| Abstract: | The term shaping applies to a family of procedures which were originally developed in animal learning as methods of producing new and sometimes elaborate forms of behavior. The success of operant shaping methods in animal and abnormal psychology has attracted the attention of some roboticists who view these procedures as a means of generating adaptive behavior in both simulated and real robots. This paper outlines the two principal forms of shaping and looks at some of the associative and motivational influences which determine the course and outcome of shaping methods in animals. A number of recent robotic models which incorporate operant shaping concepts are then reviewed in terms of their eff ectiveness; the conclusion from this analysis is that, while some progress has been made, none of these models represent a satisfactory application of animal shaping procedures. It is clear that an effective implementation of shaping methods in behaviorbased robotics requires both a better understanding of the nature and course of shaping in real animals and the development, by roboticists and others, of more sophisticated models which can exploit this improved understanding. |
