Contact Us
Hand UMI

A person holds two handheld grippers, one per hand, and does the task themselves. No robot in the loop — the gripper records what a robot would need to reproduce the motion.

16 Tasks · 24 Episodes

Two deliveries. The first is short pick-and-place, zips, lids and bins on a bare table. The second is long-form cleaning in real rooms: spray, wipe, flip, re-wipe, put back — up to three minutes per take, with the operator's own segment-by-segment labels.

4 Tactile Pads

Each gripper has a camera-based gel pad on both fingers. The gel image is recorded at 120 fps; the vendor derives deformation, shear and depth fields and a six-axis force from it at 60 Hz.

1 kHz Pose · Ego Headset

Both grippers are tracked at about 1 kHz by their own stereo-inertial units and placed in one world frame off an AprilGrid. The operator wears a stereo headset whose head pose runs at 200 Hz.

BEHIND THIS SAMPLE
622episodes · 120 min of task time · 2 rigs

The thirteen episodes below are drawn from a 622-episode delivery recorded over five days on two identical rigs — one on a white table (pens and pencil cases), the other mostly on a black table (boxes, bins and a backpack), with ten bin takes on the white table as well. Every episode passed the vendor's quality check, both gripper trajectories aligned to the AprilGrid, and none is missing a file. Six tasks, eight objects; counts below are exact, every episode was opened.

11%
22%
20%
12%
9%
14%
8%
3%
T168 ep · 39 min
Pens into holder · one hand

White table, 08-07. One to three pens lie on the table; the right gripper drops each into a white holder. The left gripper is carried open. 24–44 s per take.

T2a137 ep · 24 min
Unzip pencil case · yellow

08-11. The left gripper pinches the case body, the right takes the slider and pulls the zip open. 6–19 s per take.

T2b126 ep · 20 min
Unzip pencil case · navy

08-11 / 12. The same two-hand zip on a stiffer navy case with a smaller slider. 7–14 s per take.

T3a73 ep · 6 min
Close box lid · blue box

Black table, second rig, 08-10. A hinged blue box sits open; the left gripper steadies the base while the right flips the lid shut. 4–6 s per take.

T3b59 ep · 5 min
Close box lid · clear box

08-10. The same close on a lighter clear box whose lid snaps — the right pads peak higher than on the blue box. 4–8 s per take.

T490 ep · 14 min
Open backpack zip · two sliders

08-11, second rig. A small backpack with a double-slider zip; each gripper takes one slider and they pull apart in opposite directions. 7–12 s per take.

T648 ep · 9 min
Stand toppled bin up · one hand

08-05 / 10 / 11, second rig. A white bin lies on its side; the right gripper grips the rim, lifts it and sets it upright. Ten takes are on the white table, the rest on the black one. 7–18 s per take.

T521 ep · 2 min
Turn inverted bin upright · one hand

08-10, second rig. A light-blue bin starts upside down; the right gripper grips it, lifts and turns it over. 6–7 s per take.

Task time is the vendor's start/stop window, not the full recording. Both rigs use the same gripper model, the same headset and the same AprilGrid; the second rig's episode numbers overlap the first's, so episodes are identified by UUID. Eight takes in the delivery are exact re-exports of others and are counted once.
SECOND DELIVERY · 2026-08-22 → 08-25
38episodes · 56 min of task time · 3 rigs · real rooms

Long-form cleaning work, recorded in offices, at a window, in front of filing cabinets and a shelving unit. One towel, one spray bottle, one target object: spray it, wipe it, turn it over, wipe again, put it back where it came from. Takes run 47 to 264 seconds against 4 to 46 in the first delivery, and every take arrives with the operator's own segment-by-segment labels — start and end times, which hand, what was done, in plain language. Ten of the eleven takes below are one per object family.

W13 ep
Drinkware

Mugs and a thermos flask. Wipe, spray, wipe again, set down on a magazine. 143–264 s.

W25 ep
Storage containers

Open plastic boxes, a storage bin, trays. Inner and outer wall, one stood on its edge to reach the base. 104–204 s.

W33 ep
Bottles

Cola, mineral water, a capped plastic bottle. Alcohol spray over the body, then wiped dry. 62–82 s.

W43 ep
Canned food

Tins and a glass preserve jar, two of them lifted off a shelving unit and put back. 69–98 s.

W51 ep
Soft packaging

A crisp packet — it deforms under the towel, so the pads never settle. 81 s.

W61 ep
Cardboard

A rectangular carton off the shelf, wiped on the desk, returned. 103 s.

W74 ep
Books and stationery

Notebooks, two comic books wiped on both faces and stacked square, a pencil, a folder from a cabinet. 47–112 s.

W81 ep
Electronics

An air-conditioner remote, front then back, then into its box. 173 s.

W91 ep
Glassware

A round glass ashtray — pens taken out of it first. 114 s.

W104 ep
Fixed surfaces

A desk top, a window sill and its glass, the face of a glass cabinet, a shelf board. One take swaps the towel and the sprayer between hands mid-job. 79–142 s.

Plus ten single-hand paper-cup pick-ups in a meeting room (20–29 s), which arrived without labels — the ones shown here are Tidel-derived drafts. Two further takes in this delivery are unusable: one has a blurred headset view, the other a corrupted gripper stream. Episodes flagged by the operator as containing bystanders are not published here.
PENSone hand · right gripper acts
UNZIPtwo hands · left pins, right pulls
CLOSE LIDtwo hands · left steadies, right flips
BACKPACKtwo hands · sliders pulled apart
BINSone hand · right gripper rights the bin
WIPE · CONTAINERS
WIPE · PACKAGEDtaken off a shelf, wiped, returned
WIPE · DESK OBJECTSflip to the other face, then stack or box
CLEAN · SURFACESthe target does not move
PICK · PAPER CUPone hand · Tidel draft labels
TACTILE PADS
gel camera on each finger · left gripper first, then right · finger L / finger R are the vendor's names
0.00 / 0.00
STREAMS —
LEFT HAND—
RIGHT HAND—
GRIPPERfinger angle · rad
CONTACT|F| · N
LEFT GRIPPER · FINGER L
LEFT · FINGER R
RIGHT GRIPPER · FINGER L
RIGHT · FINGER R
CLOSED / IN CONTACT
—
Check the synchronisation yourself
Nothing on this page was aligned by hand. Each raw stream carries an epoch start stamp; the page cuts every stream at the same epoch second and lets them run. If the stamps were wrong the pads would load before the fingers close, or the ego view would show a pen already in the holder while the gripper camera still shows it on the table. The table lists what the streams themselves report for each take.
window = [task_start − 1 s, task_stop + 1 s] # vendor stamps, epoch cut(v) = ffmpeg -ss (window[0] − v.start_offset_us/1e6) # per stream closed = angle > min + 0.6·(max − min) # per gripper, own travel contact = hysteresis(max(pad_l, pad_r) |F|, on 1.0 N, off 0.5 N) travel = Σ ‖p[i+1] − p[i]‖₂ # pose_data csv, whole take
The headset keeps its own clock. Before each take the recorder measures the offset between the two and writes the residual to ego_sync.json; across all 622 episodes the residual stays within ±15 ms, under one frame at 60 fps.
The pad force is computed by the vendor from the gel deformation. On the pen task the two right-hand pads agree within a few percent at every grasp — a thin pen loads both fingers alike; on the zip task one finger carries most of the load, which is what a slider pulled against its own tape should do. Neither pattern would hold if the pads were mis-paired.
taketask windowego offsetL travelR travelL peakR peakcontacts L · R
Travel is the path length of the gripper's tracked origin. On the pen task the left gripper still moves about a metre — the operator's idle hand drifts — but its pads never load and its fingers never close; that is the test for "idle", not the travel.