anticache

ICS, CNE, HCR Doctoral Seminar on "On the use of EEG-based error potentials for mediating co-adaptation in human-robot interaction"

07.01.2019


ICS, CNE, HCR Doctoral Seminar on "Neuro-ergonomic HRI: On the use of EEG-based error potentials for mediating co-adaptation in human-robot interaction" by Stefan Ehrlich, Chair for Cognitive Systems (ICS)

9 January 2019 at 16:30, ICS Karlstraße 45, 6. Floor, room 6009

Abstract: Successful collaboration requires interaction partners to constantly monitor and predict each other’s behavior to establish shared representations of goals and intentions. In human-robot interaction (HRI) this aspect is particularly challenged by ongoing technical limitations in robot perception and reasoning about the human partner’s behavior and underlying intentions. The human partner on the other hand is not just capable of judging the robot behavior but also to oversee the overall interaction performance. Studies have demonstrated that erroneous or unexpected robot actions engage error-/performance processes in the human partner’s brain, which manifest as error-related potentials (ErrPs), observable and reliably decodeable using non-invasive electroencephalography (EEG). Real-time decoded ErrPs constitute a valuable source of information about the human partner’s expectations and subjective preferences and therefore could serve as a useful complement to existing methods for validating and improving HRI or human-machine interaction in general. This talk introduces the current state-of-the-art along this line of research and follows with the presentation of our recent study demonstrating the usability of ErrPs for mediating co-adaptation in the context of a simplified social interactive human-robot interaction task. The second part of the talk is concerned with computational modelling of the human partner’s decision-making behavior in the given context. The latter serves as a simulation-based approach to disentangle potential factors influencing convergence in ErrP-based human-robot co-adaptation.

References:

Ehrlich, S. K., & Cheng, G. (2018). Human-agent co-adaptation using error-related potentials. Journal of neural engineering, 15(6), 066014.

Ehrlich, S. K., & Cheng, G. (2018). A Feasibility Study for Validating Robot Actions Using EEG-Based Error-Related Potentials. International Journal of Social Robotics, 1-13.

Ehrlich, S., & Cheng, G. (2016, November). A neuro-based method for detecting context-dependent erroneous robot action. In Humanoid Robots (Humanoids), 2016 IEEE-RAS 16th International Conference on (pp. 477-482). IEEE.

For more info please visit: http://web.ics.ei.tum.de/~ehrlich/ICS_seminar/index.htm