Towards grounding concepts for transfer in goal learning from demonstration

We aim to build robots that frame the task learning problem as goal inference so that they are natural to teach and meet people's expectations for a learning partner. The focus of this work is the scenario of a social robot that learns task goals from human demonstrations without prior knowledge of high-level concepts. In the system that we present, these discrete concepts are grounded from low-level continuous sensor data through unsupervised learning, and task goals are subsequently learned on them using Bayesian inference. The grounded concepts are derived from the structure of the Learning from Demonstration (LfD) problem and exhibit degrees of prototypicality. These concepts can be used to transfer knowledge to future tasks, resulting in faster learning of those tasks. Using sensor data taken during demonstrations to our robot from five human teachers, we show the expressivity of using grounded concepts when learning new tasks from demonstration. We then show how the learning curve improves when transferring the knowledge of grounded concepts to future tasks.

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

[2]  J. J. Guajardo,et al.  How infants make sense of intentional action , 2001 .

[3]  Maya Cakmak,et al.  Designing Interactions for Robot Active Learners , 2010, IEEE Transactions on Autonomous Mental Development.

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

[5]  B. Kuipers,et al.  From pixels to policies: A bootstrapping agent , 2008, 2008 7th IEEE International Conference on Development and Learning.

[6]  Maya Cakmak,et al.  Exploiting social partners in robot learning , 2010, Auton. Robots.

[7]  Wayne D. Gray,et al.  Basic objects in natural categories , 1976, Cognitive Psychology.

[8]  Dana Kulic,et al.  Incremental Learning, Clustering and Hierarchy Formation of Whole Body Motion Patterns using Adaptive Hidden Markov Chains , 2008, Int. J. Robotics Res..

[9]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[10]  E. Rosch,et al.  Relationships among goodness-of-example, category norms, and word frequency , 1976 .

[11]  M. McCloskey,et al.  Decision processes in verifying category membership statements: Implications for models of semantic memory , 1979, Cognitive Psychology.

[12]  Aude Billard,et al.  A probabilistic Programming by Demonstration framework handling constraints in joint space and task space , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Jodie A. Baird,et al.  Discerning intentions in dynamic human action , 2001, Trends in Cognitive Sciences.

[14]  G. Murphy,et al.  The Big Book of Concepts , 2002 .

[15]  Maja J. Mataric,et al.  Performance-Derived Behavior Vocabularies: Data-Driven Acquisition of Skills from Motion , 2004, Int. J. Humanoid Robotics.

[16]  L. Barsalou,et al.  Ad hoc categories , 1983, Memory & cognition.

[17]  P. D. Eimas,et al.  The Emergence of Category Representations During Infancy: Are Separate Perceptual and Conceptual Processes Required? , 2000 .

[18]  Edward E. Smith,et al.  Category-Based Induction , 1990 .

[19]  Lance J. Rips,et al.  Semantic distance and the verification of semantic relations , 1973 .

[20]  Stefan Schaal,et al.  Robot Programming by Demonstration , 2009, Springer Handbook of Robotics.

[21]  Eleanor Rosch,et al.  Principles of Categorization , 1978 .

[22]  E. Rosch.  ON THE INTERNAL STRUCTURE OF PERCEPTUAL AND SEMANTIC CATEGORIES1 , 1973 .

[23]  Alex Pentland,et al.  Learning words from sights and sounds: a computational model , 2002, Cogn. Sci..

[24]  Dare A. Baldwin,et al.  Intentions and Intentionality: Foundations of Social Cognition , 2001 .

[25]  Henk Nijmeijer,et al.  Robot Programming by Demonstration , 2010, SIMPAR.

[26]  G. Csibra.  Teleological and referential understanding of action in infancy. , 2003, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[27]  Stefan Schaal,et al.  Learning and generalization of motor skills by learning from demonstration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[28]  J. Mandler.  Perceptual and Conceptual Processes in Infancy , 2000 .

[29]  Rüdiger Dillmann,et al.  Towards Cognitive Robots: Building Hierarchical Task Representations of Manipulations from Human Demonstration , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.