Taisuke Kobayashi, ”Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search,” Results in Control and Optimization, 12, 100244, 2023. DOILink
Taisuke Kobayashi, Ryoma Watanuki, ”Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World Model,” Advanced Robotics, 37, 13, 807--827, 2023. DOILinkYouTube
Taisuke Kobayashi, Takumi Aotani, ”Design of Restricted Normalizing Flow towards Arbitrary Stochastic Policy with Computational Efficiency,” Advanced Robotics, 37, 12, 719--736, 2023. DOIYouTube
Taisuke Kobayashi, ”Proximal Policy Optimization with Adaptive Threshold for Symmetric Relative Density Ratio,” Results in Control and Optimization, 10, 100192, 2023. DOILink
Taisuke Kobayashi, Kenta Yoshizawa, ”Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures,” ROBOMECH Journal, 9, 18, 1--16, 2022. DOILinkYouTube
Taisuke Kobayashi, Shingo Murata, Tetsunari Inamura, ”Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics,” IEEE Transactions on Human-Machine Systems, 52, 5, 928--940, 2022. DOILinkYouTube
Taisuke Kobayashi, Toshiya Mabuchi, Mato Kosaka, ”Light-weight Behavior-based Continuous Authentication for Personalized Mobile Robot,” International Journal of Intelligent Robotics and Applications, 6, 694--706, 2022. DOI
Tatsuya Shimizu, Hidekazu Funakoshi, Taisuke Kobayashi, Kenji Sugimoto, ”Reduction of Noise and Vibration in Drum type Washing Machine using Q-learning,” Control Engineering Practice, 122, 105095, 2022. DOI
Taisuke Kobayashi, ”Adaptive and multiple time-scale eligibility traces for online deep reinforcement learning,” Robotics and Autonomous Systems, 151, 104019, 2022. DOILinkYouTube
Takumi Aotani, Taisuke Kobayashi, Kenji Sugimoto, ”Meta-Optimization of Bias-Variance Trade-off in Stochastic Model Learning,” IEEE Access, 9, 148783--148799, 2021. DOI
Hidehito Fujiishi, Taisuke Kobayashi, Kenji Sugimoto, ”Safe and Efficient Imitation Learning by Clarification of Experienced Latent Space,” Advanced Robotics, 35, 16, 1012--1027, 2021. DOIYouTube
Taisuke Kobayashi, Emmanuel Dean-Leon, Julio Rogelio Guadarrama-Olvera, Florian Bergner, Gordon Cheng, ”Whole-Body Multicontact Haptic Human–Humanoid Interaction Based on Leader–Follower Switching: A Robot Dance of the ``Box Step'',” Advanced Intelligent Systems, 4, 2, 2100038, 2022. DOIYouTube
Taisuke Kobayashi, Yutaro Ikawa, Takamitsu Matsubara, ”Sample-efficient Gear-ratio Optimization for Biomechanical Energy Harvester,” International Journal of Intelligent Robotics and Applications, 6, 10--22, 2022. DOILink
Taisuke Kobayashi, Wendyam Eric Lionel Ilboudo, ”t-Soft Update of Target Network for Deep Reinforcement Learning,” Neural Networks, 136, 63--71, 2021. DOILink
Takumi Aotani, Taisuke Kobayashi, Kenji Sugimoto, ”Bottom-up Multi-agent Reinforcement Learning by Reward Shaping for Cooperative-Competitive Tasks,” Applied Intelligence, 51, 7, 4434--4452, 2021. DOI
Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto, ”Robust Stochastic Gradient Descent with Student-t Distribution based First-order Momentum,” IEEE Transactions on Neural Networks and Learning Systems, 33, 3, 1324--1337, 2022. DOIYouTube
Shunki Itadera, Taisuke Kobayashi, Jun Nakanishi, Tadayoshi Aoyama, Yasuhisa Hasegawa, ”Towards Physical Interaction-based Sequential Mobility Assistance using Latent Generative Model of Movement State,” Advanced Robotics, 35, 1, 3, 2021. DOI
Taisuke Kobayashi, Toshiki Sugino, ”Reinforcement Learning for Quadrupedal Locomotion with Design of Continual-Hierarchical Curriculum,” Engineering Applications of Artificial Intelligence, 95, 103869, 2020. DOI
Taisuke Kobayashi, ”q-VAE for Disentangled Representation Learning and Latent Dynamical Systems,” IEEE Robotics and Automation Letters, 5, 4, 5669--5676, 2020. DOILinkYouTube
Taisuke Kobayashi, Tadayoshi Aoyama, Kosuke Sekiyama, Yasuhisa Hasegawa, Toshio Fukuda, ”Delays in perception and action for improving walk–run transition stability in bipedal gait,” Nonlinear Dynamics, 97, 2, 1685--1698, 2019. DOI
Taisuke Kobayashi, ”Student-t policy in reinforcement learning to acquire global optimum of robot control,” Applied Intelligence, 49, 12, 4335--4347, 2019. DOIYouTube
Taisuke Kobayashi, Kosuke Sekiyama, Yasuhisa Hasegawa, Tadayoshi Aoyama, Toshio Fukuda, ”Unified bipedal gait for autonomous transition between walking and running in pursuit of energy minimization,” Robotics and Autonomous Systems, 103, 27--41, 2018. DOI
Taisuke Kobayashi, Tadayoshi Aoyama, Yasuhisa Hasegawa, Kosuke Sekiyama, Toshio Fukuda, ”Adaptive speed controller using swing leg motion for {3-D} limit-cycle-based bipedal gait,” Nonlinear Dynamics, 84, 4, 2285--2304, 2016. DOI
Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Toshio Fukuda, ”Selection of Two Arm-Swing Strategies for Bipedal Walking to Enhance Both Stability and Efficiency,” Advanced Robotics, 30, 6, 386--401, 2016. DOI
Zhiguo Lu, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Taisuke Kobayashi, Toshio Fukuda, ”Energetically Efficient Ladder Descent Motion With Internal Stress and Body Motion Optimized for a Multilocomotion Robot,” IEEE Transactions on Industrial Electronics, 62, 8, 4972--4984, 2015.
Taisuke Kobayashi, Tadayoshi Aoyama, Kosuke Sekiyama, Toshio Fukuda, ”Selection Algorithm for Locomotion Based on the Evaluation of Falling Risk,” IEEE Transactions on Robotics, 31, 3, 750--765, 2015. DOIYouTube
Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Toshio Fukuda, ”Cane-supported walking by humanoid robot and falling-factor-based optimal cane usage selection,” Robotics and Autonomous Systems, 68, 21--35, 2015. DOI
Taisuke Kobayashi, ”Consolidated Adaptive T-soft Update for Deep Reinforcement Learning,” IEEE World Congress on Computational Intelligence, Yokohama, Japan, 2024. (2061205 at IJCNN S6_31) Link
Takumi Aotani, Taisuke Kobayashi, ”Cooperative Transport by Manipulators with Uncertainty-Aware Model-Based Reinforcement Learning,” IEEE/SICE International Symposium on System Integration, 959--964, Ha Long, Vietnam, 2024. (WedCT2.3)
Taisuke Kobayashi, Yusuke Takeda, ”Autonomous Driving from Diverse Demonstrations with Implicit Selection of Optimal Mode,” IEEE/SICE International Symposium on System Integration, 441--446, Ha Long, Vietnam, 2024. (TueCM1.1)
Taisuke Kobayashi, Takahito Enomoto, ”Autonomous Driving of Personal Mobility by Imitation Learning from Small and Noisy Dataset,” IEEE/SICE International Symposium on System Integration, 404--409, Ha Long, Vietnam, 2024. (TueCK1.6) LinkYouTube
Ryoya Mori, Tadayoshi Aoyama, Taisuke Kobayashi, Kazuya Sakamoto, Masaru Takeuchi, Yasuhisa Hasegawa, ”Oocyte Rotation Assistance System Using AI Trained on the Micromanipulations of a Skilled Operator,” IEEE International Symposium on Micro-NanoMechatronics and Human Science, Nagoya, Japan, 2023.
Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Takamitsu Matsubara, ”Domains as Objectives: Multi-Domain Reinforcement Learning with Convex-Coverage Set Learning for Domain Uncertainty Awareness,” IEEE/RSJ International Conference on Intelligent Robots and Systems, 5622--5629, Detroit, Michigan, USA, 2023. (TuAT17.7) DOI
Taisuke Kobayashi, Takanori Jin, ”Mirror-Descent Inverse Kinematics for Box-constrained Joint Space,” World Congress of the International Federation of Automatic Control, 321--326, Yokohama, Japan, 2023. (MoA11.4) LinkYouTube
Taisuke Kobayashi, ”L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning,” IEEE/RSJ International Conference on Intelligent Robots and Systems, 4032--4039, Kyoto, Japan, 2022. (MoC-16.3), SICE International Young Authors Award (SIYA-IROS2022) DOILinkYouTube
Taisuke Kobayashi, ”Intentional Underestimation at Terminal State in Reinforcement Learning,” {ISCIE} International Symposium on Stochastic Systems Theory and Its Applications, 33--34, Nara, Japan, 2022. (1C1-1)
Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto, ”Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning,” IEEE/RSJ International Conference on Intelligent Robots and Systems, 7828--7834, Prague, Czech Republic (online), 2021. DOILinkYouTube
Taisuke Kobayashi, ”Adaptive Eligibility Traces for Online Deep Reinforcement Learning,” International Conference on Intelligent Autonomous Systems, 407--418, Singapore (online), 2021. Link
Taisuke Kobayashi, ”Proximal Policy Optimization with Relative Pearson Divergence,” IEEE International Conference on Robotics and Automation, 8416--8421, Xi'an, China (with online), 2021. (TuBT5) DOILink
Koki Kobayashi, Masaki Ogura, Taisuke Kobayashi, Kenji Sugimoto, ”Deep unfolding-based output feedback control design for linear systems with input saturation,” SICE International Symposium on Control Systems, Online, 2021. (2A1-5) Link
Taisuke Kobayashi, ”Towards Deep Robot Learning with Optimizer Applicable to Non-Stationary Problems,” IEEE/SICE International Symposium on System Integration, 190--194, Fukushima, Japan (Online), 2021. (TuD2.5) Link
Betz Tobias, Hidehito Fujiishi, Taisuke Kobayashi, ”Behavioral Cloning from Observation with Bi-Directional Dynamics Model,” IEEE/SICE International Symposium on System Integration, 184--189, Fukushima, Japan (Online), 2021. (TuD2.4)
Kobayashi, Taisuke, Dean-Leon, Emmanuel, Guadarrama-Olvera, Julio Rogelio, Bergner, Florian, Cheng, Gordon, ”Multi-Contacts Force-Reactive Walking Control During Physical Human-Humanoid Interaction,” IEEE-RAS International Conference on Humanoid Robots, 33--39, Toronto, Canada, 2019. (WeOral1_2.4) YouTube
Kobayashi, Taisuke, Sugino, Toshiki, ”Continual Learning Exploiting Structure of Fractal Reservoir Computing,” International Conference on Artificial Neural Networks, 5, 35--47, Munich, Germany, 2019.
Kobayashi, Taisuke, ”Variational Deep Embedding with Regularized Student-t Mixture Model,” International Conference on Artificial Neural Networks, 3, 443--455, Munich, Germany, 2019.
Taisuke Kobayashi, ”Hyperbolically-Discounted Reinforcement Learning on Reward-Punishment Framework,” Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, 99--100, Oslo, Norway, 2019. (Paper Abstracts) Link
Taisuke Kobayashi, Takumi Aotani, Julio Rogelio Guadarrama-Olvera, Emmanuel Dean-Leon, Gordon Cheng, ”Reward-Punishment Actor-Critic Algorithm Applying to Robotic Non-grasping Manipulation,” Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, 37--42, Oslo, Norway, 2019.
Shunki Itadera, Taisuke Kobayashi, Jun Nakanishi, Tadayoshi Aoyama, Yasuhisa Hasegawa, ”Impedance Control based Assistive Mobility Aid through Online Classification of User's State,” IEEE/SICE International Symposium on System Integration, 243--248, Paris, France, 2019. (Mo2D.3)
Takumi Aotani, Taisuke Kobayashi, Kenji Sugimoto, ”Bottom-up Multi-agent Reinforcement Learning for Selective Cooperation,” IEEE International Conference on Systems, Man, and Cybernetics, 3580--3585, Miyazaki, Japan, 2018. (13252)
Kobayashi, Taisuke, ”Practical Fractional-Order Neuron Dynamics for Reservoir Computing,” International Conference on Artificial Neural Networks, 3, 116--125, Rhodes, Greece, 2018.
Kobayashi, Taisuke, ”Check Regularization: Combining Modularity and Elasticity for Memory Consolidation,” International Conference on Artificial Neural Networks, 2, 315--325, Rhodes, Greece, 2018.
Takumi Aotani, Taisuke Kobayashi, Kenji Sugimoto, ”Learning of Correlation in Decentralized Robots with Individual Tasks,” {SICE} Annual Conference, 662--665, Nara, Japan, 2018. (ThA04.6)
Yutaro Ikawa, Taisuke Kobayashi, Takamitsu Matsubara, ”Biomechanical Energy Harvester with Continuously Variable Transmission: Prototyping and Preliminary Evaluation,” IEEE/ASME International Conference on Advanced Intelligent Mechatronics, 1045--1050, Auckland, New Zealand, 2018. (ThAT1.2)
Tomoro Ota, Kenichi Ohara, Akihiko Ichikawa, Taisuke Kobayashi, Yasuhisa Hasegawa, Toshio Fukuda, ”Modeling of the High-Speed Running Humanoid Robot,” IEEE International Symposium on Micro-NanoMechatronics and Human Science, 112--113, Nagoya, Japan, 2016. (MP-2-2-5)
Taisuke Kobayashi, Kosuke Sekiyama, Yasuhisa Hasegawa, Tadayoshi Aoyama, Toshio Fukuda, ”Quasi-Passive Dynamic Autonomous Control to Enhance Horizontal and Turning Gait Speed Control,” IEEE/RSJ International Conference on Intelligent Robots and Systems, 5612--5617, Daejeon, Korea, 2016. (ThCT4.4)
Taisuke Kobayashi, Yasuhisa Hasegawa, Kosuke Sekiyama, Tadayoshi Aoyama, Toshio Fukuda, ”Unified Bipedal Gait for Walking and Running by Dynamics-based Virtual Holonomic Constraint in {PDAC},” IEEE International Conference on Robotics and Automation, 1769--1775, Stockholm, Sweden, 2016. (TuDbT1.3)
Taisuke Kobayashi, Tadayoshi Aoyama, Yasuhisa Hasegawa, Kosuke Sekiyama, Toshio Fukuda, ”Dynamics-based Virtual Holonomic Constraint for {PDAC} Running,” IEEE International Symposium on Micro-NanoMechatronics and Human Science, 41--42, Nagoya, Japan, 2015. (MP-13)
Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Toshio Fukuda, ”Optimal Use of Arm-Swing for Bipedal Walking Control,” IEEE International Conference on Robotics and Automation, 5698--5703, Seattle, USA, 2015. (FrP1T6.7)
Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Toshio Fukuda, ”Optimal Selection of Cane Usage with Humanoid Robot,” IEEE-RAS International Conference on Humanoid Robots, 199--204, Madrid, Spain, 2014. (WedI1-T6.5)
Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Toshio Fukuda, ”Support of COG Trajectory Tracking by Arm-Swing with Bipedal Walking,” IEEE International Symposium on Micro-NanoMechatronics and Human Science, 150--152, Nagoya, Japan, 2014. (MP2-2-5)
Taisuke Kobayashi, Tadayoshi Aoyama, Masafumi Sobajima, Kosuke Sekiyama, Toshio Fukuda, ”Bipedal Walking by Humanoid Robot with Cane ---Preventive Usage of Cane based on Impulse Force,” IEEE International Symposium on Micro-NanoMechatronics and Human Science, 54--59, Nagoya, Japan, 2013. (MP-10)
Taisuke Kobayashi, Tadayoshi Aoyama, Masafumi Sobajima, Kosuke Sekiyama, Toshio Fukuda, ”Locomotion Selection Strategy for Multi-Locomotion Robot based on Stability and Efficiency,” IEEE/RSJ International Conference on Intelligent Robots and Systems, 2616--2621, Tokyo, Japan, 2013. (TuAT13.6)
Masafumi Sobajima, Taisuke Kobayashi, Kosuke Sekiyama, Toshio Fukuda, ”Bipedal Walking Control of Humanoid Robots by Arm-Swing,” {SICE} Annual Conference, 313--318, Nagoya, Japan, 2013. (SuAT13.5)
Tadayoshi Aoyama, Kosuke Sekiyama, Zhiguo Lu, Taisuke Kobayashi, Yasuhisa Hasegawa, Toshio Fukuda, ”Stability Enhancement of {3-D} Biped Walking based on Passive Dynamic Autonomous Control,” IEEE-RAS International Conference on Humanoid Robots, 443--448, Osaka, Japan, 2012. (FrP4T1.19)
Taisuke Kobayashi, Tadayoshi Aoyama, Kosuke Sekiyama, Toshio Fukuda, ”Stabilization and Moving Efficiency Improvement by Adjustment of Moving Speed in Single Locomotion,” IEEE International Symposium on Micro-NanoMechatronics and Human Science, 325--330, Nagoya, Japan, 2012. (TA2-2-7)
Zhiguo Lu, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Taisuke Kobayashi, Toshio Fukuda, ”Optimal Control of Energetically Efficient Ladder Decent Motion with Internal Stress Adjustment Using Key Joint Method,” IEEE/RSJ International Conference on Intelligent Robots and Systems, 2216--2221, Algarve, Portugal, 2012. (TueBT5.3)
Taisuke Kobayashi, Tadayoshi Aoyama, Kosuke Sekiyama, Zhiguo Lu, Yasuhisa Hasegawa, Toshio Fukuda, ”Locomotion Selection of Multi-Locomotion Robot based on Falling Risk and Moving Efficiency,” IEEE/RSJ International Conference on Intelligent Robots and Systems, 2869--2874, Vilamoura, Portugal, 2012. (TueDT7.4)
Taisuke Kobayashi, ”DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning,” arXiv:2410.17473, 2024. (submitted for publication) Link
Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Takamitsu Matsubara, ”Domains as Objectives: Domain-Uncertainty-Aware Policy Optimization through Explicit Multi-Domain Convex Coverage Set Learning,” arXiv:2410.04719, 2024. (submitted for publication) Link
Taisuke Kobayashi, ”LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World,” arXiv:2409.19617, 2024. (submitted for publication) LinkYouTube
Takanori Jin, Taisuke Kobayashi, Takamitsu Matsubara, ”Walking in Constrained Environment using Model-based Reinforcement Learning for Virtual Constraint-based Gait,” IEEE International Conference on Robotics and Automation (Late Breaking Results), 2024.
Ryoya Mori, Tadayoshi Aoyama, Taisuke Kobayashi, Kazuya Sakamoto, Masaru Takeuchi, Yasuhisa Hasegawa, ”Micromanipulation Assistance Via Motion Guidance
to a Spatiotemporal Ideal Trajectory Using GMM and LSTM,” IEEE International Conference on Robotics and Automation (Late Breaking Results), 2024.
Taisuke Kobayashi, ”LiRA: Light-Robust Adversary for Model-based Reinforcement Learning,” ICRA 2024 Workshop -- Back to the Future: Robot Learning Going Probabilistic, 2024.
Taisuke Kobayashi, ”Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward,” arXiv:2308.12772, 2023. (submitted for publication) LinkYouTube
Taisuke Kobayashi, Kota Fukumoto, ”Real-time Sampling-based Model Predictive Control based on Reverse Kullback-Leibler Divergence and Its Adaptive Acceleration,” arXiv:2212.04298, 2022. (submitted for publication) LinkYouTube
Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Takamitsu Matsubara, ”Noise-Aware Stochastic Gradient Optimization with AdaTerm,” IEEE/RSJ International Conference on Intelligent Robots and Systems (Late Breaking Results), 2022. Link
小林 泰介, ”5分で分かる!?有名論文ナナメ読み「Sergey Levine: Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review」,” 情報処理, 2021.
小林 泰介, ”べき乗則への転換がもたらすノイズに頑健な機械学習,” 90th BFI Group Seminar, 2020. Link
Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto, ”TAdam: A Robust Stochastic Gradient Optimizer,” arXiv:2003.00179, 2020. Link
Taisuke Kobayashi, ”Research on my visit to Technical University of Munich for Human-friendly robots,” NAIST Colloquium B: Reports of long term abroad activities, 2020.
Kobayashi, Taisuke, ”Selection Algorithm for Locomotion
based on Falling Risk and Moving Efficiency for Multi-Locomotion Robot,” Multi-Locomotion Robot Symposium, 2016.
Toshio Fukuda, Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, ”Usage of Cane for Multi-Locomotion Robot,” Yale Workshop on Adaptive and Learning Systems, 2015.