Continuous categories for a mobile robot Export

@inproceedings{citeulike:907482, abstract = {Autonomous agents make frequent use of knowledge in the form of categories | categories of objects, human gestures, web pages, and so on. This paper describes a way for agents to learn such categories for themselves through interaction with the environment. In particu- lar, the learning algorithm transforms raw sensor read- ings into clusters of time series that have predictive value to the agent. We address several issues related to the use of an uninterpreted sensory apparatus and show specic examples where a Pioneer 1 mobile robot interacts with objects in a cluttered laboratory setting.}, author = {Rosenstein, M. T. and Cohen, P. R.}, booktitle = {Proceedings of the sixteenth national conference on Artificial intelligence}, citeulike-article-id = {907482}, keywords = {need-to-print, symbol-grounding}, pages = {634--640}, posted-at = {2006-10-20 06:53:20}, priority = {3}, title = {Continuous categories for a mobile robot}, year = {1999} }

TY - CONF ID - citeulike:907482 L3 - citeulike-article-id:907482 N2 - Autonomous agents make frequent use of knowledge in the form of categories | categories of objects, human gestures, web pages, and so on. This paper describes a way for agents to learn such categories for themselves through interaction with the environment. In particu- lar, the learning algorithm transforms raw sensor read- ings into clusters of time series that have predictive value to the agent. We address several issues related to the use of an uninterpreted sensory apparatus and show specic examples where a Pioneer 1 mobile robot interacts with objects in a cluttered laboratory setting. EP - 640 TI - Continuous categories for a mobile robot T2 - Proceedings of the sixteenth national conference on Artificial intelligence SP - 634 KW - need-to-print KW - symbol-grounding AU - Rosenstein, MT AU - Cohen, PR PY - 1999/// ER -