Robotic Assistance for Physical Human–Robot Interaction Using a Fuzzy RBF Hand Impedance Compensator and a Neural Network Based Human Motion Intention Estimator

Shih-Hsuan Chien,Jyun-Hsiang Wang,Ming-Yang Cheng

doi:10.1109/access.2021.3111875

Shih-Hsuan Chien, Jyun-Hsiang Wang + Show 1 more

Open Access

https://doi.org/10.1109/access.2021.3111875

Copy DOI

Abstract

This paper proposes a robotic assistance control scheme for intuitive teaching tasks by integrating the motion intention of human and real-time hand impedance compensation based upon a fuzzy RBF (Radial Basis Function) compensator. The motion intention of a human is estimated using a feedforward neural network. The parameters of the proposed fuzzy RBF hand impedance compensator are adjusted by considering hand impedance and robot dynamics. Three robotic assistance control schemes are compared: 1) robot without an impedance compensator; 2) robot with a constant-parameter impedance compensator; 3) robot with a fuzzy RBF hand impedance compensator. Several experiments have been conducted to verify the effectiveness of the proposed approach by comparing the contour error, exerted force and task time spent on teaching tasks. Experimental results indicate that the proposed fuzzy RBF hand impedance compensator has the best assistance results among the tested robotic assistance control schemes.

Highlights

Physical human-robot interaction is a crucial issue in human-robot collaboration that is becoming more and more popular across many applications
This paper proposes a neural network (NN) based human motion intention estimator to predict the trajectory of hand movement with the aim of facilitating the design of a hand impedance compensator
The fuzzy RBF hand impedance compensator designed in this paper is implemented in an intuitive teaching task of a 6

Summary

Introduction

Physical human-robot interaction is a crucial issue in human-robot collaboration that is becoming more and more popular across many applications. Application scenarios such as rehabilitation [1] or intuitive teach pendants [2],[3] require the collaborative work of humans and robots. During these tasks, human operators need to interact with the robot for a long period of time. Impedance control [4]-[6] or admittance control [7]-[9] is usually implemented to ensure compliant motion of the robot Some tasks such as manual welding [10] or laparoscopic training [11] require the robot to perform with precision and minimize energy consumption of the operator. To emulate the human decision-making process during teach tasks, fuzzy logic related methods are commonly used when tuning variable admittance parameters or compensator gains [19]-[22]

Objectives

Results

Conclusion