2011 · 25 citations · 7 references
EngineeringComputer ScienceRobotics EngineeringHuman-robot InteractionHumanoid RoboticsRoboticsConversational User InterfacesHuman-robot CommunicationMultimodal InteractionSpeech InteractionControl ActionsHierarchyHuman ConversationHuman-ai ConversationHuman-robot DialogueSpeech-based Human-robot InteractionSpeech-based Interaction
WioNA (Wikipedia Ontology NAo) is proposed to build much better HRI by integrating four elements: Japanese speech interface, semantic interpretation, Japanese Wikipedia Ontology and Robot Action Ontology. WioNA is implemented on a humanoid robot "Nao". In WioNA, we developed two ontologies: Japanese Wikipedia Ontology and Robot Action Ontology. Japanese Wikipedia Ontology has a large size of concept hierarchy and instance network with many properties from Japanese Wikipedia (semi) automatically. By giving Japanese Wikipedia Ontology to Nao as wisdom, Nao can dialogue with users on many topics of various fields. Robot Action Ontology, in contrast, is built by organizing various performable actions of Nao to control and generate robot actions. Aligning Robot Action Ontology with Japanese Wikipedia Ontology enables Nao to perform related actions to dialogue topics. To show the validities of WioNA, we describe human-robot conversation logs of two case studies whose dialogue topics are sport and rock singer. These case studies show us how HRI goes well in WioNA with these topics.
7
Fabian M. Suchanek, Gjergji Kasneci, Gerhard Weikum · 2007 · 3.9K citations · Full text
Ontology-based multi-layered robot knowledge framework (OMRKF) for robot intelligence
Il Hong Suh, Gi Hyun Lim, Wonil Hwang et al. · 2007 · 77 citations