Evolutionary learning for intelligent automation: A case study

Industrial automation calls for behavioral intelligence, that is, a mixture of flexibility, robustness and adaptiveness of robot behavior. We argue that efficient machine learning techniques can be a valuable tool for achieving behavioral intelligence. As a case study we apply ALECSYS, an implementation of a learning classifier system on a net of transputers, to a gross-motion problem for an industrial manipulator (an IBM 7547 with a SCARA geometry). A simple simulation environment allows us to experiment with different sensor configurations, and to obtain a first, coarse approximation of the robot’s controller through learning. The controller is subsequently refined through a learning session run on the physical robot. As a whole, our work demonstrates some interesting distinctive features of the evolutionary computation approach, viewed as a possible alternative to classical methods of software development.