NeuroBots

BRAIN-CONTROLLED INTELLIGENT ROBOTIC DEVICES


Relevant for Research Area

B - Core Technologies


Abstract

Brain-controlled prosthetic devices are a powerful tool for allowing paralyzed or otherwise bodily disabled individuals to regain their freedom to interact naturally with the world. Yet as the systems to get controlled become more and more complex, from single legs or arms over mobile robotic platforms to humanoid surrogates, ways to deal with the increased cognitive load and facilitate control will need to be found. The central idea of this project is that by enhancing a prosthetic device with a certain degree of autonomy and adaptivity, control is possible on a higher cognitive level rather than on the lower level of raw motor signals. Therefore, the aim of this interdisciplinary joint project is to develop methods and technologies for brain-controlled intelligent autonomous robotic devices like robot arms or mobile platforms. This makes it an important building block and demonstrator of LiNC, which is one of the two development platforms within BrainLinks-BrainTools. On the input side, brain signals will be used to control this system to express the intention of the user, on the output side, the intention will be transmitted to the robot system. Examples of such intentions will be in the whole range of orders like \grasp the leftmost object on the table" to \get me a coke from the fridge". Building on the results of the successful exploratory project of the same name, the project will continue to improve the techniques needed to achieve a fully usable intelligent prosthesis. Such a system will require further research on both sides of the interface, i.e. the interpretation of brain signals to control the choice of the desired intention as well as research on the robotic side regarding the autonomy of the system. In addition to the non-invasive techniques (EEG) used during the exploratory stage, the present project will employ intracranial EEG both in healthy subjects and in paralyzed patients. On the computer science side, research will be focused on autonomy and reliability of robotic systems. In particular, research in the following areas will be needed: sensory perception of natural environments, closed-loop control of robots, learning and adaptivity, planning, robotic interaction with humans, as well as assurance of safety and reliability conditions.