NIM as a brain for a humanoid robot

In the context of the PACO+ project (http://www.paco-plus.org/), we aim at extending the rece ntly developed Natural Input Memory (NIM ) model [11] to a controller for a humanoid robot that translates real-world visual input into actions. The NIM controller can be conceived of as the ‘brain’ of the robot. This paper describes the initial step towards realizing a controller by extending NIM to a classifier that learns to map visual instances onto classes. The extend ed model, called NIM -CLASS is evaluated in an experiment that involves the classification of face images. The results of th e experiment show that NIM -CLASS is able to recognize and classify faces after a single encounter. In addition, NIM -CLASS is insensitive to variations in facial expressions, illumi nation conditions, and occlusions. These results lead us to the con clusion that N IM -CLASS provides a suitable basis for controlling the actions of a humanoid robot. In future work, we will extend NIM -CLASS to a controller that maps the classified visual inputs to actions.

[1]  A. L. Yarbus,et al.  Eye Movements and Vision , 1967, Springer US.

[2]  David Melcher,et al.  Accumulation and persistence of memory for natural scenes. , 2006, Journal of vision.

[3]  J. Findlay,et al.  Active Vision: The Psychology of Looking and Seeing , 2003 .

[4]  M. Chun,et al.  Contextual cueing of visual attention , 2022 .

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

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

[7]  K. Turano,et al.  Oculomotor strategies for the direction of gaze tested with a real-world activity , 2003, Vision Research.

[8]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[9]  C. Koch,et al.  A saliency-based search mechanism for overt and covert shifts of visual attention , 2000, Vision Research.

[10]  Rajesh P. N. Rao,et al.  Eye movements in iconic visual search , 2002, Vision Research.

[11]  Eric O. Postma,et al.  Modeling Recognition Memory Using the Similarity Structure of Natural Input , 2006, Cogn. Sci..

[12]  Robert M Nosofsky,et al.  A hybrid-similarity exemplar model for predicting distinctiveness effects in perceptual old-new recognition. , 2003, Journal of experimental psychology. Learning, memory, and cognition.

[13]  Aleix M. Martinez,et al.  The AR face database , 1998 .

[14]  Michael L. Mack,et al.  VISUAL SALIENCY DOES NOT ACCOUNT FOR EYE MOVEMENTS DURING VISUAL SEARCH IN REAL-WORLD SCENES , 2007 .

[15]  Jacob M.J. Murre,et al.  Learning and Categorization in Modular Neural Networks , 1992 .

[16]  Derrick J. Parkhurst,et al.  Modeling the role of salience in the allocation of overt visual attention , 2002, Vision Research.

[17]  M. Hayhoe,et al.  In what ways do eye movements contribute to everyday activities? , 2001, Vision Research.

[18]  G. Loftus.  Eye fixations and recognition memory for pictures , 1972 .

[19]  I. Gauthier,et al.  Visual object understanding , 2004, Nature Reviews Neuroscience.

[20]  David White,et al.  Robust representations for face recognition. , 2005 .

[21]  A. L. I︠A︡rbus.  Eye Movements and Vision , 1967 .

[22]  E. Postma,et al.  Knowledge-driven Gaze Control in the NIM Model , 2006 .

[23]  James L. McClelland,et al.  Familiarity breeds differentiation: a subjective-likelihood approach to the effects of experience in recognition memory. , 1998, Psychological review.

[24]  Linus Holm,et al.  Gaze control and recollective experience in face recognition , 2006 .

[25]  Rolf Pfeifer,et al.  Understanding intelligence , 2020, Inequality by Design.

[26]  J. Henderson.  Human gaze control during real-world scene perception , 2003, Trends in Cognitive Sciences.

[27]  D. S. Wooding,et al.  The relationship between the locations of spatial features and those of fixations made during visual examination of briefly presented images. , 1996, Spatial vision.

[28]  Antonio Torralba,et al.  Top-down control of visual attention in object detection , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[29]  Eugene McSorley,et al.  Saccade target selection in visual search: accuracy improves when more distractors are present. , 2003, Journal of vision.

[30]  Derrick J. Parkhurst,et al.  Scene content selected by active vision. , 2003, Spatial vision.

[31]  A. Martínez,et al.  The AR face databasae , 1998 .

[32]  Joachim Denzler,et al.  A Comparison of Nearest Neighbor Search Algorithms for Generic Object Recognition , 2006, ACIVS.

[33]  R. Shiffrin,et al.  A model for recognition memory: REM—retrieving effectively from memory , 1997, Psychonomic bulletin & review.