english only
EPFL > STI > IMT > LASA > Research > Shared control
Human-Robot Interaction
Machine Learning with Application to Robotics
Fast Adaptive Control
Dexterous Manipulation and Grasping
Computational Neuroscience and Cognitive Modeling

Computational Neuroscience and Cognitive Modeling

Artificial agents which learn through imitation and social interactions provide important insights for human social cognition. We focus on modelling the cognitive mechanisms involved in social interaction, such as intention attribution and agency. Our research enables us to design human-like robotic behaviors to reach more realistic human-robot interactions.

We develop approaches and applications:
  • propose developmental models to explain social impairments related to schizophrenia
  • model and understand social and interactive behavior using robotic platforms and computational models
  • Social and Therapeutic Robotics

    Social robots are a promising tool to provide therapeutic frameworks for individuals with social impairments such as autism and schizophrenia. In collaboration with psychiatrists specialized in social impairments, we focus on researching and providing impairment-specific social behaviors for robots.

    We develop approaches and applications:
  • use the iCub to contrast the effect of social (human-like) and non-social (computer-displayed) feedback on schizophrenic patients
  • develop and test an innovative rehabilitation method to improve relational deficits by
  • use humanoid robotics and virtual reality
  • Related publications

    I. Batzianoulis, S. El Khoury, E. Pirondini, M. Coscia and S. Micera et al. EMG-based decoding of grasp gestures in reaching-to-grasping motions, in Robotics and Autonomous Systems, vol. 91, p. 59-70, 2017.
    I. Batzianoulis, S. El-Khoury, S. Micera and A. Billard. EMG-Based Analysis of the Upper Limb Motion. 10nth ACM/IEEE International Conference on Human Robot Interaction, Portland, Oregon, USA, HRI'15 Extended Abstracts, 2015.
    S. El Khoury, I. Batzianoulis, C. Antuvan, S. Contu and L. Masia et al. EMG-based learning approach for estimating wrist motion. 37th International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), Milan, Italy, 2015.