Corpus ID: 197430879

Understanding Teacher Gaze Patterns for Robot Learning

  title={Understanding Teacher Gaze Patterns for Robot Learning},
  author={Akanksha Saran and Elaine Schaertl Short and A. Thomaz and S. Niekum},
  • Akanksha Saran, Elaine Schaertl Short, +1 author S. Niekum
  • Published in CoRL 2019
  • Computer Science, Psychology
  • Human gaze is known to be a strong indicator of underlying human intentions and goals during manipulation tasks. This work studies gaze patterns of human teachers demonstrating tasks to robots and proposes ways in which such patterns can be used to enhance robot learning. Using both kinesthetic teaching and video demonstrations, we identify novel intention-revealing gaze behaviors during teaching. These prove to be informative in a variety of problems ranging from reference frame inference to… CONTINUE READING
    5 Citations

    Figures, Tables, and Topics from this paper

    Efficiently Guiding Imitation Learning Algorithms with Human Gaze
    • 3
    • PDF
    Enhancing Robot Learning with Human Social Cues
    • 2
    Human Gaze Assisted Artificial Intelligence: A Review
    • 2
    • PDF
    Unclogging Our Arteries: Using Human-Inspired Signals to Disambiguate Navigational Intentions
    • PDF
    Not All Errors Are Created Equal: Exploring Human Responses to Robot Errors with Varying Severity
    • PDF


    Eye-Hand Behavior in Human-Robot Shared Manipulation
    • 31
    • PDF
    Learning to Recognize Daily Actions Using Gaze
    • 322
    • PDF
    Mutual Context Network for Jointly Estimating Egocentric Gaze and Action
    • 9
    • PDF
    Where are they looking?
    • 99
    • PDF
    Social eye gaze in human-robot interaction
    • 129
    • PDF
    One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video
    • Wonjoon Goo, S. Niekum
    • Computer Science, Mathematics
    • 2019 International Conference on Robotics and Automation (ICRA)
    • 2019
    • 15
    • PDF
    Physical symbol grounding and instance learning through demonstration and eye tracking
    • 18
    • PDF
    Action plans used in action observation
    • 628
    • PDF