S. Nishide, T. Ogata, R. Yokoya, Kazunori Komatani, H. Okuno, J. Tani
{"title":"基于主动感知经验的结构特征提取","authors":"S. Nishide, T. Ogata, R. Yokoya, Kazunori Komatani, H. Okuno, J. Tani","doi":"10.1109/ICKS.2008.9","DOIUrl":null,"url":null,"abstract":"Affordance is a feature of an object or environment that implies how to interact with it. Based on affordance theory, humans are said to perceive invariant structures for cognizing the object/environment for generating behaviors. In this paper, the authors present a method to extract invariant structures of objects from visual raw images, based on object manipulation experiences using a humanoid robot. The method consists of two training phases. The first phase utilizes Recurrent Neural Network with Parametric Bias (RN-NPB) to self-organize dynamical object features extracted during active sensing with objects. The second phase trains a hierarchical neural network attached to RNNPB for associating object images and robot motions with self-organized object features. Analysis of the model has uncovered static objects features that are closely related to dynamic object motions, such as round or stable.","PeriodicalId":443068,"journal":{"name":"International Conference on Informatics Education and Research for Knowledge-Circulating Society (icks 2008)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Structural Feature Extraction Based on Active Sensing Experiences\",\"authors\":\"S. Nishide, T. Ogata, R. Yokoya, Kazunori Komatani, H. Okuno, J. Tani\",\"doi\":\"10.1109/ICKS.2008.9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Affordance is a feature of an object or environment that implies how to interact with it. Based on affordance theory, humans are said to perceive invariant structures for cognizing the object/environment for generating behaviors. In this paper, the authors present a method to extract invariant structures of objects from visual raw images, based on object manipulation experiences using a humanoid robot. The method consists of two training phases. The first phase utilizes Recurrent Neural Network with Parametric Bias (RN-NPB) to self-organize dynamical object features extracted during active sensing with objects. The second phase trains a hierarchical neural network attached to RNNPB for associating object images and robot motions with self-organized object features. Analysis of the model has uncovered static objects features that are closely related to dynamic object motions, such as round or stable.\",\"PeriodicalId\":443068,\"journal\":{\"name\":\"International Conference on Informatics Education and Research for Knowledge-Circulating Society (icks 2008)\",\"volume\":\"119 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2008-01-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Informatics Education and Research for Knowledge-Circulating Society (icks 2008)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICKS.2008.9\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Informatics Education and Research for Knowledge-Circulating Society (icks 2008)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICKS.2008.9","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Structural Feature Extraction Based on Active Sensing Experiences
Affordance is a feature of an object or environment that implies how to interact with it. Based on affordance theory, humans are said to perceive invariant structures for cognizing the object/environment for generating behaviors. In this paper, the authors present a method to extract invariant structures of objects from visual raw images, based on object manipulation experiences using a humanoid robot. The method consists of two training phases. The first phase utilizes Recurrent Neural Network with Parametric Bias (RN-NPB) to self-organize dynamical object features extracted during active sensing with objects. The second phase trains a hierarchical neural network attached to RNNPB for associating object images and robot motions with self-organized object features. Analysis of the model has uncovered static objects features that are closely related to dynamic object motions, such as round or stable.