Learning-Based Optoelectronically Innervated Tactile Finger for Rigid-Soft Interactive Grasping

This letter presents a novel design of soft tactile finger with omni-directional adaptation using multi-channel optical fibers for rigid-soft interactive grasping. Machine learning methods are used to train model real-time prediction force, torque, and contact the data collected. We further integrated such fingers in reconfigurable gripper three so that arrangement can be actively adjusted based on collected during grasping, achieving process Detailed sensor calibration experimental results also included validate proposed enhanced grasping robustness. Video: https://www.youtube.com/watch?v=ynCfSA4FQnY .