|
Cognitive signals for non-invasive brain-machine interaction| old_uid | 7437 |
|---|
| title | Cognitive signals for non-invasive brain-machine interaction |
|---|
| start_date | 2009/10/12 |
|---|
| schedule | 11h |
|---|
| online | no |
|---|
| location_info | salle de conférence |
|---|
| summary | A non-invasive brain-machine interface (BMI) is a system that translates user’s intent, coded by spatiotemporal neural activity (usually EEG), into a control signal without using activity of any muscles or peripheral nerves. In this talk I will present our research aimed at the development of asynchronous BMIs. It means that users control such devices spontaneously and at their own pace, by learning to voluntarily control specific electroencephalogram (EEG) features measured from the scalp. This approach relies upon machine learning techniques to maximize the separability between different mental patterns, as well as a shared control architecture where different levels of intelligence are implemented in the robotic device in order to assist the human user in the execution of the task,
In the second part of this talk I will discuss a new brain interaction approach based on EEG correlates of cognitive states. In this approach, the user only monitors the performance of a semi-autonomous system. This system carries out its task automatically (e.g., a wheelchair navigating autonomously) and occasionally receives corrective signals derived from the user’s EEG whenever the operator wants to deliver key decisions or improve the system’s performance. In particular, we are interested in exploring the use of event-related potentials related to error detection (ErrP) and slow cortical potentials related to the anticipation of future events (i.e., contingent negative variation, CNV). This approach overcomes on of the limitations of current BCI systems which are highly demanding in terms of cognitive attention and effort, since users are required to continuously generate mental commands for the brain-actuated device. |
|---|
| responsibles | Vezoli |
|---|
| |
|