Designing Robot Systems that Learn from Everyday People
  • FENS
  • Designing Robot Systems that Learn from Everyday People

You are here

Title: Designing Robot Systems that Learn from Everyday People

Speaker: Baris Akgun

Date/Time: August 5, 2015 Wednesday, 11:00am - 12:00 noon

Place: FENS G032

Abstract: Designing Robot Systems that Learn from Everyday People Robots are destined to move beyond the "caged" factory floors towards domains where they will be interacting closely with humans. They will encounter highly varied environments, scenarios and user demands. As a result, programming robots after deployment will be an important requirement. I am interested in building robot systems that can learn from everyday human teachers to tackle this challenge In this talk, I will present results of studies with non-expert users teaching robots by demonstration and methods developed based on the lessons learned. Our main observation is these users concentrate on achieving the goal of the demonstrated skills rather than providing good quality demonstrations. I will describe a learning from demonstration system that leverages this goal directed behavior of users and self-improves its learned models without further user-input. Finally, I will comment on further interactivity between the robot and the user and future research directions.
Bio: Baris Akgun is a Ph.D. candidate in Robotics at the Georgia Institute of Technology. He is a member of the Socially Intelligent Machines Lab and is advised by Assoc. Prof. Dr. Andrea Thomaz. He received his M.Sc. degree in Computer Engineering in 2010 from METU where he was affiliated with the KOVAN Lab, working on the EU FP 7 project ROSSI under Assoc. Prof. Dr. Erol Sahin. He received his B.Sc. degree in Mechanical Engineering with an extracurricular minor in Mechatronics in 2007. His research interests lie at the intersection of human-robot interaction and machine learning for robotics. He is currently working on developing learning from demonstration algorithms and interaction paradigms that allow non-experts to teach robots new skills. He was a recipient of the Scientific and Technological Research Council of Turkey (TUBITAK) scholarship for his M.Sc and the Fulbright Scholarship for his Ph.D.