Papers - OSAWA Hirotaka

Micro Machines, Macro Visions: Experts' Visions and Laypeoples' Perceptions of Social Futures with In-Body Cybernetic Avatars

Hohendanner M., Ullstein C., Mesenhöller M., Osawa H., Grossklags J.

Hai 2025 Proceedings of the 13th International Conference on Human Agent Interaction    366 - 368 2026.01

Research paper (international conference proceedings), Joint Work, Accepted

　View Summary

Cybernetic avatars (CAs) play a key role in Japan's vision for Society 5.0 - a society where cyberspace and the physical world are closely intertwined to address social challenges. In-body cybernetic avatars, a sub-category, are remote-controlled micro-/nano-scale avatars or robots operating inside organisms, such as the human body. To explore future applications and implications of interactions with these technologies, we conducted an expert workshop (N = 16) in Japan. Experts co-created visions of a desirable future related to in-body CAs, identifying types of interactions, benefits, and potential risks. In a second study, we engaged an international student audience (N = 174) with three expert-developed scenarios to assess non-expert perceptions beyond Japan. We find that non-experts responded positively to all three types of in-body CA interactions. In addition, our study contributes to a better understanding of potential benefits and risks of in-body CAs from experts' perspectives and sheds light on which factors are perceived as most impactful by non-experts.

• Access to Document (DOI)

Effective Engagement by Agents for Sense of Ownership and Self-Determination

Fukushima K., Kawashima R., Osawa H.

Hai 2025 Proceedings of the 13th International Conference on Human Agent Interaction    415 - 417 2026.01

　View Summary

Persuasive communication that emphasizes a sense of ownership and self-determination is essential to achieve social good, such as the sustainable development goals. Although agent-based persuasion mainly targets attitude change, encouraging proactive participation in social issues also requires attention to the awareness of change, focusing on developing these internal motivations. This study aims to identify effective persuasion by agents regarding their sense of ownership and self-determination. To this end, we conducted an online survey with 400 participants, using a 2 × 2 design that manipulated the "target of persuasive act"(direct persuasion vs. indirect persuasion through agent-to-agent conversation [overheard communication (OHC)]) and the "target of persuasive content"(group- vs. individual-directed messages). The results revealed that individual-directed messages conveyed through the OHC were more effective.

• Access to Document (DOI)

NLP2025 Theme Session “AIWolf: Conversation Game of Liar Detection and Persuation with LLM”

Yoshinobu Kano, Fujio Toriumi, Michimasa Inaba, Hirotaka Osawa, Daisuke Katagami, Takashi Otsuki, Claus Aranha, Kei Harada, Takeshi Ito

Journal of Natural Language Processing (Association for Natural Language Processing)  32 ( 2 ) 720 - 726 2025

ISSN  1340-7619

• Access to Document (DOI)

Charting the Future: An Experimental Investigation of a Chart Tool's Potential to Support Science Fiction Prototyping Workshops

Tomoya Minegishi, Miwa Nishinaka, Kenichi Shibata, Kenji Nakamura, Dohjin Miyamoto, Atsuya Fujimoto, Hirotaka Osawa

Social Sciences and Humanities Open (Elsevier BV)  12 2025

　View Summary

This study investigates the potential of chart tools to augment or replace facilitation functions in Science Fiction Prototyping (SFP) workshops conducted by young students. SFP is a workshop methodology that utilizes science fiction to foster future visions, but facilitating SFP workshops poses significant challenges, particularly for young people with limited experience and vocabulary. To address this, a chart tool was developed to complement or delegate facilitation, and an experimental workshop was conducted to compare participants' discussions with and without the tool. The results indicate that the chart tool effectively supports certain facilitation functions, including “divergence and convergence” and “reflection.” The tool also enhances the length of the stories, indicating improved participants' imagination. The results of the experimental workshops suggested that the developed chart tool has the potential to complement some aspects of the facilitator's role, however, it did not replace the experienced human facilitators.

• Access to Document (DOI)

Proposing a Virtual Agent to Enhance Discussion through Idea Presentation

Tomoya Minegishi, Hirotaka Osawa

Annual conference of the Japanese Society for Artificial Intelligence (Japanese Society for Artificial Intelligence)   2024.05

Research paper (conference, symposium, etc.), Joint Work, Last author

Proposing a Virtual Agent to Enhance Discussion through Idea Presentation

Reo Fujiki, Tomoya Minegishi, Hirotaka Osawa

Annual conference of the Japanese Society for Artificial Intelligence (Japanese Society for Artificial Intelligence)   2024.05

Research paper (conference, symposium, etc.), Joint Work, Last author

Proposing a Virtual Agent to Enhance Discussion through Idea Presentation

Kazuhiro Kudo, Hirotaka Osawa, Tomoya Minegishi

Annual conference of the Japanese Society for Artificial Intelligence (Japanese Society for Artificial Intelligence)   2024.05

Research paper (conference, symposium, etc.), Joint Work

Analysis of Implicit Signals in the Cooperative Card Game Hanabi

Kansei Miyata, Hirotaka Osawa

HAI symposium 2024  2024.03

Research paper (conference, symposium, etc.), Joint Work, Last author

Representation of Openness to Experience Using a Large Language Model Chat System

Hibiki Harano, Hirotaka Osawa

HAI symposium 2024  2024.03

Research paper (conference, symposium, etc.), Joint Work, Last author

Analysis of the risks of artificial intelligence as portrayed in science fiction works

Hibiki Harano, Hirotaka Osawa

HAI symposium 2024  2024.03

Research paper (conference, symposium, etc.), Joint Work, Last author

Human interpersonal distance and impression analysis of a Virtual Robot Head

Misuzu Ando, Tomoya Minegishi, Hirotaka Osawa

HAI symposium 2024  2024.03

Research paper (conference, symposium, etc.), Joint Work, Last author

Interactive interaction between agent and toddler in a make-believe experience

Kazuma Ichikawa, Hirotaka Osawa

HAI symposium 2024  2024.03

Research paper (conference, symposium, etc.), Joint Work, Last author

良い倫理的意思決定のための倫理綱領――研究・イノベーションと倫理

Kukita Minao

電子情報通信学会誌 106(3)   178 - 183 2023

Research paper (other academic), Joint Work

• CiNii Research

協力ゲーム Hanabi を用いた察するコミュニケーションのモデル 構築

森田 純哉, 大澤 博隆

HAI シンポジウム 2023論文集 17 2023

Research paper (conference, symposium, etc.), Joint Work

• CiNii Research

SFプロトタイピングを手助けする多人数同時接続型Webアプリケーションの試作

峯岸 朋弥, 宮本 道人, 大澤 博隆

研究報告グループウェアとネットワークサービス 2022-GN-11 ( 18 ) 1 - 4 2022.03

Research paper (conference, symposium, etc.), Joint Work, Last author

The Proposal of Cooperative Behavior Analysis using Cognitive Model in Hanabi Game

KAWAGOE Atsushi, OSAWA Hirotaka

Proceedings of the Annual Conference of JSAI (The Japanese Society for Artificial Intelligence)  JSAI2022 ( 0 ) 4I3OS26b04 - 4I3OS26b04 2022

Research paper (conference, symposium, etc.), Joint Work, Last author, Corresponding author

　View Summary

<p>The cooperative game Hanabi is a suitable interactive subject for analyzing cooperative behavior based on implicit intention communication. In recent years, research has been conducted to analyze people's cooperative behavior by comparing the results of cooperating with several Hanabi agents that behave differently. However, these methods have problems such as large costs of experiment with human subjects and the inability to directly observe human's internal psychological states. One solution to these problems is to use models created on cognitive architectures, which are used to reproduce human behavior, and conduct simulations. In this study, we simulated the Hanabi game using model, developed on the cognitive architecture ACT-R, with and without risky actions. As a result, we found that the time spent per game changed similarly to that of the human Hanabi game. It was also suggested that having risky actions as options reduced the learning efficiency to improve scores and increased time required for action. In addition, memory retrieval was found to be a factor that increased the time required for action decisions in Hanabi play.</p>

• Access to Document (DOI)
• CiNii Research

協力ゲーム Hanabi を用いた協調行動のモデル化 ー共通経験の蓄積に関する検討ー

森田 純哉, 大澤 博隆

日本認知科学年次大会論文集 2022 2022

Research paper (conference, symposium, etc.), Joint Work

• CiNii Research

Evaluation of Future Vision Creation Using SF Prototyping

Hirotaka Osawa, Dohjin Miyamoto, Atsuya Fujimoto, Hozuma Sekine

Interaction 2021  2021.03

Research paper (conference, symposium, etc.), Joint Work, Lead author, Corresponding author

ENVISIONING FUTURE OF ARTIFICIAL INTELLIGENCE WITH SCIENCE FICTION

Hirotaka Osawa, Satoshi Hase, Dohjin Miyamoto, Reina Saijo, Kentaro Fukuchi, Yoichiro Miyake

Technologos (PNRPU Publishing House)  2020 ( 2 ) 42 - 52 2020.02

Research paper (bulletin of university, research institution), Joint Work, Lead author, Corresponding author,  ISSN  2687-0266

• Access to Document (DOI)

Research of correlation between personality of humans and evaluation of the game agent in cooperative game Hanabi

KAWAGOE,Atsushi, OSAWA,Hirotaka

Proceedings of the Annual Conference of JSAI (The Japanese Society for Artificial Intelligence)  2020 ( 0 ) 2F4OS20a03 - 2F4OS20a03 2020

Research paper (conference, symposium, etc.), Joint Work, Last author

　View Summary

<p>When we meet a person for the first time, impression of the person is positively correlated with the similarity of the personality. In this paper, the authors researches on whether such a correlation appears even between human and game agent. The author uses AI plays cooperative card game Hanabi as the game agent. The author implemented two kinds of Hanabi agent which has difference on tendency to take risky plays. Participants of an experiment played Hanabi with both agents and evaluate them. As a result, there are some positive correlations between humans' points of view of risk and failure and their evaluation in similar agent. This suggests that we need to take difference of users' personality into account when we design cooperative AI.</p>

• Access to Document (DOI)
• CiNii Research