Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Nov 16:7:567491.
doi: 10.3389/frobt.2020.567491. eCollection 2020.

Effective Multi-Mode Grasping Assistance Control of a Soft Hand Exoskeleton Using Force Myography

Muhammad Raza Ul Islam  1 , Shaoping Bai  1
Affiliations

Effective Multi-Mode Grasping Assistance Control of a Soft Hand Exoskeleton Using Force Myography

Muhammad Raza Ul Islam et al. Front Robot AI. .

Abstract

Human intention detection is fundamental to the control of robotic devices in order to assist humans according to their needs. This paper presents a novel approach for detecting hand motion intention, i.e., rest, open, close, and grasp, and grasping force estimation using force myography (FMG). The output is further used to control a soft hand exoskeleton called an SEM Glove. In this method, two sensor bands constructed using force sensing resistor (FSR) sensors are utilized to detect hand motion states and muscle activities. Upon placing both bands on an arm, the sensors can measure normal forces caused by muscle contraction/relaxation. Afterwards, the sensor data is processed, and hand motions are identified through a threshold-based classification method. The developed method has been tested on human subjects for object-grasping tasks. The results show that the developed method can detect hand motions accurately and to provide assistance w.r.t to the task requirement.

Keywords: FSR sensor band; exoskeleton control; grasping assistance; human intention detection; soft hand exoskeletons.

PubMed Disclaimer

Figures

Figure 1
Figure 1
(A) FSR sensors placement inside sensor bands SBw and SBe and (B) SEM Glove and sensor bands placement on forearm.
Figure 2
Figure 2
Net output voltage measured from sensor bands for opening and closing of hand (A) without grasping and (B) grasping an object.
Figure 3
Figure 3
Flow chart of multi-mode control method.
Figure 4
Figure 4
Gestures used in calibration and training stage. (A) open hand gesture to calibrate SBw, (B) close hand gesture to calibrate SBe, and (C) rest state gesture to collect data for threshold determination.
Figure 5
Figure 5
FSR data for hand closing gesture (A) before and (B) after calibration.
Figure 6
Figure 6
FSR feature dataset for grasping objects of different sizes and weights. (A) RMS and (B) slope.
Figure 7
Figure 7
Classification of TP, TN, FP, and FN samples.
Figure 8
Figure 8
Objects of different shape and weight that are grasped during task identification experiment, (A) empty cup, (B) aluminum bar, and (C) solid metal cylinder.
Figure 9
Figure 9
Tasks performed during (A) the whole span of time, (B) opening and closing of the hand, and (C) grasping object B.
Figure 10
Figure 10
Results of single instances (A) open/close, grasping objects (B) A, (C) B, and (D) C, shown in Figure 8.
Figure 11
Figure 11
Results calculated for each subject individually (A) precision, (B) recall, (C) F1-score, and (D) accuracy.
Figure 12
Figure 12
Average results of each performance measure w.r.t each task. Accuracy plot is shown normalized between 0 and 1.
Figure 13
Figure 13
Three placements of sensor bands, (A) two FSR1 from SBe and SBw are aligned with brachioradialis and near insertion of brachioradialis, (B) aligned with brachioradialis and flexor carpi ulnaris, (C) aligned with palmaris longus and near insertion of brachioradialis.
Figure 14
Figure 14
Hand motion detection with three placements of the sensor bands, (A) with placement A, (B) with placement B, (C) with placement C.
Figure 15
Figure 15
Block diagram of the exoskeleton control.
Figure 16
Figure 16
Hand exoskeleton control results: (A) task identified, (B) MCI force measured from sensor band placed near elbow joint, and (C) assistance force provided by SEM Glove.
Figure 17
Figure 17
History of task performed, average MCI forces, and grasping forces measured by SEM Glove.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Anam K., Rosyadi A. A., Sujanarko B., Al-Jumaily A. (2017). Myoelectric control systems for hand rehabilitation device: a review, in 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), 1–6. 10.1109/EECSI.2017.8239091 - DOI
    1. Arteaga M. V., Castiblanco J. C., Mondragon I. F., Colorado J. D., Alvarado-Rojas C. (2020). EMG-driven hand model based on the classification of individual finger movements. Biomed. Signal Process. Control 58:101834 10.1016/j.bspc.2019.101834 - DOI
    1. Asif A. R., Waris A., Gilani S. O., Jamil M., Ashraf H., Shafique M., et al. . (2020). Performance evaluation of convolutional neural network for hand gesture recognition using EMG. Sensors 20:1642. 10.3390/s20061642 - DOI - PMC - PubMed
    1. Bullock I. M., Zheng J. Z., De La Rosa S., Guertler C., Dollar A. M. (2013). Grasp frequency and usage in daily household and machine shop tasks. IEEE Trans. Hapt. 6, 296–308. 10.1109/TOH.2013.6 - DOI - PubMed
    1. Cho E., Chen R., Merhi L.-K., Xiao Z., Pousett B., Menon C. (2016). Force myography to control robotic upper extremity prostheses: a feasibility study. Front. Bioeng. Biotechnol. 4:18. 10.3389/fbioe.2016.00018 - DOI - PMC - PubMed

LinkOut - more resources