High Level and Low Level Behavior Planning in a Context-Aware System for Smart Homes

• Main Authors: Chia-Hung, Chen, 陳嘉宏
• Other Authors: Alan, Liu
• Format: Others
• Language: zh-TW
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/22803756419794679902

碩士 === 國立中正大學 === 電機工程研究所 === 100 === With the growing popularity of smart homes and service robot, not only devices but also a service robot can provide services for user. Therefore, how to combine devices with service robot for meeting user’s requirements becomes a challenging topic. In this thesis, I have developed a context-aware system which uses ontology and a case base. I integrated the context-aware system with hierarchical task network (HTN) planning to find the actions which should be executed by a service robot to provide services for users. The main advantage of using ontology is to express machine-interpretable definitions on basic concept. Besides, I use case-based reasoning (CBR) as the reasoning method to determine what behavior a user engages in while interacting with smart homes. In addition, I also have constructed personal ontology that represents user’s preferences and the system will use this information to choose the suitable service for the user. Moreover, by analyzing the instruction entered by the user or reasoned by context-aware system, I use rule-based reasoning (RBR) and personal ontology to find the service which the user needs. Finally, using HTN planning, the system will produce a sequence of actions which a service robot should execute in order to satisfy the user requirements.