Transparent Active Learning for Robots
Contributors: C.Chao, M.Cakmak, A.L.Thomaz

This research aims to build robots that learn from human teachers. Motivated by human social learning, we believe that a transparent learning process can help guide the human teacher to provide the most informative instruction. We believe active learning is an inherently transparent machine learning approach because it formulates queries to the oracle that reveal information about areas of uncertainty in the underlying model. In this work, we implement active learning on the Simon robot in the form of nonverbal gestures that query a human teacher about a demonstration within the context of a social dialog. Our preliminary data shows that transparency through active learning has the potential to improve the accuracy and effciency of the teaching process. However, our data also seems to indicate possible undesirable effects from the human teacher’s perspective. The results argue for a control strategy that balances leading and following during a social learning interaction.

Task Learning with Both Discrete and Continuous State Variables
Video: SimonTaskLearning
Contributors: C.Chao, M.Cakmak, A.L.Thomaz

The focus of this work is robot Learning by Demonstration, in which we target the problem of inferring the intention of a human teacher over few example demonstrations. In particular, we recognize the utility of a hybrid representation for goal learning that combines discrete and continuous features in the state representation. In this work, we present a system that generalizes using both types of data within a single task learning framework. The system is implemented on an upper-torso humanoid robot that learns and executes a variety of tasks taught by a human demonstrator.

Robot Playmates - Biologically inspired social learning mechanisms
Papers: ICDL 2009, RO-MAN 2009
Video: RobotPlaymates
Contributors: M.Cakmak, N. DePalma, R. Arriaga, A.L.Thomaz

Social learning in robotics has largely focused on imitation learning. In this work, we take a broader view of social learning and are interested in the multifaceted ways that a social partner can influence the learning process. We implement stimulus enhancement and emulation on a robot, and illustrate the computational benefits of social learning over self exploration. Additionally we characterize the differences between these two social learning strategies, showing that the preferred strategy is dependent on the current behavior of the social partner.

Learning about Objects from Humans
Paper: HRI 2009
Video: Junior
Contributors: M.Cakmak, A.L.Thomaz

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, Socially Guided Machine Learning. We conducted experiments with our robot, Junior, and made six observations characterizing how people approached teaching about objects. We showed that Junior successfully used transparency to mitigate errors. Finally, we present the impact of “social” versus “non-social” data sets when training SVM classifiers.

Shimon Listens
Videos:MidEastJam, Jazz, Head-closeup
Contributors: G. Weinberg, M.Cakmak, M. Gielniak, A.L.Thomaz

Shimon, is designed to play the marimba. It utilizes more melodic oriented algorithms for music perception and improvisation in comparison to Haile, Georgia Tech’s first robotic drummer. Shimon can also create richer sound and more communicative social cues with its human counterparts. The robot’s head is made to provide fellow musicians social cues that represent the music being played, from beat detection to tonality and spatial interaction. See review of Shimon on Wired - Robot Pass Musical Turing Test