Transferring BCI skills to successful application controls

The goal of our research is to enable various end-users to control applications by using a brain-computer interface (BCI). Since applications–like telepresence robots, wheelchairs or text entry systems–are quite demanding a good level of BCI control is needed. However, little is known on how much training is needed to achieve such a level. A second open issue is, if this can be done at rehabilitation clinics or user-centers, without BCI experts present? In this work we wanted to train BCI-naïve end-users within 10 days to successfully control such applications and present results of 23 severely motor-disabled participants.

Transferring brain-computer interfaces beyond the laboratory: Successful application control for motor-disabled users

Andrea Biasiucci, Tom Edward Carlson, Marco Creatura, Robert Leeb, Alberto Molina Arribere, Serafeim Perdikis, Michele Tavella, Luca Tonin

OBJECTIVES: Brain-computer interfaces (BCIs) are no longer only used by healthy participants under controlled conditions in laboratory environments, but also by patients and end-users, controlling applications in their homes or clinics, without the BCI experts around. But are the technology and the field mature enough for this? Especially the successful operation of applications –like text entry systems or assistive mobility devices such as tele-presence robots– requires a good level of BCI control. How much training is needed to achieve such a level? Is it possible to train naïve end-users in 10 days to successfully control such applications? METHODS AND MATERIALS: In this work, we report our experiences of training 24 motor-disabled participants at rehabilitation clinics or at the end-users’ homes, without BCI experts present. We also share the lessons that we have learned through transferring BCI technologies from the lab to the user's home or clinics. RESULTS: The most important outcome is that fifty percent of the participants achieved good BCI performance and could successfully control the applications (tele-presence robot and text-entry system). In the case of the tele-presence robot the participants achieved an average performance ratio of 0.87 (max. 0.97) and for the text entry application a mean of 0.93 (max. 1.0). The lessons learned and the gathered user feedback range from pure BCI problems (technical and handling), to common communication issues among the different people involved, and issues encountered while controlling the applications. CONCLUSION: The points raised in this paper are very widely applicable and we anticipate that they might be faced similarly by other groups, if they move on to bringing the BCI technology to the end-user, to home environments and towards application prototype control.

Elsevier2013

Are we ready? Issues in transferring BCI technology from experts to users

Andrea Biasiucci, Tom Edward Carlson, Robert Leeb, Serafeim Perdikis, Michele Tavella, Luca Tonin

Brain-Computer Interfaces (BCIs) are no longer only used by healthy subjects under control conditions in laboratory environments, but by patients controlling applications at their homes, without the BCI experts around. But are the technology and the field mature enough for this? In this work, we want to summarize the experiences gained and the lessons we learned while transferring BCI technologies from the lab to the user's home. These lessons range from pure BCI issues (technical and handling), to common communication problems between different people involved, and lessons encountered while controlling the applications. The points raised are very general and will be faced similarly by other groups, if they move on to bring the BCI technology to the end-user.

Verlag der Technischen Universitaet Graz2011

Moving Brain-Controlled Devices Outside the Lab: Principles and Applications

Ricardo Andres Chavarriaga Lozano, Inaki Asier Iturrate Gil, Robert Leeb, Serafeim Perdikis

This chapter provides an overview of the functionality and the underlying principles of the brain-computer interfaces (BCI) developed by the Chair in Non-Invasive Brain-Machine Interface (CNBI) of the Swiss Federal Institute of Technology (EPFL), as well as exemplary applications where those have been successfully evaluated. Our laboratory mainly develops \emph{non-invasive} BCI systems based on electroencephalographic (EEG) signals and, thus, devoid of medical hazards, real-time, portable, relatively low-cost and minimally obtrusive. Our research is pushing forward \emph{asynchronous} paradigms offering a spontaneous, user-driven and largely ecological interaction. Furthermore, we stand on the \emph{machine-learning} way to BCI with emphasis on personalization, configurability and adaptability, coupled with \emph{mutual learning} training protocols, so that elaborate signal processing and pattern recognition methods are optimally combined with the user's learnable modulation of brain signals towards high and robust performances and universal usability. Additionally, \emph{cognitive mental state} monitoring is employed to shape or refine the interaction. \emph{Shared-control} approaches allow smart, context-aware robotics to complement the BCI channel for more fine-grained control and reduction of the user's mental workload. Last but not least, \emph{hybrid BCI} designs exploit additional physiological signals to augment the BCI modality and enrich the control paradigm, thus also exploiting potential residual capabilities of disabled end-users. The applicability and effectiveness of the aforementioned principles is hereby demonstrated in four exemplary applications evaluated with both able-bodied and motor-disabled end-users. These applications include a hybrid, motor imagery (MI)-based speller, a telepresence robot equipped with shared-control, cognitive mental state monitoring paradigms able to recognize and correct errors, and, finally, a car driving application where a passive BCI enabled on a smart car assists towards increased safety and improved driving experience. Remarkably, our results show that the performance of end-users with disabilities was similar to that of a group of healthy users, who were more familiar with the experiment and the environment. This demonstrates that end-users are able to successfully use BCI technology.