SUGIURA, Komei

写真a

Affiliation

Faculty of Science and Technology, Department of Information and Computer Science School of Science for Open and Environmental Systems (Yagami)

Position

Associate Professor

Related Websites

Contact Address

26-208A

External Links

Career 【 Display / hide

  • 2004.04
    -
    2009.03

    ATR

  • 2006.04
    -
    2008.03

    日本学術振興会 特別研究員

  • 2008.04
    -
    2020.03

    National Institute of Information and Communications Technology, Japan

  • 2012.04
    -
    2018.03

    Doshisha University, Adjunct Lecturer

  • 2020.04
    -
    Present

    Keio University, Faculty of Science and Technology, Associate Professor

Academic Background 【 Display / hide

  • 1998.04
    -
    2002.03

    Kyoto University, 工学部, 電気電子工学科

    日本, University, Graduated

  • 2002.04
    -
    2004.03

    Kyoto University, 情報学研究科, システム科学専攻

    日本, Graduate School, Completed, Master's course

  • 2004.04
    -
    2007.03

    Kyoto University, 情報学研究科, システム科学専攻

    日本, Graduate School, Completed, Doctoral course

Academic Degrees 【 Display / hide

  • 博士(情報学), Kyoto University, Coursework, 2007.03

    自律ロボットにおける形態に基づく解釈系の構築

 

Research Areas 【 Display / hide

  • Perceptual information processing

  • Intelligent informatics

  • Intelligent robotics

 

Papers 【 Display / hide

  • Operational solar flare prediction model using Deep Flare Net

    N Nishizuka, Y Kubo, K Sugiura, M Den, M Ishii

    Earth, Planets and Space 73 (1), 1-12  2021

  • Predicting and attending to damaging collisions for placing everyday objects in photo-realistic simulations

    A Magassouba, K Sugiura, A Nakayama, T Hirakawa, T Yamashita, ...

    Advanced Robotics, 1-13 abs/2102.06507 2021

  • 生活支援ロボットによる物体配置タスクにおける Transformer PonNet に基づく危険性予測および可視化

    植田有咲, 平川翼, 山下隆義, 藤吉弘亘, 杉浦孔明

    人工知能学会全国大会論文集 第 35 回全国大会 (2021), 2J1GS8a03-2J1GS8a03 (The Japanese Society for Artificial Intelligence)  2021 ( 0 ) 2J1GS8a03 - 2J1GS8a03 2021

     View Summary

    <p>Placing everyday objects in designated areas, such as placing a glass on a table, is a crucial task for Domestic service robots (DSRs). In this paper, we propose a physical reasoning method about collisions in placement tasks. The proposed method, Transformer PonNet, predicts the probability of a possible collision and visualizes areas involved in the collision. Unlike existing methods, Transformer PonNet can be applied to objects whose models are unavailable. We propose a novel Transformer Perception Branch that handles relationships among features more complex than simple self-attention. We built simulation and physical datasets using a DSR, and validated our method on the datasets. We obtained an accuracy of 82.5% for the physical dataset.</p>

  • Target-dependent UNITER に基づく対象物体に関する参照表現を含む物体操作指示理解

    石川慎太朗, 杉浦孔明

    人工知能学会全国大会論文集 第 35 回全国大会 (2021), 4I2GS7c04-4I2GS7c04 (The Japanese Society for Artificial Intelligence)  2021 ( 0 ) 4I2GS7c04 - 4I2GS7c04 2021

     View Summary

    <p>Currently, domestic service robots have an insufficient ability to interact naturally through language. This is because understanding human instructions is complicated by a variety of ambiguities and missing information. Existing methods are insufficient to model reference expressions that specify relationships between objects. In this paper, we propose Target-dependent UNITER, which learns directly the relationship between the target object and other objects by focusing on the relevant regions within an image, instead of the whole image. Our model is validated on two standard datasets, and the results show that Target-dependent UNITER outperforms the baseline method in terms of classification accuracy.</p>

  • Case Relation Transformer に基づく対象物体及び目標領域の参照表現を含む物体操作指示文生成

    神原元就, 杉浦孔明

    人工知能学会全国大会論文集 第 35 回全国大会 (2021), 4J1GS6d05-4J1GS6d05 (The Japanese Society for Artificial Intelligence)  2021 ( 0 ) 4J1GS6d05 - 4J1GS6d05 2021

     View Summary

    <p>The purpose of this paper is to extend the dataset based on a cross-modal generative language generation model. We propose a Case Relation Transformer (CRT) that generates a fetching instruction sentence from an image, such as ``Move the blue flip-flop to the lower left box.'' Unlike existing methods, CRT uses Transformer to capture the visual and geometric features of objects in an image. The Case Relation Block allows the CRT to process the object. We conducted comparative experiments and human evaluations. Experimental results showed that CRT outperformed the baseline methods.</p>

display all >>

Research Projects of Competitive Funds, etc. 【 Display / hide

  • 生活環境対話技術の研究開発

    2020.12
    -
    2026.03

    JST, ムーンショット型研究開発事業, Commissioned research, Co-investigator

  • 実世界に埋め込まれる人間中心の人工知能技術の研究開発

    2020.07
    -
    2025.02

    NEDO 人と共に進化する次世代人工知能に関する技術開発事業, Co-investigator

  • マルチモーダル言語理解における敵対的データ拡張基盤の構築

    2020.04
    -
    2023.03

    科研費, 基盤研究(B), Principal Investigator

  • 文脈と解釈の同時推定に基づく相互理解コンピューテーションの実現

    2019.10
    -
    2025.03

    科学技術振興機構(JST) 戦略的創造研究推進事業(CREST), Co-investigator

  • 視覚的説明と言語的説明の融合によるXAIの実現に関する研究

    2019.07
    -
    2020.02

    NEDO 人工知能技術の説明性に関する研究開発, Co-investigator

display all >>

Intellectual Property Rights, etc. 【 Display / hide

  • 対象物検索システム、対象物検索方法および学習済モデル

    Application No.: 2019-095922  2019.05 

    Patent, Joint, National application

  • 言語識別装置及びそのためのコンピュータプログラム、並びに音声処理装置

    Application No.: 2019-062346  2019.03 

    Patent, Joint, National application

  • 把持装置、タグが付された容器、対象物把持プログラムおよび対象物把持方法

    Application No.: 2018-096213  2018.05 

    Announcement No.: 2019-198945  2019.11 

    Patent, Joint, National application

  • 予測システムおよび予測手法

    Application No.: 2018-090085  2018.05 

    Announcement No.: 2019-197323  2019.11 

    Patent, Joint, National application

  • 命令文推定システムおよび命令文推定方法

    Application No.: 2017-172922  2017.09 

    Announcement No.: 2019-049604  2019.03 

    Patent, Joint, National application

display all >>

Awards 【 Display / hide

  • トヨタ自動車HSRユーザ会2020優秀研究賞

    2020.11

    Type of Award: Other Awards

  • WRS2018パートナーロボットチャレンジ(バーチャルスペース)優勝 / 経済産業大臣賞

    2018.10

  • WRS2018 人工知能学会賞

    2018.10

  • IEEE/RSJ IROS 2018 RoboCup Best Paper Award

    2018.10

    Type of Award: Awards of International Conference, Council and Symposium

  • 2018年度人工知能学会 全国大会優秀賞

    2018.07

    Type of Award: Awards of National Conference, Council and Symposium

display all >>

 

Courses Taught 【 Display / hide

  • RECITATION IN INFORMATION AND COMPUTER SCIENCE

    2021

  • LABORATORIES IN SCIENCE AND TECHNOLOGY

    2021

  • LABORATORIES IN INFORMATION AND COMPUTER SCIENCE 2

    2021

  • INTRODUCTION TO MACHINE LEARNING

    2021

  • INTRODUCTION TO INFORMATION AND COMPUTER SCIENCE

    2021

display all >>

 

Committee Experiences 【 Display / hide

  • 2014
    -
    2021.06

    Trustee, RoboCup Federation

  • 2014
    -
    Present

    Associate Editor, Advanced Robotics

  • 2021

    Associate Editor, IEEE/RSJ IROS 2021

  • 2019

    Associate Editor, IEEE/RSJ IROS 2019

  • 2019

    Program Co-Chair, Conference on Robot Learning

display all >>