Related Experiment Video
Updated: Sep 1, 2025
06:34
A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
Published on: July 7, 2023
2.5K
A Comprehensive Review of Endogenous EEG-Based BCIs for Dynamic Device Control
Natasha Padfield1, Kenneth Camilleri1,2, Tracey Camilleri2
1Centre for Biomedical Cybernetics, University of Malta, MSD 2080 Msida, Malta.
Sensors (Basel, Switzerland)
|August 12, 2022
Summary
Brain-computer interfaces (BCIs) using electroencephalogram (EEG) offer intuitive control for assistive devices. This review explores challenges and advancements in EEG-based BCIs for controlling robots and mobility aids, focusing on signal stability and classification.
Area of Science:
- Neuroscience
- Robotics
- Biomedical Engineering
Background:
- Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) offer a promising avenue for individuals with severe mobility impairments.
- Endogenous BCIs, relying on user-generated commands without external stimuli, aim for intuitive device control.
Purpose of the Study:
- To review BCI-controlled dynamic devices, including exoskeletons, wheelchairs, mobile robots, and robotic arms.
- To discuss challenges in EEG signal processing, classification, and stability for endogenous BCIs.
- To explore advancements in machine learning and deep learning for BCI control.
Main Methods:
- Systematic review of BCI-controlled dynamic device literature published until the end of 2021.
- Analysis of EEG paradigms, shared control strategies, and signal stabilization techniques.
- Evaluation of traditional and deep learning methods for EEG signal classification.
Main Results:
- BCIs are being developed to control complex physical devices requiring navigation and fine motor skills.
- Achieving robust classification performance and stable EEG decoder outputs remain significant challenges.
- Shared control, signal stabilization, and advanced machine learning show potential for improving BCI functionality.
Conclusions:
- EEG-based BCIs hold significant potential for enhancing independence in individuals with motor disabilities.
- Further research is needed to address signal instability and improve classification accuracy for real-world applications.
- Future work should focus on enhancing user experience and exploring novel control strategies for dynamic devices.
