Affordance in Autonomous Robot

It is essential for the autonomous robots in the real world, filled with enormous amount of information, to catch only the useful and related information to their actions. Affordance would be one of the key-concept to be realized in the autonomous robots to make them able to perceive such useful information. This paper, therefore, tries to realize Affordance in an autonomous robot by introducing Inner Perceptual Model (IPM) as a field that will make the sensory inputs as a Grounded Symbol. An attempt to realize an emergent mechanism of Affordance is carried out by means of IPM, Active Sensing System, and Information Processing System. Four necessary-conditions to be satisfied are introduced to clarify whether the Perceptual Pattern in IPM could be the grounded inner representation of the environment. Computer simulations show the possibility that IPM would be an inner representation of the environment as Grounded Symbols. Moreover, the computer simulation shows possibility that proposed mechanism can distinguish the environment consists of the other robots from those consists of the obstacles. As a conclusion, we come to a hypothesis that the available action set recollected from observed sensory inputs corresponds to Affordance, and Affordance for robot.

[1]  Rodney A. Brooks,et al.  A Robot that Walks; Emergent Behaviors from a Carefully Evolved Network , 1989, Neural Computation.

[2]  Pattie Maes,et al.  Designing autonomous agents: Theory and practice from biology to engineering and back , 1990, Robotics Auton. Syst..

[3]  Benjamin Kuipers,et al.  Learning to Explore and Build Maps , 1994, AAAI.

[4]  Alberto Elfes,et al.  Sonar-based real-world mapping and navigation , 1987, IEEE J. Robotics Autom..

[5]  John McCarthy,et al.  SOME PHILOSOPHICAL PROBLEMS FROM THE STANDPOINT OF ARTI CIAL INTELLIGENCE , 1987 .

[6]  J. Gibson.  The Ecological Approach to Visual Perception , 1979 .

[7]  R. A. Brooks,et al.  Intelligence without Representation , 1991, Artif. Intell..

[8]  Billur Barshan,et al.  Differentiating Sonar Reflections from Corners and Planes by Employing an Intelligent Sensor , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Leslie Pack Kaelbling,et al.  Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons , 1991, IJCAI.

[10]  Franz Freyberger,et al.  Constructing maps for indoor navigation of a mobile robot by using an active 3D range imaging device , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[11]  Lindsay Kleeman,et al.  Mobile Robot Sonar for Target Localization and Classification , 1995, Int. J. Robotics Res..

[12]  E. Reed.  James J. Gibson and the psychology of perception , 1988 .

[13]  G. F. Cooper,et al.  Development of the Brain depends on the Visual Environment , 1970, Nature.

[14]  L. Kay.  An ultrasonic sensing probe as a mobility aid for the blind , 1964 .

[15]  Stevan Harnad,et al.  Symbol grounding problem , 1990, Scholarpedia.