Robot-Matched Soft Fingers for UMI Data Collection: Lessons from 100 Hours of Pick and Place
Robot-Matched Soft Fingers for UMI Data Collection: Lessons from 100 Hours of Pick and Place
This research introduces a battery-powered handheld Universal Manipulation Interface (UMI) built on YUBI, featuring soft angled fingers that wrap around objects and deform visibly under load to serve as a visual proxy for contact forces. The interface matches the grippers of target robots, enabling efficient data collection for training multi-task pick-and-place policies. Using this system, the authors collected a 99.7-hour dataset across 53 objects, trained policies on 49 of them, and held out 4 as unseen test cases. Results indicate that adding a top camera improves success rates by 13 percentage points even when only half the data includes it, and mid-training on multi-task data boosts fine-tuning success on unseen objects from 35% to 57%. The finger design, dataset, and processing code are available at https://lute-corp.github.io/soft-yubi-site/.
The authors present a battery-powered handheld interface with soft, angled fingers designed to match robot grippers and provide visual force feedback, using it to collect a dataset over 53 objects and train multi-task pick-and-place policies that show improved success rates on unseen objects.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported duration
99.7 hours
View original evidence
ery-powered handheld interface, built on YUBI, whose soft, angled fingers wrap around objects, deform visibly under load as a visual proxy for force, and match the grippers of the robot. With it, we collect a 99.7-hour dataset over 53 objects, train $\pi_{0.5}$ policies on 49 of them, and hold out the other 4 as unseen objects. We find that a top camera raises success by 13 points even when only about half of the dat
Open source S3
Dataset details reported by the source
- Modalities
- camera Open source S3force Open source S3
- Tasks
- pick and place Open source S2
- paper: not_reported
- code: Reported pending Open source S4
- weights: not_reported
- dataset: not_reported
- code: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ery-powered handheld interface, built on YUBI, whose soft, angled fingers wrap around objects, deform visibly under load as a visual proxy for force, and match the grippers of the robot. With it, we collect a 99.7-hour dataset over 53 objects, train $\pi_{0.5}$ policies on 49 of them, and hold out the other 4 as unseen objects. We find that a top camera raises success by 13 points even when only about half of the dat
Open source S3
arXiv:2611.03779v1 Announce Type: new Abstract: Training robot policies for multi-task pick and place requires demonstrations on many objects, which handheld Universal Manipulation Interfaces (UMIs) can collect quickly and cheaply. However, existing UMIs depend on external base stations, use rigid fingers that give no signal about contact forces, or use parallel-jaw fingers that limit grip strength. We present a batt
Open source S2
a includes it, and that mid-training on our multi-task data raises success after fine-tuning on unseen objects from 35% to 57%. Finger design, dataset, and data processing code: https://lute-corp.github.io/soft-yubi-site/
Open source S4
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Check the exact dataset version, license, modalities and task coverage against the intended use.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org