ADAM: adaptive autonomous machine

Abstract

This paper describes a part of the development of an adaptive autonomous machine that is able to move in an unknown world extract knowledge out of the perceived data, has the possibility to reason, and finally has the capability to exchange experiences and knowledge with other agents. The agent is not pre-programmed by its designer but was given simple rules of life, i.e. what is good and what is bad. By evaluating its sensor inputs these rules of life were transformed into a rule based reactive system. Simulations of the system showed that the agent is able to learn by its own experience. By representing the learned knowledge in an appropriate way, the acquired knowledge could be judged on its effectiveness and also this knowledge could be shared with other, less experienced agents.