Publikation

Embedded Brain Reading

Elsa Andrea Kirchner

Poster DFKI GmbH, Universität Bremen DFKI Documents (D) 14-07 11/2014.

Abstrakt

Embedded Brain Reading (eBR) empowers a human-machine interface (HMI), which can be a robotic system, to infer the human’s intention and hence her/his upcoming interaction behavior based on the context of the interaction and the human’s brain state. Decoding of brain activity into information on the user’s brain state must be done online and in single trial. This can be achieved by the application of advanced signal and machine learning methods. The upcoming interaction behavior, which is inferred by eBR, can be supported even before its execution is detected and even in case that the user is disabled to execute the behavior herself or himself. For eBR brain activity is analyzed by systems that are embedded into the robotic system or interface. Moreover, for eBR brain signals are not used alone. Instead, multimodal signal analysis, i.e., embedded brain signal analysis, is applied in most cases to improve performance, reliability and to adapt eBR to the application or user demands. Depending on the application, eBR enables implicit or explicit support while avoiding extra cognitive demands on the user. Applications of eBR are thus widespread from passive user support to the active control of machines, e.g., in the field of rehabilitation robotics.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence