Design and Optimization of a BCI-Driven Telepresence Robot Through Programming by Demonstration

Research output: Contribution to journalArticle

Abstract

Improving the life quality of people with severe motor paralysis has a significant impact on restoring their functional independence to perform activities of daily living (ADL). Telepresence is a subfield of the robotic-assisted route, where human plays the role of an operator, sending high-level instructions to an assistive robot while receiving sensory feedback. However, for severely motor-impaired people, conventional interaction modalities may not be suitable due to their complete paralysis. Thus, designing alternative ways of interaction such as Brain-Computer Interfaces (BCI) is essential for a telepresence capability. We propose a novel framework that integrates a BCI system and a humanoid robot to develop a brain-controlled telepresence system with multimodal control features. In particular, the low-level control is executed by Programming by Demonstration (PbD) models, and the higher-level cognitive commands are produced by a BCI system to perform vital ADLs. The presented system is based on real-time decoding of attention-modulated neural responses elicited in the brain electroencephalographic signals and generating multiple control commands. As a result, the system allows a user to interact with a humanoid robot while receiving auditory and visual feedback from the robot's sensors. We validated our system across ten subjects in a realistic scenario. The experimental results show the feasibility of the approach in the design of a telepresence robot with high BCI decoding performances.
Original languageEnglish
Pages (from-to)111625
Number of pages111636
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - Aug 5 2019

Fingerprint

Brain computer interface
Demonstrations
Robots
Decoding
Brain
Sensory feedback
Level control
Robotics
Feedback
Sensors

Cite this

Design and Optimization of a BCI-Driven Telepresence Robot Through Programming by Demonstration. / Abibullaev, Berdakh; Zollanvari, Amin; Saduanov, Batyrkhan; Alizadeh, Tohid.

In: IEEE Access, Vol. 7, 05.08.2019, p. 111625.

Research output: Contribution to journalArticle

@article{06bce68202ba4590a08272983f1a0fc7,
title = "Design and Optimization of a BCI-Driven Telepresence Robot Through Programming by Demonstration",
abstract = "Improving the life quality of people with severe motor paralysis has a significant impact on restoring their functional independence to perform activities of daily living (ADL). Telepresence is a subfield of the robotic-assisted route, where human plays the role of an operator, sending high-level instructions to an assistive robot while receiving sensory feedback. However, for severely motor-impaired people, conventional interaction modalities may not be suitable due to their complete paralysis. Thus, designing alternative ways of interaction such as Brain-Computer Interfaces (BCI) is essential for a telepresence capability. We propose a novel framework that integrates a BCI system and a humanoid robot to develop a brain-controlled telepresence system with multimodal control features. In particular, the low-level control is executed by Programming by Demonstration (PbD) models, and the higher-level cognitive commands are produced by a BCI system to perform vital ADLs. The presented system is based on real-time decoding of attention-modulated neural responses elicited in the brain electroencephalographic signals and generating multiple control commands. As a result, the system allows a user to interact with a humanoid robot while receiving auditory and visual feedback from the robot's sensors. We validated our system across ten subjects in a realistic scenario. The experimental results show the feasibility of the approach in the design of a telepresence robot with high BCI decoding performances.",
author = "Berdakh Abibullaev and Amin Zollanvari and Batyrkhan Saduanov and Tohid Alizadeh",
year = "2019",
month = "8",
day = "5",
doi = "10.1109/ACCESS.2019.2933268",
language = "English",
volume = "7",
pages = "111625",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Design and Optimization of a BCI-Driven Telepresence Robot Through Programming by Demonstration

AU - Abibullaev, Berdakh

AU - Zollanvari, Amin

AU - Saduanov, Batyrkhan

AU - Alizadeh, Tohid

PY - 2019/8/5

Y1 - 2019/8/5

N2 - Improving the life quality of people with severe motor paralysis has a significant impact on restoring their functional independence to perform activities of daily living (ADL). Telepresence is a subfield of the robotic-assisted route, where human plays the role of an operator, sending high-level instructions to an assistive robot while receiving sensory feedback. However, for severely motor-impaired people, conventional interaction modalities may not be suitable due to their complete paralysis. Thus, designing alternative ways of interaction such as Brain-Computer Interfaces (BCI) is essential for a telepresence capability. We propose a novel framework that integrates a BCI system and a humanoid robot to develop a brain-controlled telepresence system with multimodal control features. In particular, the low-level control is executed by Programming by Demonstration (PbD) models, and the higher-level cognitive commands are produced by a BCI system to perform vital ADLs. The presented system is based on real-time decoding of attention-modulated neural responses elicited in the brain electroencephalographic signals and generating multiple control commands. As a result, the system allows a user to interact with a humanoid robot while receiving auditory and visual feedback from the robot's sensors. We validated our system across ten subjects in a realistic scenario. The experimental results show the feasibility of the approach in the design of a telepresence robot with high BCI decoding performances.

AB - Improving the life quality of people with severe motor paralysis has a significant impact on restoring their functional independence to perform activities of daily living (ADL). Telepresence is a subfield of the robotic-assisted route, where human plays the role of an operator, sending high-level instructions to an assistive robot while receiving sensory feedback. However, for severely motor-impaired people, conventional interaction modalities may not be suitable due to their complete paralysis. Thus, designing alternative ways of interaction such as Brain-Computer Interfaces (BCI) is essential for a telepresence capability. We propose a novel framework that integrates a BCI system and a humanoid robot to develop a brain-controlled telepresence system with multimodal control features. In particular, the low-level control is executed by Programming by Demonstration (PbD) models, and the higher-level cognitive commands are produced by a BCI system to perform vital ADLs. The presented system is based on real-time decoding of attention-modulated neural responses elicited in the brain electroencephalographic signals and generating multiple control commands. As a result, the system allows a user to interact with a humanoid robot while receiving auditory and visual feedback from the robot's sensors. We validated our system across ten subjects in a realistic scenario. The experimental results show the feasibility of the approach in the design of a telepresence robot with high BCI decoding performances.

U2 - 10.1109/ACCESS.2019.2933268

DO - 10.1109/ACCESS.2019.2933268

M3 - Article

VL - 7

SP - 111625

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -