Brain Mediated Human-Robot Interaction

A half-day tutorial at the
 March 6-9, 2011, EPFL, Lausanne, Switzerland



The use of brain-generated signals for human-robot interaction has gained increasing attention in the last years. Indeed brain-controlled robots and neuroprostheses can potentially be employed to substitute motor capabilities (e.g. brain-controlled prosthetics for amputees or patients with spinal cord injuries); to help in the restoration of such functions (e.g. as a tool for stroke rehabilitation) as well as non-clinical applications like telepresence or entertainment. This half-day tutorial gives an introduction to the field of brain-computer interfaces and presents several design principles required to successfully employ them for robot control.

A non-invasive brain-computer interface (BCI) is a system that translates user’s intent, coded by spatiotemporal neural activity (usually recorded through EEG), into a control signal without using activity of any muscles or peripheral nerves. Current EEG-based BCIs are limited by a low information transfer rate and the low signal to noise ratio of the brain-generated signals. Nevertheless, it has been shown that online asynchronous analysis of spontaneous EEG signals, in combination with statistical machine learning techniques and smart interaction design, is sufficient for allowing humans to do so. Based on the principles of mutual learning and shared control, users convey high level mental commands that the devices interpret and execute in the most appropriate way to achieve the goal. Thus allowing the efficient control of mobile robots (e.g. automated wheelchairs), or neuroprostheses.

Moreover, brain-robot interaction can be enriched by detection of user’s cognitive states. These states may provide information about interaction errors as perceived by the user, as well as fatigue or perception of relevant feedback information. In particular, EEG correlates of error awareness can be used for correcting BCI misclassifications of the user’s intent, as well as be used as a teaching signal to improve the performance of an adaptive device through human supervision. Experiments using simulated and real interaction with mobile robots shows the feasibility of detecting such signals in real time; thus providing an alternative, natural way of interaction to current BCI systems, while reducing the user demands in terms of cognitive attention and effort.

This tutorial will introduce the basic principles for human-robot interaction using brain-computer interfaces and is composed of the following components:

* Introduction to brain-computer interfaces
* Feature selection and classification techniques
* Shared control
* Cognitive signals for human-robot interaction

Keywords: Neurorobotics, Neuroprostheses, Brain-machine interface, Shared control

Target Audience

The intended audience is both novices and experts in human-robot interaction systems. This tutorial is appropriate for students and researchers in the engineering and computer science disciplines. No prior experience in neuroscience or brain signal analysis is required. 


Perrin, X., Chavarriaga, R., Colas, F., Siegwart, R., and Millán, J. d. R. (2010). Brain-coupled Interaction for Semi-autonomous Navigation of an Assistive Robot. Robotics and Autonomous Systems.

Tonin, L., Leeb, R., Tavella, M., Perdikis, S., and Millán, J. d. R. (2010). The Role of Shared-Control in BCI-based Telepresence. In 2010 IEEE International Conference on Systems, Man, and Cybernetics.

Galán, F., Nuttin, M., Lew, E., Ferrez, P. W., Vanacker, G., Philips, J., and Millán, J. d. R. (2008). A Brain-Actuated Wheelchair: Asynchronous and Non-Invasive Brain-Computer Interfaces for Continuous Control of Robots. Clinical Neurophysiology, 119(9):2159-2169.

Perrin, X., Chavarriaga, R., Ray, C., Siegwart, R., and Millán, J. d. R. (2008). A Comparative Psychophysical and EEG Study of Different Feedback Modalities for HRI. In 3rd ACM/IEEE Conf on Human-Robot Interaction (HRI08).


Participants should register through the the conference website


Ricardo Chavarriaga, José del R. Millán
Defitech Foundation Chair in Non-invasive Brain-machine Interface
Ecole Polytechnique Fédérale de Lausanne (EPFL)