The initial development of object knowledge by a learning robot

We describe how a robot can develop knowledge of the objects in its environment directly from unsupervised sensorimotor experience. The object knowledge consists of multiple integrated representations: trackers that form spatio-temporal clusters of sensory experience, percepts that represent properties for the tracked objects, classes that support efficient generalization from past experience, and actions that reliably change object percepts. We evaluate how well this intrinsically acquired object knowledge can be used to solve externally specified tasks including object recognition and achieving goals that require both planning and continuous control.

[1]  Pat Langley,et al.  Learning Recursive Control Programs from Problem Solving , 2006, J. Mach. Learn. Res..

[2]  Jefferson Provost and Benjamin J. Kuipers and Risto Miikkulainen.  Self-Organizing Distinctive State Abstraction Using Options , 2007 .

[3]  Benjamin Kuipers,et al.  Map Learning with Uninterpreted Sensors and Effectors , 1995, Artif. Intell..

[4]  Leslie Pack Kaelbling,et al.  Learning Planning Rules in Noisy Stochastic Worlds , 2005, AAAI.

[5]  Lorenzo Natale,et al.  Linking Action to Perception in a Humanoid Robot: a Developmental Approach to Grasping , 2004 .

[6]  Benjamin Kuipers,et al.  Bootstrap learning for object discovery , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[7]  Silvio Savarese,et al.  3D generic object categorization, localization and pose estimation , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[8]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[9]  Dekang Lin,et al.  WordNet: An Electronic Lexical Database , 1998 .

[10]  Elizabeth S. Spelke,et al.  Principles of Object Perception , 1990, Cogn. Sci..

[11]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[12]  Scott Benson,et al.  Inductive Learning of Reactive Action Models , 1995, ICML.

[13]  Yoonsuck Choe,et al.  Motion-Based Autonomous Grounding: Inferring External World Properties from Encoded Internal Sensory States Alone , 2006, AAAI.

[14]  David G. Stork,et al.  Pattern Classification , 1973 .

[15]  Pierre-Yves Oudeyer,et al.  Discovering communication , 2006, Connect. Sci..

[16]  J. Kevin O'Regan,et al.  Is There Something Out There? Inferring Space from Sensorimotor Dependencies , 2003, Neural Computation.

[17]  Pietro Perona,et al.  A Bayesian approach to unsupervised one-shot learning of object categories , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[18]  Pietro Perona,et al.  A Bayesian approach to unsupervised one-shot learning of object categories , 2003, ICCV 2003.

[19]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[20]  Benjamin Kuipers,et al.  The Spatial Semantic Hierarchy , 2000, Artif. Intell..

[21]  Chen Yu,et al.  The Role of Embodied Intention in Early Lexical Acquisition , 2005, Cogn. Sci..

[22]  Alexander Stoytchev,et al.  Behavior-Grounded Representation of Tool Affordances , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[23]  Richard T. Vaughan,et al.  The Player/Stage Project: Tools for Multi-Robot and Distributed Sensor Systems , 2003 .

[24]  Benjamin Kuipers,et al.  Autonomous shape model learning for object localization and recognition , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[25]  Benjamin Kuipers,et al.  Autonomous Development of a Grounded Object Ontology by a Learning Robot , 2007, AAAI.

[26]  Scott Sanner,et al.  Towards object mapping in non-stationary environments with mobile robots , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[27]  Stephen Hart,et al.  A Relational Representation for Procedural Task Knowledge , 2005, AAAI.

[28]  P. Bloom.  Précis of How Children Learn the Meanings of Words , 2001, Behavioral and Brain Sciences.

[29]  Rakesh Gupta,et al.  Common Sense Data Acquisition for Indoor Mobile Robots , 2004, AAAI.

[30]  Wei-Min Shen,et al.  Functional transformations in AI discovery systems , 1988, [1988] Proceedings of the Twenty-First Annual Hawaii International Conference on System Sciences. Volume III: Decision Support and Knowledge Based Systems Track.

[31]  Chrystopher L. Nehaniv,et al.  From unknown sensors and actuators to actions grounded in sensorimotor perceptions , 2006, Connect. Sci..

[32]  C. Kemp,et al.  What Can I Control ? : The Development of Visual Categories for a Robot ’ s Body and the World that it Influences , 2006 .

[33]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[34]  Yolanda Gil,et al.  Acquiring domain knowledge for planning by experimentation , 1992 .