TacHair: Tactile Contact-Distribution Guided Online Correction for Robotic Hair Stroking and Perception
TacHair: Tactile Contact-Distribution Guided Online Correction for Robotic Hair Stroking and Perception
This research presents TacHair, a tactile contact-distribution guided online correction framework for robotic hair stroking and perception. The method improves task success and contact maintenance by separating motion generation from contact correction, achieving a 62.3% success rate and 88.0% contact maintenance in real-robot trials.
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
real-robot trials
525
Reported trials
View original evidence
We evaluate TacHair in 525 real-robot trials across five head geometries and three hair conditions.
Open source S4head geometries
5
View original evidence
We evaluate TacHair in 525 real-robot trials across five head geometries and three hair conditions.
Open source S4hair conditions
3
View original evidence
We evaluate TacHair in 525 real-robot trials across five head geometries and three hair conditions.
Open source S4
- paper: not_reported
- code: Available Artifact link Open source S5
- dataset: Available Artifact link Open source S5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
eviations, separating task progression from contact recovery. We evaluate TacHair in 525 real-robot trials across five head geometries and three hair conditions. A successful stroke requires both sufficient task progression and contact maintenance; our method improves success from 42.9% to 62.3% and contact maintenance from 59.4% to 88.0% over the same visuotactile policy without correction. These results demonstrate
Open source S4
spatial tactile contact distributions as an effective feedback representation for contact-preserving interaction with deformable and visually occluded surfaces. Demos, code, and datasets are available at https://tachair.github.io.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org