Visible to the public Lifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence

TitleLifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence
Publication TypeConference Paper
Year of Publication2019
AuthorsPark, Chan Mi, Lee, Jung Yeon, Baek, Hyoung Woo, Lee, Hae-Sung, Lee, JeeHang, Kim, Jinwoo
Conference Name2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)
Date Publishedmar
Keywordsconversation agents, conversational agent, conversational agents, Data labeling, Growth and regression metaphor, Human Behavior, human computer interaction, human-robot interaction, intelligent robots, interaction design principle, Labeling, learning (artificial intelligence), lifespan design, Metrics, natural supervision, online labeling activity, Proposals, pubcrawl, real-time activity events, regression analysis, regression metaphor, regression metaphoric interaction design, robot intelligence, Robot sensing systems, Scalability, supervision process, Synthetic sensor
AbstractHuman's direct supervision on robot's erroneous behavior is crucial to enhance a robot intelligence for a `flawless' human-robot interaction. Motivating humans to engage more actively for this purpose is however difficult. To alleviate such strain, this research proposes a novel approach, a growth and regression metaphoric interaction design inspired from human's communicative, intellectual, social competence aspect of developmental stages. We implemented the interaction design principle unto a conversational agent combined with a set of synthetic sensors. Within this context, we aim to show that the agent successfully encourages the online labeling activity in response to the faulty behavior of robots as a supervision process. The field study is going to be conducted to evaluate the efficacy of our proposal by measuring the annotation performance of real-time activity events in the wild. We expect to provide a more effective and practical means to supervise robot by real-time data labeling process for long-term usage in the human-robot interaction.
DOI10.1109/HRI.2019.8673212
Citation Keypark_lifespan_2019