A Brain Controlled Robotic Gait Trainer for Neurorehabilitation

This paper discusses a brain controlled robotic gait
trainer for neurorehabilitation of Spinal Cord Injury (SCI) patients.
Patients suffering from Spinal Cord Injuries (SCI) become unable to
execute motion control of their lower proximities due to degeneration
of spinal cord neurons. The presented approach can help SCI patients
in neuro-rehabilitation training by directly translating patient motor
imagery into walkers motion commands and thus bypassing spinal
cord neurons completely. A non-invasive EEG based brain-computer
interface is used for capturing patient neural activity. For signal
processing and classification, an open source software (OpenVibe)
is used. Classifiers categorize the patient motor imagery (MI) into
a specific set of commands that are further translated into walker
motion commands. The robotic walker also employs fall detection
for ensuring safety of patient during gait training and can act as a
support for SCI patients. The gait trainer is tested with subjects, and
satisfactory results were achieved.

Authors:

• Qazi Umer Jamil
• Abubakr Siddique
• Mubeen Ur Rehman
• Nida Aziz
• Mohsin I. Tiwana

Keywords:

• Brain Computer Interface (BCI)
• gait trainer
• Spinal Cord Injury (SCI)
• neurorehabilitation.

References:

[1] Yip PK, Malaspina A. Spinal cord trauma and the molecular point of
no return. Mol Neurodegener. 2012;7:6. [2] http://www.who.int/mediacentre/news/releases/2013/spinal-cord-injury-
20131202/en/ (Last accessed: 05 June 2018).
[3] http://www.asia-spinalinjury.org/committees/prevention facts.php.
[4] Donovan, William H. ”Spinal cord injurypast, present, and future.” The
Journal of Spinal Cord Medicine 30.2 (2007): 85.
[5] http://www.mayoclinic.org/diseases-conditions/spinal-cord-injury/basics/
treatment/con-20023837 (Last accessed: 05 June 2018).
[6] King, Christine E., et al. ”The feasibility of a brain-computer interface
functional electrical stimulation system for the restoration of overground
walking after paraplegia.” Journal of neuroengineering and rehabilitation
12.1 (2015): 80.
[7] Birbaumer, Niels, and Leonardo G. Cohen. ”Braincomputer interfaces:
communication and restoration of movement in paralysis.” The Journal
of physiology 579.3 (2007): 621-636.
[8] Decety J, Gre‘zes J. Neural mechanisms subserving the perception of
human actions. Trends Cogn Sci 1999;3:172-8.
[9] Cramer, Steven C., et al. ”Effects of motor imagery training after
chronic, complete spinal cord injury.” Experimental brain research 177.2
(2007): 233-242.
[10] https://www.intel.com/content/www/us/en/support/articles/000005985/
mini-pcs/intel-compute-sticks.html (Last accessed: 05 June 2018).
[11] Ang, Kai Keng, and Cuntai Guan. ”Brain-computer interface in stroke
rehabilitation.” (2013).
[12] Nicolas-Alonso, Luis Fernando, and Jaime Gomez-Gil. ”Brain computer
interfaces, a review.” Sensors 12.2 (2012): 1211-1279.
[13] Usakli, Ali Bulent. ”Improvement of eeg signal acquisition: An electrical
aspect for state of the art of front end.” Computational intelligence and
neuroscience 2010 (2010): 12.
[14] https://www.emotiv.com/product/emotiv-epoc-14-channel-mobile-eeg/
tab-description (Last accessed: 05 June 2018).
[15] https://www.trans-cranial.com/local/manuals/10 20 pos man v1 0 pdf.
pdf (Last accessed: 05 June 2018).
[16] http://openvibe.inria.fr/ (Last accessed: 05 June 2018).
[17] G. Pfurtscheller and C. Neuper. Motor imagery and direct braincomputer
communication. proc. of the IEEE, 89(7):11231134, 2001.
[18] http://fourier.eng.hmc.edu/e84/lectures/ActiveFilters/node6.html (Last
accessed: 05 June 2018).
[19] http://openvibe.inria.fr/documentation/1.0.1/Doc BoxAlgorithm Simple
DSP.html (Last accessed: 05 June 2018).
[20] https://github.com/vrpn/vrpn/wiki (Last accessed: 05 June 2018).