Hokyun Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hokyun Lee has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Jaeheung Park
Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea
5 shared publications - Donghyeon Kim
Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Suwon-si, Republic of Korea
2 shared publications - Junewhee Ahn
Graduate School of Convergence Science and Technology, Seoul National University (SNU), Seoul, Korea
2 shared publications - Junhyeok Cha
Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Suwon-si, Republic of Korea
2 shared publications - Junhyung Kim
Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Republic of Korea
2 shared publications - Beomyeong Park
Florida Institute for Human and Machine Cognition (IHMC), Pensacola, USA
1 shared publication
Latest Publications
- 4 November 2025
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 23 (11) , 3338-3348
Real-time Whole-body Model Predictive Control for Bipedal Locomotion With Novel Kino-dynamic Model and Warm-start Method
- 4 November 2025
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 23 (11) , 3338-3348
Real-time Whole-body Model Predictive Control for Bipedal Locomotion With Novel Kino-dynamic Model and Warm-start Method
- 9 September 2025
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 23 (9) , 2656-2665
Efficient Computation of Whole-body Control Utilizing Simplified Whole-body Dynamics via Centroidal Dynamics
- 9 September 2025
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 23 (9) , 2656-2665
Efficient Computation of Whole-body Control Utilizing Simplified Whole-body Dynamics via Centroidal Dynamics
- Open Access
- 25 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 2286-2297
Time-Efficient Contact Consistent Whole-Body Control Framework via Reduced-Dimension Dynamics Construction
Whole-body control frameworks for highly redundant, floating-base robots like humanoids are challenging due to the increased computational complexity arising from their high degrees of freedom. In this paper, the concept of reduced-dimension dynamics previously applied to whole-body control frameworks is extended by integrating it into the operational space formulation. The reduced-dimension dynamics simplifies the dimension of the dynamic model of humanoid robots by partitioning the kinematic chain into constrained and unconstrained chains. The unconstrained chain is reduced using centroidal dynamics, enabling efficient computational modeling in the operational space. By applying the reduced-dimension dynamics to operational space whole-body control, the computational burden caused by the high degrees of freedom in the whole-body dynamics is reduced, leading to shorter computation times. Unlike existing methods that utilize full-dimensional whole-body dynamics, the proposed method constructs a more efficient framework by performing optimization on reduced-dimensional dynamics, combined with operational space formulation. Comparative simulation results demonstrate a significant reduction in computation time, specifically a 41% decrease compared to existing methods, which provides a new approach to contact-consistent control in humanoid robots.
- 25 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 2286-2297
Open AccessTime-Efficient Contact Consistent Whole-Body Control Framework via Reduced-Dimension Dynamics Construction
Whole-body control frameworks for highly redundant, floating-base robots like humanoids are challenging due to the increased computational complexity arising from their high degrees of freedom. In this paper, the concept of reduced-dimension dynamics previously applied to whole-body control frameworks is extended by integrating it into the operational space formulation. The reduced-dimension dynamics simplifies the dimension of the dynamic model of humanoid robots by partitioning the kinematic chain into constrained and unconstrained chains. The unconstrained chain is reduced using centroidal dynamics, enabling efficient computational modeling in the operational space. By applying the reduced-dimension dynamics to operational space whole-body control, the computational burden caused by the high degrees of freedom in the whole-body dynamics is reduced, leading to shorter computation times. Unlike existing methods that utilize full-dimensional whole-body dynamics, the proposed method constructs a more efficient framework by performing optimization on reduced-dimensional dynamics, combined with operational space formulation. Comparative simulation results demonstrate a significant reduction in computation time, specifically a 41% decrease compared to existing methods, which provides a new approach to contact-consistent control in humanoid robots.
- 12 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 32 (1) , 49-58
Bridging the Reality Gap: Analyzing Sim-to-Real Transfer Techniques for Reinforcement Learning in Humanoid Bipedal Locomotion
Reinforcement learning (RL) offers a promising solution for controlling humanoid robots, particularly for bipedal locomotion, by learning adaptive and flexible control strategies. However, direct RL application is hindered by time-consuming trial-and-error processes, necessitating training in simulation before real-world transfer. This introduces a reality gap that degrades performance. Although various methods have been proposed for sim-to-real transfer, they have not been validated on a consistent hardware platform making it difficult to determine which components are key to overcoming the reality gap. In contrast, we systematically evaluate techniques to enhance RL policy robustness during sim-to-real transfer by controlling variables and comparing them on a single robot to isolate and analyze the impact of each technique. These techniques include dynamics randomization, state history usage, noise/bias/delay modeling, state selection, perturbations, and network size.We quantitatively assess the reality gap by simulating diverse conditions and conducting experiments on real hardware. Our findings provide insights into bridging the reality gap, advancing robust RL-trained humanoid robots for real-world applications.
- 12 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 32 (1) , 49-58
Bridging the Reality Gap: Analyzing Sim-to-Real Transfer Techniques for Reinforcement Learning in Humanoid Bipedal Locomotion
Reinforcement learning (RL) offers a promising solution for controlling humanoid robots, particularly for bipedal locomotion, by learning adaptive and flexible control strategies. However, direct RL application is hindered by time-consuming trial-and-error processes, necessitating training in simulation before real-world transfer. This introduces a reality gap that degrades performance. Although various methods have been proposed for sim-to-real transfer, they have not been validated on a consistent hardware platform making it difficult to determine which components are key to overcoming the reality gap. In contrast, we systematically evaluate techniques to enhance RL policy robustness during sim-to-real transfer by controlling variables and comparing them on a single robot to isolate and analyze the impact of each technique. These techniques include dynamics randomization, state history usage, noise/bias/delay modeling, state selection, perturbations, and network size.We quantitatively assess the reality gap by simulating diverse conditions and conducting experiments on real hardware. Our findings provide insights into bridging the reality gap, advancing robust RL-trained humanoid robots for real-world applications.
- Open Access
- 28 June 2024
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 17 (3) , 379-407
Intuitive and Interactive Robotic Avatar System for Tele-Existence: TEAM SNU in the ANA Avatar XPRIZE Finals
Avatar robots enable the teleoperation and telepresence of an operator with a rich and meaningful sense of existence in another location. Robotic avatar systems rely on intuitive interactions to afford operators comfortable and accurate robot control to perform various tasks. The ability of operators to feel immersed within a robot has drawn interest in multiple research fields to explore the future capabilities of such systems. This paper presents a robotic avatar system based on a custom humanoid robot, TOCABI, with a mobile base. Its teleoperation system was developed in response to the ANA Avatar XPRIZE. Combining the life-size humanoid robot and the mobile base allows for improved mobility and dexterous manipulation. The robotic avatar system comprises the robot/base and an operator station that incorporates haptic feedback devices, trackers, a head-mounted display, gloves, and pedals. These devices connect the robot-environment interaction and operator-avatar robot experience through visual, auditory, tactile, haptic, and kinesthetic feedback. Combining the untethered battery-operated and Wi-Fi-enabled robot with these sensory experiences enables intuitive control through the operator’s body movement. The performance of the robotic avatar system was evaluated through user studies and demonstrated in the ANA Avatar XPRIZE Finals, represented by Team SNU, where it completed 8 of the 10 missions, placing the team eighth among the 17 finalists.
- 28 June 2024
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 17 (3) , 379-407
Open AccessIntuitive and Interactive Robotic Avatar System for Tele-Existence: TEAM SNU in the ANA Avatar XPRIZE Finals
Avatar robots enable the teleoperation and telepresence of an operator with a rich and meaningful sense of existence in another location. Robotic avatar systems rely on intuitive interactions to afford operators comfortable and accurate robot control to perform various tasks. The ability of operators to feel immersed within a robot has drawn interest in multiple research fields to explore the future capabilities of such systems. This paper presents a robotic avatar system based on a custom humanoid robot, TOCABI, with a mobile base. Its teleoperation system was developed in response to the ANA Avatar XPRIZE. Combining the life-size humanoid robot and the mobile base allows for improved mobility and dexterous manipulation. The robotic avatar system comprises the robot/base and an operator station that incorporates haptic feedback devices, trackers, a head-mounted display, gloves, and pedals. These devices connect the robot-environment interaction and operator-avatar robot experience through visual, auditory, tactile, haptic, and kinesthetic feedback. Combining the untethered battery-operated and Wi-Fi-enabled robot with these sensory experiences enables intuitive control through the operator’s body movement. The performance of the robotic avatar system was evaluated through user studies and demonstrated in the ANA Avatar XPRIZE Finals, represented by Team SNU, where it completed 8 of the 10 missions, placing the team eighth among the 17 finalists.