The Seer project: robotic experiments in sub-symbolic psychology

摘要

One of the major contributing factors to the success of tomorrow's robots will be their ability to learn and usefully adapt to new tasks and situations. Without this flexibility, robots will remain useful only in highly-constrained and controlled environments. For them to truly act in the real world they must be able to cope with a highly dynamic and changing environment while continually acquiring and refining new skills. Such robots must incorporate their experiences into future decision-making processes. Traditional approaches have been restricted by their need for predesigned symbolic representations. This is insufficient for the kind of real-world, flexible, open-ended functionality required of intelligent robots.