Automatic language acquisition by an autonomous robot

There is no such thing as a disembodied mind. We posit that cognitive development can only occur through interaction with the physical world. To this end, we are developing a robotic platform for the purpose of studying cognition. We suggest that the central component of cognition is a memory which is primarily associative, one where learning occurs as the correlation of events from diverse inputs. We also posit that human-like cognition requires a well-integrated sensory-motor system, to provide these diverse inputs. As implemented in our robot, this system includes binaural hearing, stereo vision, tactile sense, and basic proprioceptive control. On top of these abilities, we are implementing and studying various models of processing, learning and decision making. Our goal is to produce a robot that will learn to carry out simple tasks in response to natural language requests. The robot's understanding of language will be learned concurrently with its other cognitive abilities. We have already developed a robust system and conducted a number or experiments on the way to this goal, some details of which appear in this paper. This is a first progress report of what we believe will be a long term project with significant implications.

[1]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[2]  M. Ashcraft Human memory and cognition , 1989 .

[3]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[4]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[5]  Andrew McCallum,et al.  Instance-Based State Identification for Reinforcement Learning , 1994, NIPS.

[6]  V. Gullapalli,et al.  Acquiring robot skills via reinforcement learning , 1994, IEEE Control Systems.

[7]  Sebastian Thrun,et al.  An approach to learning mobile robot navigation , 1995, Robotics Auton. Syst..

[8]  David R. Shanks,et al.  The Psychology of Associative Learning , 1995 .

[9]  M. Tovée,et al.  An Introduction to the Visual System , 1997 .

[10]  Andrew D. Ellington,et al.  Solution-based analysis of multiple analytes by a sensor array: toward the development of an electronic tongue , 1998 .

[11]  Hiroyuki Shinoda,et al.  Telemetric robot skin , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[12]  A. Gopnik The scientist in the crib , 1999 .

[13]  R. Brooks,et al.  The cog project: building a humanoid robot , 1999 .

[14]  Eiji Takimoto,et al.  On-Line Estimation of Hidden Markov Model Parameters , 2000, Discovery Science.

[15]  Stephen E. Levinson,et al.  Edge orientation-based multi-view object recognition , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  Chrystopher L. Nehaniv Computation for Metaphors, Analogy, and Agents , 2000, Lecture Notes in Computer Science.

[17]  Juyang Weng,et al.  Grounded auditory development by a developmental robot , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[18]  R. Brooks,et al.  Petitagé: A Case Study in Developmental Robotics , 2001 .

[19]  Silvia Coradeschi,et al.  Odor source identification by grounding linguistic descriptions in an artificial nose , 2001, SPIE Defense + Commercial Sensing.

[20]  A. Drogoul,et al.  Shaping of Robot Behaviors by Demonstrations , 2001 .

[21]  Song Wang,et al.  Tracking of object with SVM regression , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[22]  R. Moratz,et al.  From Communicative Strategies to Cognitive Modelling , 2001 .

[23]  Stephen E. Levinson,et al.  PQ−Learning: An Efficient Robot Learning Method for Intelligent Behavior Acquisition , 2001 .

[24]  Qiong Liu,et al.  Interactive and Incremental Learning via a Multisensory Mobile Robot , 2001 .

[25]  Paul R. Cohen,et al.  Learning effects of robot actions using temporal associations , 2002, Proceedings 2nd International Conference on Development and Learning. ICDL 2002.

[26]  Juyang Weng,et al.  Dav: a humanoid robot platform for autonomous mental development , 2002, Proceedings 2nd International Conference on Development and Learning. ICDL 2002.

[27]  Ian R. Fasel,et al.  Combining embodied models and empirical research for understanding the development of shared attention , 2002, Proceedings 2nd International Conference on Development and Learning. ICDL 2002.

[28]  Juyang Weng,et al.  A theory for mentally developing robots , 2002, Proceedings 2nd International Conference on Development and Learning. ICDL 2002.

[29]  J. C. Middlebrooks,et al.  Listener weighting of cues for lateral angle: the duplex theory of sound localization revisited. , 2002, The Journal of the Acoustical Society of America.

[30]  Paulina Varshavskaya,et al.  Behavior-Based Early Language Development on a Humanoid Robot , 2002 .

[31]  Juyang Weng,et al.  Developing early senses about the world: "Object Permanence" and visuoauditory real-time learning , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[32]  M. Lungarella,et al.  Beyond Gazing, Pointing, and Reaching: A Survey of Developmental Robotics , 2003 .

[33]  Danfeng Li Computational Models for Binaural Sound Source Localization and Sound Understanding , 2003 .

[34]  Stephen E. Levinson,et al.  A Bayes-rule based hierarchical system for binaural sound source localization , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[35]  Minoru Asada,et al.  Purposive behavior acquisition for a real robot by vision-based reinforcement learning , 1995, Machine Learning.

[36]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[37]  Yoram Singer,et al.  The Hierarchical Hidden Markov Model: Analysis and Applications , 1998, Machine Learning.

[38]  Roderic A. Grupen,et al.  A Developmental Organization for Robot Behavior , 2005 .