UniForce: A Unified Latent Force Model for Robot Manipulation with Diverse Tactile Sensors
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914299313651712 |
|---|---|
| author | Chen, Zhuo Ni, Fei Luo, Kaiyao Wu, Zhiyuan Zhang, Xuyang Spyrakos-Papastavridis, Emmanouil Jamone, Lorenzo Lepora, Nathan F. Deng, Jiankang Luo, Shan |
| author_facet | Chen, Zhuo Ni, Fei Luo, Kaiyao Wu, Zhiyuan Zhang, Xuyang Spyrakos-Papastavridis, Emmanouil Jamone, Lorenzo Lepora, Nathan F. Deng, Jiankang Luo, Shan |
| contents | Force sensing is essential for dexterous robot manipulation, but scaling force-aware policy learning is hindered by the heterogeneity of tactile sensors. Differences in sensing principles (e.g., optical vs. magnetic), form factors, and materials typically require sensor-specific data collection, calibration, and model training, thereby limiting generalisability. We propose UniForce, a novel unified tactile representation learning framework that learns a shared latent force space across diverse tactile sensors. UniForce reduces cross-sensor domain shift by jointly modeling inverse dynamics (image-to-force) and forward dynamics (force-to-image), constrained by force equilibrium and image reconstruction losses to produce force-grounded representations. To avoid reliance on expensive external force/torque (F/T) sensors, we exploit static equilibrium and collect force-paired data via direct sensor--object--sensor interactions, enabling cross-sensor alignment with contact force. The resulting universal tactile encoder can be plugged into downstream force-aware robot manipulation tasks with zero-shot transfer, without retraining or finetuning. Extensive experiments on heterogeneous tactile sensors including GelSight, TacTip, and uSkin, demonstrate consistent improvements in force estimation over prior methods, and enable effective cross-sensor coordination in Vision-Tactile-Language-Action (VTLA) models for a robotic wiping task. Code and datasets will be released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01153 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UniForce: A Unified Latent Force Model for Robot Manipulation with Diverse Tactile Sensors Chen, Zhuo Ni, Fei Luo, Kaiyao Wu, Zhiyuan Zhang, Xuyang Spyrakos-Papastavridis, Emmanouil Jamone, Lorenzo Lepora, Nathan F. Deng, Jiankang Luo, Shan Robotics Force sensing is essential for dexterous robot manipulation, but scaling force-aware policy learning is hindered by the heterogeneity of tactile sensors. Differences in sensing principles (e.g., optical vs. magnetic), form factors, and materials typically require sensor-specific data collection, calibration, and model training, thereby limiting generalisability. We propose UniForce, a novel unified tactile representation learning framework that learns a shared latent force space across diverse tactile sensors. UniForce reduces cross-sensor domain shift by jointly modeling inverse dynamics (image-to-force) and forward dynamics (force-to-image), constrained by force equilibrium and image reconstruction losses to produce force-grounded representations. To avoid reliance on expensive external force/torque (F/T) sensors, we exploit static equilibrium and collect force-paired data via direct sensor--object--sensor interactions, enabling cross-sensor alignment with contact force. The resulting universal tactile encoder can be plugged into downstream force-aware robot manipulation tasks with zero-shot transfer, without retraining or finetuning. Extensive experiments on heterogeneous tactile sensors including GelSight, TacTip, and uSkin, demonstrate consistent improvements in force estimation over prior methods, and enable effective cross-sensor coordination in Vision-Tactile-Language-Action (VTLA) models for a robotic wiping task. Code and datasets will be released. |
| title | UniForce: A Unified Latent Force Model for Robot Manipulation with Diverse Tactile Sensors |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.01153 |