Capture and quality infrastructure for robot manipulation data
Standard capture. Verified data.
A handheld capture device and a quality platform, for teams post-training
a policy onto a robot they already have.
Handheld capture unit — no robot arm, no teleoperation rig.
The bottleneck
Taking the robot out of data collection also takes away the guarantees
that came with it. Two failure modes make an episode unusable, and
neither is visible while you are still collecting.
Tracking loss
The device loses track of its own pose. The video looks perfect. The trajectory does not exist.
Unreachable poses
The human hand went somewhere the target robot cannot follow. Clean data, physically unexecutable.
Recent work names both as fundamental blockers to using handheld data at
scale.2
How it works
01 /
Capture every episode
One rig, one set of specifications, one output format. Different
operators on different floors produce episodes of the same shape,
so the data composes instead of fragmenting.
capture spec
camera fisheye · fixed FOV · rigid to the fingers
pose 6-DoF · metric scale · one world frame
aperture absolute mm from a magnetic encoder
clock one monotonic clock across all streams
calibration intrinsics + camera-to-finger extrinsic
every episode carries all five, or it is not an episode
02 /
Check it on the spot
Validity is decided while the operator is still standing there. A
failed episode gets recollected in the same session — not
discovered days later, back at the lab, after the floor has gone
back to production.
session_2026-08-14_kitting · episode 0473
tracking health pass 0.94 — pose held for the full episode
reachability fail17 frames outside UR5e workspace (t=4.1–4.7s)
time alignment passmax skew 1.2 ms · camera / encoder / IMU
aperture sanity pass
metric scale pass 0.998
rejected— flagged on device at 4.1s, recollected same session
03 /
See the whole session
Every episode visualised, every check recorded, every rejection
attributed to a cause. You know what you are handing to training
before you train on it.
session_2026-08-14_kitting · summary
captured
312
4h 18m
usable
287
92%
rejected
25
all recollected
rejections by cause
unreachable pose 17
tracking loss 6
time skew 2
Training, deployment and the decision of what to collect next stay
yours. Our job is to make the input to those decisions verifiable.
Team
Andrew Wang
Ayan Bhatia
Shivani Kandula
Pretraining scaled on handheld capture.1 Deployment is next.