Teaching robots to feel.

First collection begins in Moradabad, in the brass workshops. Leave an address and we will send the first release when it is published.

Read the thesis

The thesis

India never finished automating. That is the asset.

The work still done by hand here survived because machines could not do it. Cloth, leather, wire, sheet brass. Deformable, contact rich, two handed, irregular. Not an accident of development. A filter, and it selected for exactly the problems robotics has left.

Our approach

A camera records where a hand went. It does not record how hard it pressed, when contact began, or whether the material slipped. We intend to capture that from the muscles that drive the hand, a hundred times a second, and release it openly.

See the spec

Placeholder footage, illustrative only. Not our capture data.

Force and video, on one clock.

Load at grip0.00 N
Planned rate100 Hz
Threads taut0

Physics simulation, not sensor data. Drag the weave.

What is settled

Human video scales. Published work shows manipulation performance rising monotonically with hours of egocentric footage, and a million hours are now free to download.

What is not

Whether contact must be measured or can be estimated from video. Recent work argues both ways. We are running the cheap version of that experiment before building at scale, and we will publish the answer either way.

Forearm muscle signalrare8 ch · 1000 HzDry electrodes on the upper forearm. Raw signal retained alongside the derived envelope, so anyone can reprocess it.
Derived contact forcerareper digit · 100 HzEstimated from the muscle signal, calibrated against measured force. An estimate, not a direct measurement, and reported as such.
Egocentric RGB1080p · 30 fpsHead mounted. Fisheye intrinsics solved per device, Kannala-Brandt, four coefficients.
Exocentric RGB2 × 1080p · 30 fpsFixed at the bench, extrinsics solved per workstation, so ego and exo share a frame.
Hand orientation9-axis · 100 HzOne IMU in the band, onboard fusion, quaternion output. Wrist angle changes how muscle activity maps to force, so it is recorded alongside.
Skill graderareper workerYears in trade, recorded on the same task at the same bench. Apprentice failures and recoveries kept, not filtered out.
Shear forcenot in v0Arguably what governs whether cloth slips. We do not have it yet and will say so plainly at release.

The rig

Reference design · nothing built yet

128° 1 2 3 4 5 6 Open frame, side view
  • 1Camera moduleMonocular, 1080p at 30 fps, 128 degree fisheye. Intrinsics calibrated per device and shipped with the footage.
  • 2Brow padLoad spread across the forehead. It has to be wearable for an eight hour shift or the data never gets collected.
  • 3Head strapRigid open frame with an elastic crown strap. No nose bridge, no prescription fitting, works over existing eyewear.
  • 4Recorder and batteryLocal microSD at roughly 1.6 GB per hour. Uploads overnight on factory wifi, never mid shift.
  • 5Port, status, kill switchUSB-C charge, one status light, one press to stop recording. That last part is why factory owners say yes.
  • 6Field of viewAngled down to hold both hands and the working surface of a bench in frame.

The band infers force from muscle activity rather than measuring it at the contact. Calibration against measured force is required, and the mapping shifts when the band is removed and replaced. Shear is not measured in this version.

As intended

Industrial design concept

What the rig is meant to become. A head unit that records what the hands did, and a forearm band that records how hard they pressed. Neither has been built.

Head unit worn by a worker at a bench
Concept render

Head unit, in use

The camera points where the work is.

Angled down to hold both hands and the bench surface in frame at working posture. The wearer never looks up, so the optics are aimed for the head angle rather than the horizon.

Close view of the head unit showing camera, brow pad and crown strap Concept render

Balanced front to back

Camera at the temple, battery and recorder in the rear housing, so the mass sits over the crown. A front heavy rig is unbearable by hour three, and a rig that comes off produces no data.

Forearm band with electrode array on the inner face Concept render

Nothing on the hands

Dry contacts on the inner face read the forearm muscles that drive the fingers. The fingertips stay bare, because a craftsman who cannot feel his material stops wearing the device.

Industrial design concept. Nothing built yet. These are renders, not photographs of hardware in use.

Target sites

Force-dominant trades · in approach

01

Garment construction

Mass Knit Garments

Velampalayam, Tiruppur, Tamil Nadu

Collar attach, hemming, gathering. The canonical deformable problem, done by people who do it four thousand times a week.

Prospective site · no agreement yet
02

Hand chasing, sheet brass

A. J. Brass Emporium

Rehmat Nagar, Moradabad, Uttar Pradesh

Sheet brass moves only under correct pressure. Video of hand chasing is close to useless on its own. Force is what makes it legible.

Prospective site · no agreement yet

Placeholder footage, illustrative only. Not our capture data.

Access

The first release will be open.

Open licence, LeRobot format, other formats on request. If you train manipulation policies and there is a material, task or force profile you need, tell us now and we will collect for it.

We reply to every lab within two working days.