A situated model for sensory-motor coordination in gaze control

This paper shows that sensory-motor coordination contributes to the performance of situated models on the high-level task of artificial gaze control for gender recognition in static natural images. To investigate the advantage of sensory-motor coordination, we compare a non-situated model of gaze control with a situated model. The non-situated model is incapable of sensory-motor coordination. It shifts the gaze according to a fixed set of locations, optimised by an evolutionary algorithm. The situated model determines gaze shifts on the basis of local inputs in a visual scene. An evolutionary algorithm optimises the model's gaze control policy. In the experiments performed, the situated model outperforms the non-situated model. By adopting a Bayesian framework, we show that the mechanism of sensory-motor coordination is the cause of this performance difference. The essence is that the mechanism maximises task-specific information in the observations over time, by establishing dependencies between multiple actions and observations.

[1]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[2]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[3]  Paul A. Viola,et al.  Robust Real-time Object Detection , 2001 .

[4]  Ben J. A. Kröse,et al.  Probabilistic localization by appearance models and active vision , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[5]  Stefano Nolfi,et al.  Power and the limits of reactive agents , 2002, Neurocomputing.

[6]  Thomas G. Dietterich What is machine learning? , 2020, Archives of Disease in Childhood.

[7]  Bir Bhanu,et al.  Closed-Loop Object Recognition Using Reinforcement Learning , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[9]  Paul R. Cohen,et al.  Empirical methods for artificial intelligence , 1995, IEEE Expert.

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

[11]  Xin Yao,et al.  Performance Scaling of Multi-objective Evolutionary Algorithms , 2003, EMO.

[12]  Mario Köppen,et al.  Design of image exploring agent using genetic programming , 1999, Fuzzy Sets Syst..

[13]  M. Hartl,et al.  In the Eye of the Beholder , 1992 .

[14]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[15]  Andrew J. Calder,et al.  PII: S0042-6989(01)00002-5 , 2001 .

[16]  Dario Floreano,et al.  Coevolution of active vision and feature selection , 2004, Biological Cybernetics.

[17]  D. Parisi,et al.  The Agent-Based Approach: A New Direction for Computational Models of Development , 2001 .

[18]  Ming-Hsuan Yang,et al.  Learning Gender with Support Faces , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Eric O. Postma,et al.  Reactive Agents and Perceptual Ambiguity , 2005, Adapt. Behav..

[20]  A. Noë,et al.  A sensorimotor account of vision and visual consciousness. , 2001, The Behavioral and brain sciences.

[21]  S. Nolfi,et al.  Evolving Robots Able to Visually Discriminate Between Objects with Different Size , 2003 .

[22]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[23]  Randall D. Beer,et al.  The Dynamics of Active Categorical Perception in an Evolved Model Agent , 2003, Adapt. Behav..

[24]  Dana H. Ballard,et al.  Eye Movements for Reward Maximization , 2003, NIPS.