LEARNING CONCEPTS FROM SENSOR DATA OF A MOBILE ROBOT

Machine learning can be a most valuable tool for improving the flexibi lity and efficiency of robot applications. Many approaches to applying machine learning to robotics are known. Some approaches enhance the r obot's high-level processing, the planning capabilities, Other approac hes enhance the low-level processing, the control of basic actions. In contrast, the approach presented in this paper uses machine learning for enhancing the link between the low-level representations of sensin g and action and the high-level representation of planning. The aim is to facilitate the communication between the robot and the human user. A hierarchy of concepts is learned from route records of a mobile rob ot. Perception and action are combined at every level, i.e., the conce pts are perceptually anchored. The relational learning algorithm GRDT has been developed which completely searches in a hypothesis space, th at is restricted by rule schemata, which the user defines in terms of grammars.