Konstantinos Tsiakas
    Ph.D. Candidate
    HERACLEIA Human-Centered Computing Laboratory
    Computer Science and Engineering Department
    University of Texas at Arlington
    Intitute of Informatics and Telecommunications, NCSR Demokritos

    Office: ERB 306, CSE@UTA
    Office Hours: TuTh 12:30pm - 2:00pm
    Phone: 817-805-9043
    Email: konstantinos.tsiakas@mavs.uta.edu
    LinkedIn Google Scholar ResearchGate


Home Research Publications CV

Research

My main research interests are Machine Learning, Reinforcement Learning, Human-Computer and Human-Robot Interaction with applications to Robot-Assisted Training, Socially-Assistive Robotics and Vocational Rehabilitation and Training. I focus mainly on the adaptability of such interfaces (computers, robots) towards specific user abilities and needs. My research on my Ph.D. moves towards the definition, implementation and evaluation of a computational framework for Interactive Learning and Adaptation for Robot-Assisted Training and Socially Assistive Robotics. Related research project and dataset can be found here.

I am investigating how Interactive Reinforcement Learning apporaches (Learning from Feedback, Learning from Guidance) can be utilized and integrated to the adaptation mechanism of an interactive system (HRI, HCI), to cope with unknown users. I am also interested in Interactive Machine Learning, studying and researching how humans teach machines and how machines can learn from humans, during the interaction. Currently, I am investigating the concept of co-adaptation; the process of the adjustment of both the machine and the human user, as they perform a task (e.g., training, collaboration), considering both goal-oriented concepts (e.g., task completion) and human-centered approaches (e.g., user engagement, enjoyment and performance).

Apart from my research, I am also interested in Computational Neuroscience, in order to extend my knowledge in Computational Learning Theory, with applications to Robot Learning. I recently received my Coursera Certificate for completing the "Computational Neuroscience" course from University of Washington. In the future, I would also like to learn more about Computing for Interactive Arts, specifically about adaptive systems in art practice. Moreover, I am interested in the theory and study of emotions (Coursera Certificate), with applications to Affective Computing and Bio-inspired Robotics.

Project Experience
Demos