Grasping State Analysis of Soft Manipulator Based on Flexible Tactile Sensor and High-Dimensional Fuzzy System

The analysis of grasping states in soft manipulators is crucial but is currently lacking in research. In this article, we propose a method for analyzing grasping states in soft manipulators. A flexible sensor with rapid response, excellent repeatability, and customizable size and shape is designed. We developed a soft manipulator with this sensor, named Soft Manipulator Based on Flexible Tactile Sensor Arrays (SM-FTSA). Four grasping states, including inflation, shaking, stable, and slipping, are proposed in this study. A high-dimensional Takagi–Sugeno–Kang (TSK) fuzzy system based on switchable normalization, referred to as SR-HTSK, is proposed for grasping state classification. Static and dynamic experimental scenarios are designed to evaluate the method. The results demonstrate that the proposed method achieved high accuracy rates of 96.92% and 95.88% for the SR-HTSK method in static and dynamic experiments, respectively. Comparative analysis showed higher accuracy rates at slower movement speeds in dynamic experimental scenarios. Through ablation experiments, sensitivity analysis, and comparison with other machine learning methods and research, we validate the outstanding performance of the proposed SR-HTSK method in analyzing grasping states for soft manipulators.