論文 - 大澤　博隆

ソシオンモデルを用いたHuman-Agent Interactionのシミュレーショ ンの検討

今井 倫太, 大隅 俊宏, 大澤 博隆

人工知能学会全国大会論文集 （人工知能学会）  27 （ 0 ） 1 - 3 2013年

共著,  ISSN  1347-9881

　概要を見る

<p>人同士のコミュニケーションの分析に用いるソシオンモデルを，人だけではなくエージェントのモデルに拡張し，人とエージェントの関係性のシミュレーションに用いる方法を検討する．</p>

• Access to Document (DOI)
• CiNii Research

エージェントのインタラクション戦略探索のための没入型発見法:エージェントの自由度とインタラクション戦略の変化

大澤 博隆, 今井 倫太

人工知能学会論文誌 （一般社団法人 人工知能学会）  28 （ 2 ） 160 - 169 2013年

共著, 筆頭著者, 責任著者, 査読有り,  ISSN  1346-0714

　概要を見る

We propose an alternative approach to find each robotic agent's unique interaction strategies, called Immersing Discovery Method. In this approach, the human manipulator behaves as if she/he becomes the robot and finds efficient interaction strategies based on each robot's shape and modalities. We implement the system including a reconfigurable body robot, an easier manipulation system, and a recording system to evaluate the validity of our method. We evaluate a block-assembling task by the system by turning on and off the modality of the robot's head. Subsequently, the robot's motion during player's motion significantly increases whereas the ratio of confirmatory behavior significantly decreases in the head-fixed design. This result suggests that the robot leads the users and the user follows the robot in head-fixed condition not as in a normal turn-taking interaction style of the head-free condition.

• Access to Document (DOI)
• CiNii Research

Pygmy: A ring-shaped robotic device for storytelling

Ogata, M., Sugiura, Y., Osawa, H., Imai, M.

International Journal of Innovative Computing, Information and Control 9 （ 12 ）  2013年

共著, 査読有り

Morphing agency—deconstruction of an agent with transformative agential triggers

Hirotaka Osawa, Michita Imai

CHI '13 Extended Abstracts on Human Factors in Computing Systems （ACM）     2237 - 2246 2013年

共著, 筆頭著者, 責任著者, 査読有り

• Access to Document (DOI)

Interaction with an agent in blended reality.

Yusuke Kanai, Hirotaka Osawa, Michita Imai

PROCEEDINGS OF THE 8TH ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION (HRI 2013) （IEEE）     153 - 154 2013年

共著, 査読有り,  ISSN  2167-2121

　概要を見る

This paper proposes a Blended Reality Agent called "BReA" that can exist in both the real and virtual world and has communicative advantages that is more than simply the sum of those of a robotic agent and an on-screen agent. BReA can seamlessly transfer between the real world and virtual world and users can communicate with BReA without interruption during the transference. We conducted a field test and showed that users can recognize when it points from the virtual world to a real world object after it moves from the real world to virtual world. This result supports a hypothesis that communicating with BReA helps users recognize the link between real world and virtual world objects and virtual world information.

Interaction with an agent in Blended Reality

Yusuke Kanai, Hirotaka Ohsawa, Michita Imai

ACM/IEEE International Conference on Human-Robot Interaction    153 - 154 2013年

共著, 査読有り,  ISSN  2167-2148

　概要を見る

This paper proposes a Blended Reality Agent called 'BReA' that can exist in both the real and virtual world and has communicative advantages that is more than simply the sum of those of a robotic agent and an on-screen agent. BReA can seamlessly transfer between the real world and virtual world and users can communicate with BReA without interruption during the transference. We conducted a field test and showed that users can recognize when it points from the virtual world to a real world object after it moves from the real world to virtual world. This result supports a hypothesis that communicating with BReA helps users recognize the link between real world and virtual world objects and virtual world information. © 2013 IEEE.

• Access to Document (DOI)

FlashTouch : Data Communication through Touchscreens

Masa,Ogata, Yuta,Sugiura, Hirotaka,Osawa, Michita,Imai

Annual conference on Human Factors in Computing Systems （ACM）     2321 - 2324 2013年

共著, 査読有り

　概要を見る

FlashTouch is a new technology that enables data communication between touchscreen-based mobile devices and digital peripheral devices. Touchscreen can be used as communication media using visible light and capacitive touch. In this paper, we designed a stylus prototype to describe the concept of FlashTouch. With this prototype, users can easily transfer data from one mobile device to another. It eliminates the complexity associated with data sharing among mobile users, which is currently achieved by online data sharing services or wireless connections for data sharing that need a pairing operation to establish connections between devices. Therefore, it can prove to be of particular significance to people who are not adept at current software services and hardware functions. Finally, we demonstrate the valuable applications in online settlements via mobile device, and data communication for mobile robots. Copyright © 2013 ACM.

• Access to Document (DOI)

iRing : 赤外線反射を用いてジェスチャ認識する指輪型インタフェース

尾形 正泰, 杉浦 裕太, 大澤 博隆

日本バーチャルリアリティ学会大会論文集 Proceedings of the Virtual Reality Society of Japan annual conference （[東京] : [日本バーチャルリアリティ学会]）  17   11 - 14 2012年09月

ISSN  13495062

• CiNii Research

ユーザの状態を考慮した能動的情報提示システムIPSODAの検証

大西 樹, 北出 卓也, 大澤 博隆

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）  112 （ 105 ） 17 - 21 2012年06月

ISSN  09135685

• CiNii Research

チューリングテストを用いたロボットの自律的振る舞い改善

飛田 国星, 大澤 博隆, 山田 誠二

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）  111 （ 446 ） 25 - 28 2012年02月

ISSN  09135685

• CiNii Research

ロボットハードウェア構成を考慮したアプリケーション選定クラウドシステムの提案

加賀美 崇紘, 尾形 正泰, 大澤 博隆

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）  111 （ 446 ） 19 - 23 2012年02月

ISSN  09135685

• CiNii Research

Behavioral Turing test using two-axis actuators.

Hirotaka Osawa, Kunitoshi Tobita, Yuki Kuwayama, Michita Imai, Seiji Yamada

Proceedings - IEEE International Workshop on Robot and Human Interactive Communication （IEEE）     328 - 333 2012年

共著, 筆頭著者, 責任著者, 査読有り

　概要を見る

The Turing test is an imitation game for determining the intelligence of an agent. In spite of its simplified setting, the use of natural language between two agents in the test is still too high a hurdle for achieving fruitful results in the field of artificial intelligence. In this paper, the authors propose a variation of the Turing test with a restricted communication method. This modified test uses behaviors generated by two-axis actuators for communication instead of the natural language dialogue used in the normal Turing test. This reduction of scope reveals what kinds of features are essential for an imitation game, and broaden the application brought by Turing test. When we learn what sorts of communication become possible with restricted actuation, we can apply this knowledge to any kind of robot or device in the real world. First, we tried to determine what elements are critical for communication between a user and a robot through a preliminary experiment involving human-human communication. A human manipulator received a video image as input and controlled a "robot box" with two actuators in a way that would lead a user to put other objects into the box. The results indicated what kinds of behavior are required to show the intention of the manipulator to the user. Second, we analyzed the result of the preliminary experiment, organized a behavioral model from the result, and programmed the robot box to run the model. The behavior of the robot was programmed according to the user's head and hand locations as identified by a motion captures system. The robot automatically interact with a human without human manipulation with this program. Third, we conducted a behavioral Turing test in a communication task whereby the human collected items according to the instructions of the robot box. In this test, two actuators on the box is controlled both by human manipulator and our program. The answers of users suggests that the users could not identify which is controlled by a human manipulator or the program. This result indicates that the Turing test succeed in a restricted behavioral level. © 2012 IEEE.

• Access to Document (DOI)

二軸のロボットを用いた非言語チューリングテストの可能性の検討 (人工知能学会全国大会(第26回)文化,科学技術と未来) -- (インタラクティブ発表)

飛田 国星, 大澤 博隆, 山田 誠二

人工知能学会全国大会論文集 （人工知能学会）  26   1 - 4 2012年

共著,  ISSN  1347-9881

Embodiment of an agent by anthropomorphization of a common object.

Hirotaka Osawa, Yuji Matsuda, Ren Ohmura, Michita Imai

Web Intell. Agent Syst. （IOS Press）  10 （ 3 ） 345 - 358 2012年

共著, 筆頭著者, 責任著者, 査読有り,  ISSN  1570-1263

• Access to Document (DOI)

Where do you want to use a robotic arm ? And what do you want from the robot ?

Mahisorn,Wongphati, Yuji,Matsuda, Hirotaka,Osawa, Michita,Imai

International Symposium on Robot and Human Interactive Communication    322 - 327 2012年

共著, 査読有り

　概要を見る

What will users want from robotic arms when they become part for their daily lives? We conducted an online survey to collect ideas from people about the places in which they would want to use a robotic arm and tasks that they would want the robot arm to perform. 96 people anonymously volunteered to participate in this study. More than 240 sets of place and task were identified in the results of two versions of the web-based questionnaires. The results suggest that the household, workplace, and working surface are, respectively, the three most-mentioned places for robotic arm usage in daily life, that participants who were from different countries but were familiar with information technology did not show significant differences in their answers, and that females showed more interest in household and self-care tasks. Our findings can be used as a guideline for future research and development that focuses on daily life tasks for robotic arms. © 2012 IEEE.

• Access to Document (DOI)

TEROOS: a wearable avatar to enhance joint activities.

Tadakazu Kashiwabara, Hirotaka Osawa, Kazuhiko Shinozawa, Michita Imai

Conference on Human Factors in Computing Systems - Proceedings （ACM）     2001 - 2004 2012年

共著, 査読有り

　概要を見る

This paper proposes a wearable avatar named TEROOS, which is mounted on a person's shoulder. TEROOS allows the users who wear it and control it to share a vision remotely. Moreover, the avatar has an anthropomorphic face that enables the user who controls it to communicate with people co-located with the user who wears it. We have a field test by using TEROOS and observed that the wearable avatar innovatively assisted the users to communicate during their joint activities such as route navigating and buying goods at a shop. The user controlling TEROOS could give the user wearing it appropriate route instructions on the basis of the situation around TEROOS. In addition, both users could easily identify objects that they discussed. Moreover, shop staff members communicated with the user controlling TEROOS and behaved as they normally would when the user asked questions about the goods. Copyright 2012 ACM.

• Access to Document (DOI)

TEROOS: a wearable avatar to enhance joint activities (video preview).

Tadakazu Kashiwabara, Hirotaka Osawa, Kazuhiko Shinozawa, Michita Imai

CHI Conference on Human Factors in Computing Systems （ACM）     1433 - 1434 2012年

共著

• Access to Document (DOI)

Researching Nonverbal Communication Strategies in Human-Robot Interaction.

Hirotaka Osawa, Michita Imai

Communications in Computer and Information Science （Springer Verlag）  358   417 - 432 2012年

共著, 筆頭著者, 責任著者, 査読有り,  ISSN  1865-0929

　概要を見る

We propose an alternative approach to find each robot's unique communication strategies. In this approach, the human manipulator behaves as if she/he becomes the robot and finds the optimal communication strategies using attachable and detachable robot's shapes and modalities. We implement the system including a reconfigurable body robot, an easier manipulation system, and a recording system to evaluate the validity of our method. We evaluate a block-assembling task by the system by turning on and off the modality of the robot's head. Subsequently, the robot's motion during player's motion significantly increases whereas the ratio of confirmatory behavior significantly decreases in the head-fixed design. In this case, the robot leads the users and the user follows the robot as in the turn-taking communication style of the Head-free condition. © Springer-Verlag Berlin Heidelberg 2013.

• Access to Document (DOI)

Pygmy: a ring-shaped robotic device that promotes the presence of an agent on human hand.

Masa Ogata, Yuta Sugiura, Hirotaka Osawa, Michita Imai

APCHI'12 - Proceedings of the 2012 Asia Pacific Conference on Computer-Human Interaction （ACM）     85 - 92 2012年

共著, 査読有り

　概要を見る

The human hand is an appropriate part to attach an agent robot. Pygmy is an anthropomorphic device that produces a presence on a human hand by magnifying the fingerexpressions. This device is in trial to develop an interaction model of an agent on the hand. It is based on the concept of hand anthropomorphism and uses finger movements to create the anthropomorphic effect. Wearing the device is similar to having eyes and a mouth on the hand
the wearer's hand spontaneously expresses the agent's presence with the emotions conveyed by the eyes and mouth. Interactive manipulation by controllers and sensors make the hand look animated. We observed that the character animated with the device provided user collaboration and interaction as though there were a living thing on the user's hand. Further, the users play with the device by representing characters animated with Pygmy as their doubles. Copyright 2012 ACM.

• Access to Document (DOI)

Pygmy: a ring-like anthropomorphic device that animates the human hand.

Masayasu Ogata, Yuta Sugiura, Hirotaka Osawa, Michita Imai

Conference on Human Factors in Computing Systems - Proceedings （ACM）     1003 - 1006 2012年

共著, 査読有り

　概要を見る

Pygmy is an anthropomorphic device that magnifies hand expressions. It is based on the concept of hand anthropomorphism and it uses finger movements to create the anthropomorphic effect. Wearing the device is similar to having eyes and a mouth on the hand
the wearer's hand spontaneously expresses their emotions. Interactive manipulation by controllers and sensors make the hand look animated. © 2012 Authors.

• Access to Document (DOI)