Brain-Computer Interface (BCI) are devices that enable its users to interact with computers by mean of brain-activity only, this activity being generally measured by ElectroEncephaloGraphy (EEG). A typical example of a BCI would be a system in which a user can imagine movements of his left or right hand in order to move a cursor on a computer screen towards the left or right respectively. BCI systems are a very promising tool for severely paralysed people such as those suffering from late-stage Amyotrophic Lateral Sclerosis (ALS). Indeed, for those people, BCI can be the only mean of communication with the external world. Some BCI research groups have actually designed BCI prototypes with which disabled people could operate a text editor or a prosthesis. However, BCI can also be a promising interaction tool for healthy people, with several potential applications in the field of multimedia, virtual reality or video games among many other potential applications.
While they are very promising for numerous applications, BCI remain barely used outside laboratories, notably due to their lack of robustness and practicality. My long-term research objective is to designing practical BCI technologies that could be used outside the lab. To do so, I target 3 main research directions:
Although Brain-Computer Interfaces (BCI) have demonstrated their tremendous potential in numerous applications, they are still mostly prototypes, not used outside laboratories. This is mainly due to the following limitations:
As part of our research on EEG-based BCI, we notably aim at addressing these limitations by designing robust EEG signal processing and classification tools with minimal calibration times, in order to design practical BCI systems, usable and useful outside laboratories. To do so we explore the design of alternative features and robust spatial filtering algorithms to make BCI more robust to noise and non-stationarities, as well as more accurate. We also explore artificial EEG data generation and user-to-user data transfer to reduce calibration times.
Poor BCI performances are partly due to imperfect EEG signal processing algorithms but also to the user, who may not be able to produce reliable EEG patterns. Indeed, BCI use is a skill, requiring the user to be properly trained to achieve BCI control. If he/she cannot perform the desired mental commands, no signal processing algorithm could identify them. Therefore, rather than improving EEG signal processing alone, an interesting research direction is to also guide users to learn BCI control mastery. Our current work aims at addressing this objective. We notably explore theoretical models and guidelines from psychology and cognitive sciences about human learning in order to improve BCI training protocols. Our studies notably illustrate the theoretical limitations of current standard BCI training approaches and the need for alternative approaches. We also perform some actual experiments to further illustrate some limitations of current BCI training protocols and try to understand and analyse them. We notably study which users’ profile (personality and cognitive profile) fail or succeed at learning BCI control. Finally, we explore new feedback types and new EEG visualization techniques in order to help users to learn BCI control skills more efficiently. These new feedback and visualizations notably aim at providing BCI users with more information about their EEG patterns, in order to identify more easily relevant BCI control strategies, as well as motivating and engaging them in the learning task.
Can new feedback improve user learning of a Brain-Computer Interface skill?
Recently, physiological computing has been shown to be a promising companion to Human-Computer Interfaces (HCI) in general, and to 3D User Interfaces (3DUI) in particular, in several directions. Among them, in our group, we are first interested in using various physiological signals, and notably EEG signals, as a new tool to assess objectively the ergonomic quality of a given 3DUI, to identify where and when are the pros and cons of this interface, based on the user’s mental state during interaction. For instance, estimating the user’s mental workload during interaction can give insights about where and when the interface is cognitively difficult to use. This could be useful for 2D HCI in general, and even more for 3DUI. Indeed, in a 3DUI, the user perception of the 3D scene – part of which could potentially be measured in EEG, is essential. Moreover, the usual need for a mapping between the user inputs and the corresponding actions on 3D objects make 3DUI and interaction techniques more difficult to assess and to design. Beyond evaluation alone, physiological computing could also improve existing 3DUI by increasing the symbiosis between the user and the interface, e.g., for visualization and analysis of large amounts of (3D) data.
Using EEG to assess the ergonomic qualities of 3D User Interfaces
As haptics did a few years ago, BCI have the potential to completely revolutionize the way people interact with applications such as Virtual Reality (VR) applications. However, a considerable research effort must be done in order to actually use BCI for practical VR applications. Indeed, current BCI systems provide the user with a limited number of commands, thus impeding natural and efficient interaction. Also, VR is a specific kind of feedback which may affect the user and as such his mental states. As such, what are the effects of this feedback must be also studied. My research in this topic is dedicated to the design of new interaction techniques, to the evaluation of such techniques and to the study of the user experience while using a BCI for interacting with a VR application.
For a complete list of my publications, you can go there.
For interesting papers about BCI in general, you can go there.