( 01 )Scene family

F&B Storefront

7,466 hours in inventory · 7.5% of corpus · ships in 10 business days

Order taking, plating, serving, table turnover and POS operation during real service hours.

L1–L5 4D MOCAP 3D RETARGET
TASKS COVERED

order taking · beverage preparation · plating · serving · table turnover · POS operation · tray handling

WHY IT IS HARD

Speed constraints in a cluttered, shared workspace, with frequent handovers between people. Time pressure changes how a task is performed — demonstrations captured at leisure do not transfer to a service rush.

What you get

Licensed by annotation depth. A first engagement usually starts at L1–L3.

DELIVERY LEAD TIMES

Start with existing inventory.

Instead of waiting months for collection.

Evaluation subset (≤ 50 h)
on request
3 business days
Single scene family, L1–L3
up to 25,636 h
10 business days
Family with aligned layers, L1–L5
by scope
15 business days
Multi-family programme
by scope
20 business days
Targeted re-capture at a contracted site
by scope
scoped per engagement

All hours quoted are captured, refined and in storage — not collection capacity. Where a figure refers to work not yet captured, it is labelled as such.

Hardware-synchronised by default. Delivered in UMI, LeRobot, RDT, Open-X-Embodiment or MOVAS native — to your cloud, your VPC, or air-gapped media. Rights structure published at data rights.

FAQ

F&B Storefront — Common Questions

7,466 hours are in inventory today, 7.5% of the MOVAS-Ego 100K corpus. This is captured and refined material in storage, not collection capacity. A single family at L1–L3 ships in 10 business days; an evaluation subset ships in three.

L1–L5 control annotation and Human2Robot retargeting are available across the family. 4D ground truth, motion capture and 3D assets are available for the instrumented subset; real coverage is stated on the data card rather than averaged.

Yes, at sites already under contract. If your policy fails on a specific step we can return to the same site, with the same fixtures and objects, and capture that failure mode with 4D and mocap on the same take.

Request this family.

Tell us the failure mode you are working on and we will scope the smallest subset that moves it.

Request a Subset

Data moves robots. MOVAS moves data.