Description of field of research

This project explores the field of humanoid robots as they offer great advantages in terms of flexibility and versatility. In this regard, it has been hypothesized that anthropomorphic embodiment is required for natural human-robot interaction and to model human behaviour [1].

iCub is a humanoid platform that was developed for research to study cognition in humans and artificial systems. It was designed to be used as a testbed for algorithms and theories modelling aspects of human cognition, including learning, perception and motor control [2].

Research Area

Robotics | Machine learning | Artificial intelligence

Robotics lab at CSE. J17 room 510.

At the end of the project, it is expected the student will develop algorithms to test different learning capabilities in the iCub robot such as sensorimotor coordination, contextual affordances, and decision-making in dynamic environments.

  1. Natale, L., Bartolozzi, C., Nori, F., Sandini, G., & Metta, G. (2021). iCub. arXiv preprint arXiv:2105.02313.
  2. Zhao, J., Risi, N., Monforte, M., Bartolozzi, C., Indiveri, G., & Donati, E. (2020). Closed-loop spiking control on a neuromorphic processor implemented on the iCub. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 10(4), 546-556.
  3. https://www.science.org/doi/full/10.1126/scirobotics.aaq1026