Detail of the student project

Topic:Seberozpoznání robota v zrcadle
Department: Vidění pro roboty a autonomní systémy
Supervisor:Mgr. Matěj Hoffmann, Ph.D.
Announce as:Diplomová práce, Bakalářská práce, Semestrální projekt
Description:Motivated by studies in children and animals on self-recognition in the mirror, the goal of the project is to replicate similar behavior in a humanoid robot. Our hypothesis is that any agent can pass the mirror test through unconscious processes based on sensorimotor integration. The goal is to enable the Nao robot to pass the mirror test, i.e. reach for a salient object (such as Post-it) on its face. Next to using the camera input of the robot, we will also employ the artificial skin on the robot face to aid localization.
The main steps are the following:
1. Familiarization with the Nao robot
2. Learning the face in the mirror and detecting novelty when another object is present on the face.
3. Collecting dataset relating novelty region of interest in mirrored image and tactile activations.
4. If time allows: Reaching for the stimulus.
Bibliography:Hart, J. W. (2014), 'Robot self-modeling', PhD thesis, Yale University.

Gold, K., & Scassellati, B. (2007). A Bayesian Robot That Distinguishes" Self" from" Other". In Proceedings of the Annual Meeting of the Cognitive Science Society (Vol. 29, No. 29).

Hoffmann, M.; Chinn, L. K.; Somogyi, E.; Heed, T.; Fagard, J.; Lockman, J. J. & O'Regan, J. K. (2017), Development of reaching to the body in early infancy: From experiments to robotic models, in 'Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)', pp. 112-119.
Responsible person: Petr Pošík