A Differentiable Dynamic Model for Musculoskeletal Simulation and Exoskeleton Control

Abstract

An exoskeleton, a wearable device, was designed based on the user’s physical and cognitive interactions. The control of the exoskeleton uses biomedical signals reflecting the user intention as input, and its algorithm is calculated as an output to make the movement smooth. However, the process of transforming the input of biomedical signals, such as electromyography (EMG), into the output of adjusting the torque and angle of the exoskeleton is limited by a finite time lag and precision of trajectory prediction, which result in a mismatch between the subject and exoskeleton. Here, we propose an EMG-based single-joint exoskeleton system by merging a differentiable continuous system with a dynamic musculoskeletal model. The parameters of each muscle contraction were calculated and applied to the rigid exoskeleton system to predict the precise trajectory. The results revealed accurate torque and angle prediction for the knee exoskeleton and good performance of assistance during movement. Our method outperformed other models regarding the rate of convergence and execution time. In conclusion, a differentiable continuous system merged with a dynamic musculoskeletal model supported the effective and accurate performance of an exoskeleton controlled by EMG signals.

A Review of EMG-, FMG-, and EIT-Based Biosensors and Relevant Human–Machine Interactivities and Biomedical Applications

“… Application in human–machine interaction. ( a ) A myoelectric prosthesis control based on the combination of EMG and FMG [ 5 ]; ( b ) a prosthetic control using high-density FMG [ 131 ]; ( c ) an EMG-controlled dynamic model for musculoskeletal simulation and exoskeleton control [ 132 ]; ( d ) application of EMG pattern recognition in manipulator control [ 133 ]; ( e ) estimation of grip strength and three-dimensional push–pull force using electromyography [ 134 ]; ( f ) a control scheme of the elbow joint memory alloy exoskeleton based on sEMG signals [ 135 ]. …”

“…A summary of the different reference articles is shown in Table 4. the combination of EMG and FMG [5]; (b) a prosthetic control using high-density FMG [131]; (c) an EMG-controlled dynamic model for musculoskeletal simulation and exoskeleton control [132];…”

Experimental Study of Fully Passive, Fully Active, and Active–Passive Upper-Limb Exoskeleton Efficiency: An Assessment of Lifting Tasks

“…Prior to practical exoskeleton deployment across diverse work situations, several technical, physical, and psychological factors require evaluation. Analysis of these factors is not standardized and varies according to application domain, focused research objectives, and types of studies performed (simulation [ 7 ] or experiment [ 8 ]). For example, Hodson [ 9 ], Kim et al [ 10 ] and Alemi et al [ 11 ] have used maximum voluntary isometric contractions (MVICs) [ 12 ] for exoskeleton evaluation.…”

“…Specifically, some prior studies have relied on simplifications in terms of the human-exoskeleton kinematic closed-loop interaction and have employed different (e.g., Hill-type) muscle models. For example, Marinou et al [ 22 ], Sharafi and Uchida [ 23 ], and Shushtari et al [ 24 ] conducted simulation-based evaluations of the human skeletal system with an exoskeleton (without experimental evaluation), and Kuo et al [ 7 ] and Li et al [ 25 ] carried out experimental evaluations using detailed Hill-type muscle models within musculoskeletal models and simplified exoskeletons without closed-loop interaction.…”

Editorial: Advanced technological applications in neurosurgery

“…Further advanced technology focused not only improvement of clinical outcome, but recovery neurological deficits via rehabilitation with training by the exoskeleton ( 11 , 12 ). Nonetheless, there is a gap in our knowledge of biophysiological functions and their effects on functional performance ( 13 , 14 ).…”