Hanbit OH

오 한빛

Researcher, Ph.D. in Engineering, Japan.

I am a research scientist@AIST(国立研究開発法人産業技術総合研究所) in Odaiba, Tokyo, Japan. My research topic is robotics, manipulation and machine learning (AI robotics).

Email Google Scholar Research Map ORCiD
Hanbit OH

Research

SART: Safe Self-augmented Robot Trajectory

Oh et al., Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precision, Advanced Robotics, 2025.

Project Paper

DPIIL: Demonstrator-Perceived Precision IIL

Oh et al., Leveraging Demonstrator-Perceived Precision for Safe Interactive Imitation Learning of Clearance-Limited Tasks, IEEE Robotics and Automation Letters, 2024.

Project Paper

RIP: Robust Instant Policy

Oh et al., Robust Instant Policy: Student’s-t-Based Trajectory Aggregation for Reliable In-Context Imitation Learning in Robot Manipulation, IEEE Access, 2026. (Accepted)

Project Paper
ISPIL Overview

ISPIL: Interactive Sub-Goal Planning IL

Ochoa* and Oh* et al., Interactive Sub-Goal-Planning Imitation Learning for Long-Horizon Tasks With Diverse Goals, IEEE Access, 2024. *: Equal contribution.

Paper

Publications

Preprints

  1. T. Motoda*, K. Makihara*, R. Nakajo*, H. Oh*, K. Shirai, R. Hanai, M. Murooka, Y. Suzuki, H. Nishihara, M. Takeda, and others.
    "Recipe for Vision-Language-Action Models in Robotic Manipulation: A Survey,"
    Authorea Preprints, Authorea, 2025. *: Equal contribution. Preprint

Journal Articles

  1. Yukiyasu Domae, Keisuke Shirai, Hanbit OH, Ryoichi Nakajo, Tomohiro Motoda, Koshi Makihara, Masaki Murooka, Takuma Yagi, Yoshiaki Bando, and Ryo Hanai.
    "The Embodiment Gap in Robot Foundation Models,"
    Transactions on Machine Learning Research, 2026. (Refereed) Paper OpenReview
  2. Hanbit OH, Andrea M. Salcedo-Vázquez, Ixchel G. Ramirez-Alpizar, and Yukiyasu Domae.
    "Robust Instant Policy: Student’s-t-Based Trajectory Aggregation for Reliable In-Context Imitation Learning in Robot Manipulation,"
    IEEE Access, 2026. (Accepted) Paper: Coming Soon Project
  3. H. Oh*, M. Murooka*, T. Motoda, R. Nakajo, and Y. Domae.
    "SART: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precision,"
    Advanced Robotics, , pp. 1–15, 2024. (Refereed) *: Equal contribution. paper Project
  4. Cynthia Ochoa *, Hanbit OH *, Yuhwan Kwon, Yukiyasu Domae, and Takamitsu Matsubara.
    "ISPIL: Interactive Sub-Goal-Planning Imitation Learning for Long-Horizon Tasks With Diverse Goals,"
    IEEE Access, 2024. (Refereed), *: Equal contribution. Paper
  5. Hanbit OH and Takamitsu Matsubara.
    "Leveraging Demonstrator-Perceived Precision for Safe Interactive Imitation Learning of Clearance-Limited Tasks,"
    IEEE Robotics and Automation Letters, Vol. 9, no. 4, pp. 3387-3394, 2024. (Refereed) Paper Project
  6. Hirotaka Tahara, Hikaru Sasaki, Hanbit OH, Edgar Anarossi, and Takamitsu Matsubara.
    "Disturbance Injection Under Partial Automation: Robust Imitation Learning for Long-Horizon Tasks,"
    IEEE Robotics and Automation Letters, Vol. 8, no. 5, pp. 2377-3774, 2023. (Refereed) Paper
  7. Hanbit OH, Hikaru Sasaki, Brendan Michael, and Takamitsu Matsubara.
    "Bayesian Disturbance Injection: Robust imitation learning of flexible policies for robot manipulation,"
    Neural Networks, Vol. 158, pp. 42-58, 2023. (Refereed) Paper

International conferences (peer-reviewed)

  1. Hanbit OH, Andrea M. Salcedo-Vázquez, Ixchel G. Ramirez-Alpizar, and Yukiyasu Domae.
    "Robust Instant Policy: Leveraging Student's t-Regression Model for Robust In-context Imitation Learning of Robot Manipulation,"
    In Proceeding of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025. (Refereed) Paper Project
  2. Hirotaka Tahara, Hikaru Sasaki, Hanbit OH, Brendan Michael, and Takamitsu Matsubara.
    "Disturbance-injected Robust Imitation Learning with Task Achievement,"
    In Proceeding of IEEE International Conference on Robotics and Automation (ICRA), pp. 2466-2472, 2022. (Refereed) Paper
  3. Hanbit OH, Hikaru Sasaki, Brendan Michael, and Takamitsu Matsubara.
    "Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies,"
    In Proceeding of IEEE International Conference on Robotics and Automation (ICRA), pp. 8629-8635, 2021. (Refereed) Paper

Awards

  1. [学内] 黒正賞(sumacumlaude), 岡山大学, 2019. 黒正賞, This award is presented each year on the day of the graduation ceremony to a new graduate of Okayama University who has shown outstanding academic achievement and a good personality.
  2. 奨励賞, 2019年度情報処理学会関西支部 支部大会, 2019.
  3. 最優秀賞, NAIST CICP (Creative and International Competitiveness Project) 2019 work shop, 2020.
  4. 最優秀講演賞, 第21回 計測自動制御学会システムインテグレーション部門講演会, 2020.
  5. Best Oral Presentation Award, NAIST CICP (Creative and International Competitiveness Project) 2020 work shop, 2020.
  6. Young Award (IROS 2024), IEEE Robotics and Automation Society Japan Joint Chapter, 2024. pdf, link

Dissertation (Doctoral thesis)

  1. URL: https://library.naist.jp/opac/book/110449

Educational Activities

TA

  1. Apr. 2020 – Sep. 2020, Teaching Assistant, Software Engineering, NAIST, Japan.
  2. Oct. 2020 – Mar. 2021, Teaching Assistant, Operating Systems and Systems Software, NAIST, Japan.
  3. Apr. 2021 – Sep. 2021, Teaching Assistant, Software Engineering, NAIST, Japan.
  4. Oct. 2021 – Mar. 2022, Teaching Assistant, Operating Systems and Systems Software, NAIST, Japan.
  5. Apr. 2022 – Sep. 2022, Teaching Assistant, Software Engineering, NAIST, Japan.

Tutor

  1. Oct. 2019 – Mar. 2020, Tutor for international students, NAIST, Japan.
  2. Apr. 2020 – Sep. 2020, Tutor for international students, NAIST, Japan.
  3. Oct. 2020 – Mar. 2021, Tutor for international students, NAIST, Japan.

CV

📚 2025-present, Research Scientist in the Embodied AI Research Team, Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology in Odaiba, Tokyo.

📚 2024-2025, Research Scientist in the Automation Research Team, Industrial CPS Research Center, National Institute of Advanced Industrial Science and Technology in Odaiba, Tokyo.

👨‍🎓 2021-2024, Ph.D. student, Division of Advanced Science and Technology, Nara Institute of Science and Technology (NAIST).
👨‍🎓 2019-2021, Master student, Division of Advanced Science and Technology, Nara Institute of Science and Technology (NAIST).
👨‍🎓 2013-2019, Bachelor student, Department of Mechanical and System Engineering, Faculty of Engineering, Okayama University.
🎖️ 2014-2015, Military service, Republic of Korea.

Download CV (PDF)

  1. Activity 1：robotpaper.challengeメンバー
    - ICRA2024 速報: https://speakerdeck.com/rpc/icra2024-su-bao

© OH Homepage All Rights Reserved.