TouchBridge: Tactile-Conditioned Human-to-Robot Transfer for Dexterous Manipulation
TouchBridge: Tactile-Conditioned Human-to-Robot Transfer for Dexterous Manipulation
This paper presents TouchBridge, a framework for transferring human demonstrations to robot manipulation using tactile sensing and contact alignment. The method enables direct conversion of human demonstrations into robot-domain training data without requiring object meshes or physics simulations, achieving 72.5% success rate in real-world tasks.
TouchBridge introduces a hardware-software framework for transferring human demonstrations to robot manipulation, leveraging tactile sensing and contact alignment without requiring object meshes or physics simulations. The method achieves competitive performance in real-world tasks, with policies trained on TouchBridge-converted data outperforming teleoperated demonstrations.
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.
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
simulation for retargeting, enabling direct and scalable conversion of human demonstrations into robot-domain training data. Combined with visual synthesis and camera-anchored action conversion, TouchBridge produces robot-domain demonstrations for fine-tuning a pretrained vision-language-action (VLA) model. Across four real-world contact-rich tasks, policies fine-tuned solely on TouchBridge-converted human demonstra
Open source S4
tions achieve a 72.5% average success rate, compared with 77.5% using an equal number of teleoperated robot demonstrations, while human demonstration collection is 7.0x faster. Under the same policy and training setup, Tac-Retarget outperforms DexPilot and UniDex by 25.0 and 42.5 percentage points, respectively.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org