論文 - 大澤　博隆

A Model for Addition of User Information to Sensor Data Obtained from Living Environment

大澤 博隆

Cybernetics and Systems, An International Journal (掲載確定) （TAYLOR & FRANCIS INC）  41 （ 3 ） 194-215 - 215 2010年

研究論文（学術雑誌）, 共著,  ISSN  0196-9722

　概要を見る

In this article, we propose a model for the addition of user information to sensor data. The problem is that it is difficult to identify a user of objects that are used by multiple people and to define a unique way to identify the user. The proposed model identifies the user assuming that the objects are used by multiple people. Further, it introduces three policies. By our experiment, we have proved the following: (1) Addition of user information to sensor data by the model is valid. (2) By presenting a difference in policies, it is possible to draw someone's attention.

• Access to Document (DOI)
• CiNii Research

A Portable Robots to Share Real World Experiences

Michita Imai, Masato Noda, Kenta Fujimoto, Tosihiro Ohsumi, Yuki Kuwayama, Hirotaka Osawa

WMSCI 2010: 14TH WORLD MULTI-CONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL I （INT INST INFORMATICS & SYSTEMICS）     1 - 5 2010年

共著, 査読有り

　概要を見る

The paper proposes a new reading style of blog contents by developing a cell phone based portable robot named BlogRobot. BlogRobot presents the contents with its embodied expressions and enhances the user's feelings of sharing experience with his/her friend. Moreover, he/she easily prepares the contents of BlogRobot by just inserting icons into the blog texts with an authoring tool. The paper explains the overview of the mechanisms used by BlogRobot.

Maintaining learning motivation of older people by combining household appliance with a communication robot.

Hirotaka Osawa, Jarrod Orszulak, Kathryn M. Godfrey, Joseph F. Coughlin

IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010) （IEEE）     5310 - 5316 2010年

共著, 筆頭著者, 責任著者, 査読有り,  ISSN  2153-0858

　概要を見る

Today's household appliances are quickly increasing their features and functions. These new technologies require innovative training methods to maintain learning motivation especially with older users, because they may need more time to learn. Conventional manuals are insufficient to maintain motivation in this population. Previously studied assistive communication robots also have difficulty explaining a second device because their strong presence distracts the user from the device during explanation. We propose an anthropomorphized learning method that sustains older people's motivations to learn new technologies. Our method creates an anthropomorphized household appliance using robot eyes and arms. This method assists the learning process using human expressions. These human-like expressions attract users during training and maintain learning motivation. Our system uses three forms of anthropomorphization: pointing, directive motion, and emotion. We designed and implemented both hardware and software and evaluated the method by training older people to learn a vacuum's features. Our method increased older people's emotional status by an average of 2.53 points compared with the manual learning that decreased emotional status by -.53. This increased emotional status suggests that our system could maintain older users' motivation more effectively compared with traditional manual methods.

• Access to Document (DOI)

Improving voice interaction for older people using an attachable gesture robot.

Hirotaka Osawa, Jarrod Orszulak, Kathryn M. Godfrey, Michita Imai, Joseph F. Coughlin

2010 IEEE RO-MAN （IEEE）     179 - 184 2010年

共著, 筆頭著者, 責任著者, 査読有り

　概要を見る

Dialogue interface with voice is one of the common methods of interaction between a user and a machine. This interface is believed to be easy for all people because auditory information doesn't require additional knowledge from users. However, having only auditory instructions sometimes causes misinterpretation of spatial information like locations and directions. This risk becomes large, especially with older people, because users' mental abilities to manipulate images or patterns decrease with age. We support older people's learning of spatial information by using an attachable gesture robot. Our robot consists of human-like eyes and arms and is attached to the object. It supports older people's mental manipulation of space with gestures during voice interaction. We designed and implemented both hardware and software on a vacuum robot and evaluated the method by training older people to learn its features. We compared two instructional methods that explained eight features on the vacuum, one method with voice and gestures and one with only voice. The results show that the subjects were more likely to remember two features if given training with gestures. We also found that their learning motivation was increased when given voice and gesturing instructional methods.

• Access to Document (DOI)

HRI pioneers workshop 2010.

Kate Tsui, Min Kyung Lee, Kristen Stubbs, Henriette S. M. Cramer, Laurel D. Riek, Ja-Young Sung, Hirotaka Osawa, Satoru Satake

Proceedings of the 5th ACM/IEEE International Conference on Human Robot Interaction(HRI) （ACM）     9 - 9 2010年

共著

• Access to Document (DOI)

Toward the body image horizon: how do users recognize the body of a robot?

Hirotaka Osawa, Yuji Matsuda, Ren Ohmura, Michita Imai

PROCEEDINGS OF THE 5TH ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION (HRI 2010) （IEEE）     179 - 180 2010年

共著, 筆頭著者, 責任著者, 査読有り,  ISSN  2167-2121

　概要を見る

In this study, we investigated the boundary for recognizing robots. Many anthropomorphic robots are used for interactions with users. These robots show various body forms and appearances, which are recognized by their users. This ability to recognize a variety of robotic appearances suggests that a user can recognize a wide range of imaginary body forms compared with the native human appearance. We attempted to determine the boundary for the recognition of robot appearances. On the basis of our previous studies, we hypothesized that the discrimination of robot appearances depends of the order of the parts. If the body parts of a robot are placed in order from top to bottom, the user can recognize the assembly as a robot body. We performed a human-robot experiment in which we compared the results for robots with ordered parts with those for robots with inverted parts. The result showed that the users' perception of the robot's body differed between the two groups. This result confirms our hypothesized boundary for the recognition of robot appearances.

• Access to Document (DOI)

SIAC：SLAMアルゴリズムを応用した実世界対話システムの提案

松元 崇裕, 大澤 博隆, 大村 廉, 今井 倫太

人工知能学会全国大会論文集 （一般社団法人 人工知能学会）  JSAI2010 （ 0 ） 2C42 - 2C42 2010年

ISSN  13479881

　概要を見る

<p>言語処理の問題に単語の参照関係と文脈の相互依存問題がある。単語は意味解釈の際に実世界の情報と単語の関係（参照関係と呼ぶ）を決定する必要があり、双方の関係は対話時の文脈から決定できる。しかし、文脈自体が意味解釈が与えられた単語により構成されるため参照関係と文脈は同時に解決する必要がある。本研究では文脈と参照関係を同時に解決する手法SIACを提案し、実際に対話ロボットを構築することで動作検証を行う。</p>

• Access to Document (DOI)
• CiNii Research

SRTを用いた擬人化ロボットの表出要素の組合せの評価

松田 祐児、大澤 博隆、大村 廉、今井 倫太

電子情報通信学会（基礎・境界ソサイエティ）和文論文誌A （電子情報通信学会）  92-A （ 11 ） 806-817 - 817 2009年11月

研究論文（学術雑誌）, 共著,  ISSN  0913-5707

　概要を見る

本研究では,発話音声,表情パーツである目や口などの表出要素の組合せによりユーザと擬人化ロボット間のインタラクションを改善させることを目的としている.ロボットの外見を検討した関連研究は存在するが,共通の土台に各表出要素を組み合わせ,ユーザとのインタラクションにおける各表出要素の影響を評価した研究は存在しない.本研究ではインタラクションを改善する表出要素を検討するため,各表出要素を組み合わせた台車ロボットとユーザがインタラクションを行う対人実験を2種類実施した.各表出要素は台車ロボットがユーザに返答する時間SRTに対するユーザの許容度を測ることで評価した.一つ目の対人実験では,音声とディスプレイ,目パーツの組合せにより各4条件をそれぞれ比較し,発話と外見どちらの表出要素にユーザは影響を受けるか検討した.二つ目の対人実験では,目と口パーツの組合せにより2×2条件を比較し,目と口のどちらの表出要素がインタラクションを改善するか検討した.結果として,擬人的な外見を与えるかどうかではなく,発話の有無によりSRTに対するユーザの評価は影響を受けること,また目が口よりもSRTに対するユーザの許容度を大きくすることが分かった.

• CiNii Research

Mundus Traducere : Interpretation of Natural Language using a Semantic Sensor Network

Antoine,Chaussin, Hirotaka,Osawa, Ren,Ohmura, Michita,Imai

Workshop on Advanced Robotics and its Social Inpacts （IEEE）     104 - 108 2009年11月

共著, 査読有り

• Access to Document (DOI)

擬人化した物体からの情報提示手法のための後付け可能な指示区画検知センサの開発

大澤 博隆、野田 誠人、大村 廉、今井 倫太

日本知能情報ファジィ学会誌 （日本知能情報ファジィ学会）  21 （ 1 ） 12-23 - 23 2009年

研究論文（学術雑誌）, 共著, 筆頭著者, 責任著者,  ISSN  1347-7986

　概要を見る

本研究では，物体に対し擬人的な入出力デバイスを取り付け，物体全体を擬人化し，物体に直接ふれ合いながら情報提示を行なう直接擬人化手法を提案する．このため我々は，対象となる物体に対し，後から検知領域の側面に取り付ける事で，物体の表面に仮想的な接触検知領域を実装する「指示区画検知センサ」を開発した．指示区画検知センサは検知領域の側面に取り付けて二次元平面を検知する事が可能であり，簡易に取り付け可能で，物体の要素を隠さず，人間の手の接触のみに反応した応答が可能となる．本研究では，指示区画検知センサの精度改善のため，ビタビアルゴリズムを用いたユーザの手の指示位置を推定する手法を考案した．これにより，センサから40cmの二次元検知領域内に侵入した人間の手を，平均して80％の精度で検知する事が可能となった．さらに，開発した指示区画検知センサを他の擬人化パーツと連携させ，物体を擬人化した機能説明をおこなった．その結果，直接擬人化手法による情報提示が円滑に行なわれる事が確認できた．

• Access to Document (DOI)
• CiNii Research

Using Attachable Humanoid Parts for Realizing Imaginary Intention and Body Image

大澤 博隆、大村 廉、今井 倫太

International Journal of Social Robotics （Springer Science and Business Media LLC）  1 （ 1 ） 109-123 - 123 2009年

研究論文（学術雑誌）, 共著, 筆頭著者, 責任著者,  ISSN  1875-4791

　概要を見る

We propose a new approach to human-robot interaction (HRI) in which a common target object is anthropomorphized using attachable humanoid parts. With this approach, the user perceives that the target has an intention and senses what the imaginary body of the target looks like through the attached body parts. We experimented how users accepted the intentions and imaginary body image of a common target object using the humanoid parts. We also compared the resulting HRI with that in the case of the general communication robot Robovie to demonstrate the possibilities our proposed method offers. The results indicated that an anthropomorphized target object can interact with users through this approach. Furthermore, in comparison to interaction with an independent communication robot, with this approach, users remembered the functions of the anthropomorphized target to a greater extent and were more intimate with it.

• Access to Document (DOI)
• CiNii Research

An Individual Data Extraction Model for Objects Used by a Number of People

Hitoshi Kawasaki, Ren Ohmura, Hirotaka Osawa, Michita Imai

ISWPC: 2009 4TH INTERNATIONAL SYMPOSIUM ON WIRELESS PERVASIVE COMPUTING （IEEE）     98 - + 2009年

共著, 査読有り

　概要を見る

This study investigates people's use of objects and the things they do in their daily lives. This is because interaction with objects can give us valuable insights with regard to behavior. The problem is that in an environment where multiple users interact with the same object, it is difficult to obtain data relating to each individual. To this end, we propose a model that extracts individual data from a data set. We can recognize individual users in environments where multiple users interact with an object. The model consists of 3 policies. As a result of our experiment, we proved that the system could extract individual data that fits an individual examinee's consciousness an average of 85.3% of the time. In addition, by letting each examinee look back on the system results, we could make the examinee conscious of behavior of which they had previously been unaware.

BlogRobot: Mobile Terminal for Blog Browse Using Physical Representation.

Toshihiro Osumi, Kenta Fujimoto, Yuki Kuwayama, Masato Noda, Hirotaka Osawa, Michita Imai, Kazuhiko Shinozawa

PROGRESS IN ROBOTICS, PROCEEDINGS （SPRINGER-VERLAG BERLIN）  44   96 - 101 2009年

共著, 査読有り,  ISSN  1865-0929

　概要を見る

Mobile phones and PDAs with GPS became widespread, and GPS-based service of mobile terminal is rising, so needs for presentation interface for GPS-based contents are increasing. We employ a robot as a presentation interface. In this paper, we use a blog as our content and propose a portable robot named "BlogRobot" that presents blog content by using verbal and non-verbal expression. Using BlogRobot, people who don't have the knowledge of a specialist can create behavior contents as they note in a diary, and the contents can give reader a feeling like a man who write a blog's entry explain the entry near the entry location.

• Access to Document (DOI)

Blog robot: a new style for accessing location-based contents.

Masato Noda, Toshihiro Osumi, Kenta Fujimoto, Yuki Kuwayama, Hirotaka Osawa, Michita Imai, Kazuhiko Shinozawa

Proceedings of the 4th ACM/IEEE International Conference on Human Robot Interaction(HRI) （ACM）     203 - 204 2009年

共著, 査読有り

• Access to Document (DOI)

Anthropomorphization of a space with implemented human-like features.

Hirotaka Osawa, Kentaro Ishii, Toshihiro Osumi, Ren Ohmura, Michita Imai

International Conference on Computer Graphics and Interactive Techniques （ACM）     2 - 1 2009年

共著, 筆頭著者, 責任著者, 査読有り

• Access to Document (DOI)

Anthropomorphization method using attachable humanoid parts.

Hirotaka Osawa, Ren Ohmura, Michita Imai

Proceedings of the 4th ACM/IEEE International Conference on Human Robot Interaction(HRI) （ACM）     207 - 208 2009年

共著, 筆頭著者, 責任著者, 査読有り

• Access to Document (DOI)

Self introducing poster using attachable humanoid parts.

Hirotaka Osawa, Ren Ohmura, Michita Imai

International Conference on Human-Robot Interaction （ACM）     327 - 328 2009年

共著, 筆頭著者, 責任著者, 査読有り

• Access to Document (DOI)

BoDiD: コミュニケーションロボットのための対話者判定システムの提案

桑山 裕基, 大澤 博隆, 今井 倫太

人工知能学会全国大会論文集 （一般社団法人 人工知能学会）  JSAI2009 （ 0 ） 1H21 - 1H21 2009年

ISSN  13479881

　概要を見る

<p>本研究では，コミュニケーションロボットのための，人の体の向きを検知して対話者を判定するシステムBoDiDを提案する． BoDiDは顔検出による肩位置の検出モジュールとレーザレンジファインダの計測による人の体の向きの推定モジュールを持ち，推定された体の向きをベースにコミュニケーションロボットのユーザが対話相手となっているかどうか判定することを可能にする．</p>

• Access to Document (DOI)
• CiNii Research

Variable Body Image – Evaluation Framework of Robot’s Appearance using Movable Human-like Parts

Hirotaka,Osawa, Yuji,Matsuda, Ren,Ohmura, Michita,Imai

AAAI 2009 Spring Symposium （AAAI）     33 - 40 2009年

共著, 筆頭著者, 責任著者, 査読有り

顔パーツの有無による人の擬人化認識度合いの調査と検討--SRTを用いた擬人化測定法の提案

松田 祐児, 大澤 博隆, 大村 廉

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）  108 （ 317 ） 41 - 46 2008年11月

ISSN  09135685

• CiNii Research