Light-Perception-Based Interactive Control of an Underwater Digital Twin Hand

With increasing demand for ocean exploration, underwater tasks become more complex. Soft robotic hands leverage flexible structures and biomimetic properties to provide a strong alternative to rigid robotic hands. However, most existing studies on underwater soft robotic hands focus on novel materials and improved biomimetic structural designs. These systems often suffer from low sensing accuracy and poor human–machine interaction performance, making it difficult to achieve real-time and precise control in complex environments. Here, we propose a Light-Perception-Based Underwater Digital Twin Hand Interactive Control System (LP-UDTHS) that integrates a multi-degree-of-freedom (multi-DOF) biomimetic pneumatic soft robotic hand with a wearable data glove based on fiber Bragg grating (FBG) sensors. By fusing data from FBGs, RGB cameras, and inertial measurement units (IMUs), and optimizing control strategies through reinforcement learning, we established a light-dominated perception–control–feedback closed-loop system that significantly enhances the control performance of the system in complex and dynamic underwater environments. With light as the information carrier, the system integrates a data glove with high strain sensitivity (1.148 pm/µε, linearity = 0.9996) and high bending sensitivity (26.667 pm/°, linearity = 0.9791). It achieves four-dimensional collaborative interaction and control between the human operator, the machine, the virtual space, and the environment. The system achieves posture monitoring and precise grasping control across various underwater scenarios. It demonstrates advantages such as low cost, high precision, rapid response, strong interference resistance, and stable interaction. This establishes a new paradigm for underwater intelligent equipment by integrating light sensing with digital twin technology, offering broad prospects for future underwater operations.