Publications

Journal Papers

  1. Offline Reinforcement Learning with Mixture of Deterministic Policies
    T. Osa, A. Hayashi, P. Deo, N. Morihira, T. Yoshiike
    Transactions on Machine Learning Research, 2023
    [pdf][ publisher website]
  2. Learning Adaptive Policies for Autonomous Excavation Under Various Soil Conditions by Adversarial Domain Sampling
    T. Osa, N. Osajima, M. Aizawa, T. Harada
    IEEE Robotics and Automation Letters, Vol. 8, No. 9, pp. 5536-5543, Sept. 2023, doi: 10.1109/LRA.2023.3296933.
    [pdf][ publisher website]
  3. Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information
    T. Osa, V. Tangkaratt, and M. Sugiyama
    Neural Networks, Vol. 152, pp. 90-104, 2022.
    [ arXiv][ publisher website]
  4. Motion Planning by Learning the Solution Manifold in Trajectory Optimization
    T. Osa
    The International Journal of Robotics Research, Vol. 41, No. 3, pp. 291-311, 2022.
    [ arXiv] [ publisher website]
  5. Sample-Efficient Parameter Exploration of the Powder Film Drying Process Using Experiment-Based Bayesian Optimization
    K. Nagai, T. Osa, G. Inoue, T. Tsujiguchi, T. Araki, Y. Kuroda, M. Tomizawa, and K. Nagato
    Scientific report, Vol. 12, No. 1615, 2022.
    [ publisher website(open access)]
  6. Deep Reinforcement Learning with Adversarial Training for Automated Excavation using Depth Images
    T. Osa and M. Aizawa
    IEEE Access, vol. 10, pp. 4523-4535, 2022.
    [ publisher website(open access)]
  7. Multimodal Trajectory Optimization for Motion Planning
    T. Osa
    The International Journal of Robotics Research, Vol. 39 No. 8, pp. 983–-1001, 2020.
    [ arXiv] [publisher website]
  8. Hierarchical Stochastic Optimization with Application to Parameter Tuning for Electronically Controlled Transmissions
    H. Karasawa, T. Kanemaki, K. Oomae, R. Fukui, M. Nakao and T. Osa
    IEEE Robotics and Automation Letters with Presentation at the IEEE International Conference on Robotics and Automation (ICRA), Vol. 5, No. 2, pp. 628--635, 2020.
  9. Goal-Conditioned Variational Autoencoder Trajectory Primitives with Continuous and Discrete Latent Codes
    T. Osa, S. Ikemoto
    SN Computer Science, Vol. 1, No. 303, Springer Nature, 2020.
    [ arXiv]
  10. 端点の多峰性最適化による複数の解が導出可能な軌道計画法
    長隆之, 佐藤 雅也, 森木 和也, 杉山 聡, 杉田 直彦, 中尾 政之
    日本ロボット学会誌, Vol. 37, Oct., 2019.
  11. Hierarchical Reinforcement Learning of Multiple Grasping Strategies with Human Instructions,
    T. Osa, J. Peters and G. Neumann,
    Advanced Robotics, Vol. 32 No. 18, pp 955-968, 2018.
    The publication is available via https://doi.org/10.1080/01691864.2018.1509018
  12. An Algorithmic Perspective on Imitation Learning,
    T. Osa, J. Pajarinen, G. Neumann, J. A. Bagnell, P Abbeel, and J. Peters.
    Trends and Foundations in Robotics, Vol. 7: No. 1-2, pp 1-179, 2018.
    The publication is available from now publishers via http://dx.doi.org/10.1561/2300000053
    [ paper]
  13. Online Trajectory Planning and Force Control for Automation of Surgical Tasks,
    T. Osa, N. Sugita, and M. Mitsuishi.
    IEEE Transactions on Automation Science and Engineering, Volume: 15, Issue: 2, 2018.
    [ paper] [youtube ]
  14. Guiding Trajectory Optimization by Demonstrated Distributions,
    T. Osa, A. M. Ghalamzan E., R. Stolkin, R. Lioutikov, J. Peters, and G. Neumann.
    IEEE Robotics and Automation Letter, Vol.2, No.2, pages 819-826, 2017.
    [ paper ] [youtube ]
  15. Hybrid Rate-Admittance Control with Force Reflection for Safe Teleoperated Surgery,
    T. Osa, S. Uchida, N. Sugita, and M. Mitsuishi.
    IEEE/ASME Transactions on Mechatronics, 20(5):2379-2390, Oct. 2015.
    [ paper ]
  16. Hand-Held Bone Cutting Tool with Autonomous Penetration Detection for Spinal Surgery,
    T. Osa, C. F. Abawi, N. Sugita, H. Chikuda, S. Sugita, T. Tanaka, H. Oshima, T. Moro, S. Tanaka, and M. Mitsuishi.
    IEEE/ASME Transactions on Mechatronics, Vol.20, No.6, pages 3018-3027, Dec. 2015.
    [ paper ]
  17. A New Cutting Method for Bone Based on Crack Propagation Characteristics,
    N. Sugita, T. Osa, R. Aoki, and M. Mitsuishi.
    Cirp Annals-Manufacturing Technology, pages 113-118, 2009.
    [ paper ]
  18. Analysis and Estimation of Cutting-Temperature Distribution during End Milling in Relation to Orthopedic Surgery,
    N. Sugita, T. Osa, and M. Mamoru.
    Medical engineering & physics, pages 101-107, 2009.
    [ paper ]
  19. A Study on Improvement of Machining Precision in a Medical Milling Robot,
    N. Sugita, T. Osa, Y. Nakajima, M. Mori, H. Saraie and M. Mitsuishi.
    Transactions of the Institute of Systems, Control and Information Engineers, Vol.22, No.2, pages 66-73, 2009.
    [ paper ]
  20. Cutting Tool Protects for Soft Tissues in Bone-Milling Machining,
    N. Sugita, T. Nakano, T. Osa, Y. Nakajima, K. Fujiwara, N. Abe, T. Ozaki, M. Suzuki, and M. Mitsuishi.
    International Journal of Automation Technology, Vol.2, pages 185-192, 2009.
    [ paper ]
  21. 多軸医用加工機のための工具経路決定法
    杉田 直彦, 源馬 文章, 長 隆之, 中島 義和, 加藤 丈晴, 光石 衛.
    日本機械学會論文集.C編, 74, 743, pp.1907-1913, 2008
    [ paper (in Japanese) ]

Major Conference Papers

  1. Stabilizing Extreme Q-learning by Maclaurin Expansion
    M. Omura, T. Osa, Y. Mukuta, and T. Harada
    In Proceedings of the Reinforcement Learning Conference (RLC), 2024, to appear.
    [ arXiv]
  2. Offline Reinforcement Learning from Datasets with Structured Non-Stationarity
    J. Ackermann, T. Osa, and M. Sugiyama
    In Proceedings of the Reinforcement Learning Conference (RLC), 2024, to appear.
    [ arXiv]
  3. Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning
    T. Osa and T. Harada
    In Proceedings of the International Conference on Machine Learning (ICML), 2024, to appear.
    [ arXiv][ website]
  4. Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks
    T. Osa and T. Harada
    In Proceedings of the IEEE International Conferences on Robotics and Automation (ICRA), 2024.
    [ arXiv]
  5. Touch-Based Manipulation with Multi-Fingered Robot using Off-policy RL and Temporal Contrastive Learning
    N. Morihira, P. Deo, M. Bhadu, A. Hayashi, T. Hasegawa, S. Otsubo, T. Osa
    In Proceedings of the IEEE International Conferences on Robotics and Automation (ICRA), 2024.
  6. Open X-Embodiment: Robotic Learning Datasets and RT-X Models
    Open X-Embodiment Collaboration (173 authors, including Takayuki Osa)
    In Proceedings of the IEEE International Conferences on Robotics and Automation (ICRA), 2024r.
    [ arXiv]
  7. Symmetric Q-Learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning
    M. Omura, T. Osa, Y. Mukuta, T. Harada
    In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI), 2024.
    [ arXiv]
  8. Forward/Inverse Kinematics Modeling for Tensegrity Manipulator based on Goal-conditioned Variational Autoencoder,
    Y. Yoshimitsu, T. Osa, S. Ikemoto.
    In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023.
  9. Meta-Model-Based Meta-Policy Optimization
    T. Hiraoka, T. Imagawa, V. Tangkaratt, T. Osa, T. Onishi, Y. Tsuruoka.
    In Proceedings of the Asian Conference on Machine Learning (ACML), 2021.
    [ arXiv]
  10. Parameter Optimization in the Drying Process of Catalyst Ink for PEFC Electrode Films with Few Cracks
    K. Nagai, K. Nagato, T. Osa, T. Araki, G. Inoue, T. Tsujiguchi, Y. Kuroda, M. Tomizawa and M. Kurosu
    ECS Transactions, Vol. 104, No. 9, pp 17-23, 2021.
  11. Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization
    T. Osa, V. Tangkaratt, M. Sugiyama.
    In Proceedings of the International Conference on Learning Representations (ICLR), 2019.
  12. Sample and Feedback Efficient Hierarchical Reinforcement Learning from Human Preferences,
    R. Pinsler, R. Akrour, T. Osa, J. Peters, G. Neumann.
    In Proceedings of the IEEE International Conferences on Robotics and Automation (ICRA), 2018.
  13. Hierarchical Policy Search via Return-Weighted Density Estimation,
    T. Osa and M. Sugiyama.
    In Proceedings of the AAAI conference on Artificial Intelligence (AAAI), 2018.
    [ arXiv ]
  14. Active Incremental Learning of Robot Movement Primitives,
    G. Maeda, M. Ewarton, T. Osa, B. Busch, J. Peters.
    In Proceedings of the Conference on Robot Learning (CoRL), Proceedings of Machine Learning Research 78:37-46, 2017.
    [ paper ] [youtube ]
  15. A Learning-Based Shared Control Architecture for Interactive Task Execution,
    F. B. Farraj, T. Osa, N. Pedemonte, J. Peters, G. Neumann, P. R. Giordano.
    In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2017.
    [ paper ]
  16. Experiments with Hierarchical Reinforcement Learning of Multiple Grasping Policies,
    T. Osa, J. Peters, and G. Neumann.
    In Proceedings of International Symposium on Experimental Robotics (ISER), 2016.
    [ paper ]
  17. Online Trajectory Planning in Dynamic Environments for Surgical Task Automation,
    T. Osa, N. Sugita, and M. Mitsuishi.
    In Proceedings of Robotics: Science and Systems (R:SS), 2014.
    [ paper ]
  18. Hybrid Control of Master-Slave Velocity Control and Admittance Control for Safe Remote Surgery,
    T. Osa, S. Uchida, N. Sugita, and M. Mitsuichi.
    In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2014, pages 1328-1334. IEEE, 2014.
    [ paper ]
  19. Intelligent Bone-cutting Tool with Autonomous Penetration Detection by Learning from Human Expert for Spinal Surgery,
    T. Osa, C. Abawi, N. Sugita, S. Sugita, H. Chikuda, H. Ito, T. Moro, Y. Takatori, S. Tanaka and M. Mitsuishi.
    In Proceedings of International Congress and Exhibition of Computer Assisted Radiology and Surgery (CARS), 2014.
  20. Trajectory Planning under Different Initial Conditions for Surgical Task Automation by Learning from Demonstration,
    T. Osa, K. Harada, N. Sugita, and M. Mitsuishi.
    In Proceedings of IEEE International Conference on Robotics and Automation (ICRA) 2014, pages 6507-6513. IEEE, May 2014.
    [ paper ]
  21. Autonomous Penetration Detection for Bone Cutting Tool using Demonstration-Based Learning,
    T. Osa, C. F. Abawi, N. Sugita, H. Chikuda, S. Sugita, H. Ito, T. Moro, Y. Takatori, S. Tanaka, and M. Mitsuishi.
    In Proceedings of IEEE International Conference on Robotics and Automation (ICRA) 2014, pages 290-296. IEEE, May 2014.
    [ paper ]
  22. Perforation Risk Detector using Demonstration-Based Learning for Teleoperated Robotic Surgery,
    T. Osa, T. Haniu, K. Harada, N. Sugita, and M. Mitsuishi.
    In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2013, pages 2572-2577. IEEE, 2013.
    [ paper ]
  23. Framework of Automatic Robot Surgery System using Visual Servoing,
    T. Osa, C. Staub, and A. Knoll.
    In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2010, pages 1837-1842. IEEE, 2010.
    [ paper ]
  24. Automation of Tissue Piercing using Circular Needles and Vision Guidance for Computer Aided Laparoscopic Surgery,
    C. Staub, T. Osa, A. Knoll, and R. Bauernschmitt.
    In Proceedings of IEEE International Conference on Robotics and Automation (ICRA) 2010, pages 4585-4590. IEEE, 2010.
    [ paper ]
  25. Asynchronous Force and Visual Feedback in Teleoperative Laparoscopic Surgical System,
    K. Onda, T. Osa, N. Sugita, M. Hashizume, and M. Mitsuishi.
    In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2010, pages 844-849. IEEE, Oct 2010.
    [ paper ]
  26. Autonomous High Precision Positioning of Surgical Instruments in Robot-Assisted Minimally Invasive Surgery under Visual Guidance,
    C. Staub, A. Knoll, T. Osa, and R. Bauernschmitt.
    In Proceedings of Sixth International Conference on Autonomic and Autonomous Systems (ICAS) 2010, pages 64-69. IEEE, March 2010.
    [ paper ]
  27. Deformation Analysis and Active Compensation of Surgical Milling Robot Based on System Error Evaluation,
    N. Sugita, T. Osa, Y. Nakajima, M. Mitsuishi.
    In Proceedings of IEEE International Conference on Robotics and Automation (ICRA) 2008, pages 3389-3394. IEEE, 2008.
    [ paper ]