Exploiting social partners in robot learning

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 social learning mechanisms on a robot: stimulus enhancement, emulation, mimicking, and imitation, and illustrate the computational benefits of each. In particular, we illustrate that some strategies are about directing the attention of the learner to objects and others are about actions. Taken together these strategies form a rich repertoire allowing social learners to use a social partner to greatly impact their learning process. We demonstrate these results in simulation and with physical robot ‘playmates’.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  Chrystopher L. Nehaniv,et al.  Action, State and Effect Metrics for Robot Imitation , 2006, ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication.

[3]  José Santos-Victor,et al.  A unified framework for imitation-like behaviors , 2007 .

[4]  Monica N. Nicolescu,et al.  Natural methods for robot task learning: instructive demonstrations, generalization and practice , 2003, AAMAS '03.

[5]  Daniel H. Grollman,et al.  Sparse incremental learning for interactive robot control policy estimation , 2008, 2008 IEEE International Conference on Robotics and Automation.

[6]  L. S. Vygotskiĭ,et al.  Mind in society : the development of higher psychological processes , 1978 .

[7]  Andrew Stern,et al.  Virtual petz (video session): a hybrid approach to creating autonomous, lifelike dogz and catz , 1998, AGENTS '98.

[8]  Pierre-Yves Oudeyer,et al.  Robotic clicker training , 2002, Robotics Auton. Syst..

[9]  Leslie Pack Kaelbling,et al.  Effective reinforcement learning for mobile robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[10]  Chrystopher L. Nehaniv,et al.  Three Sources of Information in Social Learning , 2002 .

[11]  Maya Cakmak,et al.  To Afford or Not to Afford: A New Formalization of Affordances Toward Affordance-Based Robot Control , 2007, Adapt. Behav..

[12]  R. Pea.  Practices of distributed intelligence and designs for education , 1993 .

[13]  Peter Stone,et al.  Cobot: A Social Reinforcement Learning Agent , 2001, NIPS.

[14]  P. Greenfield.  A theory of the teacher in the learning activities of everyday life. , 1984 .

[15]  J. Stevenson.  The cultural origins of human cognition , 2001 .

[16]  B. Rogoff,et al.  Adult guidance of cognitive development. , 1984 .

[17]  Pradeep K. Khosla,et al.  A Multi-Agent System for Programming Robotic Agents by Human Demonstration , 1998 .

[18]  Richard Alan Peters,et al.  Robonaut task learning through teleoperation , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[19]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[20]  Andrea Lockerd Thomaz,et al.  Tutelage and Collaboration for Humanoid Robots , 2004, Int. J. Humanoid Robotics.

[21]  C. Breazeal,et al.  Robots that imitate humans , 2002, Trends in Cognitive Sciences.

[22]  Manuel Lopes,et al.  A Computational Model of Social-Learning Mechanisms , 2009, Adapt. Behav..

[23]  Pat Langley,et al.  An Analysis of Bayesian Classifiers , 1992, AAAI.

[24]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[25]  Maja J. Mataric,et al.  Deriving action and behavior primitives from human motion data , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[26]  Aude Billard,et al.  What is the Teacher"s Role in Robot Programming by Demonstration? - Toward Benchmarks for Improved Learning , 2007 .

[27]  Andrea Lockerd Thomaz,et al.  Teachable robots: Understanding human teaching behavior to build more effective robot learners , 2008, Artif. Intell..

[28]  Pradeep K. Khosla,et al.  A multi-agent system for programming robots by human demonstration , 2001, Integr. Comput. Aided Eng..

[29]  Maya Cakmak,et al.  Learning about objects with human teachers , 2009, 2009 4th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[30]  Manuela M. Veloso,et al.  Confidence-based policy learning from demonstration using Gaussian mixture models , 2007, AAMAS '07.

[31]  Bruce Blumberg,et al.  Integrated learning for interactive synthetic characters , 2002, SIGGRAPH.

[32]  Stefan Schaal,et al.  Robot Learning From Demonstration , 1997, ICML.

[33]  Etienne Wenger,et al.  Situated Learning: Legitimate Peripheral Participation , 1991 .

[34]  Masayuki Inaba,et al.  Learning by watching: extracting reusable task knowledge from visual observation of human performance , 1994, IEEE Trans. Robotics Autom..

[35]  Yi-Min Huang,et al.  Weighted support vector machine for classification with uneven training class sizes , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[36]  Maya Cakmak,et al.  Computational benefits of social learning mechanisms: Stimulus enhancement and emulation , 2009, 2009 IEEE 8th International Conference on Development and Learning.

[37]  Gillian M. Hayes,et al.  Imitation as a dual-route process featuring prediction and learning components: A biologically plaus , 2002 .

[38]  Michael A. Arbib,et al.  Affordances, effectivities, and assisted imitation: Caregivers and the directing of attention , 2007, Neurocomputing.

[39]  Peter Stone,et al.  A social reinforcement learning agent , 2001, AGENTS '01.

[40]  J. Wertsch,et al.  The creation of context in joint problem-solving. , 1984 .

[41]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[42]  Stefan Schaal,et al.  Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.

[43]  David S. Touretzky,et al.  Shaping robot behavior using principles from instrumental conditioning , 1997, Robotics Auton. Syst..