Autonomous Acquisition of Sensor-Motor Couplings in Robots

Fixed robot controllers are suitable for tasks whose main characteristics are known a priori. However, for tasks such as exploration of unknown territory, xed controllers tend to be too brittle as they rely on prede ned knowledge, supplied by the designer. For such tasks (i.e. tasks in which a-priori knowledge is limited) we propose to use self-organising controllers which allow the robot to acquire the necessary competences autonomously ([Nehmzow et al. 89]). The paper describes experiments with mobile robots, in which the robots autonomously determine e ective connections between their sensory input and their motor response to it. In these experiments, arti cial neural networks are used to store associations between sensory input and motor responses, the networks are trained in a selfsupervised way, making use of so-called instinct-rules which govern the robots' behaviour. The fast learning achieved enables the robots to adapt to changing circumstances such as changes in their environment or their morphology (e.g. sensor failure).