Skip to content
Solutions · Physical AI & Robot Data

Tactile Manipulation Data: The Modality Simulation Cannot Fake

Tactile manipulation data from real contact: per-finger 16x16 taxel force arrays at 100Hz, synced to stereo video, depth and 21-point hand pose. Adding tactile to vision policies lifts task success 8 to 12 percent on contact-rich assembly, measured on a real robot, not a contact-blind sim.

Book a Tactile Data Strategy Session Free 30-minute call · mutual NDA included
8-12%Task-success lift on contact-rich assembly, measured on a real robot.
16x16Taxels per finger pad, sampled at 100Hz.
100k+Actuation cycles of durability, no gel to wear out.
Outcomes

What's in Our Tactile Dataset

Every episode pairs per-finger force with vision on one clock: 16x16 taxels at 100Hz, stereo depth, dual wrist views and 21-point hand pose, so contact is measured, not guessed.

Per-Finger Force Arrays

16x16 taxels at 100Hz on each finger pad — the contact signal simulation cannot fake.

Slip Detection

Onset of slip captured at rates 30Hz video aliases away.

Grasp Stability

Contact distribution that tells a stable grip from a failing one.

Contact-Phase Segmentation

When contact starts and ends, aligned to the video.

Synced to Vision

Force time-aligned sub-frame to stereo video and hand pose.

Deformables

Compliant and deformable object handling that vision alone misses.

The Problem

Why Vision Alone Misses Contact

A slip that starts and ends inside one 33ms video frame is invisible to 30Hz vision — which is exactly why the force channel exists. Simulation barely models contact, so it under-measures the benefit, and gel-based tactile sensors wear out and stay lab-bound. Three gaps every vision-only or sim-only pipeline leaves open:

1 A slip that starts and ends inside one 33ms video frame is invisible to 30Hz vision — no force channel, no signal.
2 Simulation cannot fake contact, friction or slip, and sim benchmarks like LIBERO and SIMPLER barely model it — so they under-measure tactile's benefit.
3 Gel sensors like GelSight and DIGIT deliver high resolution but the gel wears and they stay largely lab-bound — not deployable at scale.
The Force-Plus-Vision Answer

We measure contact, not infer it.

Force plus vision on one synced clock: the contact signal a manipulation policy needs, and the one simulation cannot fake. PaXini PXCap taxel arrays record 16x16 force at 100Hz, time-aligned sub-frame to stereo video, depth and 21-point hand pose.

Real 16x16 taxel force, not synthetic guesses
Sub-frame sync to stereo video and hand pose
Durable taxel arrays, no gel to wear out
The Sensor Landscape

What We Capture, and How

The sensor landscape, honestly compared, plus the sampling rates and delivery formats that make tactile data usable — with the caveats stated up front.

1

PaXini PXCap taxel arrays

Piezoresistive 16x16 taxels at 100Hz in a 2mm profile, with 100k-plus cycle durability and no gel to wear out. Durable, deployable force capture at scale — the tradeoff GelSight and DIGIT cannot make.

2

Honest sensor comparison

GelSight and DIGIT are vision-based gel sensors with very high spatial resolution but the gel wears and they stay lab-bound. If your task hinges on fine texture rather than force distribution, GelSight wins on resolution and we are the wrong supplier.

3

Tactile at 30 to 60Hz

Contact perception is captured at 30 to 60Hz — fast enough to catch the onset of slip and the contact transitions a 30Hz video feed aliases away.

4

Force-torque up to 500Hz

Whole-arm control needs higher rates, so we capture wrist force-torque up to 500Hz alongside the per-finger tactile channel.

5

IMU at 200Hz

High-rate inertial capture at 200Hz preserves the fast motion that lower-rate channels miss, so contact-rich and dynamic tasks are represented accurately.

6

Sub-frame sync to vision

Force is time-aligned sub-frame, on a shared hardware clock, so tactile lines up with stereo video, depth and 21-point hand pose per frame — no post-hoc timestamp guessing.

7

LeRobot and MCAP delivery

Every episode ships LeRobot-ready, with ROS 2 / Foxglove MCAP and a sync manifest, so force, depth and video line up out of the box — no conversion project before you can train.

8

Prove it on a real robot

One honest caveat: tactile needs paired vision to be useful, and sim benchmarks like LIBERO and SIMPLER barely model contact, so they under-measure the benefit. The 8 to 12 percent lift has to be shown on a real robot.

Start Today

Adding Contact to Your Policy?

Tell us the manipulation task. We'll map the tactile capture and send a representative sample pack — the same taxel arrays, sampling rates and delivery format you'd get in production, so your team can inspect force-to-vision alignment before any commitment.

Book a Strategy Session →
Ask us about
Per-finger 16x16 taxel force arrays at 100Hz, synced sub-frame to vision
GelSight and DIGIT versus PaXini PXCap taxel arrays for your task
Sampling rates — tactile at 30 to 60Hz, force-torque to 500Hz, IMU at 200Hz
LeRobot, ROS 2 / Foxglove MCAP delivery with a sync manifest
Proving the 8 to 12 percent lift on a real robot, not in contact-blind sim
Custom tactile capture for insertion, deformables, grasp and tool use
Where It Gets Used

Where Our Tactile Data Gets Used

Contact-rich tasks where force closes the loop and vision-only policies fall short — captured to your taxonomy, not a generic corpus:

Insertion and assembly — peg-in-hole, connectors and fasteners where force closes the loop.
Deformable handling — cloth, cable and compliant parts that defeat vision-only policies.
Grasp and slip — stable grasping and slip recovery from real contact signals.
Tool use — contact-rich tool work in unstructured workshops.
Force plus vision on one clock — tactile synced sub-frame to stereo video, depth and 21-point hand pose.
Durable, deployable capture — taxel arrays at 100k-plus cycles, no gel to wear out at scale.

Send your manipulation task and we scope a tactile capture program against it. Force plus vision on one synced clock is the contact signal a manipulation policy needs, and the one simulation cannot fake — so the data you train on is measured on real contact, not inferred from contact-blind video or sim.

Questions

Frequently Asked Questions

GelSight gives higher spatial resolution but the gel wears and it stays lab-bound. PaXini taxel arrays give durable, deployable force at 100Hz with no gel. We use taxel arrays for field capture at scale; if you need fine texture, GelSight is the better fit.

Yes. Adding force and tactile to vision policies reports an 8 to 12 percent success lift on contact-rich assembly. Because sim barely models contact, that lift has to be shown on a real robot.

30 to 60Hz for tactile contact perception, up to 500Hz for whole-arm force-torque control, and 200Hz IMU. We capture all three.

Sub-frame, on a shared hardware clock, with a sync manifest, so force lines up with stereo video, depth and hand pose per frame.

Per-dataset and non-exclusive by default, permitting commercial training, with exclusive and custom-capture terms on request.

See the Data Before You Decide

A 30-minute strategy call. We'll walk through your manipulation task, target model and delivery format — then scope a representative sample pack so your team can inspect force-to-vision alignment and prove the lift on a real robot.

Discuss Your Project