Continuous Categories for a Mobile Robot

Autonomous agents makefrequent use of knowledgein the formof categories -- categories of objects, human gestures, webpages, and so on. This paper describes a wayfor agents to learn such categories for themselves through interaction with the environment. In particular, the learning algorithmtransformsraw sensor readings into clusters of time series that havepredictive value to the agent. Weaddress several issues related to the use of an uninterpreted sensory apparatus and showspecific exampleswherea Pioneer 1 mobilerobot interacts withobjects in a cluttered laboratorysetting.

Authors

• Michael T. Rosenstein Andrew H. Fagg
• Paul R. Cohen University of Massachusetts; Tim Oates
• University of Massachusetts

Keywords

No keywords are indexed for this paper.