Estimation of Multijoint Stiffness Using Electromyogram and Artificial Neural Network

Kim, H.K.; Kang, Byungduk; Kim, Byungchan; Park, Shinsuk

doi:10.1109/tsmca.2009.2025021

Cited by 34 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a different study, surface EMG sensors were used to estimate joint moments and trajectories using ANN (Koike et al 2000). Also, ANN was previously used to estimate multiple joint stiffness of the human arm, taking either muscle EMG or the combined muscle EMG and the joint angles as input to ANN and the estimated joint stiffness as output (Kim et al 2009). In (Sepulveda et al 1993), using EMG and ANN to estimate joint moments and angles of the lower extremity was proposed, but not the impedance.…”

Section: Introductionmentioning

confidence: 99%

Estimating the multivariable human ankle impedance in dorsi-plantarflexion and inversion-eversion directions using EMG signals and artificial neural networks

Dallali

Knop

Castelino

et al. 2017

Int J Intell Robot Appl

View full text Add to dashboard Cite

The use of a suitably designed ankle-foot prosthesis is essential for transtibial amputees to regain lost mobility. A desired ankle-foot prosthesis must be able to replicate the function of a healthy human ankle by transferring the ground reaction forces to the body, absorbing shock during contact, and providing propulsion. During the swing phase of walking, the human ankle is soft and relaxed; however, it hardens as it bears the body weight and provides force for push-off. The stiffness is one of the components of the mechanical impedance, and it varies with muscle activation (Stochastic estimation of human ankle mechanical impedance in medial-lateral direction, 2014, Stochastic estimation of the multivariable mechanical impedance of the human ankle with active muscles, 2010). This study defines the relationship between ankle impedance and the lower extremity muscle activations using artificial neural networks (ANN). We used the Anklebot, a highly backdrivable, safe, and therapeutic robot to apply stochastic position perturbations to the human ankle in the sagittal and frontal planes. A previously proposed system identification method was used to estimate the target ankle impedance to train the ANN. The ankle impedance was estimated with relaxed muscles and with lower leg muscle activations at 10 and 20% of the maximum voluntary contraction (MVC) of each individual subject. Given the root mean squared (rms) of the electromyography (EMG) signals, the proposed ANN effectively predicted the ankle impedance with mean accuracy of 89.8 ± 6.1% in DP and mean accuracy of 88.3 ± 5.7% in IE, averaged across three muscle activation levels and all subjects.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimating the multivariable human ankle impedance in dorsi-plantarflexion and inversion-eversion directions using EMG signals and artificial neural networks

Dallali

Knop

Castelino

et al. 2017

Int J Intell Robot Appl

View full text Add to dashboard Cite

show abstract

“…In the latter category of approaches, multiple studies combine measurements of muscle activity with parametric muscle models, e.g., linear models of muscle stiffness (Osu and Gomi, 1999), quadratic models of muscle tension (Shin et al, 2009), or calibrated models of musculotendon unit forces (Buzzi et al, 2017). In Kim et al (2009), an artificial neural network produces a mapping between EMG data and stiffness estimates, that are obtained from measured joint torques and an empirically determined linear model. In Lakatos et al (2013) and Ajoudani et al (2015), similar mappings are produced by pairing stiffness estimates obtained by application of the perturbation paradigm with EMG data.…”

Section: Related Workmentioning

confidence: 99%

Estimation of Involuntary Components of Human Arm Impedance in Multi-Joint Movements via Feedback Jerk Isolation

2020

View full text Add to dashboard Cite

“…If the difference is recognized between the estimated position (x(t+Δt), y(t+Δt)) and the desired position (x d (t + Δt), y d (t + Δt)) of desired trajectory, to make the human-like robot arm move directly to the new temporary goal point, a modification torque τ d based the optimal D * (t) or R * (t) using the proposed algorithm can be obtained. To find the optimal solution that minimizes the cost function given in (23), firstly the parameters β y = βẏ =0.7 in (34) and (35 ), Fig. 9 The obtained optimal R * (t) by simulation Fig.…”

Section: Journal Of System Design and Dynamicsmentioning

confidence: 99%

Human Arm-Like Robot Control Based on Human Multi-Joint Arm Viscoelastic Properties and A Modified Forward Gaze Model

Wang

Deng

2012

JSDD

View full text Add to dashboard Cite

In this paper, a human arm-like robot control scheme is proposed based on timevarying viscoelastic properties which consist of multi-joint stiffness and multi-joint viscosity during human arm movements and a modified forward gaze model. In general, in human multi-joint arm movements, the multi-joint torque is assumed to be a function of multi-joint stiffness matrix, multi-joint viscosity matrix, and motor command descending from central nervous system (CNS). In order to make the present human arm-like robot move like a human multi-joint arm, a feedback controller and a modified forward gaze model are presented in the human arm-like robot control system. That is, the feedback controller is designed to obtain desired motion mechanism based on real measured data from viscoelastic properties of human multi-joint arm, and the forward gaze model in which steering gains are modified using a cost function is used to compensate the term related to the effect of CNS. The effectiveness of the proposed method is confirmed by the simulation results based on experimental data.

show abstract

Estimation of Multijoint Stiffness Using Electromyogram and Artificial Neural Network

Cited by 34 publications

References 29 publications

Estimating the multivariable human ankle impedance in dorsi-plantarflexion and inversion-eversion directions using EMG signals and artificial neural networks

Estimating the multivariable human ankle impedance in dorsi-plantarflexion and inversion-eversion directions using EMG signals and artificial neural networks

Estimation of Involuntary Components of Human Arm Impedance in Multi-Joint Movements via Feedback Jerk Isolation

Human Arm-Like Robot Control Based on Human Multi-Joint Arm Viscoelastic Properties and A Modified Forward Gaze Model

Contact Info

Product

Resources

About