Taisuke Kobayashi

107 papers A* 3A 7B 2C 1Journal 67Unranked 27

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Domains as objectives: Domain-uncertainty-aware policy optimization through explicit multi-domain convex coverage set learning. Int. J. Robotics Res. Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Takamitsu Matsubara
2026	J	`jnl`	Improvements to dark experience replay and reservoir sampling for better balance between consolidation and plasticity. Frontiers Artif. Intell. Taisuke Kobayashi
2026	J	`jnl`	VDoF-MPC: Variable Degrees-of-Freedom Whole-Body Model Predictive Control. IEEE Access Takanori Jin, Taisuke Kobayashi, Masahiro Doi
2025	—	`conf`	Adaptive Absolute-Relative Rating for Noise Rejection in Behavioral Cloning based on Tsallis Statistics. SII Taisuke Kobayashi, Tadayoshi Aoyama
2025	J	`jnl`	CubeDAgger: Improved Robustness of Interactive Imitation Learning without Violation of Dynamic Stability. CoRR Taisuke Kobayashi
2025	—	`conf`	Cyclic Exploration and Exploitation in Surprise Minimizing Reinforcement Learning. ICDL Kinari Kubota, Taisuke Kobayashi
2025	—	`conf`	Development of the Leg Structure with Concentrated Liquid-Cooling Actuators for Long-Term Operation. Humanoids Takanori Jin, Taisuke Kobayashi, Masahiro Doi
2025	—	`conf`	Extraction of Latent Variables for Modeling Subjective Quality in Time-series Human-Robot Interaction. SII Yoshiaki Mizuchi, Taisuke Kobayashi, Tetsunari Inamura
2025	J	`jnl`	Improvements of Dark Experience Replay and Reservoir Sampling towards Better Balance between Consolidation and Plasticity. CoRR Taisuke Kobayashi
2025	J	`jnl`	LiRA: Light-Robust Adversary for model-based reinforcement learning in real world. Robotics Auton. Syst. Taisuke Kobayashi
2025	—	`conf`	Skin-Machine Interface with Multimodal Contact Motion Classifier. Humanoids Alberto Confente, Takanori Jin, Taisuke Kobayashi, Julio Rogelio Guadarrama-Olvera, Gordon Cheng
2025	J	`jnl`	Skin-Machine Interface with Multimodal Contact Motion Classifier. CoRR Alberto Confente, Takanori Jin, Taisuke Kobayashi, Julio Rogelio Guadarrama-Olvera, Gordon Cheng
2025	—	`conf`	Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks. ICDL Taisuke Kobayashi, Shingo Murata
2025	J	`jnl`	Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks. CoRR Taisuke Kobayashi, Shingo Murata
2025	J	`jnl`	Weber-Fechner law in temporal difference learning derived from control as inference. Frontiers Robotics AI Keiichiro Takahashi, Taisuke Kobayashi, Tomoya Yamanokuchi, Takamitsu Matsubara
2024	—	`conf`	Autonomous Driving from Diverse Demonstrations with Implicit Selection of Optimal Mode. SII Taisuke Kobayashi, Yusuke Takeda
2024	—	`conf`	Autonomous Driving of Personal Mobility by Imitation Learning from Small and Noisy Dataset. SII Taisuke Kobayashi, Takahito Enomoto
2024	B	`conf`	Consolidated Adaptive T-soft Update for Deep Reinforcement Learning. IJCNN Taisuke Kobayashi
2024	J	`jnl`	Constrained footstep planning using model-based reinforcement learning in virtual constraint-based walking. Adv. Robotics Takanori Jin, Taisuke Kobayashi, Takamitsu Matsubara
2024	—	`conf`	Cooperative Transport by Manipulators with Uncertainty-Aware Model-Based Reinforcement Learning. SII Takumi Aotani, Taisuke Kobayashi
2024	J	`jnl`	DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning. CoRR Taisuke Kobayashi
2024	J	`jnl`	Design of Restricted Normalizing Flow towards Arbitrary Stochastic Policy with Computational Efficiency. CoRR Taisuke Kobayashi, Takumi Aotani
2024	J	`jnl`	Domains as Objectives: Domain-Uncertainty-Aware Policy Optimization through Explicit Multi-Domain Convex Coverage Set Learning. CoRR Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Takamitsu Matsubara
2024	J	`jnl`	Latent regression based model predictive control for tissue triangulation. Adv. Robotics Songtao Liu, Jacinto Colan, Yaonan Zhu, Taisuke Kobayashi, Kazunari Misawa, Masaru Takeuchi, Yasuhisa Hasegawa
2024	J	`jnl`	LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World. CoRR Taisuke Kobayashi
2024	J	`jnl`	Real-Time Spatiotemporal Assistance for Micromanipulation Using Imitation Learning. IEEE Robotics Autom. Lett. Ryoya Mori, Tadayoshi Aoyama, Taisuke Kobayashi, Kazuya Sakamoto, Masaru Takeuchi, Yasuhisa Hasegawa
2024	—	`conf`	Real-time Detailed Self-collision Avoidance in Whole-body Model Predictive Control. Humanoids Takanori Jin, Taisuke Kobayashi, Masahiro Doi
2024	J	`jnl`	Revisiting Experience Replayable Conditions. CoRR Taisuke Kobayashi
2024	J	`jnl`	Revisiting experience replayable conditions. Appl. Intell. Taisuke Kobayashi
2024	J	`jnl`	Weber-Fechner Law in Temporal Difference learning derived from Control as Inference. CoRR Keiichiro Takahashi, Taisuke Kobayashi, Tomoya Yamanokuchi, Takamitsu Matsubara
2023	J	`jnl`	AdaTerm: Adaptive T-distribution estimated robust moments for Noise-Robust stochastic gradient optimization. Neurocomputing Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Takamitsu Matsubara
2023	J	`jnl`	Design of restricted normalizing flow towards arbitrary stochastic policy with computational efficiency. Adv. Robotics Taisuke Kobayashi, Takumi Aotani
2023	A	`conf`	Domains as Objectives: Multi-Domain Reinforcement Learning with Convex-Coverage Set Learning for Domain Uncertainty Awareness. IROS Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Takamitsu Matsubara
2023	J	`jnl`	Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward. CoRR Taisuke Kobayashi
2023	J	`jnl`	Soft Actor-Critic Algorithm with Truly Inequality Constraint. CoRR Taisuke Kobayashi
2023	J	`jnl`	Sparse representation learning with modified q-VAE towards minimal realization of world model. Adv. Robotics Taisuke Kobayashi, Ryoma Watanuki
2022	J	`jnl`	AdaTerm: Adaptive T-Distribution Estimated Robust Moments towards Noise-Robust Stochastic Gradient Optimizer. CoRR Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto
2022	J	`jnl`	Adaptive and multiple time-scale eligibility traces for online deep reinforcement learning. Robotics Auton. Syst. Taisuke Kobayashi
2022	J	`jnl`	Consolidated Adaptive T-soft Update for Deep Reinforcement Learning. CoRR Taisuke Kobayashi
2022	A	`conf`	L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning. IROS Taisuke Kobayashi
2022	J	`jnl`	L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning. CoRR Taisuke Kobayashi
2022	J	`jnl`	Latent Representation in Human-Robot Interaction With Explicit Consideration of Periodic Dynamics. IEEE Trans. Hum. Mach. Syst. Taisuke Kobayashi, Shingo Murata, Tetsunari Inamura
2022	J	`jnl`	Light-weight behavior-based continuous authentication for personalized mobile robot. Int. J. Intell. Robotics Appl. Taisuke Kobayashi, Toshiya Mabuchi, Mato Kosaka
2022	J	`jnl`	Optimistic reinforcement learning by forward Kullback-Leibler divergence optimization. Neural Networks Taisuke Kobayashi
2022	J	`jnl`	Proximal Policy Optimization with Adaptive Threshold for Symmetric Relative Density Ratio. CoRR Taisuke Kobayashi
2022	J	`jnl`	Real-time Sampling-based Model Predictive Control based on Reverse Kullback-Leibler Divergence and Its Adaptive Acceleration. CoRR Taisuke Kobayashi, Kota Fukumoto
2022	J	`jnl`	Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search. CoRR Taisuke Kobayashi
2022	J	`jnl`	Robust Stochastic Gradient Descent With Student-t Distribution Based First-Order Momentum. IEEE Trans. Neural Networks Learn. Syst. Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto
2022	J	`jnl`	Sample-efficient gear-ratio optimization for biomechanical energy harvester. Int. J. Intell. Robotics Appl. Taisuke Kobayashi, Yutaro Ikawa, Takamitsu Matsubara
2022	J	`jnl`	Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World Model. CoRR Taisuke Kobayashi, Ryoma Watanuki
2022	J	`jnl`	Whole-Body Multicontact Haptic Human-Humanoid Interaction Based on Leader-Follower Switching: A Robot Dance of the "Box Step". Adv. Intell. Syst. Taisuke Kobayashi, Emmanuel C. Dean-Leon, Julio Rogelio Guadarrama-Olvera, Florian Bergner, Gordon Cheng
2021	C	`conf`	Adaptive Eligibility Traces for Online Deep Reinforcement Learning. IAS Taisuke Kobayashi
2021	A	`conf`	Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning. IROS Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto
2021	J	`jnl`	Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning. CoRR Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto
2021	—	`conf`	Behavioral Cloning from Observation with Bi-directional Dynamics Model. SII Tobias Betz, Hidehito Fujiishi, Taisuke Kobayashi
2021	J	`jnl`	Bottom-up multi-agent reinforcement learning by reward shaping for cooperative-competitive tasks. Appl. Intell. Takumi Aotani, Taisuke Kobayashi, Kenji Sugimoto
2021	J	`jnl`	Hyperbolically-Discounted Reinforcement Learning on Reward-Punishment Framework. CoRR Taisuke Kobayashi
2021	J	`jnl`	Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics. CoRR Taisuke Kobayashi, Shingo Murata, Tetsunari Inamura
2021	J	`jnl`	Meta-Optimization of Bias-Variance Trade-Off in Stochastic Model Learning. IEEE Access Takumi Aotani, Taisuke Kobayashi, Kenji Sugimoto
2021	J	`jnl`	Mirror-Descent Inverse Kinematics for Box-constrained Joint Space. CoRR Taisuke Kobayashi
2021	J	`jnl`	Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization. CoRR Taisuke Kobayashi
2021	J	`jnl`	Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures. CoRR Taisuke Kobayashi, Kenta Yoshizawa
2021	A*	`conf`	Proximal Policy Optimization with Relative Pearson Divergence. ICRA Taisuke Kobayashi
2021	J	`jnl`	Safe and efficient imitation learning by clarification of experienced latent space. Adv. Robotics Hidehito Fujiishi, Taisuke Kobayashi, Kenji Sugimoto
2021	J	`jnl`	Sample-efficient Gear-ratio Optimization for Biomechanical Energy Harvester. CoRR Taisuke Kobayashi, Yutaro Ikawa, Takamitsu Matsubara
2021	J	`jnl`	Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning. CoRR Taisuke Kobayashi, Takahito Enomoto
2021	—	`conf`	Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems. SII Taisuke Kobayashi
2021	J	`jnl`	Towards physical interaction-based sequential mobility assistance using latent generative model of movement state. Adv. Robotics Shunki Itadera, Taisuke Kobayashi, Jun Nakanishi, Tadayoshi Aoyama, Yasuhisa Hasegawa
2021	J	`jnl`	t-soft update of target network for deep reinforcement learning. Neural Networks Taisuke Kobayashi, Wendyam Eric Lionel Ilboudo
2020	J	`jnl`	Adaptive and Multiple Time-scale Eligibility Traces for Online Deep Reinforcement Learning. CoRR Taisuke Kobayashi
2020	J	`jnl`	Deep unfolding-based output feedback control design for linear systems with input saturation. CoRR Koki Kobayashi, Masaki Ogura, Taisuke Kobayashi, Kenji Sugimoto
2020	J	`jnl`	Proximal Policy Optimization with Relative Pearson Divergence. CoRR Taisuke Kobayashi
2020	J	`jnl`	Reinforcement learning for quadrupedal locomotion with design of continual-hierarchical curriculum. Eng. Appl. Artif. Intell. Taisuke Kobayashi, Toshiki Sugino
2020	J	`jnl`	TAdam: A Robust Stochastic Gradient Optimizer. CoRR Wendyam Eric Lionel Ilboudo, Taisuke Kobayashi, Kenji Sugimoto
2020	J	`jnl`	Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems. CoRR Taisuke Kobayashi
2020	J	`jnl`	q-VAE for Disentangled Representation Learning and Latent Dynamical Systems. CoRR Taisuke Kobayashi
2020	J	`jnl`	q-VAE for Disentangled Representation Learning and Latent Dynamical Systems. IEEE Robotics Autom. Lett. Taisuke Kobayashi
2020	J	`jnl`	t-Soft Update of Target Network for Deep Reinforcement Learning. CoRR Taisuke Kobayashi, Wendyam Eric Lionel Ilboudo
2019	—	`conf`	Continual Learning Exploiting Structure of Fractal Reservoir Computing. ICANN (Workshop) Taisuke Kobayashi, Toshiki Sugino
2019	—	`conf`	Impedance Control based Assistive Mobility Aid through Online Classification of User's State. SII Shunki Itadera, Taisuke Kobayashi, Jun Nakanishi, Tadayoshi Aoyama, Yasuhisa Hasegawa
2019	—	`conf`	Multi-Contacts Force-Reactive Walking Control during Physical Human-Humanoid Interaction. Humanoids Taisuke Kobayashi, Emmanuel C. Dean-Leon, Julio Rogelio Guadarrama-Olvera, Florian Bergner, Gordon Cheng
2019	—	`conf`	Reward-Punishment Actor-Critic Algorithm Applying to Robotic Non-grasping Manipulation. ICDL-EPIROB Taisuke Kobayashi, Takumi Aotani, Julio Rogelio Guadarrama-Olvera, Emmanuel C. Dean-Leon, Gordon Cheng
2019	J	`jnl`	Student-t policy in reinforcement learning to acquire global optimum of robot control. Appl. Intell. Taisuke Kobayashi
2019	—	`conf`	Variational Deep Embedding with Regularized Student-t Mixture Model. ICANN (3) Taisuke Kobayashi
2018	—	`conf`	Biomechanical Energy Harvester with Continuously Variable Transmission: Prototyping and Preliminary Evaluation. AIM Yutaro Ikawa, Taisuke Kobayashi, Takamitsu Matsubara
2018	B	`conf`	Bottom-up Multi-agent Reinforcement Learning for Selective Cooperation. SMC Takumi Aotani, Taisuke Kobayashi, Kenji Sugimoto
2018	—	`conf`	Check Regularization: Combining Modularity and Elasticity for Memory Consolidation. ICANN (2) Taisuke Kobayashi
2018	—	`conf`	Practical Fractional-Order Neuron Dynamics for Reservoir Computing. ICANN (3) Taisuke Kobayashi
2018	J	`jnl`	Unified bipedal gait for autonomous transition between walking and running in pursuit of energy minimization. Robotics Auton. Syst. Taisuke Kobayashi, Kosuke Sekiyama, Yasuhisa Hasegawa, Tadayoshi Aoyama, Toshio Fukuda
2016	—	`conf`	Modeling of the high-speed running humanoid robot. MHS Tomoro Ota, Kenichi Ohara, Akihiko Ichikawa, Taisuke Kobayashi, Yasuhisa Hasegawa, Toshio Fukuda
2016	A	`conf`	Quasi-passive dynamic autonomous control to enhance horizontal and turning gait speed control. IROS Taisuke Kobayashi, Kosuke Sekiyama, Yasuhisa Hasegawa, Tadayoshi Aoyama, Toshio Fukuda
2016	J	`jnl`	Selection of two arm-swing strategies for bipedal walking to enhance both stability and efficiency. Adv. Robotics Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Toshio Fukuda
2016	A*	`conf`	Unified bipedal gait for walking and running by dynamics-based virtual holonomic constraint in PDAC. ICRA Taisuke Kobayashi, Yasuhisa Hasegawa, Kosuke Sekiyama, Tadayoshi Aoyama, Toshio Fukuda
2015	J	`jnl`	Cane-supported walking by humanoid robot and falling-factor-based optimal cane usage selection. Robotics Auton. Syst. Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Toshio Fukuda
2015	—	`conf`	Dynamics-based virtual holonomic constraint for PDAC running. MHS Taisuke Kobayashi, Tadayoshi Aoyama, Yasuhisa Hasegawa, Kosuke Sekiyama, Toshio Fukuda
2015	J	`jnl`	Energetically Efficient Ladder Descent Motion With Internal Stress and Body Motion Optimized for a Multilocomotion Robot. IEEE Trans. Ind. Electron. Zhiguo Lu, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Taisuke Kobayashi, Toshio Fukuda
2015	A*	`conf`	Optimal use of arm-swing for bipedal walking control. ICRA Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Toshio Fukuda
2015	J	`jnl`	Selection Algorithm for Locomotion Based on the Evaluation of Falling Risk. IEEE Trans. Robotics Taisuke Kobayashi, Tadayoshi Aoyama, Kosuke Sekiyama, Toshio Fukuda
2014	—	`conf`	Optimal selection of cane usage with humanoid robot. Humanoids Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Toshio Fukuda
2014	—	`conf`	Support of COG trajectory tracking by arm-swing with bipedal walking. MHS Taisuke Kobayashi, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Toshio Fukuda
2013	—	`conf`	Bipedal walking by humanoid robot with cane - Preventive usage of cane based on impulse force. MHS Taisuke Kobayashi, Tadayoshi Aoyama, Masafumi Sobajima, Kosuke Sekiyama, Toshio Fukuda
2013	A	`conf`	Locomotion selection strategy for multi-locomotion robot based on stability and efficiency. IROS Taisuke Kobayashi, Tadayoshi Aoyama, Masafumi Sobajima, Kosuke Sekiyama, Toshio Fukuda
2012	A	`conf`	Locomotion selection of Multi-Locomotion Robot based on Falling Risk and moving efficiency. IROS Taisuke Kobayashi, Tadayoshi Aoyama, Kosuke Sekiyama, Zhiguo Lu, Yasuhisa Hasegawa, Toshio Fukuda
2012	A	`conf`	Optimal control of energetically efficient ladder decent motion with internal stress adjustment using key joint method. IROS Zhiguo Lu, Kosuke Sekiyama, Tadayoshi Aoyama, Yasuhisa Hasegawa, Taisuke Kobayashi, Toshio Fukuda
2012	—	`conf`	Stability enhancement of 3-D biped walking based on Passive Dynamic Autonomous Control. Humanoids Tadayoshi Aoyama, Kosuke Sekiyama, Zhiguo Lu, Taisuke Kobayashi, Yasuhisa Hasegawa, Toshio Fukuda
2012	—	`conf`	Stabilization and moving efficiency improvement by adjustment of moving speed in single locomotion. MHS Taisuke Kobayashi, Tadayoshi Aoyama, Kosuke Sekiyama, Toshio Fukuda
1994	J	`jnl`	Computer Graphics System for Reproducing Three-dimensional Shape from Idea Sketch. Comput. Graph. Forum Makoto Akeo, Hiroshi Hashimoto, Taisuke Kobayashi, Tetsuo Shibusawa