EMG-based decoding of grasp gestures in reaching-to-grasping motions

Batzianoulis, Iason; El-Khoury, Sahar; Pirondini, Elvira; Coscia, Martina; Micera, Silvestro; Billard, Aude

doi:10.1016/j.robot.2016.12.014

Cited by 67 publications

(32 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reach-to-grasp movements are important activities of daily living that require dynamic motions. A few studies have attempted to decode grasping intention from EMG during reach-to-grasp motions, but only with able-bodied subjects [19,20]. When reaching to grasp an object, the opening and closing of the hand is in coordination with the motion of the arm [21,22], see Fig.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Decoding the grasping intention from electromyography during reaching motions

Batzianoulis

Krausz

Simon

et al. 2018

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

BackgroundActive upper-limb prostheses are used to restore important hand functionalities, such as grasping. In conventional approaches, a pattern recognition system is trained over a number of static grasping gestures. However, training a classifier in a static position results in lower classification accuracy when performing dynamic motions, such as reach-to-grasp. We propose an electromyography-based learning approach that decodes the grasping intention during the reaching motion, leading to a faster and more natural response of the prosthesis.Methods and ResultsEight able-bodied subjects and four individuals with transradial amputation gave informed consent and participated in our study. All the subjects performed reach-to-grasp motions for five grasp types, while the elecromyographic (EMG) activity and the extension of the arm were recorded. We separated the reach-to-grasp motion into three phases, with respect to the extension of the arm. A multivariate analysis of variance (MANOVA) on the muscular activity revealed significant differences among the motion phases. Additionally, we examined the classification performance on these phases. We compared the performance of three different pattern recognition methods; Linear Discriminant Analysis (LDA), Support Vector Machines (SVM) with linear and non-linear kernels, and an Echo State Network (ESN) approach. Our off-line analysis shows that it is possible to have high classification performance above 80% before the end of the motion when with three-grasp types. An on-line evaluation with an upper-limb prosthesis shows that the inclusion of the reaching motion in the training of the classifier importantly improves classification accuracy and enables the detection of grasp intention early in the reaching motion.ConclusionsThis method offers a more natural and intuitive control of prosthetic devices, as it will enable controlling grasp closure in synergy with the reaching motion. This work contributes to the decrease of delays between the user’s intention and the device response and improves the coordination of the device with the motion of the arm.Electronic supplementary materialThe online version of this article (10.1186/s12984-018-0396-5) contains supplementary material, which is available to authorized users.

show abstract

Section: Introductionmentioning

confidence: 99%

“…A self-paced reaching motion of an able-bodied hand could take approximately 1 s to complete [19,24]. In contrast, the activation of prosthetic hands could occur more than one second after the onset of the motion [25,26] (see Fig.…”

Section: Introductionmentioning

confidence: 99%

Decoding the grasping intention from electromyography during reaching motions

Batzianoulis

Krausz

Simon

et al. 2018

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

show abstract

“…Basic human control tasks, such as reaching and grasping, are important for human interfaces for controlling robotic systems [5][6][7]. Identification of hand movements based on EMG measurements have been largely used in the field of computer and automatic video games, robotic exoskeleton, operative devices and for power prostheses and, thus has been the subject of many studies over the past few years [8][9][10][11]. A large number of these studies focus on feature selection for EMG movement classifications and include a dimensionality-reduction step followed by machinelearning-based classification.…”

Section: Introductionmentioning

confidence: 99%

Electromyography Classification during Reach-to-Grasp Motion using Manifold Learning

Lashgari

Maoz

2020

Preprint

View full text Add to dashboard Cite

Electromyography (EMG) is a simple, non-invasive, and cost-effective technology for sensing muscle activity. However, EMG is also noisy, complex, and high-dimensional. It has nevertheless been widely used in a host of human-machine-interface applications (electrical wheelchairs, virtual computer mice, prosthesis, robotic fingers, etc.) and in particular to measure reaching and grasping motions of the human hand. Here, we developd a more automated pipeline to predict object weight in a reach-and-grasp task from an open dataset relying only on EMG data. In that we shifted the focus from manual feature-engineering to automated feature-extraction by using raw (filtered) EMG signals and thus letting the algorithms select the features. We further compared intrinsic EMG features, derived from several dimensionality-reduction methods, and then ran some classification algorithms on these low-dimensional representations. We found that the Laplacian Eigenmap algorithm generally outperformed other dimensionality-reduction methods. What is more, optimal classification accuracy was achieved using a combination of Laplacian Eigenmaps (simple-minded) and k-Nearest Neighbors (88% for 3-way classification). Our results, using EMG alone, are comparable to others in the literature that used EMG and EEG together. They also demonstrate the usefulness of dimensionality reduction when classifying movement based on EMG signals and more generally the usefulness of EMG for movement classification.

show abstract

“…In [14], a synchronization recognition method of gripping force and posture with respect to EMG signals was proposed to explore the relationship between EMG signal and force. An EMG-based learning method was developed to decode the grasping intention for controlling a robotic assistive device in the early stage of reach-tograsp motion [15]. In [16], Park et al proposed a motion intention decoding method based on convolutional neural network with human bio-signals.…”

Section: Introductionmentioning

confidence: 99%

A Framework of Human Impedance recognition

Luo

Liu

et al. 2019

2019 25th International Conference on Automation and Computing (ICAC)

View full text Add to dashboard Cite

A framework for estimating the human impedance is proposed in this paper. In physical human-robot interaction (pHRI), safety and human acceptance are key issues when humans directly interact with the robots. In order to guarantee the safety and improve performance in pHRI, it is important to estimate the dynamics and intention of the human hand. In this work, we consider that a human subject physically contacts with a force sensor when a haptic device sets force in the proposed framework. The measured force, the surface electromyographic signal and the motion of the hand are used to estimate the parameters of human forearm's impedance. The effectiveness of the proposed framework is demonstrated by experimental results. Index Terms-surface electromyographic signal (sEMG), human intention, physical human-robot interaction (pHRI), impedance parameters.

show abstract

EMG-based decoding of grasp gestures in reaching-to-grasping motions

Cited by 67 publications

References 39 publications

Decoding the grasping intention from electromyography during reaching motions

Decoding the grasping intention from electromyography during reaching motions

Electromyography Classification during Reach-to-Grasp Motion using Manifold Learning

A Framework of Human Impedance recognition

Contact Info

Product

Resources

About