The idea of controlling machines not by manual control, but by mere "thinking" (i.e., the brain activity of human subjects) has fascinated humankind since ever, and researchers working at the crossroads of computer science, neurosciences, and biomedical engineering have started to develop the first prototypes of brain-machine interfaces (BMI) over the last decade or so. Thus, researchers have been able to train monkeys, who had implanted tens of microelectrodes in their brain, to control a robot arm. Human subjects, on their side, have shown the possibility to drive a mobile robot between rooms in a house model using non-invasive EEG recordings .

Although these promising first results are attracting significant attention from an increasing number of research laboratories around the world, most of the issues being explored are related to "augmented communication" where fast decision-making is not critical as it is the case for real-time control of robotics devices and neuroprosthesis. The latter kind of applications is the most challenging for BMI and it is the goal of this IP. In particular, we will explore mental teleoperation of a mobile robot based on non-invasive brain activity related to motor tasks (i.e., subjects imagine natural movements of their body that are translated into similar actions of the robot) and multiple modalities of feedback (visual, auditory, haptic and vestibular).

It is worth noting that, despite BMI is a field still in its infancy and brain signals cannot be easily combined with other interaction modalities by the time being, the long-term vision behind this IM2.BMI is allow people convey their intents through a conscious control of their brain activity in combination with other sensory interaction modalities (e.g., speech, gestures) and physiological signals (e.g., electromyogram, skin conductivity). To do so it is necessary to improve the performance of BMIs until they reach similar levels to other modalities. In addition, by putting a strong emphasis on the analysis and understanding of brain patterns associated to multiple modalities of feedback signals, work in this IM2.BMI may help design better interaction systems.