Imai, Michita

写真a

Affiliation

Faculty of Science and Technology, Department of Information and Computer Science ( Yagami )

Position

Professor

Related Websites

External Links

Career 【 Display / hide 】

  • 1994.04
    -
    1997.02

    NTT

  • 1994.08
    -
    1997.02

    NTT Human Interface Laboratories

  • 1997.03
    -
    2001.09

    ATR Media Integration and Communications Laboratories

  • 2001.10
    -
    2002.03

    ATR Media Information Laboratries

  • 2002.04
    -
    Present

    Keio University, Department of Information and Computer Science

Academic Background 【 Display / hide 】

  • 1992.03

    Keio University, Faculty of Science and Engineering, 電気工学科

    University, Graduated

  • 1994.03

    Keio University, Graduate School, Division of Science and Engineeri, 計算機科学専攻

    Graduate School, Completed, Master's course

Academic Degrees 【 Display / hide 】

  • 博士(工学), Keio University, Coursework, 2002.03

 

Research Areas 【 Display / hide 】

  • Informatics / Intelligent robotics

  • Informatics / Intelligent informatics

  • Humanities & Social Sciences / Cognitive science

Research Keywords 【 Display / hide 】

  • Interactive Intelligent System

  • Human Agent Interaction

  • Human-Robot Interaction

 

Books 【 Display / hide 】

  • Web Intelligence and Intelligent Agents

    IMAI MICHITA, InTech, Publishing, 2010.03

  • ロボット情報学ハンドブック

    IMAI MICHITA, ナノオプトニクスエナジー, 2010.03

    Scope: 639-640, 674

Papers 【 Display / hide 】

  • Graph-Based Simultaneous Path and Foothold Planning for Multi-Limbed Intra-Vehicular Robots in Space Stations

    Masazumi Imai, Kentaro Uno, Toshinori Kuwahara, Kazuya Yoshida

     2026.09

     View Summary

    Robot-aided operations in space stations are essential for reducing the workload of astronauts and improving the efficiency of on-orbit activities. Multi-limbed intra-vehicular robots (MLIVRs) equipped with grappling end-effectors have emerged as a promising solution, as they can securely grasp pre-existing interfaces, such as handrails and seat tracks, thereby enabling stable locomotion and forceful manipulation in microgravity environments. Since graspable locations on these interfaces are spatially limited and discretely distributed, motion planning for MLIVRs must be addressed jointly with foothold planning. This paper presents a simultaneous path and foothold planning framework based on graph theory for MLIVRs. The proposed method efficiently searches for feasible stance sequences for a multi-limbed robot while satisfying manipulability constraints. The effectiveness of the proposed framework is validated through simulations in a 3D model of the International Space Station (ISS) cabin, demonstrating its capability to generate feasible and efficient locomotion plans in realistic intra-vehicular environments.

  • First Trigonometric Parallax Measurements with the KVN and VERA Array (KaVA)

    Nobuyuki Sakai, Daisuke Sakai, Noriyuki Kawaguchi, Shuangjing Xu, Bo Zhang, Taehyun Jung, Chungsik Oh, Jeong-Sook Kim, Soon-Wook Kim, Hiroshi Imai, Yuanwei Wu, Maria Rioja, Niu Liu, Zehao Lin, Ibnu Nurul Huda, Shuaibo Bian, Leonid Petrov, Jingdong Zhang, Takaaki Jike, Yoshiaki Tamura, Jeong Ae Lee, Hao Ding, Koichiro Sugiyama, Kazuhiro Hada, Kiyoaki Wajima, Kazuya Hachisuka, Mareki Honma, Kee-Tae Kim, Se-Jin Oh

    Publ. Astron. Soc. Japan (2026), psag117  2026.09

     View Summary

    To demonstrate the astrometric capability of the combined Korean VLBI (Very Long Baseline Interferometry) Network (KVN) and VLBI Exploration of Radio Astrometry (VERA) Array (KaVA), we conducted six-epoch VLBI observations of 22-GHz H$_{2}$O masers associated with the star-forming region W3(OH). Two atmospheric calibration methods, (1) GPS and (2) JMA (Japan Meteorological Agency) mesoscale analysis data, and two phase-reference sources were independently applied to the astrometric analysis. Trigonometric parallaxes of W3(OH) were successfully measured with all calibration strategies, including the first successful parallax measurement using JMA calibration. The combined-fit parallax is 0.497$\pm$0.024 mas, corresponding to a distance of 2.01$^{+0.10}_{-0.09}$ kpc. This value is consistent with the previous Very Long Baseline Array (VLBA) result of 0.489$\pm$0.017 mas. KaVA achieved a 55$\%$ higher signal-to-noise ratio in phase-referenced maps than VERA, in good agreement with theoretical expectations. These results suggest that KaVA will enable trigonometric parallax measurements of 22-GHz H$_2$O masers that are difficult to observe with VERA alone because of low flux densities and/or limited $uv$ coverage. A flux variation from 510\,$\pm$\,50 to 3900\,$\pm$\,400 Jy was detected in W3(OH) over a one-year observing campaign and is attributed to two nearby maser features separated by only $\sim$64 AU at 2.01 kpc. The brightest feature showed a decrease in linewidth with increasing peak flux density, consistent with unsaturated maser amplification, whereas no similar trend was found for the other feature, suggesting different responses to the same amplification conditions, possibly owing to differences in saturation state and internal velocity structure.

  • From Task Success to Productive Success: Evaluating Human-AI Collaboration by Quality and Cost

    Saki Imai, Mert İnan, Malihe Alikhani

     2026.09

     View Summary

    AI productivity is often measured by task completion time, economic value, or improvements in outcome quality. However, these measures usually treat collaboration as a black box where they capture what output was produced, but not the interaction cost required to produce it. Motivated by economics literature, we introduce a productivity-oriented framework for evaluating human-AI collaboration as outcome quality relative to interaction cost. Across two datasets spanning four tasks, we show that: (1) sessions with identical quality ratings can differ by up to 70 times in interaction cost; (2) quality-cost relationships vary by task, with some tasks rewarding extended interaction and others favoring fast convergence; (3) subjective user ratings are not reliable substitutes for productivity; and (4) productive sessions are characterized by agents probing earlier and users spending less effort repairing the interaction. By distinguishing productive success from costly success, our framework makes interactional cost visible and shows how dialogue analysis can inform the evaluation and design of AI systems.

  • A diagnostic system of 5.7 keV muon beam for muon accelerator

    M. Wada, M. Kimura, S. Aritome, E. Cicek, K. Futatsukawa, K. Hirai, M. Hoshiai, T. Iijima, Y. Imai, K. Inami, K. Ishida, S. Kamioka, Y. Kawase, A. Kondo, Y. Kondo, M. Lyu, T. Mibe, Y. Nagatani, Y. Nakazawa, S. Ogawa, Y. Oishi, M. Otani, N. Saito, K. Shimomura, K. Suzuki, T. Takayanagi, K. Ueda, S. Uetake, S. Yamamoto, T. Yamazaki, M. Yang

     2026.08

     View Summary

    Realization of a low-emittance muon beam through the acceleration of keV-scale muons requires the injection of a suitably matched beam into an accelerator, since beam mismatch can lead to emittance growth and reduced acceleration efficiency. In one such scheme, muons are first thermalized to room temperature and then injected into a linear accelerator. Non-destructive diagnostics are challenging because of the low energy and low intensity. We developed a compact low-energy muon diagnostic system compatible with the accelerator under construction at J-PARC. The system is designed to evaluate beam conditions required for precise tuning prior to acceleration. Commissioning with low-energy muon sources shows the system's capability to identify low-energy muon signals and measure beam profiles.

  • Coarse-to-Fine Registration of Jawbone CT and Intraoral Scan Data Using GeDi and ICP with Pseudo-IOS Ground Truth

    Sho Mitarai, Hikaru Kayo, Hisashi Ozaki, Yuichiro Imai, Megumi Nakao

     2026.08

     View Summary

    In digital dentistry and oral surgery, the registration of jawbone CT and intraoral scanner (IOS) data is essential for integrating internal bone structure with high-resolution dental surface geometry. However, this registration is challenging because the two modalities share only a limited region in common, and their true correspondence is generally unknown. This uncertainty has prevented rigorous quantitative evaluation of registration accuracy. In this study, we propose a pseudoIOS evaluation framework in which a point cloud emulating an intraoral scan is generated from CT data within the same coordinate frame, so that the transformation between them is known by construction and can serve as a true ground truth. Using this framework, we propose a coarse-to-fine registration method that combines a domain-generalizable local descriptor (GeDi) for initialization-independent global alignment with the iterative closest point (ICP) algorithm for local refinement, and also evaluate the influence of metal artifacts on registration. In experiments on seven cases, ICP alone frequently converged to local minima from a perturbed initial position, whereas GeDi$+$ICP maintained submillimeter mean absolute error (MAE) across all evaluated jaw and artifact conditions (0.55-0.69 mm). A three-way repeated-measures analysis confirmed that GeDi$+$ICP was significantly more accurate than GeDi alone. Metal artifacts had a statistically detectable overall effect, but their absolute impact on GeDi$+$ICP was small.

display all >>

Papers, etc., Registered in KOARA 【 Display / hide 】

Reviews, Commentaries, etc. 【 Display / hide 】

  • Telecommunication support system with an avatar in blended reality

    金井 祐輔, 大澤 博隆, 今井 倫太

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

    ISSN  1347-9881

  • 1P1-P06 Pygmy : Development of A Ring-like Anthropomorphic Robot(Robots for Amusement and Entertainment)

    OGATA Masayasu, SUGIURA Yuta, OSAWA Hirotaka, IMAI Michita

    ロボティクス・メカトロニクス講演会講演概要集 (The Japan Society of Mechanical Engineers)  2012   "1P1 - P06(1)"-"1P1-P06(2)" 2012.05

     View Summary

    The human hand is used to express characters by its posure. Pygmy is an anthropomorphic device that magnifies the finger expressions. 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 a presence of living thing with the emotions conveyed by the eyes and mouth. Interactive manipulation by controllers and sensors make the hand look animated. We developed small parts of robotic eye and mouth with electromagnetic motor. 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.

Presentations 【 Display / hide 】

  • Where Should Robots Talk?: Spatial Arrangement Study from a Participant Workload Perspective

    Takahiro Matsumoto

    IEEE/ACM HRI’18, 

    2018.03
    , 

    Oral presentation (general)

  • Is a Robot a Better Walking Partner If It Associates Utterances with Visual Scenes?

    Satoru Satake

    [International presentation]  the 2017 ACM/IEEE International Conference on Human-Robot Interaction, 

    2017.03
    , 

    Oral presentation (general)

  • An Implementation of Working Memory Using Stacked Half Restricted Boltzmann Machine: Toward to Restricted Boltzmann Machine-Based Cognitive Architecture

    Masahiko Osawa

    [International presentation]  The 23rd International Conference on Neural Information Processing, 

    2016.10
    , 

    Oral presentation (general)

  • The Use of The BDI Model As Design Principle for A Migratable Agent

    Mamoru Yamanouchi

    [International presentation]  The 4th International Conference on Human-Agent Interaction, 

    2016.10
    , 

    Oral presentation (general)

  • A Study on Controlling Method for an Autonomous Personal Vehicle Based On User’s Heart Rate Variability

    Taichi Sono

    [International presentation]  the IEEE International Symposium on Robot and Human Interactive Communication, 

    2016.08
    , 

    Oral presentation (general)

display all >>

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

  • 対ロボット認知に基づくインタラクションの「間」の実践的意味づけモデル

    2016.04
    -
    2020.03

    MEXT,JSPS, Grant-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (B), Principal investigator

  • 人の適応性を支える環境知能システムの構築

    2014.07
    -
    2019.03

    MEXT,JSPS, Grant-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research on Innovative Areas, Principal investigator

Awards 【 Display / hide 】

  • 2013年度論文賞

    2014.06, 人工知能学会, 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

    Type of Award: Award from Japanese society, conference, symposium, etc.

  • Best Note Honorable Mention

    2012.05, ACM SIG-CHI

  • 日本人工知能学会全国大会優秀論文賞

    今井 倫太, 1999.12, 日本人工知能学会

 

Courses Taught 【 Display / hide 】

  • GRADUATE RESEARCH ON INFORMATICS, MANAGEMENT, AND HUMAN SCIENCES A2

    2026

  • INTERNATIONAL INITIATIVE OVERSEAS 3

    2026

  • RECITATION IN INFORMATION AND COMPUTER SCIENCE

    2026

  • THEORY OF COMPUTING

    2026

  • INTERNATIONAL INITIATIVE OVERSEAS 4

    2026

display all >>

 

Social Activities 【 Display / hide 】

  • ACM

    2002.05
    -
    Present
  • 国際電気通信基礎技術研究所

    2002.04
    -
    Present

Memberships in Academic Societies 【 Display / hide 】

  • ACM HRI2010, 

    2009.08
    -
    2010.03
  • HAI 2009, 

    2009.04
    -
    2009.12
  • IEEE RO-MAN 2009, 

    2009.03
    -
    2009.09
  • IEEE RO-MAN 2009, 

    2009.02
    -
    2009.09
  • ISCR 2009, 

    2009.01
    -
    2009.08

display all >>

Committee Experiences 【 Display / hide 】

  • 2009.08
    -
    2010.03

    Program Committee, ACM HRI2010

  • 2009.04
    -
    2009.12

    実行委員, HAI 2009

  • 2009.03
    -
    2009.09

    IDEA Session Organizer, IEEE RO-MAN 2009

  • 2009.02
    -
    2009.09

    Program Committee, IEEE RO-MAN 2009

  • 2009.01
    -
    2009.08

    Program Committee, ISCR 2009

display all >>