{"title":"RECOGNIZING BEHAVIOR IN HAND-EYE COORDINATION PATTERNS.","authors":"Weilie Yi, Dana Ballard","doi":"10.1142/S0219843609001863","DOIUrl":null,"url":null,"abstract":"<p><p>Modeling human behavior is important for the design of robots as well as human-computer interfaces that use humanoid avatars. Constructive models have been built, but they have not captured all of the detailed structure of human behavior such as the moment-to-moment deployment and coordination of hand, head and eye gaze used in complex tasks. We show how this data from human subjects performing a task can be used to program a dynamic Bayes network (DBN) which in turn can be used to recognize new performance instances. As a specific demonstration we show that the steps in a complex activity such as sandwich making can be recognized by a DBN in real time.</p>","PeriodicalId":50319,"journal":{"name":"International Journal of Humanoid Robotics","volume":null,"pages":null},"PeriodicalIF":0.9000,"publicationDate":"2009-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1142/S0219843609001863","citationCount":"51","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Humanoid Robotics","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1142/S0219843609001863","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ROBOTICS","Score":null,"Total":0}
引用次数: 51
Abstract
Modeling human behavior is important for the design of robots as well as human-computer interfaces that use humanoid avatars. Constructive models have been built, but they have not captured all of the detailed structure of human behavior such as the moment-to-moment deployment and coordination of hand, head and eye gaze used in complex tasks. We show how this data from human subjects performing a task can be used to program a dynamic Bayes network (DBN) which in turn can be used to recognize new performance instances. As a specific demonstration we show that the steps in a complex activity such as sandwich making can be recognized by a DBN in real time.
期刊介绍:
The International Journal of Humanoid Robotics (IJHR) covers all subjects on the mind and body of humanoid robots. It is dedicated to advancing new theories, new techniques, and new implementations contributing to the successful achievement of future robots which not only imitate human beings, but also serve human beings. While IJHR encourages the contribution of original papers which are solidly grounded on proven theories or experimental procedures, the journal also encourages the contribution of innovative papers which venture into the new, frontier areas in robotics. Such papers need not necessarily demonstrate, in the early stages of research and development, the full potential of new findings on a physical or virtual robot.
IJHR welcomes original papers in the following categories:
Research papers, which disseminate scientific findings contributing to solving technical issues underlying the development of humanoid robots, or biologically-inspired robots, having multiple functionality related to either physical capabilities (i.e. motion) or mental capabilities (i.e. intelligence)
Review articles, which describe, in non-technical terms, the latest in basic theories, principles, and algorithmic solutions
Short articles (e.g. feature articles and dialogues), which discuss the latest significant achievements and the future trends in robotics R&D
Papers on curriculum development in humanoid robot education
Book reviews.