{"title":"Mapping the space of skills: An approach for comparing embodied sensorimotor organizations","authors":"F. Kaplan, V. Hafner","doi":"10.1109/DEVLRN.2005.1490960","DOIUrl":null,"url":null,"abstract":"This article presents a mathematical framework based on information theory to compare temporally-extended embodied sensorimotor organizations. Central to this approach is the notion of configuration: a set of distances between information sources, statistically evaluated for a given time span. Because information distances capture simultaneously effects of physical closeness, intermodality, functional relationship and external couplings, a configuration characterizes an embodied interaction with a particular environment. In this approach, collections of skills can be mapped in a unified space as configurations of configurations. This article describes these different abstractions in a formal manner and presents results of preliminary experiments showing how this framework can be used to capture the behavioral organization of an autonomous robot","PeriodicalId":297121,"journal":{"name":"Proceedings. The 4nd International Conference on Development and Learning, 2005.","volume":"482 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2005-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"18","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. The 4nd International Conference on Development and Learning, 2005.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DEVLRN.2005.1490960","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 18
Abstract
This article presents a mathematical framework based on information theory to compare temporally-extended embodied sensorimotor organizations. Central to this approach is the notion of configuration: a set of distances between information sources, statistically evaluated for a given time span. Because information distances capture simultaneously effects of physical closeness, intermodality, functional relationship and external couplings, a configuration characterizes an embodied interaction with a particular environment. In this approach, collections of skills can be mapped in a unified space as configurations of configurations. This article describes these different abstractions in a formal manner and presents results of preliminary experiments showing how this framework can be used to capture the behavioral organization of an autonomous robot