• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.123-136
• /
• 2021

Teddy bear is a typical rag doll which has been loved by people all over the world for more than 100 years based on its cute and friendly image. In addition, as it has been together for a long time with us, it is considered as a friend of people with memories of all ages and sexes, not just animal doll. Teddy bear has been developing its appearance and character continually playing a role as the symbol of society and issues of an era beyond toys, however it still remains in the image of stuffed toys. Therefore, more advanced teddy bear characters should be created in line with the current environment and market conditions that are undergoing major changes based on the Internet and smart phones. Thus, the concept of the character and the recent development of the market were reflected and the meaning and current image of teddy bears were analyzed to develop new teddy bear stories, worldviews, and characters through design process. And it was created 3D characters, videos, and SNS channels through the developed 3D character design and motion design. Furthermore, we want to take a look at the direction in which Korea's character business can develop in accordance with global changes and suggest the possibility of entering as a character powerhouse.

• ETRI Journal
• /
• v.38 no.6
• /
• pp.1229-1239
• /
• 2016

For efficient interaction between humans and robots, robots should be able to understand the meaning and intention of human behaviors as well as recognize them. This paper proposes an interactive human intention reading method in which a robot develops its own knowledge about the human intention for an object. A robot needs to understand different human behavior structures for different objects. To this end, this paper proposes a hierarchical behavior knowledge network that consists of behavior nodes and directional edges between them. In addition, a human intention reading algorithm that incorporates reinforcement learning is proposed to interactively learn the hierarchical behavior knowledge networks based on context information and human feedback through human behaviors. The effectiveness of the proposed method is demonstrated through play-based experiments between a human and a virtual teddy bear robot with two virtual objects. Experiments with multiple participants are also conducted.