Fiber Bragg grating tactile perception system based on cross-modal transformer

This study proposes a fiber Bragg grating (FBG) tactile sensing system utilizing a cross-modal Transformer architecture. Human tactile perception relies not only on single modalities but also on multimodal perception. Therefore, we decode the collected FBG tactile signals into dynamic vibration and static stress signals, and perform cross-modal perception to enable a robotic hand to perceive tactile properties of touched objects for precise manipulation. Experimental results demonstrate accuracy rates exceeding 87% for identifying the hardness and roughness properties of objects. Furthermore, the system occupies only 2.4 MB of storage space and achieves a recognition time of only 0.92 s per instance. Due to its lightweight and low-latency characteristics, the system holds wide application prospects in the field of tactile perception, including smart manufacturing, virtual reality, and online healthcare.