Fethiye Irmak Dogan



Fethiye Irmak Doğan is a Ph.D. student at the Division of Robotics, Perception and Learning, KTH Royal Institute of Technology. She is currently working with Iolanda Leite on understanding natural language instructions and resolving ambiguities in Human-Robot Conversation. She received her B.Sc. (2015) and M.Sc. (2018) degrees in Computer Engineering from Middle East Technical University (METU). While pursuing her M.Sc. degree, she worked as a researcher at Kovan Robotics Research Lab in METU. Her research interests include Human-Robot Interaction, Computer Vision, and Deep Learning.

Speaker Links: Website - Google Scholar


Verbal communication is a key challenge in human-robot interaction. For effective verbal interaction, comprehending natural language instructions and clarifying ambiguous user requests are crucial for social robots. To understand the described objects in the requests, the robot should be able to comprehend referring expressions, i.e., the expressions used for describing objects with their distinguishing features. Furthermore, if there are ambiguities in the instructions, the robot should be able to identify these ambiguities and ask follow-up questions by generating referring expressions. In this talk, our latest efforts on comprehending and generating referring expressions will be presented.

Papers covered during the talk

  • Dogan, F. I., Melsion, G. I., & Leite, I. (2021). Leveraging Explainability for Comprehending Referring Expressions in the Real World. arXiv preprint arXiv:2107.05593.
  • Dogan, F. I., & Leite, I. (2021). Using Depth for Improving Referring Expression Comprehension in Real-World Environments. arXiv preprint arXiv:2107.04658.
  • Doğan, F. I., Gillet, S., Carter, E. J., & Leite, I. (2020). The impact of adding perspective-taking to spatial referencing during human–robot interaction. Robotics and Autonomous Systems, 134, 103654.
  • Doğan, F. I., Kalkan, S., & Leite, I. (2019). Learning to generate unambiguous spatial referring expressions for real-world environments. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 4992-4999). IEEE.