Dynamic Role Allocation in Shared Control: Challenges in Human-Robot Collaborative Teamwork

Add to your list(s) Download to your calendar using vCal

• Ayse Kucukyilmaz, Assistant Professor at University of Nottingham
• Friday 09 July 2021, 10:00-11:00
• Venue to be confirmed.

If you have a question about this talk, please contact Martin Rudorfer.

Today’s robots can be programmed to “learn” to perform physical tasks, enabling a range of manipulation or navigation skills. However, the autonomous abilities of robots, especially in complex environments, dealing with heaps or intricate clutters of unknown objects, has been very limited due to challenges in perception, grasping, and decision making. This shortcoming is often targeted through involving a human in the loop when dealing with extremely complex manipulation tasks or those which could have dangerous consequences, e.g. in nuclear environments or in robot-assisted surgery, where the robot can act as an aide to the human, creating a human-robot team. Unfortunately, despite all developments, existing interactions within current human-robot systems are still artificial and highly constrained when compared to natural human-human collaboration. Shared control naturally occurs in human-human collaboration, where the continuous and prolonged nature of interaction characterises an allocation of roles within the team. In this talk, I will discuss our research on learning from human demonstrations and shared control, and present dynamic role allocation techniques to enable human-robot teamwork in close physical contact. I will elaborate on if and how the use of haptics will enhance the communication and interaction capabilities in collaborative robots. My talk will end with a short discussion of future research directions, such as aspects of trust in human-robot interaction.

Dr Ayse Kucukyilmaz is an Assistant Professor of Computer Science at the University of Nottingham, UK. Her research interests include haptics, physical HRI , assistive robotics, and machine learning. Her current work is on human-in-the loop learning and shared control in the haptic teleoperation domain. Previously, Dr Kucukyilmaz worked as a Senior Lecturer at the School of Computer Science in University of Lincoln, UK, was a Postdoctoral Research Associate at the Personal Robotics Laboratory of Imperial College London, and an Assistant Professor at the Department of Computer Engineering at Yeditepe University. She was a visiting researcher at the Information-Oriented Control group in Technical University of Munich in 2011. She received her Ph.D. in Computational Sciences and Engineering from Koc University in 2013, and B.Sc. and M.Sc. degrees in Computer Engineering from Bilkent University in 2004 and 2007. She was the recipient of the Academic Excellence Award at her graduation from Koc University in 2013, and has received fellowships from EC Marie Skłodowska-Curie Actions and TUBITAK , and holds grants from EPSRC and CHIST -ERA.

This talk is part of the IRLab Seminars: Robotics, Computer Vision & AI series.

This talk is included in these lists:

• IRLab Seminars: Robotics, Computer Vision & AI
• Venue to be confirmed

Note that ex-directory lists are not shown.