How to Train your Tactile Model: Tactile Perception with Multi-fingered Robot Hands
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911559789314048 |
|---|---|
| author | Ford, Christopher J. Shi, Kaichen Butcher, Laura Lepora, Nathan F. Psomopoulou, Efi |
| author_facet | Ford, Christopher J. Shi, Kaichen Butcher, Laura Lepora, Nathan F. Psomopoulou, Efi |
| contents | Rapid deployment of new tactile sensors is essential for scalable robotic manipulation, especially in multi-fingered hands equipped with vision-based tactile sensors. However, current methods for inferring contact properties rely heavily on convolutional neural networks (CNNs), which, while effective on known sensors, require large, sensor-specific datasets. Furthermore, they require retraining for each new sensor due to differences in lens properties, illumination, and sensor wear. Here we introduce TacViT, a novel tactile perception model based on Vision Transformers, designed to generalize on new sensor data. TacViT leverages global self-attention mechanisms to extract robust features from tactile images, enabling accurate contact property inference even on previously unseen sensors. This capability significantly reduces the need for data collection and retraining, accelerating the deployment of new sensors. We evaluate TacViT on sensors for a five-fingered robot hand and demonstrate its superior generalization performance compared to CNNs. Our results highlight TacViTs potential to make tactile sensing more scalable and practical for real-world robotic applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00744 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | How to Train your Tactile Model: Tactile Perception with Multi-fingered Robot Hands Ford, Christopher J. Shi, Kaichen Butcher, Laura Lepora, Nathan F. Psomopoulou, Efi Robotics Rapid deployment of new tactile sensors is essential for scalable robotic manipulation, especially in multi-fingered hands equipped with vision-based tactile sensors. However, current methods for inferring contact properties rely heavily on convolutional neural networks (CNNs), which, while effective on known sensors, require large, sensor-specific datasets. Furthermore, they require retraining for each new sensor due to differences in lens properties, illumination, and sensor wear. Here we introduce TacViT, a novel tactile perception model based on Vision Transformers, designed to generalize on new sensor data. TacViT leverages global self-attention mechanisms to extract robust features from tactile images, enabling accurate contact property inference even on previously unseen sensors. This capability significantly reduces the need for data collection and retraining, accelerating the deployment of new sensors. We evaluate TacViT on sensors for a five-fingered robot hand and demonstrate its superior generalization performance compared to CNNs. Our results highlight TacViTs potential to make tactile sensing more scalable and practical for real-world robotic applications. |
| title | How to Train your Tactile Model: Tactile Perception with Multi-fingered Robot Hands |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.00744 |