Sensor-Invariant Tactile Representation

High-resolution tactile sensors have become critical for embodied perception and robotic manipulation. However, a key challenge in the field is the lack of transferability between sensors due to design and manufacturing variations, which result in significant differences in tactile signals. This limitation hinders the ability to transfer models or knowledge learned from one sensor to another. To address this, we introduce a novel method to extract Sensor-Invariant Tactile Representations (SITR), enabling zero-shot transfer across optical tactile sensors. Our approach utilizes a transformer-based architecture trained on a diverse dataset of simulated sensor designs, allowing generalizability to new sensors in the real world with minimal calibration. Experimental results demonstrate our method's effectiveness across various tactile sensing applications, facilitating data and model transferability for future advancements in the field. Figure 1 : Vision-based tactile sensors vary in both optical design and physical properties. Even with the same contact object, a screw, the tactile images produced by each sensor differ significantly. These variations highlight the challenge of transferring models from one sensor to another.