Brain-computer interface technique to assist neurorehabilitation
2021
University of Bath, Bath, United Kingdom
Electroencephalography (EEG)-based brain-computer interfaces (BCIs) have been used in the control of robotic arms. The performance of non-invasive BCIs may not be satisfactory due to the poor quality of EEG signals, so shared control strategies were tried as an alternative solution. In this paper, a brain-actuated robotic arm system based on a novel shared control model with a hybrid BCI scheme was proposed. Specifically, a shared controller was built, which dynamically integrated the human intention with machine autonomy and intelligently optimized the robotic arm control process based on the actual control context. The adoption of the hybrid BCI scheme with SI and PI in this study aimed to extend the dimensionality of BCI control and optimize the BCI resources (e.g. decoding computing power, GUI occupation) for the system. The experiment results showed in the current system, all eleven subjects could pick the desired target from
multiple objects under shared control and ten could complete the pick-place task. Moreover, the experiment results also demonstrated that shared control outperformed the pure BCI control, indicating shared control may be a promising method for brain-actuated systems.
This technology could improve the activities of daily living of people with disabilities.
A brain-actuated robotic arm system using noninvasive hybrid brain–computer interface and shared control strategy
Dingguo Zhang
Linfeng Cao et al. Journal of Neural Engineering 2021 [1]
Physicians Committee for Responsible Medicine [2]
Added on: 09-12-2022
[1] https://iopscience.iop.org/article/10.1088/1741-2552/abf8cb[2] https://www.pcrm.org/news/ethical-science/brain-computer-interface-technique-assist-neurorehabilitation