Details of a Researcher - OSAWA Hirotaka

Papers - OSAWA Hirotaka

Division display 101 - 120 of about 302 ／ All the affair displays >>

Generating human-like discussion by paraphrasing a translation by the AIWolf protocol using werewolf BBS logs.

Hirofumi Nakamura, Daisuke Katagami, Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Kosuke Shinoda, Yoshinobu Kano

IEEE International Conference on Fuzzy Systems (Institute of Electrical and Electronics Engineers Inc.) 1 - 6 2017

Joint Work, Accepted, ISSN 1098-7584

'Are you a werewolf?' is one of the most popular communication games and is played globally. The AIWolf Project developed an agent, named 'the AIWolf,' that can play 'Areyou a werewolf?'. An AIWolf utters its thoughts using an AIWolf Protocol. As it is difficult for humans to understand the AIWolf Protocol, translation into natural language is required when human players are involved. However, the conventional method of translation uses a word-to-word method, creating the impression that the utterances have been generated by a machine. This study aimed make the utterances of AIWolf sound more human. The authors set the target that a human player would be unable to distinguish human speech from that generated by AIWolves (the Turing test). The authors define the situation as the maximum value of humanity. The output of translated AIWolf Protocol was paraphrased using data from Werewolf BBS Logs. This study considers making the utterances of AIWolf sound more human using Werewolf BBS Logs and a possibility assignment equation with fuzzy sets. In this paper, an experiment was conducted to confirm whether paraphrasing the utterances of AIWolf using Werewolf BBS Logs for human-like speech is useful or not. It was shown that the experimental method produced slightly more human-like speech than the conventional method.

Access to Document (DOI)

テレプレゼンスロボットにおける同調動作の効果

米津, 壮二, 大澤, 博隆

Proc. of JSAI (The Japanese Society for Artificial Intelligence) 2017 ( 0 ) 3Q11in1 - 3Q11in1 2017

Joint Work, Last author, Corresponding author

<p>遠隔対話を円滑にする目的で、発話者の言語的・非言語的動作を代替するテレプレゼンスロボットが開発されている。遠隔対話の質をより向上させるために、対話者のしぐさを真似ることで親近感が得られるとされる同調動作を利用することを考えた。そこで対話者の表情、視線、ジェスチャーを自動で追加するテレプレゼンスロボットを開発した。本研究ではテレプレゼンスロボットが行う同調動作が有用かを検証した。</p>

Why Do We Need the Ethical Guideline for Internet Research? : The Development of Internet Research Ethics and Its Introduction to Japan

大谷卓史, 西條玲奈, 久保明教, 大澤博隆, 江間有沙, 神崎宣次, 服部宏充, 市瀬龍太郎, 秋谷直矩, 駒谷和範, 宮野公樹

信学技報, Vol.117, No.286, pp.51-55 (電子情報通信学会) 117 ( 285 ) 51 - 55 2017

Joint Work, ISSN 0913-5685

What is Real Risk and Benefit on Work with Robots?: From the Analysis of a Robot Hotel.

Hirotaka Osawa, Arisa Ema, Hiromitsu Hattori, Naonori Akiya, Nobutsugu Kanzaki, Akinori Kubo, Tora Koyama, Ryutaro Ichise

Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction (ACM) 241 - 242 2017

Joint Work, Lead author, Accepted

Access to Document (DOI)

Wearable social prosthetics: supporting joint attention during communication with artificial eyes.

Hirotaka Osawa, Takeomi Goto, Bohao Wang

Proceedings of the 2017 ACM International Symposium on Wearable Computers(ISWC) (ACM) 168 - 169 2017

Joint Work, Lead author

Access to Document (DOI)

Telepresence robot with behavior synchrony: Merging the emotions and behaviors of users.

Soji Yonezu, Hirotaka Osawa

26th IEEE International Symposium on Robot and Human Interactive Communication(RO-MAN) (IEEE) 213 - 218 2017

Joint Work, Last author, Corresponding author, Accepted

Access to Document (DOI)

Simulation of Bullying and Conforming in a Class Based on Socion Theory

Toshihiro Osumi, Hirotaka Osawa, Michita Imai

ELECTRONICS AND COMMUNICATIONS IN JAPAN (WILEY-BLACKWELL) 99 ( 7 ) 12 - 24 2016.07

Joint Work, Accepted, ISSN 1942-9533

Bullying is a serious problem, especially at elementary schools and junior high schools, and occurs all over the world with some variations. As a countermeasure against bullying, many interventions and preventive programs have been proposed (e.g., counseling, dispatch of advisers, group work, suspension orders) and there have been many investigations presenting analyses of bullying along with intervention and prevention strategies. However, numerous samples and long times are required for the analysis of strategies in the real world. We believe that simulations of bullying and countermeasures are effective in providing quick and easy analysis. In this investigation, we developed a simulation model of school bullying "within-group" or "within-class" that is based on "socion theory". The primary feature of socion theory is that each agent has an imagined personal relationship. We implemented a strategy called the "conforming strategy" to simulate bullying caused by conforming behavior of students. Student agents who implement the conforming strategy watch the human relationships around them and update their own imagined relationships. They then conform to the behavior of other students to achieve better social standing or to maintain their position on the basis of simulation results based on their own imagined relationships. The results of the experiments show that the conforming strategy increases the probability of bullying and the number of victims, and that conforming behavior increases the probability of bullying in the real world. We also describe a situation in which teachers underestimate or cannot perceive bullying when it occurs, and many teachers underestimate or cannot perceive bullying in the real world. Overall, we show that socion theory has sufficient expressiveness to be used as a foundation for bullying simulation. (C) 2016 Wiley Periodicals, Inc.

Access to Document (DOI)

機能説明エージェントの実世界拡張トリガーによるMFP機能説明改善

豊野拓也, 栢野航, 大澤博隆, 遠藤航, 三浦友博

電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 (東京 : 電子情報通信学会) 116 ( 106 ) 1 - 6 2016.06

ISSN 09135685

機能説明エージェントの実世界拡張トリガによる機能説明改善

大澤博隆, 栢野航, 遠藤航, 三浦友博, 丹波正登, 守谷友里, 結城明, 長野正

情報処理学会論文誌 57 ( 4 ) 1128 - 1136 2016.04

Accepted, ISSN 18827764

技術の発達によって機器の機能が増加している．増加した機能をユーザに分かりやすく伝える手法として，擬人化エージェントを用いた機能説明が提案されてきた．本研究では擬人化エージェントを実世界に拡張させる演出を用いて，複合機（Multi-Function Printer，MFP）の操作説明を行い，人間のインタラクションがどのように変化するか検証した．検証結果として，スクリーン上のエージェントの説明を実世界に拡張することにより，その後のユーザの操作時間が有意に短くなることを確認した．また，ユーザの発話量が有意に増加すること，説明後に学習への興味が向上することが評価結果から示唆された．

プロジェクタロボットを用いた運転支援システムにおけるエージェントの振る舞いの研究

堀元見, 長谷川孔明, 大澤博隆, 今井倫太

第78回全国大会講演論文集 2016 ( 1 ) 223 - 224 2016.03

本研究では、運転支援システムにおけるエージェントの振る舞いを扱う。従来のカーナビゲーションシステムのような単調で一方的な情報提示ではなく、運転手の視線や発言、および周囲の状況に応じた情報提示を行うシステムを作成し、このようなシステムの中で、エージェントのどのような振る舞いのが必要なのかを探る。運転手がエージェントと快適なインタラクションを行うためには、運転手の動きに対する反応の速さが不可欠である。本研究では、速い反応性を実現するためにプロジェクタロボットを用いた。プロジェクタロボットは、半球状のスクリーンに内部のプロジェクタから顔の画像を投影するロボットであり、動かすためにモータの動きを必要としない。したがって従来のロボットよりも速い反応を実現することが容易である。このような速い反応を活かしたインタラクションのための振る舞いを実装し、その効果について研究した。

Design of Ambient Intelligent System for Supporting Human's Natural Adaption(<Special Issue>Cognitive Interaction Design)

IMAI Michita, ONO Tetsuo, SHINOZAWA Kazuhiko, OSAWA Hirotaka, IIZUKA Hiroyuki, SUZURIKAWA Jun

Journal of the Japanese Society for Artificial Intelligence (The Japanese Society for Artificial Intelligence) 31 ( 1 ) 43 - 49 2016.01

ISSN 21882266

３者間人狼における戦略の検討

大澤, 博隆, 佐藤, 健

Proc. of JSAI (The Japanese Society for Artificial Intelligence) 2016 ( 0 ) 2F43 - 2F43 2016

Joint Work, Lead author

感情労働代替デバイスが与えるタスク処理時間と心理的負荷への影響

後藤, 豪臣, 大澤, 博隆

Proc. of JSAI (The Japanese Society for Artificial Intelligence) 2016 ( 0 ) 2N5OS29b4 - 2N5OS29b4 2016

Joint Work, Last author, Corresponding author

人狼知能大会における統計分析とSVMを用いた人狼推定を行うエージェントの設計

梶原, 健吾, 鳥海, 不二夫, 稲葉, 通将, 大澤, 博隆, 片上, 大輔, 篠田, 孝祐, 松原, 仁, 狩野, 芳伸

Proc. of JSAI (The Japanese Society for Artificial Intelligence) 2016 ( 0 ) 2F41 - 2F41 2016

Joint Work

Constructing a Human-like agent for the Werewolf Game using a psychological model based multiple perspectives.

Noritsugu Nakamura, Michimasa Inaba, Kenichi Takahashi, Fujio Toriumi, Hirotaka Osawa, Daisuke Katagami, Kousuke Shinoda

PROCEEDINGS OF 2016 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI) (IEEE) 1 - 8 2016

Joint Work

In this paper, we focus on the Werewolf Game. The Werewolf Game is an advanced communication-game in which winning or losing is directly linked to one's success or failure in communication. Therefore, we expect exponential developments in artificial intelligence by studying the Werewolf Game. In this current study, we propose a psychological model that considers multiple perspectives to model the play of a human such as inferring the intention of the other side. As one of the psychological models, we constructed a "one's self model" that models the role of others as viewed from their own viewpoint. In addition, to determine whether one's opinion is reliable after inferring other's intentions, we also constructed an "others model" that models the role of others as viewed from their viewpoints. Combining these models, we showed through experimentation that a combined approach achieved better results, i.e., higher win percentages.

Access to Document (DOI)

Constructing a Human-like agent for the Werewolf Game using a psychological model based multiple perspectives

Noritsugu Nakamura, Michimasa Inaba, Kenichi Takahashi, Fujio Toriumi, Hirotaka Osawa, Daisuke Katagami, Kousuke Shinoda

PROCEEDINGS OF 2016 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI) (IEEE) 2016

Joint Work, Accepted

AI達は物語を生み出すか

鳥海, 不二夫, 大澤, 博隆

Proc. of JSAI (The Japanese Society for Artificial Intelligence) 2016 ( 0 ) 2F45 - 2F45 2016

Joint Work, Last author

AI Wolf Contest - Development of Game AI Using Collective Intelligence -.

Fujio Toriumi, Hirotaka Osawa, Michimasa Inaba, Daisuke Katagami, Kosuke Shinoda, Hitoshi Matsubara

Communications in Computer and Information Science (Springer Verlag) 705 101 - 115 2016

Joint Work, Lead author, Accepted, ISSN 1865-0929

In this study, we specify the design of an artificial intelligence (AI) player for a communication game called “Are You a Werewolf?” (AI Wolf). We present the Werewolf game as a standard game problem in the AI field. It is similar to game problems such as Chess, Shogi, Go, and Poker. The Werewolf game is a communication game that requires several AI technologies such as multi-agent coordination, intentional reading, and understanding of the theory of mind. Analyzing and solving the Werewolf game as a standard problem will provide useful results for our research field and its applications. Similar to the RoboCup project, the goal of this project is to determine new themes while creating a communicative AI player that can play the Werewolf game with humans. As an initial step, we designed a platform to develop a game-playing AI for a compe tition. First, we discuss the essential factors in Werewolf with reference to other studies. We then develop a platform for an AI game competition that uses simpli fied rules to support the development of AIs that can play Werewolf. The paper reports the process and analysis of the results of the competition.

E-Gaze Glasses: Simulating Natural Gazes for Blind People.

Shi Qiu, Siti Aisyah Anas, Hirotaka Osawa, Matthias Rauterberg, Jun Hu 0001

PROCEEDINGS OF THE TENTH ANNIVERSARY CONFERENCE ON TANGIBLE EMBEDDED AND EMBODIED INTERACTION (TEI16) (ASSOC COMPUTING MACHINERY) 563 - 569 2016

Joint Work, Accepted

Gaze and eye contact are frequently in social occasions used among sighted people. Gaze is considered as a predictor of attention and engagement between interlocutors in conversations. However, gaze signals from the sighted are not accessible for the blind person in face-to-face communication. In this paper, we present functional work-in-progress prototype, E-Gaze glasses, an assistive device based on an eye tracking system. E-Gaze simulates natural gaze for blind people, especially establishing the "eye contact" between blind and sighted people to enhance their engagement in face-to-face conversations. The gaze behavior is designed based on a turn-taking model, which interprets the corresponding relationship between the conclusive gaze behavior and the interlocutors' conversation flow.

Access to Document (DOI)

Development of Game AI by using Collective Intelligence:-Analysis of Agents in AI Wolf Contest-

鳥海, 不二夫, 稲葉, 通将, Osawa, Hirotaka, 片上, 大輔, 篠田, 孝祐, 松原, 仁

Journal of Digital Games Research (Digital Games Research Association Japan) 9 ( 1 ) 1 - 11 2016

Joint Work, Accepted, ISSN 1882-0913

The communication game "Are you a Werewolf?"can be next-generation standard problem for artificial intelligence which comes after Chess, Go or Shogi and so on. Our goal is to find "How can people enjoy playing the games with AI". For the purpose, we employ the collective intelligence method to develop AI which can play Werewolf. In this paper, we introduce the AIWolf project and game platform which designed to play Werewolf by artificial intelligence agents. Number of participated agents are 38, and 15 of them became finalists. Also, we describe about the First AIWolf contest and analyze the result of the contest. From the analysis, we found that the winner agent has significantly higher winning rate. Also, we found the relationships between roles and winning rates which are important information to develop agents.

　 Previous page - Next page 　