In this study, we aim to clarify the mutual physical behavior to generate empathy between speakers in group discussion (group discussion), and to develop teaching devices to support the acquisition. In this study, we use “werewolf game", an educational game to gain trust within a group through discussion, as an index problem of analysis and teaching of physical interaction in group discussion. The werewolf analysis included several studies, including an analysis of werewolf game communication, a study of tri-werewolf, the smallest system in werewolf games, and an analysis of non-verbal information in human-to-human werewolf games.

論文

  • Osawa, Hirotaka, Takashi Otsuki, Claus de Castro Aranha, and Fujio Toriumi. 2019. “Negotiation in Hidden Identity: Designing Protocol for Werewolf Game.” In Twelfth International Workshop on Agent-Based Complex Automated Negotiations, 1–4.
  • 高山周太郎, and 大澤博隆. 2019. “実世界人狼ゲームのジェスチャーの分析.” In 人工知能学会全国大会, 3F3-OS-14a – 01.
  • Wang, Bohao, Hirotaka Osawa, Takuya Toyono, Fujio Toriumi, and Daisuke Katagami. 2018. “Development of Real-World Agent System for Werewolf Game.” Proceedings of the 17th International Conference on Autonomous Agents and Multi-Agent Systems. International Foundation for Autonomous Agents and Multiagent Systems.
  • Hirofumi Nakamura, Daisuke Katagami, Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Kosuke Shinoda, and Yoshinobu Kano. 2017. Generating human-like discussion by paraphrasing a translation by the AIWolf Protocol using Werewolf BBS Logs. In FUZZ-IEEE.
  • 大澤博隆, 汪博豪, and 佐藤健. 2017. 進化シミュレーションを用いた３人人狼の分析. In 日本ソフトウェア科学会第34回大会, 2–6.
  • 豊野拓也 and 大澤博隆. 2017. 人狼ゲームを演じるロボットエージェントシステムの作成. In 人工知能学会全国大会, 1L2-3.
  • Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Daisuke Katagami, Kosuke Shinoda, and Hitoshi Matsubara. 2016. AI Wolf Contest － Development of Game AI using Collective Intelligence －. In Computer Games Workshop at IJCAI 2016.
  • Nakamura, Hirofumi, Daisuke Katagami, Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Kosuke Shinoda, and Yoshinobu Kano. 2017. “Generating Human-like Discussion by Paraphrasing a Translation by the AIWolf Protocol Using Werewolf BBS Logs.” In FUZZ-IEEE.
  • 鳥海不二夫, 稲葉通将, 大澤博隆, 片上大輔, 篠田孝祐, and 松原仁. 2016. “ゲームプログラミング大会を用いた集合知的ゲーム AI 開発手法－人狼知能大会の開催と参加エージェントの分析－.” 日本デジタルゲーム学会論文誌 9 (1): 1–11.
  • 鳥海不二夫, 片上大輔, 大澤博隆, 稲葉通将, 篠田孝祐, and 狩野芳伸. 2016. 人狼知能 だます・見破る・説得する人工知能. 森北出版.
  • Hideyuki Takahashi, Midori Ban, Hirotaka Osawa, Junya Nakanishi, Hidenobu Sumioka, and Hiroshi Ishiguro. 2017. Huggable Communication Medium Maintains Level of Trust during Conversation Game Hideyuki. frontiers in Psychology 8: 1862.
  • Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Daisuke Katagami, Kosuke Shinoda, and Hitoshi Matsubara. 2016. AI Wolf Contest － Development of Game AI using Collective Intelligence －. In Computer Games Workshop at IJCAI 2016.
  • Nakamura, Noritsugu, Michimasa Inaba, Kenichi Takahashi, Fujio Toriumi, Hirotaka Osawa, Daisuke Katagami, and Kousuke Shinoda. 2016. “Constructing a Human-like Agent for the Werewolf Game Using a Psychological Model Based Multiple Perspectives.” In IEEE SSCI, 1–8.
  • Katagami, D., M. Kanazawa, F. Toriumi, H. Osawa, M. Inaba, and K. Shinoda. 2015. “Movement Design of a Life-like Agent for the Werewolf Game.” In IEEE International Conference on Fuzzy Systems. Vol. 2015-Novem. https://doi.org/10.1109/FUZZ-IEEE.2015.7338087.
  • 栢野航, 工藤佑介, 大澤博隆, 片上大輔, 鳥海不二夫, 稲葉通将, and 篠田考祐. 2015. 人狼を演じるロボットエージェントシステムの作成. In HAIシンポジウム2015, G-21.
  • Kobayashi, Yu, Hirotaka Osawa, Michimasa Inaba, Kosuke Shinoda, Fujio Toriumi, and Daisuke Katagami. 2014. “Development of Werewolf Match System for Human Players Mediated with Lifelike Agents.” In Proceedings of the Second International Conference on Human-Agent Interaction - HAI ’14, 205–7. New York, New York, USA: ACM Press. https://doi.org/10.1145/2658861.2658923.
  • Katagami, Daisuke, Shono Takaku, Michimasa Inaba, Hirotaka Osawa, Kosuke Shinoda, Junji Nishino, and Fujio Toriumi. 2014. “Investigation of the Effects of Nonverbal Information on Werewolf.” In 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 982–87. IEEE. https://doi.org/10.1109/FUZZ-IEEE.2014.6891847.
  • 大澤博隆. 2013. コミュニケーションゲーム「人狼」におけるエージェント同士の会話プロトコルのモデル化. In HAIシンポジウム2013.

解説

  • 鳥海不二夫, 狩野芳伸, 大槻恭士, 大澤博隆, アランニャクラウス, 稲葉通将, and 片上大輔. 2020. “人狼知能大会 ─国際大会と自然言語大会を終えて─.” 人工知能 35 (3): 344–50.
  • 片上大輔, 鳥海不二夫, 大澤博隆, 狩野芳伸, 稲葉通将, and 大槻 恭士. 2018. “人狼知能研究のすすめ.” 知能と情報 30 (5): 236–44.
  • 片上大輔, 鳥海不二夫, 大澤博隆, 稲葉通将, 篠田孝祐, and 松原仁. 2015. “人狼知能プロジェクト.” 人工知能学会誌 30 (1): 65–73.

本研究では、人間の集団討論（グループディスカッション）において、話者間に共感を生みだすための相互の身体的振る舞いの解明を行うとともに、その習得支援を行うための教示デバイスの開発を目指す。本研究では集団討論における身体的相互作用の解析および教示の指標課題として、討論を通じてグループ内の信頼を勝ち取る教育ゲームである「人狼ゲーム」を用いる。人狼の分析では、人狼ゲームのコミュニケーションの分析、人狼ゲームの最小系である3人人狼の検討、人間同士の人狼ゲームの非言語情報分析など、いくつかの研究を行っている。

論文

  • Osawa, Hirotaka, Takashi Otsuki, Claus de Castro Aranha, and Fujio Toriumi. 2019. “Negotiation in Hidden Identity: Designing Protocol for Werewolf Game.” In Twelfth International Workshop on Agent-Based Complex Automated Negotiations, 1–4.
  • 高山周太郎, and 大澤博隆. 2019. “実世界人狼ゲームのジェスチャーの分析.” In 人工知能学会全国大会, 3F3-OS-14a – 01.
  • Wang, Bohao, Hirotaka Osawa, Takuya Toyono, Fujio Toriumi, and Daisuke Katagami. 2018. “Development of Real-World Agent System for Werewolf Game.” Proceedings of the 17th International Conference on Autonomous Agents and Multi-Agent Systems. International Foundation for Autonomous Agents and Multiagent Systems.
  • Hirofumi Nakamura, Daisuke Katagami, Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Kosuke Shinoda, and Yoshinobu Kano. 2017. Generating human-like discussion by paraphrasing a translation by the AIWolf Protocol using Werewolf BBS Logs. In FUZZ-IEEE.
  • 大澤博隆, 汪博豪, and 佐藤健. 2017. 進化シミュレーションを用いた３人人狼の分析. In 日本ソフトウェア科学会第34回大会, 2–6.
  • 豊野拓也 and 大澤博隆. 2017. 人狼ゲームを演じるロボットエージェントシステムの作成. In 人工知能学会全国大会, 1L2-3.
  • Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Daisuke Katagami, Kosuke Shinoda, and Hitoshi Matsubara. 2016. AI Wolf Contest － Development of Game AI using Collective Intelligence －. In Computer Games Workshop at IJCAI 2016.
  • Nakamura, Hirofumi, Daisuke Katagami, Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Kosuke Shinoda, and Yoshinobu Kano. 2017. “Generating Human-like Discussion by Paraphrasing a Translation by the AIWolf Protocol Using Werewolf BBS Logs.” In FUZZ-IEEE.
  • 鳥海不二夫, 稲葉通将, 大澤博隆, 片上大輔, 篠田孝祐, and 松原仁. 2016. “ゲームプログラミング大会を用いた集合知的ゲーム AI 開発手法－人狼知能大会の開催と参加エージェントの分析－.” 日本デジタルゲーム学会論文誌 9 (1): 1–11.
  • 鳥海不二夫, 片上大輔, 大澤博隆, 稲葉通将, 篠田孝祐, and 狩野芳伸. 2016. 人狼知能 だます・見破る・説得する人工知能. 森北出版.
  • Hideyuki Takahashi, Midori Ban, Hirotaka Osawa, Junya Nakanishi, Hidenobu Sumioka, and Hiroshi Ishiguro. 2017. Huggable Communication Medium Maintains Level of Trust during Conversation Game Hideyuki. frontiers in Psychology 8: 1862.
  • Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Daisuke Katagami, Kosuke Shinoda, and Hitoshi Matsubara. 2016. AI Wolf Contest － Development of Game AI using Collective Intelligence －. In Computer Games Workshop at IJCAI 2016.
  • Nakamura, Noritsugu, Michimasa Inaba, Kenichi Takahashi, Fujio Toriumi, Hirotaka Osawa, Daisuke Katagami, and Kousuke Shinoda. 2016. “Constructing a Human-like Agent for the Werewolf Game Using a Psychological Model Based Multiple Perspectives.” In IEEE SSCI, 1–8.
  • Katagami, D., M. Kanazawa, F. Toriumi, H. Osawa, M. Inaba, and K. Shinoda. 2015. “Movement Design of a Life-like Agent for the Werewolf Game.” In IEEE International Conference on Fuzzy Systems. Vol. 2015-Novem. https://doi.org/10.1109/FUZZ-IEEE.2015.7338087.
  • 栢野航, 工藤佑介, 大澤博隆, 片上大輔, 鳥海不二夫, 稲葉通将, and 篠田考祐. 2015. 人狼を演じるロボットエージェントシステムの作成. In HAIシンポジウム2015, G-21.
  • Kobayashi, Yu, Hirotaka Osawa, Michimasa Inaba, Kosuke Shinoda, Fujio Toriumi, and Daisuke Katagami. 2014. “Development of Werewolf Match System for Human Players Mediated with Lifelike Agents.” In Proceedings of the Second International Conference on Human-Agent Interaction - HAI ’14, 205–7. New York, New York, USA: ACM Press. https://doi.org/10.1145/2658861.2658923.
  • Katagami, Daisuke, Shono Takaku, Michimasa Inaba, Hirotaka Osawa, Kosuke Shinoda, Junji Nishino, and Fujio Toriumi. 2014. “Investigation of the Effects of Nonverbal Information on Werewolf.” In 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 982–87. IEEE. https://doi.org/10.1109/FUZZ-IEEE.2014.6891847.
  • 大澤博隆. 2013. コミュニケーションゲーム「人狼」におけるエージェント同士の会話プロトコルのモデル化. In HAIシンポジウム2013.

解説

  • 鳥海不二夫, 狩野芳伸, 大槻恭士, 大澤博隆, アランニャクラウス, 稲葉通将, and 片上大輔. 2020. “人狼知能大会 ─国際大会と自然言語大会を終えて─.” 人工知能 35 (3): 344–50.
  • 片上大輔, 鳥海不二夫, 大澤博隆, 狩野芳伸, 稲葉通将, and 大槻 恭士. 2018. “人狼知能研究のすすめ.” 知能と情報 30 (5): 236–44.
  • 片上大輔, 鳥海不二夫, 大澤博隆, 稲葉通将, 篠田孝祐, and 松原仁. 2015. “人狼知能プロジェクト.” 人工知能学会誌 30 (1): 65–73.