The University of Edinburgh -
Division of Informatics
Forrest Hill & 80 South Bridge

Research Paper #824

Title:Sufficient Neurocontrollers can be Surprisingly Simple
Authors:Lund,HH; Hallam,JC
Date:Aug 1996
Presented:Submitted to Robotics and Autonomous Systems
Keywords:evolutionary robotics, neurcontroller, khepera robot, sufficient requirements
Abstract:Behaviors such as exploration and homing, that seemingly demand a complex control system, only require a perceptron that connects a robot's sensors to its motors. this is shown by evolving such neurocontrollers for the Khepera robot. An exploitation of the robot's perception of the environment's geometrical shape allows the robot to encode time, even though explicitly it is not presented with the time and there are no recurrent connections in the neurocontroller. In a biological context, the robotics approach to show sufficient requirements for obtaining specific behaviors suggest that some biological experiments have to be re-done in order for the conclusion drawn from these biological experiments to be valid.

[Search These Pages] [DAI Home Page] [Comment]