Artificial neural networks for coordination and control: The portability of experiential representations

It is time to locate Connectionist representation theory in the new wave of robotics research. The utility of representations developed in Artiicial Neural Networks during learning has been demonstrated in Cognitive Science research since the 1980s. The research reported here puts learned representations to work in a decentered control task, the disembodied arm problem, in which a mobile robot operates an arm xed to a table to pick up objects. There is no physical linkage between the arm and the robot and so the robot's point of view must be decentered. This is done by developing a modular Artiicial Neural Net system in three stages: (i) a Classiier net is trained with laser scan data; (ii) an Arm net is trained for picking up objects; (iii) an Inter net is trained to communicate and coordinate the sensing and acting. The completed system is shown to create new nonsymbolic transformationally invariant representations in order to perform the eeective generalisation of decentered viewpoints.