Robot Cognition using Bayesian Symmetry Networks

(Leyton, 2001) proposed a generative theory of shape, and general cognition, based on group actions on sets as defined by the wreath product. Our position expressed here is that this approach can provide a strong basis for robot cognition when: 1. tightly coupled to sensorimotor data and analysis, 2. used to structure both general concepts and specific instances, and 3. combined with a probabilistic framework (Bayesian networks) to characterize uncertainty. We describe a roadmap to achieve these and provide some evidence of feasibility.

[1]  Dennis M. Healy,et al.  A wreath product group approach to signal and image processing .I. Multiresolution analysis , 2000, IEEE Trans. Signal Process..

[2]  Michael Leyton,et al.  A generative theory of shape , 2004, Proceedings Shape Modeling Applications, 2004..

[3]  Roland Siegwart,et al.  Bayesian space conceptualization and place classification for semantic maps in mobile robotics , 2008, Robotics Auton. Syst..

[4]  Isaac Dialsingh,et al.  Risk assessment and decision analysis with Bayesian networks , 2014 .

[5]  Thomas C. Henderson Hongchang Peng,et al.  Symmetry : A Basis for Sensorimotor Reconstruction , 2011 .

[6]  B. Scassellati,et al.  A Bayesian Robot That Distinguishes "Self" from "Other" , 2007 .

[7]  Thomas O. Binford,et al.  Bayesian inference in model-based machine vision , 1987, Int. J. Approx. Reason..

[8]  Giulio Sandini,et al.  A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents , 2007, IEEE Transactions on Evolutionary Computation.

[9]  Thomas C. Henderson,et al.  From Sensorimotor Data to Concepts : The Role of Symmetry , 2012 .

[10]  Michael E. Orrison,et al.  Image Processing with Wreath Product Groups , 2004 .

[11]  Thomas C. Henderson,et al.  Apparent symmetries in range data , 1988, Pattern Recognit. Lett..

[12]  Qiang Ji,et al.  A Bayesian Network Model for Automatic and Interactive Image Segmentation , 2011, IEEE Transactions on Image Processing.

[13]  Thomas C. Henderson,et al.  Symmetry as a basis for perceptual fusion , 2012, 2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[14]  Norman Fenton,et al.  Risk Assessment and Decision Analysis with Bayesian Networks , 2012 .

[15]  Thomas L. Griffiths,et al.  Visual Concept Learning: Combining Machine Vision and Bayesian Generalization on Concept Hierarchies , 2013, NIPS.

[17]  J. Tenenbaum,et al.  Generalization, similarity, and Bayesian inference. , 2001, The Behavioral and brain sciences.