Now showing items 7-26 of 32

    • Designing Interactions for Robot Active Learners 

      Cakmak, Maya; Chao, Crystal; Thomaz, Andrea L. (Georgia Institute of TechnologyInstitute of Electrical & Electronics Engineers, 2010-06)
      This paper addresses some of the problems that arise when applying active learning to the context of human–robot interaction (HRI). Active learning is an attractive strategy for robot learners because it has the potential ...
    • Effective robot task learning by focusing on task-relevant objects 

      Lee, Kyu Hwa; Lee, Jinhan; Thomaz, Andrea L.; Bobick, Aaron F. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2009-10)
      In a robot learning from demonstration framework involving environments with many objects, one of the key problems is to decide which objects are relevant to a given task. In this paper, we analyze this problem and propose ...
    • Effects of Social Exploration Mechanisms on Robot Learning 

      Cakmak, Maya; DePalma, Nick; Thomaz, Andrea L.; Arriaga, Rosa (Georgia Institute of TechnologyInstitute of Electrical & Electronics Engineers, 2009)
      Social learning in robotics has largely focused on imitation learning. Here we take a broader view and are interested in the multifaceted ways that a social partner can influence the learning process. We implement four ...
    • Enhancing Interaction Through Exaggerated Motion Synthesis 

      Gielniak, Michael J.; Thomaz, Andrea L. (Georgia Institute of Technology, 2012-03)
      Other than eye gaze and referential gestures (e.g. pointing), the relationship between robot motion and observer attention is not well understood. We explore this relationship to achieve social goals, such as influencing ...
    • Exploiting social partners in robot learning 

      Cakmak, Maya; DePalma, Nick; Arriaga, Rosa; Thomaz, Andrea L. (Georgia Institute of TechnologySpringer, 2010)
      Social learning in robotics has largely focused on imitation learning. Here we take a broader view and are interested in the multifaceted ways that a social partner can in uence the learning process. We implement four ...
    • Generating Human-like Motion for Robots 

      Gielniak, Michael J.; Liu, C. Karen; Thomaz, Andrea L. (Georgia Institute of TechnologySage Publications, 2013-07)
      Action prediction and fluidity are key elements of human-robot teamwork. If a robot’s actions are hard to understand, it can impede fluid HRI. Our goal is to improve the clarity of robot motion by making it more humanlike. ...
    • Human-like Action Segmentation for Option Learning 

      Shim, Jaeeun; Thomaz, Andrea L. (Georgia Institute of TechnologyInstitute of Electrical & Electronics Engineers, 2011)
      Robots learning interactively with a human partner has several open questions, one of which is increasing the efficiency of learning. One approach to this problem in the Reinforcement Learning domain is to use options, ...
    • Keyframe-based Learning from Demonstration Method and Evaluation 

      Akgun, Baris; Cakmak, Maya; Jiang, Karl; Thomaz, Andrea L. (Georgia Institute of TechnologySpringer, 2012-06)
      We present a framework for learning skills from novel types of demonstrations that have been shown to be desirable from a human-robot interaction perspective. Our approach –Keyframe-based Learning from Demonstration (KLfD)– ...
    • Learning about Objects with Human Teachers 

      Thomaz, Andrea L.; Cakmak, Maya (Georgia Institute of TechnologyAssociation for Computing Machinery, 2009)
      A general learning task for a robot in a new environment is to learn about objects and what actions/effects they afford. To approach this, we look at ways that a human partner can intuitively help the robot learn, ...
    • Multi-Cue Contingency Detection 

      Lee, Jinhan; Chao, Crystal; Bobick, Aaron F.; Thomaz, Andrea L. (Georgia Institute of TechnologySpringer, 2012-04)
      The ability to detect a human's contingent response is an essential skill for a social robot attempting to engage new interaction partners or maintain ongoing turn-taking interactions. Prior work on contingency detection ...
    • Multimodal Real-Time Contingency Detection for HRI 

      Chu, Vivian; Bullard, Kalesha; Thomaz, Andrea L. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2014-09)
      Our goal is to develop robots that naturally engage people in social exchanges. In this paper, we focus on the problem of recognizing that a person is responsive to a robot’s request for interaction. Inspired by human ...
    • Object Focused Q-Learning for Autonomous Agents 

      Cobo, Luis C.; Isbell, Charles L., Jr.; Thomaz, Andrea L. (Georgia Institute of TechnologyACM Press, 2013)
      We present Object Focused Q-learning (OF-Q), a novel reinforcement learning algorithm that can offer exponential speed-ups over classic Q-learning on domains composed of independent objects. An OF-Q agent treats the state ...
    • Optimality of Human Teachers for Robot Learners 

      Cakmak, Maya; Thomaz, Andrea L. (Georgia Institute of TechnologyInstitute of Electrical & Electronics Engineers, 2010)
      In this paper we address the question of how closely everyday human teachers match a theoretically optimal teacher. We present two experiments in which subjects teach a concept to our robot in a supervised fashion. In ...
    • Policy Shaping: Integrating Human Feedback with Reinforcement Learning 

      Griffith, Shane; Subramanian, Kaushik; Scholz, Jonathan; Isbell, Charles L.; Thomaz, Andrea L. (Georgia Institute of TechnologyNeural Information Processing System, 2013)
      A long term goal of Interactive Reinforcement Learning is to incorporate non- expert human feedback to solve complex tasks. Some state-of -the-art methods have approached this problem by mapping human information to ...
    • Secondary Action in Robot Motion 

      Gielniak, Michael J.; Liu, C. Karen; Thomaz, Andrea L. (Georgia Institute of TechnologyInstitute of Electrical & Electronics Engineers, 2010)
      Secondary action, a concept borrowed from character animation, improves the animation realism by augmenting natural, passive motion to primary action. We use dynamic simulation to induce three techniques of secondary motion ...
    • Simon plays Simon says: The timing of turn-taking in an imitation game 

      Chao, Crystal; Lee, Jinhan; Begum, Momotaz; Thomaz, Andrea L. (Georgia Institute of TechnologyInstitute of Electrical & Electronics Engineers, 2011)
      Turn-taking is fundamental to the way humans engage in information exchange, but robots currently lack the turn-taking skills required for natural communication. In order to bring effective turn-taking to robots, we must ...
    • Social Learning Mechanisms for Robots 

      Thomaz, Andrea L.; Cakmak, Maya (Georgia Institute of Technology, 2009)
      There is currently a surge of interest in service robotics—a desire to have robots leave the labs and factory floors to help solve critical issues facing our society, ranging from eldercare to education. A critical issue ...
    • Spatiotemporal Correspondence as a Metric for Human-like Robot Motion 

      Gielniak, Michael J.; Thomaz, Andrea L. (Georgia Institute of TechnologyAssociation for Computing Machinery, 2011)
      Coupled degrees-of-freedom exhibit correspondence, in that their trajectories in uence each other. In this paper we add evidence to the hypothesis that spatiotemporal corre- spondence (STC) of distributed actuators is ...
    • Stylized Motion Generalization Through Adaptation of Velocity Profiles 

      Gielniak, Michael J.; Liu, C. Karen; Thomaz, Andrea L. (Georgia Institute of TechnologyInstitute of Electrical & Electronics Engineers, 2010)
      Stylized motion is prevalent in the field of Human-Robot Interaction (HRI). Robot designers typically hand craft or work with professional animators to design behaviors for a robot that will be communicative or life-like ...
    • Task-Aware Variations in Robot Motion 

      Gielniak, Michael J.; Liu, C. Karen; Thomaz, Andrea L. (Georgia Institute of TechnologyInstitute of Electrical & Electronics Engineers, 2011-05)
      Social robots can benefit from motion variance because non-repetitive gestures will be more natural and intuitive for human partners. We introduce a new approach for synthesizing variance, both with and without constraints, ...