Triboelectric nanogenerator sensors for soft robotics aiming at digital twin applications

Tao Jin,Long Li,Zhongda Sun,Yingzhong Tian,Chengkuo Lee,Minglu Zhu,Xuyan Hou,Zixuan Zhang,Guangjie Yuan,Quan Zhang,Tao Chen

doi:10.1038/s41467-020-19059-3

Abstract

Designing efficient sensors for soft robotics aiming at human machine interaction remains a challenge. Here, we report a smart soft-robotic gripper system based on triboelectric nanogenerator sensors to capture the continuous motion and tactile information for soft gripper. With the special distributed electrodes, the tactile sensor can perceive the contact position and area of external stimuli. The gear-based length sensor with a stretchable strip allows the continuous detection of elongation via the sequential contact of each tooth. The triboelectric sensory information collected during the operation of soft gripper is further trained by support vector machine algorithm to identify diverse objects with an accuracy of 98.1%. Demonstration of digital twin applications, which show the object identification and duplicate robotic manipulation in virtual environment according to the real-time operation of the soft-robotic gripper system, is successfully created for virtual assembly lines and unmanned warehouse applications.

Highlights

Designing efficient sensors for soft robotics aiming at human machine interaction remains a challenge
With the aid of AI of things (AIoT), computation capacity, and ubiquitous sensory information, digital twin is proposed to be a digital copy of the physical system, i.e., a cyber-physical system, to perform real-time control and optimization of products and production lines, because the required time of getting an optimized solution from cloud server reduces to an ignorable level[4]
Configuration and working mechanism of the L-triboelectric nanogenerator (TENG) and TTENG sensors. Both of the length TENG (L-TENG) sensor and tactile TENG (T-TENG) sensor work in single-electrode mode

Summary

Introduction

Designing efficient sensors for soft robotics aiming at human machine interaction remains a challenge. Using TENG approaches to realize tactile sensing skins integrated with soft or rigid actuators have been reported by Professor Wang’s group frequently[20,33] These studies only address contact-separation detection, without the capability of detecting the sliding and continuous motions, which requires further study. Sundaram et al.[39] reported a glove with a dense matrix of 548 resistive sensors, to obtain the grasping signatures Another approach is to leverage the minimalistic design, i.e., the minimum number of sensors, to provide just enough sensory information as a low-cost solution requiring less computation capacity[32]. To further explore the potentials of these facile designed TENG sensors, the machine learning (ML) technique can be utilized to enhance the data interpretation for better manipulation or detection, i.e., accurate gesture recognition, which is equivalent to the continuous motion sensors[41]. There is little research reporting the TENG sensor-integrated soft pneumatic finger with ML-assisted recognition in details, while the significance of relevant technique is already addressed in the reported works, such as self-powered stretchable soft-robotic skin as mentioned previously[20]

Methods

Results

Conclusion