Estimating Exerted Hand Force via Force Myography to Interact with a Biaxial Stage in Real-Time by Learning Human Intentions: A Preliminary Investigation.

Umme Zakia,Carlo Menon

doi:10.3390/s20072104

Abstract

Force myography (FMG) signals can read volumetric changes of muscle movements, while a human participant interacts with the environment. For collaborative activities, FMG signals could potentially provide a viable solution to controlling manipulators. In this paper, a novel method to interact with a two-degree-of-freedom (DoF) system consisting of two perpendicular linear stages using FMG is investigated. The method consists in estimating exerted hand forces in dynamic arm motions of a participant using FMG signals to provide velocity commands to the biaxial stage during interactions. Five different arm motion patterns with increasing complexities, i.e., “x-direction”, “y-direction”, “diagonal”, “square”, and “diamond”, were considered as human intentions to manipulate the stage within its planar workspace. FMG-based force estimation was implemented and evaluated with a support vector regressor (SVR) and a kernel ridge regressor (KRR). Real-time assessments, where 10 healthy participants were asked to interact with the biaxial stage by exerted hand forces in the five intended arm motions mentioned above, were conducted. Both the SVR and the KRR obtained higher estimation accuracies of 90–94% during interactions with simple arm motions (x-direction and y-direction), while for complex arm motions (diagonal, square, and diamond) the notable accuracies of 82–89% supported the viability of the FMG-based interactive control.

Highlights

Human robot interaction (HRI) is observed as a growing interest in manufacturing environments.In recent years, robots working in collaboration with human workers in final assembly lines have boosted up productivity [1,2,3]
Intended motion statistically significant (p = 7.89 × 10–51 ). This result meant that force myography (FMG) signals in x- and y-axes corresponding to arm flexion and extension were distinguishable and revealed the potential of
These FMG signals during flexion and extension were found statistically significant (p = 7.89 × 10–51). This result meant that FMG signals in x- and y-axes corresponding to arm flexion and extension were distinguishable and revealed the potential of using FMG signals in recognizing arm motion patterns in a planar surface

Summary

Introduction

Human robot interaction (HRI) is observed as a growing interest in manufacturing environments.In recent years, robots working in collaboration with human workers in final assembly lines have boosted up productivity [1,2,3]. A variety of measures, such as vision systems (cameras, image/depth sensors, and tracking systems), ultrasonic or wideband/radio frequency (RF) transceivers, proximity detections (capacitive, inductive, infrared, or magnetic sensors) are implemented for surveying, monitoring and sharing the workplace [4,5,6]. These tools can be either attached to the robot or installed in the workspace. A dynamic and unpredictable environment during collaboration introduces uncertainties increasing risks of injuries for workers [7,8,9] To address such variabilities, some input signals from human would help implementing better collaboration.

Objectives

Methods

Results

Discussion

Conclusion