Related Experiment Video
Updated: May 14, 2026
06:11
Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients
Published on: April 18, 2025
First study towards linear control of an upper-limb neuroprosthesis with an EEG-based Brain-Computer Interface.
Javier Pascual1, Francisco Velasco-Alvarez, Klaus-Robert Muller
1Machine Learning Group, Computer Science Faculty, Berlin Institute of Technology, Berlin, Germany.
Summary
Healthy subjects achieved linear control of an upper-limb neuroprosthesis using a non-invasive Brain Computer Interface (BCI) and motor imagery (MI). Performance was maintained with neuromuscular electrical stimulation (NMES), though user experience varied.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Rehabilitation Technology
Background:
- Brain-Computer Interfaces (BCIs) offer potential for restoring function in individuals with motor impairments.
- Motor Imagery (MI) is a non-invasive BCI control strategy.
- Neuromuscular Electrical Stimulation (NMES) can activate muscles for functional movement.
Purpose of the Study:
- To investigate the feasibility of linear control of an upper-limb neuroprosthesis using an MI-based BCI.
- To evaluate the impact of NMES on BCI performance and user experience.
Main Methods:
- Healthy participants used a non-invasive MI-BCI to control an upper-limb neuroprosthesis.
- The BCI required discrimination of two MI classes with >80% reliability for linear control.
- NMES was applied to the upper limb during the BCI task.
Main Results:
- Linear control of the neuroprosthesis was achieved via MI-BCI.
- No significant performance degradation was observed when NMES was used compared to MI alone.
- User experiences with NMES varied, with some reporting positive reinforcement and others reporting concentration difficulties.
Conclusions:
- MI-BCI enables linear control of NMES-driven neuroprostheses in healthy individuals.
- NMES integration does not significantly impair BCI task performance.
- Subjective user experience with NMES during BCI control is highly variable and warrants further investigation.
