and raw joint angles, so your retarget starts from a real hand rather than an assumed one. Ours runs against a virtual hand today.

What a recorded session contains

  • Per-joint flexion angles for the thumb and all four fingers
  • Full session time series, sampled continuously, not keyframed
  • The calibration solved for that wearer, stored with the session
  • Session metadata: who wore it, what the task was, which trial
  • Synchronised video of the same session for grounding and review
The Grasp capture application: the 3D hand viewer driven live by the glove, with the calibration step list and session settings
Capture app · live glove, 14-gesture calibration

Limits

What we don't capture yet.

You would find these out in the first ten minutes of an evaluation. If one is disqualifying for your work, tell us — it moves up the roadmap.

Next revision

Wrist pose in world space

Potentiometers measure joint angles, not where the hand is. A 6-DoF wrist tracker is the next hardware revision.

Roadmap

Contact forces

We record how the hand moved, not how hard it pressed. Fingertip force sensing is the next sensor we want to add.

Partner-dependent

Object and scene state

Sessions ship with synchronised video, but we do not currently provide segmented object poses.

Next

If the numbers work for you.

Four ways in, from a free capture app to a pilot where we record your task with a matched expert. Or write to hello@usegrasp.co and describe the task — that is faster than any of the forms.

What each one includes, and what it leaves out →