Staged Development of Robot Skills: Behavior Formation, Affordance Learning and Imitation with Motionese

Inspired by infant development, we propose a three staged developmental framework for an anthropomorphic robot manipulator. In the first stage, the robot is initialized with a basic reach-and- enclose-on-contact movement capability, and discovers a set of behavior primitives by exploring its movement parameter space. In the next stage, the robot exercises the discovered behaviors on different objects, and learns the caused effects; effectively building a library of affordances and associated predictors. Finally, in the third stage, the learned structures and predictors are used to bootstrap complex imitation and action learning with the help of a cooperative tutor. The main contribution of this paper is the realization of an integrated developmental system where the structures emerging from the sensorimotor experience of an interacting real robot are used as the sole building blocks of the subsequent stages that generate increasingly more complex cognitive capabilities. The proposed framework includes a number of common features with infant sensorimotor development. Furthermore, the findings obtained from the self-exploration and motionese guided human-robot interaction experiments allow us to reason about the underlying mechanisms of simple-to-complex sensorimotor skill progression in human infants.

[1]  Alexander Stoytchev,et al.  Some Basic Principles of Developmental Robotics , 2009, IEEE Transactions on Autonomous Mental Development.

[2]  M. Lungarella,et al.  Adaptivity via alternate freeing and freezing of degrees of freedom , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[3]  Emre Ugur,et al.  Traversability: A Case Study for Learning and Perceiving Affordances in Robots , 2010, Adapt. Behav..

[4]  A. Meltzoff,et al.  Imitation of Facial and Manual Gestures by Human Neonates , 1977, Science.

[5]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[6]  Harold Bekkering,et al.  Imitation in infancy: rational or motor resonance? , 2011, Child development.

[7]  Dare A. Baldwin,et al.  Evidence for ‘motionese’: modifications in mothers’ infant-directed action , 2002 .

[8]  Giulio Sandini,et al.  Developmental Perception of the Self and Action , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[9]  M. Asada,et al.  Infant's action skill dynamically modulates parental action demonstration in the dyadic interaction. , 2015, Developmental science.

[10]  K. H. Stauder,et al.  Psychology of the Child , 1959 .

[11]  Tamim Asfour,et al.  Learn to wipe: A case study of structural bootstrapping from sensorimotor experience , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Brian Scassellati,et al.  Robotic Self-Models Inspired by Human Development , 2010, Metacognition for Robust Social Systems.

[13]  Florentin Wörgötter,et al.  Cognitive agents - a procedural perspective relying on the predictability of Object-Action-Complexes (OACs) , 2009, Robotics Auton. Syst..

[14]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[15]  Y. Nagai From bottom-Up visual attention to robot action learning , 2009, 2009 IEEE 8th International Conference on Development and Learning.

[16]  Katharina J. Rohlfing,et al.  How can multimodal cues from child-directed interaction reduce learning complexity in robots? , 2006, Adv. Robotics.

[17]  Xin Zhang,et al.  Learning Robotic Hand-eye Coordination Through a Developmental Constraint Driven Approach , 2013, Int. J. Autom. Comput..

[18]  H. Sakata,et al.  Selectivity for the shape, size, and orientation of objects for grasping in neurons of monkey parietal area AIP. , 2000, Journal of neurophysiology.

[19]  B. Elsner Infants' imitation of goal-directed actions: the role of movements and action effects. , 2007, Acta psychologica.

[20]  Masaki Ogino,et al.  Cognitive Developmental Robotics: A Survey , 2009, IEEE Transactions on Autonomous Mental Development.

[21]  M. Arbib,et al.  Neural Organization: Structure, Function, and Dynamics , 1997 .

[22]  Manuel Lopes,et al.  Learning Object Affordances: From Sensory--Motor Coordination to Imitation , 2008, IEEE Transactions on Robotics.

[23]  Hans Forssberg,et al.  Sensorimotor Control of Grasping: Development of grasping and object manipulation , 2009 .

[24]  Justus H. Piater,et al.  Bootstrapping paired-object affordance learning with learned single-affordance features , 2014, 4th International Conference on Development and Learning and on Epigenetic Robotics.

[25]  Karl M. Newell,et al.  Constraints on the Development of Coordination , 1986 .

[26]  Igor Skrjanc,et al.  Editorial A Successful Change From TNN to TNNLS and a Very Successful Year , 2013, IEEE Trans. Neural Networks Learn. Syst..

[27]  Katharina J. Rohlfing,et al.  Computational Analysis of Motionese Toward Scaffolding Robot Action Learning , 2009, IEEE Transactions on Autonomous Mental Development.

[28]  Oliver Kroemer,et al.  Learning Visual Representations for Interactive Systems , 2009, ISRR.

[29]  Minoru Asada,et al.  How a Robot’s Attention Shapes The Way People Teach , 2010, EpiRob.

[30]  Pierre-Yves Oudeyer,et al.  Intrinsic Motivation Systems for Autonomous Mental Development , 2007, IEEE Transactions on Evolutionary Computation.

[31]  Tony Charman,et al.  Gradations of emulation learning in infants' imitation of actions on objects. , 2005, Journal of experimental child psychology.

[32]  Dimitrios Gunopulos,et al.  Discovering similar multidimensional trajectories , 2002, Proceedings 18th International Conference on Data Engineering.

[33]  Sinan Kalkan,et al.  Verb concepts from affordances , 2014 .

[34]  Jun Tani,et al.  Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment , 2003, IEEE Trans. Syst. Man Cybern. Part A.

[35]  Danica Kragic,et al.  Birth of the Object: Detection of Objectness and Extraction of Object Shape through Object-Action complexes , 2008, Int. J. Humanoid Robotics.

[36]  Jivko Sinapov,et al.  A Behavior-Grounded Approach to Forming Object Categories: Separating Containers From Noncontainers , 2012, IEEE Transactions on Autonomous Mental Development.

[37]  P. Willatts Development of means-end behavior in young infants: pulling a support to retrieve a distant object. , 1999, Developmental psychology.

[38]  Justus H. Piater,et al.  Bottom-up learning of object categories, action effects and logical rules: From continuous manipulative exploration to symbolic planning , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[39]  Sachin Chitta,et al.  Human-Inspired Robotic Grasp Control With Tactile Sensing , 2011, IEEE Transactions on Robotics.

[40]  M. Tomasello,et al.  Social cognition, joint attention, and communicative competence from 9 to 15 months of age. , 1998, Monographs of the Society for Research in Child Development.

[41]  Maya Cakmak,et al.  The learning and use of traversability affordance using range images on a mobile robot , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[42]  Mark H. Lee,et al.  The infant development timeline and its application to robot shaping , 2011, Adapt. Behav..

[43]  M. Arbib,et al.  Infant grasp learning: a computational model , 2004, Experimental Brain Research.

[44]  Hema Swetha Koppula,et al.  Learning human activities and object affordances from RGB-D videos , 2012, Int. J. Robotics Res..

[45]  B. Hommel,et al.  Effect anticipation and action control. , 2001, Journal of experimental psychology. Human perception and performance.

[46]  Luc De Raedt,et al.  Learning relational affordance models for robots in multi-object manipulation tasks , 2012, 2012 IEEE International Conference on Robotics and Automation.

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

[48]  Stefano Nolfi,et al.  A Robotic Model of Reaching and Grasping Development , 2013, IEEE Transactions on Autonomous Mental Development.

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

[50]  Oliver Kroemer,et al.  Learning visual representations for perception-action systems , 2011, Int. J. Robotics Res..

[51]  Stephen C. Want,et al.  How do children ape? Applying concepts from the study of non-human primates to the developmental study of 'imitation' in children , 2002 .

[52]  Giulio Sandini,et al.  A developmental approach to visually-guided reaching in artificial systems , 1999, Neural Networks.

[53]  Rebecca J. Brand,et al.  Fine-Grained Analysis of Motionese: Eye Gaze, Object Exchanges, and Action Units in Infant-versus Adult-Directed Action. , 2007 .

[54]  Alan Bundy,et al.  Dynamic Time Warping , 1984 .

[55]  Joëlle Provasi,et al.  Do 9- and 12-month-olds learn means-ends relation by observing? , 2001 .

[56]  Pierre-Yves Oudeyer,et al.  Object Learning Through Active Exploration , 2014, IEEE Transactions on Autonomous Mental Development.

[57]  Mark H. Lee,et al.  Developmental learning for autonomous robots , 2007, Robotics Auton. Syst..

[58]  J. Gibson The Ecological Approach to Visual Perception , 1979 .

[59]  P. Willatts The stage-IV infant's solution of problems requiring the use of supports** , 1984 .

[60]  Tetsuya Ogata,et al.  Autonomous Motion Generation Based on Reliable Predictability , 2009, J. Robotics Mechatronics.

[61]  James Parker,et al.  on Knowledge and Data Engineering, , 1990 .

[62]  Julie C. Rutkowska,et al.  Scaling Up Sensorimotor Systems: Constraints from Human Infancy , 1994, Adapt. Behav..

[63]  K. Bard Neonatal imitation in chimpanzees (Pan troglodytes) tested with two paradigms , 2007, Animal Cognition.

[64]  Pierre-Yves Oudeyer,et al.  Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learner , 2012, Paladyn J. Behav. Robotics.

[65]  Manuel Lopes,et al.  Affordance-based imitation learning in robots , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[66]  Pierre-Yves Oudeyer,et al.  What is Intrinsic Motivation? A Typology of Computational Approaches , 2007, Frontiers Neurorobotics.

[67]  Michael A. Arbib,et al.  Perceptual Structures and Distributed Motor Control , 1981 .

[68]  N. A. Bernshteĭn The co-ordination and regulation of movements , 1967 .

[69]  Stephen Hart,et al.  Learning Generalizable Control Programs , 2011, IEEE Transactions on Autonomous Mental Development.

[70]  T. Ogata,et al.  Developmental Human-Robot Imitation Learning with Phased Structuring in Neuro Dynamical System , 2012 .

[71]  H. Sakata,et al.  Toward an understanding of the neural processing for 3D shape perception , 2005, Neuropsychologia.

[72]  Giulio Sandini,et al.  In Press, Ieee Transactions on Autonomous Mental Development , 2010 .

[73]  Justus H. Piater,et al.  Knowledge propagation and relation learning for predicting action effects , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[74]  Hein T. van Schie,et al.  You'll never crawl alone: Neurophysiological evidence for experience-dependent motor resonance in infancy , 2008, NeuroImage.

[75]  Emre Ugur,et al.  Affordance learning from range data for multi-step planning , 2009, EpiRob.

[76]  Aude Billard,et al.  Modulating vision with motor plans: A biologically-inspired efficient allocation of visual resources , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[77]  S. Schaal Dynamic Movement Primitives -A Framework for Motor Control in Humans and Humanoid Robotics , 2006 .

[78]  Giulio Sandini,et al.  Developmental robotics: a survey , 2003, Connect. Sci..

[79]  P. L. Adams THE ORIGINS OF INTELLIGENCE IN CHILDREN , 1976 .

[80]  Sinan Kalkan,et al.  The learning of adjectives and nouns from affordance and appearance features , 2013, Adapt. Behav..

[81]  Christopher W. Geib,et al.  Structural bootstrapping at the sensorimotor level for the fast acquisition of action knowledge for cognitive robots , 2013, 2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL).

[82]  Linda G. Shapiro,et al.  Computer and Robot Vision (Volume II) , 2002 .

[83]  Gisa Aschersleben,et al.  Do I get what you get? Learning about the effects of self-performed and observed actions in infancy , 2003, Consciousness and Cognition.

[84]  Patricia Shaw,et al.  A psychology based approach for longitudinal development in cognitive robotics , 2014, Front. Neurorobot..

[85]  Justus H. Piater,et al.  Emergent structuring of interdependent affordance learning tasks , 2014, 4th International Conference on Development and Learning and on Epigenetic Robotics.

[86]  Meinard Müller,et al.  Information retrieval for music and motion , 2007 .

[87]  Ales Ude,et al.  Probabilistic semantic models for manipulation action representation and extraction , 2015, Robotics Auton. Syst..

[88]  M. Trivedi,et al.  Learning trajectory patterns by clustering: Experimental studies and comparative evaluation , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[89]  David James,et al.  Fetal learning: a critical review , 2010 .

[90]  Dirk Kraft,et al.  A Survey of the Ontogeny of Tool Use: From Sensorimotor Experience to Planning , 2013, IEEE Transactions on Autonomous Mental Development.

[91]  Emre Ugur,et al.  Going beyond the perception of affordances: Learning how to actualize them through behavioral parameters , 2011, 2011 IEEE International Conference on Robotics and Automation.

[92]  Emre Ugur,et al.  Goal emulation and planning in perceptual space using learned affordances , 2011, Robotics Auton. Syst..

[93]  Erhan Oztop,et al.  Redundancy Parameterization for Flexible Motion Control , 2010 .

[94]  Stefan Schaal,et al.  Reinforcement Learning With Sequences of Motion Primitives for Robust Manipulation , 2012, IEEE Transactions on Robotics.

[95]  Jun Morimoto,et al.  Task-Specific Generalization of Discrete and Periodic Dynamic Movement Primitives , 2010, IEEE Transactions on Robotics.

[96]  Yukie Nagai,et al.  Parental scaffolding as a bootstrapping mechanism for learning grasp affordances and imitation skills , 2014, Robotica.

[97]  Benjamin Kuipers,et al.  The initial development of object knowledge by a learning robot , 2008, Robotics Auton. Syst..

[98]  Connor Schenck,et al.  Grounding semantic categories in behavioral interactions: Experiments with 100 objects , 2014, Robotics Auton. Syst..

[99]  James L. McClelland,et al.  Autonomous Mental Development by Robots and Animals , 2001, Science.