CoLoRs Research Group at Osaka University for the the Lifelong Robot Learning Project

Torobo, Erhan Oztop, Emre Ugur

Professor Minoru Asada, administrative director of the Symbiotic Intelligent Systems Center (SisReC) of the Institute for Open and Transdisciplinary Research Initiatives, Associate Professor Emre Uğur, the head of The Cognition, Learning and Robotics (CoLoRs) lab at Bogazici University Computer Engineering Department and Professor Erhan Öztop, who is a Specially Appointed Professor at Osaka University in the Symbiotic Intelligent Systems Center (SisReC) of Institute for Open and Transdisciplinary Research Initiatives (OTRI) and co-directs Ozu Robotics Laboratory at Ozyegin University Science Department are together collaboration in several projects including the following:

The lifelong robot learning project (which is also supported by the Japan Society for the Promotion of Science with the project titled Human-like Continual Robot Learning based on Three-level Computational Energy Cost Regulation) focuses on computational energy cost (CEC) constraints in robots inspired by the organisms that have energy cost limits that enable efficient and useful behavioral learning and development throughout their lives. The research aims to understand how well this constraint works for the continuous behavior learning and development of robots as in humans. In particular, the synergistic study of intrinsic motivation, energy preservation, and symbol formation for continual learning is conducted.

G. Tuba C. Girgin, MS student at the Computer Engineering Department of Bogazici University, who is experienced with Intrinsic Motivation in Robot Learning and Symbol Learning, studies computational energy cost (CEC) based on Intrinsic Motivation and Symbol Formation within the scope of this project. The study will continue for three months at Osaka University, Osaka, Japan.

T. Baturhan Akbulut is a junior computer engineering student doing a double major in Mathematics at Bogazici University. He has been undertaking these tasks:

  1. The integration of touch sensors to the robot control system to control the facial expressions of the Affetto Robot. By using this system, along with Maša Tomšič (Visiting Researcher to SisReC from University of Lisbon) they are conducting research on the connection between touch and robotic emotion. Besides, this pressure feedback system will be used for artificial pain implementation in robots.
  2. To enhance robot learning through a demonstration system, the transfer of the depth camera display to the VR system to create 1st person view experience for intuitive teleoperation of the robot.
  3. CNMP(Conditional Neural Movement Primitives) implementation on the robot for enhanced soft object manipulation skills.

The study will continue for three months at SisReC, Osaka University, Osaka, Japan.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s