The Technology
Non-invasive Brain Computer Interfaces (BCIs) measure electroencephalography (EEG) potentials from the scalp and interpret them, through signal processing and machine learning, to make decisions and operate computers or other external devices. However, practical applications of BCIs are hampered due to their high error-rate.
A promising strategy for improving BCI accuracy is to detect error-related potentials (ErrPs), which are EEG potentials evoked in the brain when making or observing errors. ErrPs offer a valuable insight into investigating how the brain processes errors. Error-related potentials can be monitored to categorize actions as correct or erroneous. Detection of erroneous movement can be used to improve BCIs, detect task-relevant erroneous movements, identify instances of motor errors, and enhance motor training, rehabilitation, and other applications. Common approaches involve binary classification of error-related potentials (error/no error or error A/error B).
A novel approach has been developed to classify the type of error from ErrPs and to determine how to correct actions that elicited those ErrPs. Error detection and classification is critical fordeveloping self-corrected BCIs, where the detected type of error is used to correct the corresponding mistake made by the BCI. This is critical since the main challenge in using BCIs is their low accuracy.
The new approach has specific advantage for automatic annotation of erroneous and dangerous situations by detecting error-related potentials in observers. it enables real time or video observations and can facilitate video annotation. Most importantly, it allows synchronization between the event and its annotation and the reduced mental load on the observer compared to manual annotation.
Advantages
- Accurate and well-synchronized annotation
- Less strenuous process
Applications and Opportunities
- Self-correcting BCIs for commanding different applications including virtual reality interfaces and augmented reality headsets.
- Assistive robotics.
- Robotic neuro-rehabilitation, where the robotic help is conditioned on motor-related and error-related potentials. Cognitive and other types of training, where it is important to determine whether the trainee was aware of his/her own errors.
- Annotation of erroneous/dangerous situations for training AI and ML systems, including training of autonomous driving, and virtual trainers.
Business Development Contacts