Reactive Agents and Perceptual Ambiguity

Reactive agents are generally believed to be incapable of coping with perceptual ambiguity (i.e., identical sensory states that require different responses). However, a recent finding suggests that reactive agents can cope with perceptual ambiguity in a simple model (Nolfi, 2002). This paper investigates to what extent reactive and nonreactive agents can cope with perceptual ambiguity, and which strategies are employed when doing so. A model of active categorical perception (called Acp) is introduced. In Acp, situated agents with different types of neurocontrollers are optimized to categorize objects by adaptively coordinating action and perception. Our experiments show that both nonreactive and reactive agents can cope with perceptual ambiguity. An analysis of the behavior reveals that nonreactive agents use their internal memory to cope with perceptual ambiguity, while reactive agents use the environment as an external memory to compensate for their lack of an internal memory. We conclude that reactive agents can cope with perceptual ambiguity in the context of active categorical perception, and that they can organize their behavior according to stimuli that are no longer present, especially when they incorporate a nonlinear sensorimotor mapping. Moreover, we may conclude that sensory state-transition diagrams provide insight into the strategies employed by reactive agents to deal with perceptual ambiguity, and their use of the environment as an external memory.

[1]  A. Clark.  Being There: Putting Brain, Body, and World Together Again , 1996 .

[2]  Guy Hartcup,et al.  Camouflage: A History of Concealment and Deception in War , 1979 .

[3]  R. L. Gregory,et al.  Perceptual filling in of artificially induced scotomas in human vision , 1991, Nature.

[4]  Stefano Nolfi,et al.  Evolving robots able to integrate sensory-motor information over time , 2001, Theory in Biosciences.

[5]  P. Maglio,et al.  Reaction and reflection in Tetris , 1992 .

[6]  David E. Goldberg,et al.  Genetic Algorithms, Tournament Selection, and the Effects of Noise , 1995, Complex Syst..

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

[8]  Stefano Nolfi,et al.  Exploiting the Power of Sensory-Motor Coordination , 1999, ECAL.

[9]  S. Harnad.  Categorical Perception: The Groundwork of Cognition , 1990 .

[10]  Seth Bullock,et al.  Advances in Artificial Life: Proceedings of the Seventh European Conference on Artificial Life (ECAL 2003) , 1999 .

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

[13]  Stevan Harnad,et al.  Cognition is categorization , 2005 .

[14]  Bram Bakker,et al.  Trading off perception with internal state: reinforcement learning and analysis of Q-Elman networks in a Markovian task , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[15]  Daniel Reisberg,et al.  Can mental images be ambiguous , 1985 .

[16]  Eric O. Postma,et al.  The Natural Input Memory Model , 2005 .

[17]  Tao Xiong,et al.  A combined SVM and LDA approach for classification , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[18]  J. O'Regan,et al.  Solving the "real" mysteries of visual perception: the world as an outside memory. , 1992, Canadian journal of psychology.

[19]  G. Hesslow.  Conscious thought as simulation of behaviour and perception , 2002, Trends in Cognitive Sciences.

[20]  Edwin Hutchins,et al.  How a Cockpit Remembers Its Speeds , 1995, Cogn. Sci..

[21]  Pattie Maes,et al.  Toward the Evolution of Dynamical Neural Networks for Minimally Cognitive Behavior , 1996 .

[22]  C. Balkenius.  Natural intelligence in artificial creatures , 1995 .

[23]  Wai-Tat Fu,et al.  Soft constraints in interactive behavior: the case of ignoring perfect knowledge in-the-world for imperfect knowledge in-the-head , 2004, Cogn. Sci..

[24]  Jane Van Zandt Brower,et al.  EXPERIMENTAL STUDIES OF MIMICRY IN SOME NORTH AMERICAN BUTTERFLIES: PART I. THE MONARCH, DANAUS PLEXIPPUS, AND VICEROY, LIMENITIS ARCHIPPUS ARCHIPPUS , 1958 .

[25]  H. Evans.  The Study of Instinct , 1952 .

[26]  JANE VAN ZANDT BROWER,et al.  Experimental Studies of Mimicry in some North American Butterflies , 1957, Nature.

[27]  Edwin Hutchins.  How a Cockpit Remembers Its Speeds , 1995 .

[28]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[29]  R. Shillcock,et al.  Proceedings of the Seventeenth Annual Conference of the Cognitive Science Society , 1995 .

[30]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[31]  Tijsseling Ag,et al.  Connectionist models of catergorization : a dynamical approach to cognition. , 1998 .

[32]  R. Bajcsy.  Active perception , 1988 .

[33]  William Rowan,et al.  The Study of Instinct , 1953 .

[34]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[35]  Stewart W. Wilson,et al.  From Animals to Animats 5. Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior , 1997 .

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

[37]  E. Thelen.  Motor development: A new synthesis. , 1995 .

[38]  David Kirsh,et al.  Complementary Strategies: Why we use our hands when we think , 1995 .

[39]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[40]  Stefano Nolfi,et al.  Active perception: a sensorimotor account of object categorization , 2002 .

[41]  Rolf Pfeifer,et al.  Sensory - motor coordination: The metaphor and beyond , 1997, Robotics Auton. Syst..