A Human-Inspired Thumb-Index Robotic Hand with Strain Gauges Embedded in Soft Joints

2026-06-19

AI Summary

This work proposes a lightweight, low-cost underactuated two-fingered robotic hand inspired by human hand biomechanics, addressing the limited adaptability of conventional robotic hands that rely on external vision or fingertip tactile sensing for safe grasping. For the first time, flexible strain sensors are directly embedded within silicone-based soft joints, integrating structural compliance with proprioception in a unified design. This approach enables passive adaptive grasping without requiring visual feedback or fingertip sensors and achieves high-accuracy identification of object size, shape, and material stiffness across 20 distinct objects through unsupervised data analysis. Experimental results demonstrate that the system significantly outperforms existing solutions in grasp sensitivity and safety, validating the effectiveness and novelty of the sensorized soft joint architecture.

Abstract

Human hand grasp adaptation depends mainly on the synergy between physical structure and biological feedback. Inspired by this biomechanical principle, the Safe Thumb-Index Robotic (STIR) Hand was developed as a minimal, lightweight, and low-cost two-digit prototype featuring an asymmetric thumb-index configuration. By pairing an underactuated, tendon-driven mechanical design with flexible strain gauges embedded into silicone-encapsulated soft joints, the system achieves passive grasp adaptation while establishing both internal proprioception and external perception. Unsupervised analysis was carried out on a dataset of the STIR hand grasping 20 different objects, along with an object classification task and an ablation study to highlight the contribution of the soft joint sensors. The object classification task discriminated object size, shape, and material stiffness with a high classification accuracy. In contrast to traditional industrial grippers and robotic hands, the STIR Hand demonstrates that sensorized compliant joints significantly improve overall sensitivity and ensure safe grasping, while remaining independent of additional fingertip tactile elements or external vision systems. Finally, a comparison to similar devices grasping identical objects validates the utility of the STIR Hand.

Problem

• robotic hand
• grasp adaptation
• soft joints
• proprioception
• object classification

Innovation

• soft robotic hand
• strain gauge
• passive grasp adaptation
• compliant joints
• proprioception