Attentive in-screen agent — In-screen agent that looks like a specific direction —,Takuto Watanabe,IEICE Tech. Rep., vol. 119, no. 189, CNR2019-15, pp. 19-23, Aug. 2019.

In recent years, 3DCG characters have become widespread and are being used in-screen agents as avatarsfor interactive agents. In this study, we propose a method to give a sense of coexistence and unity of space by lettingthe user follow the background and the method of projecting the gaze target to the pupil. For the experiment, anagent that can manually select the gaze target was created and evaluated.

Voice Expression with Pseudo-emotion in Human-Robot Communication, Tae Kuwahara, Takumi Horie, Kazunori Takashio, IEICE Tech. Rep., vol. 119, no. 81, CNR2019-2, pp. 7-11, June 2019.

In a robot and human conversation, the robot’s flat voice is a one of the factor that boring conversation. Automatically adjust emotional expressions to speech from virtual emotion in a robot. In this study, I verify that communication will be smooth when it considers the flow of emotional change from the conversation history.

Matching Things and Information Using Associative Concept Dictionary in v-IoT, Kentaro Taninaka, Kazunori Takashio, IEICE Tech. Rep., vol. 119, no. 81, CNR2019-8, pp. 37-42, June 2019.

The miniaturization and decreasing cost of networking computers, alongwith the advancement of cloud infrastructure has eased the implementation of it inproducts for manufacturers. The increase in such products has led to the rise in IoTdevices with information-provision function. However, it is difficult to give suchfunction to products which engage in an one-way association in our daily life likedaily commodities, since it requires the device to have a wealth of computationalresource. In this paper, we propose Virtual IoT system, the approach which addinformation-giving functions to the non-computing objects using Mixed Realitytechnology. This system enables appropriate things to give adequate informationat the right timing. In this paper, we explain the detail and design of Virtual IoTsystem. In addition, we conduct an experiment to evaluate impression and usabilityof Virtual IoT to disclose the descriptive power.

Effectiveness of Manga-Effects To Telepresence Communication System, Risa Takemura, Takumi Horie, Kazunori Takashio, IEICE Tech. Rep., vol. 118, no. 306, CNR2018-33, pp. 87-92, Nov. 2018.

Today’s telecommunication systems have been greatly evolving, while the video calls used on telepresence robots still seems bland. We hypothesize that the augmentation of video calls with Manga-Effects will help users attain a sense of familiarity and find entertaining components within their conversations. In specific, adding various Manga-Effects over the video call, respectively selected upon the users’ facial expression, will help visually emphasize certain emotions. This experiment analyzes the level of users’ involvement in the conversation, and verifies our hypothesis.

Effective use of AR and IoT Technology for Displaying Life-support Information — Comparison between IoT Devises versus Information-giving from Commodity –, Kentaro Taninaka, Kazunori Takashio, IEICE Tech. Rep., vol. 118, no. 184, CNR2018-12, pp. 7-11, Aug. 2018.

IoT devices which display life-support information to users is increasing. However, it is difficult to add information-giving function to the product which close to user’s life, i.e. commodity. In fact, this information is given from the device which have a wealth computation source. In this research, we propose the approach which add information-giving function to those IoT introduction difficult things, using augmented reality technology. This system enables right things to give right information in right timing.

C2AT2 HUB: Long-term Characterization of Robots based on Human Child’s Personality Development, Shintaro Kawanago, Kazunori Takashio, 27th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2018), Aug. 2018.

Inadequate variety of personalities for communication robots may cause unnatural interac- tion with them and reduction in attachment. This paper proposes C2 AT2 HUB, where communication robots are characterized by changing tendency of affect transition based on long-term interaction with users. In C2AT2 HUB, robots’ affect is defined as two types; “interpersonal affect” and “emotions”, and transition of each type of affect is adjusted by history of users’ actions to robots in order to characterize robots gradually. Evaluation experiment revealed our approach characterizes robots naturally and improves impression of robots.

Handling Conversation Interruption in Many-to-Many HR Interaction Considering Emotional Behaviors and Human Relationships : Takumi Horie, Kazunori Takashio, 27th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2018), Aug, 2018.

In the future, communication robots are expected to join many-to-many human-robot interactions. Thus, robots must handle interruptions requesting a new task outside of the current conversation. In this paper, we propose a novel scheduler which decides switch timing of conversational tasks when a robot is interrupted. The model grasps the structure of the conversation and finds its breakpoints based on adjacency pairs. In order to decide whether to switch conversational tasks on each breakpoint or not, the model prioritizes conversational tasks considering an importance of its topic and a length as contexts of each conversational task. The model also uses human relationships and emotional behaviors to decide priority of conversational tasks. The result of an evaluation experiment shows that our proposed scheduler could impress subjects more favorably than that which always prioritizes an interrupter.