Active immersion: the goal of communications with interactive agents

The creation of interactive animated agents is one of the most active research areas for researchers who are trying to develop various kinds of technologies that give such agents human-like behaviors. However, there are other important issues concerning the agents. One is the introduction of narratives into the behaviors of the agents. Since narratives are the basic way movies and novels take us into cyberspace, they can be effective for creating really human-like agents. Based on this idea, we have developed an interactive movie system (R. Nakatsu and N. Tosa, 1997) in which people can act the main roles and enjoy the story development. At the same time, we have learned that the existence of spontaneous interactions is also the key to the success of this new media. Based on this lesson, we have developed a second system (R. Nakatsu et al., 1999), where we tried to achieve a good balance between narrative-based and spontaneous interactions. In the first part of the paper we introduce our interactive movie system by focusing on how we achieved an integration of narrative-based and spontaneous interactions. Also, there is the important question: what is the objective of creating interactive animated agents? Although the technological aspects of such agents have been studied and discussed in detail, this critical question has rarely been discussed. In the latter part of the paper, we discuss what is the ultimate goal of interactions with interactive agents