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

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.

Toward Long-Term FMG Model-Based Estimation of Applied Hand Force in Dynamic Motion During Human–Robot Interactions

“…Since FMG signals can read muscle contractions during such activities, it can be a viable tool for predicting worker's intended interactions or applied forces [14]. Therefore, a few studies were conducted to determine isometric hand forces, dynamic forces in motion via FMG signals [15], [16]. Although the study in [16] showed impressive results in recognizing applied forces in dynamic motion during HRI, it had a few shortcomings.…”

“…Therefore, a few studies were conducted to determine isometric hand forces, dynamic forces in motion via FMG signals [15], [16]. Although the study in [16] showed impressive results in recognizing applied forces in dynamic motion during HRI, it had a few shortcomings. First, a separate regression model was trained for predicting forces applied by each participant for one specific motion.…”

“…Performances of these LCFMG models were evaluated in RT and compared to each other. A few models were also trained with "new input sample data" only (no population data), as mentioned in [16]. These models were termed as "specialized trained models (STMs)" hereinafter and were compared with the proposed LCFMG models for performance evaluation.…”

Force Myography-Based Human Robot Interactions via Deep Domain Adaptation and Generalization

“…Estimating isometric or dynamic hand force/torque using FMG signals via FSRs were found favorable to FT sensors [ 28 , 29 , 30 ]. Recently, measuring force via FMG bio signals during physical human robot interactions (pHRI) between human participants and a linear robot was found effective for intra-session evaluation using traditional ML algorithms [ 31 ]. However, intra-session FMG-based pHRI required collecting adequate labelled training data, which was biased and impractical in real scenarios.…”

FMG- and RNN-Based Estimation of Motor Intention of Upper-Limb Motion in Human-Robot Collaboration

“…Force Myography (FMG) is a technique to quantify changes in the volume of a limb resulting from muscle contractions and relaxations (Xiao and Menon, 2014 ). This biosignal has been employed in a variety of applications including gesture recognition, control of exoskeletons, prostheses, and linear actuators, and estimation of user-applied forces to manipulate planar linear actuators (Xiao et al, 2014 ; Cho et al, 2016 ; Sakr and Menon, 2016a , b , 2017 , 2018 ; Jiang et al, 2017 ; Sadarangani and Menon, 2017 ; Zakia and Menon, 2020 ). Force myography from upper-limbs could be collected using lightweight, compact, and unobtrusive bands wrapped around wrist, forearm, and/or upper arm, which makes it an attractive technique for developing wearables.…”