Seungwoo Hong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Seungwoo Hong has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Hae-Won Park
Korea Advanced Institute of Science and Technology
6 shared publications - Joon-Ha Kim
Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea
3 shared publications Sangbae Kim
Massachusetts Institute of Technology
3 shared publications- Charles Khazoom
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
2 shared publications - Donghee Han
Research & Development Division, Hyundai Motor Company, Hwaseong 18280, Korea
2 shared publications - Donghyuk Jung
Department of Automotive Engineering, Hanyang University, Seoul 04763, Korea
2 shared publications
Latest Publications
- 15 July 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 11 (116) , eadz7397
Agile perceptive multiskill locomotion for quadrupedal robots in the wild.
Enabling quadrupedal robots to traverse complex terrains, from rugged outdoor environments to urban landscapes, requires seamless integration of multiple motor skills, smooth transitions between gaits, and high-speed perceptive locomotion using only onboard sensors. We present APT-RL (action pretrained transformer-based reinforcement learning), a unified framework that enables multiskill locomotion to achieve high-speed traversal in complex environments through autonomous skill transitions using only onboard perception and computation. Our approach generates large-scale, feature-rich two-dimensional (2D) motion datasets through trajectory optimization with simplified dynamics. These datasets enable training of diverse, reusable locomotion skills that transfer effectively to a real quadruped robot operating on complex uneven terrains. The resulting high-quality skills serve as strong priors for efficient learning of complex downstream tasks and extend naturally to 3D environments, enabling smooth, high-speed multiskill locomotion in deployed policy. Real-world experiments demonstrate the framework's capabilities: The robot performed agile maneuvers through complex indoor obstacles and outdoor wild environments, including dynamic drop-down maneuvers that reached instantaneous peak speeds of up to 6 meters per second. A single onboard policy enabled robust traversal of diverse obstacles, including stairs, hurdles, stepping stones, gaps, and fallen branches, demonstrating the versatility and effectiveness of our approach.
- 15 July 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 11 (116) , eadz7397
Agile perceptive multiskill locomotion for quadrupedal robots in the wild.
Enabling quadrupedal robots to traverse complex terrains, from rugged outdoor environments to urban landscapes, requires seamless integration of multiple motor skills, smooth transitions between gaits, and high-speed perceptive locomotion using only onboard sensors. We present APT-RL (action pretrained transformer-based reinforcement learning), a unified framework that enables multiskill locomotion to achieve high-speed traversal in complex environments through autonomous skill transitions using only onboard perception and computation. Our approach generates large-scale, feature-rich two-dimensional (2D) motion datasets through trajectory optimization with simplified dynamics. These datasets enable training of diverse, reusable locomotion skills that transfer effectively to a real quadruped robot operating on complex uneven terrains. The resulting high-quality skills serve as strong priors for efficient learning of complex downstream tasks and extend naturally to 3D environments, enabling smooth, high-speed multiskill locomotion in deployed policy. Real-world experiments demonstrate the framework's capabilities: The robot performed agile maneuvers through complex indoor obstacles and outdoor wild environments, including dynamic drop-down maneuvers that reached instantaneous peak speeds of up to 6 meters per second. A single onboard policy enabled robust traversal of diverse obstacles, including stairs, hurdles, stepping stones, gaps, and fallen branches, demonstrating the versatility and effectiveness of our approach.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42, 3469-3488
Residual MPC: Blending Reinforcement Learning With GPU-Parallelized Model Predictive Control
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42, 3469-3488
Residual MPC: Blending Reinforcement Learning With GPU-Parallelized Model Predictive Control
- 25 June 2025
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 45 (2) , 285-307
Design of LIGHTDOG: A high payload-to-weight, hose-less hydraulic quadrupedal robot
This paper presents LIGHTDOG, a torque-controlled, hydraulically-actuated quadrupedal robot designed for a high power-to-weight ratio and substantial payload capabilities. Hydraulic systems present complexity, weight, and thermal management challenges, which are addressed by embedding all the oil channels inside the robot, inspired by biological vascular structures. This embedding is facilitated by a distinctive robot body design featuring integrated oil channels and the inclusion of a double-vane rotary actuator design, allowing for the internalization of oil channels within the joints. These oil channels not only contribute to the robot’s compactness and lightness, but also allow heat spread throughout the body to dissipate through the robot’s frame, managing heat during robot motion without the need for external radiators. The rotary actuator is equipped with a structure designed to reduce internal leakage and friction torque, which can reduce energy losses in the hydraulic system. Optimization methods were applied to the slider-crank mechanism and hydraulic actuator sizing to reduce lateral and axial forces, as well as the energy consumed by the hydraulic actuators. Our work has validated the feasibility and payload capacity of LIGHTDOG through several experiments. LIGHTDOG, weighing 45 kg, demonstrates a payload capacity of 130 kg during a squatting motion, significantly exceeding its own weight.
- 25 June 2025
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 45 (2) , 285-307
Design of LIGHTDOG: A high payload-to-weight, hose-less hydraulic quadrupedal robot
This paper presents LIGHTDOG, a torque-controlled, hydraulically-actuated quadrupedal robot designed for a high power-to-weight ratio and substantial payload capabilities. Hydraulic systems present complexity, weight, and thermal management challenges, which are addressed by embedding all the oil channels inside the robot, inspired by biological vascular structures. This embedding is facilitated by a distinctive robot body design featuring integrated oil channels and the inclusion of a double-vane rotary actuator design, allowing for the internalization of oil channels within the joints. These oil channels not only contribute to the robot’s compactness and lightness, but also allow heat spread throughout the body to dissipate through the robot’s frame, managing heat during robot motion without the need for external radiators. The rotary actuator is equipped with a structure designed to reduce internal leakage and friction torque, which can reduce energy losses in the hydraulic system. Optimization methods were applied to the slider-crank mechanism and hydraulic actuator sizing to reduce lateral and axial forces, as well as the energy consumed by the hydraulic actuators. Our work has validated the feasibility and payload capacity of LIGHTDOG through several experiments. LIGHTDOG, weighing 45 kg, demonstrates a payload capacity of 130 kg during a squatting motion, significantly exceeding its own weight.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (2) , 899-906
CusADi: A GPU Parallelization Framework for Symbolic Expressions and Optimal Control
The parallelism afforded by GPUs presents significant advantages in training controllers through reinforcement learning (RL). However, integrating model-based optimization into this process remains challenging due to the complexity of formulating and solving optimization problems across thousands of instances. In this work, we present CusADi , an extension of the casadi symbolic framework to support the parallelization of arbitrary closed-form expressions on GPUs with CUDA . We also formulate a closed-form approximation for solving general optimal control problems, enabling large-scale parallelization and evaluation of MPC controllers. Our results show a ten-fold speedup relative to similar MPC implementation on the CPU, and we demonstrate the use of CusADi for various applications, including parallel simulation, parameter sweeps, and policy training.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (2) , 899-906
CusADi: A GPU Parallelization Framework for Symbolic Expressions and Optimal Control
The parallelism afforded by GPUs presents significant advantages in training controllers through reinforcement learning (RL). However, integrating model-based optimization into this process remains challenging due to the complexity of formulating and solving optimization problems across thousands of instances. In this work, we present CusADi , an extension of the casadi symbolic framework to support the parallelization of arbitrary closed-form expressions on GPUs with CUDA . We also formulate a closed-form approximation for solving general optimal control problems, enabling large-scale parallelization and evaluation of MPC controllers. Our results show a ten-fold speedup relative to similar MPC implementation on the CPU, and we demonstrate the use of CusADi for various applications, including parallel simulation, parameter sweeps, and policy training.
- 1 October 2024
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 44 (3) , 486-510
Contact-implicit Model Predictive Control: Controlling diverse quadruped motions without pre-planned contact modes or trajectories
This paper presents a contact-implicit model predictive control (MPC) framework for the real-time discovery of multi-contact motions, without predefined contact mode sequences or foothold positions. This approach utilizes the contact-implicit differential dynamic programming (DDP) framework, merging the hard contact model with a linear complementarity constraint. We propose the analytical gradient of the contact impulse based on relaxed complementarity constraints to further the exploration of a variety of contact modes. By leveraging a hard contact model-based simulation and computation of search direction through a smooth gradient, our methodology identifies dynamically feasible state trajectories, control inputs, and contact forces while simultaneously unveiling new contact mode sequences. However, the broadened scope of contact modes does not always ensure real-world applicability. Recognizing this, we implemented differentiable cost terms to guide foot trajectories and make gait patterns. Furthermore, to address the challenge of unstable initial roll-outs in an MPC setting, we employ the multiple shooting variant of DDP. The efficacy of the proposed framework is validated through simulations and real-world demonstrations using a 45 kg HOUND quadruped robot, performing various tasks in simulation and showcasing actual experiments involving a forward trot and a front-leg rearing motion.
- 1 October 2024
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 44 (3) , 486-510
Contact-implicit Model Predictive Control: Controlling diverse quadruped motions without pre-planned contact modes or trajectories
This paper presents a contact-implicit model predictive control (MPC) framework for the real-time discovery of multi-contact motions, without predefined contact mode sequences or foothold positions. This approach utilizes the contact-implicit differential dynamic programming (DDP) framework, merging the hard contact model with a linear complementarity constraint. We propose the analytical gradient of the contact impulse based on relaxed complementarity constraints to further the exploration of a variety of contact modes. By leveraging a hard contact model-based simulation and computation of search direction through a smooth gradient, our methodology identifies dynamically feasible state trajectories, control inputs, and contact forces while simultaneously unveiling new contact mode sequences. However, the broadened scope of contact modes does not always ensure real-world applicability. Recognizing this, we implemented differentiable cost terms to guide foot trajectories and make gait patterns. Furthermore, to address the challenge of unstable initial roll-outs in an MPC setting, we employ the multiple shooting variant of DDP. The efficacy of the proposed framework is validated through simulations and real-world demonstrations using a 45 kg HOUND quadruped robot, performing various tasks in simulation and showcasing actual experiments involving a forward trot and a front-leg rearing motion.
- Top Cited Papers
- 9 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (12) , 11074-11081
Tailoring Solution Accuracy for Fast Whole-Body Model Predictive Control of Legged Robots
Identifying the physical properties of the surrounding environment is essential for robotic locomotion and navigation to deal with non-geometric hazards, such as slippery and deformable terrains. It would be of great benefit for robots to anticipate these extreme physical properties before contact; however, estimating environmental physical parameters from vision is still an open challenge. Animals can achieve this by using their prior experience and knowledge of what they have seen and how it felt. In this work, we propose a cross-modal selfsupervised learning framework for vision-based environmental physical parameter estimation, which paves the way for future physical-property-aware locomotion and navigation. We bridge the gap between existing policies trained in simulation and identification of physical terrain parameters from vision. We propose to train a physical decoder in simulation to predict friction and stiffness from multi-modal input. The trained network allows the labeling of real-world images with physical parameters in a self-supervised manner to further train a visual network during deployment, which can densely predict the friction and stiffness from image data. We validate our physical decoder in simulation and the real world using a quadruped ANYmal robot, outperforming an existing baseline method. We show that our visual network can predict the physical properties in indoor and outdoor experiments while allowing fast adaptation to new environments
- 9 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (12) , 11074-11081
Top Cited PapersTailoring Solution Accuracy for Fast Whole-Body Model Predictive Control of Legged Robots
Identifying the physical properties of the surrounding environment is essential for robotic locomotion and navigation to deal with non-geometric hazards, such as slippery and deformable terrains. It would be of great benefit for robots to anticipate these extreme physical properties before contact; however, estimating environmental physical parameters from vision is still an open challenge. Animals can achieve this by using their prior experience and knowledge of what they have seen and how it felt. In this work, we propose a cross-modal selfsupervised learning framework for vision-based environmental physical parameter estimation, which paves the way for future physical-property-aware locomotion and navigation. We bridge the gap between existing policies trained in simulation and identification of physical terrain parameters from vision. We propose to train a physical decoder in simulation to predict friction and stiffness from multi-modal input. The trained network allows the labeling of real-world images with physical parameters in a self-supervised manner to further train a visual network during deployment, which can densely predict the friction and stiffness from image data. We validate our physical decoder in simulation and the real world using a quadruped ANYmal robot, outperforming an existing baseline method. We show that our visual network can predict the physical properties in indoor and outdoor experiments while allowing fast adaptation to new environments
- 30 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (8) , 5031-5038
Seamless Reaction Strategy for Bipedal Locomotion Exploiting Real-Time Nonlinear Model Predictive Control
This letter presents a reactive locomotion method for bipedal robots enhancing robustness and external disturbance rejection performance by seamlessly rendering several walking strategies of the ankle, hip, and footstep adjustment. The Nonlinear Model Predictive Control (NMPC) is formulated to take into account nonlinear Divergent Component of Motion (DCM) error dynamics that predicts the future states of the robot in response to the walking strategies. This formulated NMPC enables the seamless application of these strategies improving push disturbance rejection performance. The proposed controller is validated in simulation and through an experiment on a bipedal robot platform, Gazelle, which confirms its effectiveness in real-time.
- 30 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (8) , 5031-5038
Seamless Reaction Strategy for Bipedal Locomotion Exploiting Real-Time Nonlinear Model Predictive Control
This letter presents a reactive locomotion method for bipedal robots enhancing robustness and external disturbance rejection performance by seamlessly rendering several walking strategies of the ankle, hip, and footstep adjustment. The Nonlinear Model Predictive Control (NMPC) is formulated to take into account nonlinear Divergent Component of Motion (DCM) error dynamics that predicts the future states of the robot in response to the walking strategies. This formulated NMPC enables the seamless application of these strategies improving push disturbance rejection performance. The proposed controller is validated in simulation and through an experiment on a bipedal robot platform, Gazelle, which confirms its effectiveness in real-time.
- Top Cited Papers
- 21 December 2022
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 7 (73) , eadd1017
Agile and versatile climbing on ferromagnetic surfaces with a quadrupedal robot
A climbing robot that can rapidly move on diverse surfaces such as floors, walls, and ceilings will have an enlarged operational workspace compared with other terrestrial robots. However, the climbing skill of robots in such environments has been limited to low speeds or simple locomotion tasks. Here, we present an untethered quadrupedal climbing robot called MARVEL (magnetically adhesive robot for versatile and expeditious locomotion), capable of agile and versatile climbing locomotion in ferromagnetic environments. MARVEL excels over prior climbing robots in terms of climbing speed and ability to execute various motions. It demonstrates the fastest vertical and inverted walking speed, whereas its versatile locomotion ability enables the highest number of gaits and locomotion tasks. The key innovations are an integrated foot design using electropermanent magnets and magnetorheological elastomers that provide large adhesion and traction forces, torque control actuators, and a model predictive control framework adapted for stable climbing. In experiments, the robot achieved locomotion on ceilings and vertical walls up to 0.5 meter (1.51 body lengths) per second and 0.7 meter (2.12 body lengths) per second, respectively. Furthermore, the robot exhibited complex behaviors such as stepping over 10-centimeter-wide gaps; overcoming 5-centimeter-high obstacles; and making transitions between floors, walls, and ceilings. We also show that MARVEL could climb on a curved surface of a storage tank covered with up to 0.3-millimeter-thick paint with rust and dust.
- 21 December 2022
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 7 (73) , eadd1017
Top Cited PapersAgile and versatile climbing on ferromagnetic surfaces with a quadrupedal robot
A climbing robot that can rapidly move on diverse surfaces such as floors, walls, and ceilings will have an enlarged operational workspace compared with other terrestrial robots. However, the climbing skill of robots in such environments has been limited to low speeds or simple locomotion tasks. Here, we present an untethered quadrupedal climbing robot called MARVEL (magnetically adhesive robot for versatile and expeditious locomotion), capable of agile and versatile climbing locomotion in ferromagnetic environments. MARVEL excels over prior climbing robots in terms of climbing speed and ability to execute various motions. It demonstrates the fastest vertical and inverted walking speed, whereas its versatile locomotion ability enables the highest number of gaits and locomotion tasks. The key innovations are an integrated foot design using electropermanent magnets and magnetorheological elastomers that provide large adhesion and traction forces, torque control actuators, and a model predictive control framework adapted for stable climbing. In experiments, the robot achieved locomotion on ceilings and vertical walls up to 0.5 meter (1.51 body lengths) per second and 0.7 meter (2.12 body lengths) per second, respectively. Furthermore, the robot exhibited complex behaviors such as stepping over 10-centimeter-wide gaps; overcoming 5-centimeter-high obstacles; and making transitions between floors, walls, and ceilings. We also show that MARVEL could climb on a curved surface of a storage tank covered with up to 0.3-millimeter-thick paint with rust and dust.
- 30 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (4) , 6733-6740
Legged Robot State Estimation With Dynamic Contact Event Information
This letter presents a state estimation algorithm for the legged robot by defining the problem as a Maximum A Posteriori (MAP) estimation problem and solving the problem with the Gauss-Newton algorithm. Moreover, marginalization by the Schur Complement method is adopted to make a fixed size problem. Each component of the cost function and its Jacobian are derived utilizing the SO(3) manifold structure, while we reparameterize the state with nominal state and variation to make linear algebra and vector calculus applied properly. Furthermore, a slip rejection method is proposed to reduce the erroneous effect of fault modeling of kinematics models. The proposed algorithm is verified by comparison with the Invariant Extended Kalman Filter (IEKF) in real robot experiments on various environments.
- 30 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (4) , 6733-6740
Legged Robot State Estimation With Dynamic Contact Event Information
This letter presents a state estimation algorithm for the legged robot by defining the problem as a Maximum A Posteriori (MAP) estimation problem and solving the problem with the Gauss-Newton algorithm. Moreover, marginalization by the Schur Complement method is adopted to make a fixed size problem. Each component of the cost function and its Jacobian are derived utilizing the SO(3) manifold structure, while we reparameterize the state with nominal state and variation to make linear algebra and vector calculus applied properly. Furthermore, a slip rejection method is proposed to reduce the erroneous effect of fault modeling of kinematics models. The proposed algorithm is verified by comparison with the Invariant Extended Kalman Filter (IEKF) in real robot experiments on various environments.
- Open Access
Minimization of Torque Deviation of Cylinder Deactivation Engine through 48V Mild-Hybrid Starter-Generator Control
Cylinder deactivation (CDA) is an effective technique to improve fuel economy in spark ignition (SI) engines. This technique enhances volumetric efficiency and reduces throttling loss. However, practical implementation is restricted due to torque fluctuations between individual cylinders that cause noise, vibration, and harshness (NVH) issues. To ease torque deviation of the CDA, we propose an in-cylinder pressure based 48V mild-hybrid starter-generator (MHSG) control strategy. The target engine realizes CDA with a specialized engine configuration of separated intake manifolds to independently control the airflow into the cylinders. To handle the complexity of the combined CDA and mild-hybrid system, GT-POWER simulation environment was integrated with a SI turbulent combustion model and 48V MHSG model with actual part specifications. The combustion model is essential for in-cylinder pressure-based control; thus, it is calibrated with actual engine experimental data. The modeling results demonstrate the precise accuracy of the engine cylinder pressures and of quantities such as MAF, MAP, BMEP, and IMEP. The proposed control algorithm also showed remarkable control performance, achieved by instantaneous torque calculation and dynamic compensation, with a 99% maximum reduction rate of engine torque deviation under target CDA operations.
Open AccessMinimization of Torque Deviation of Cylinder Deactivation Engine through 48V Mild-Hybrid Starter-Generator Control
Cylinder deactivation (CDA) is an effective technique to improve fuel economy in spark ignition (SI) engines. This technique enhances volumetric efficiency and reduces throttling loss. However, practical implementation is restricted due to torque fluctuations between individual cylinders that cause noise, vibration, and harshness (NVH) issues. To ease torque deviation of the CDA, we propose an in-cylinder pressure based 48V mild-hybrid starter-generator (MHSG) control strategy. The target engine realizes CDA with a specialized engine configuration of separated intake manifolds to independently control the airflow into the cylinders. To handle the complexity of the combined CDA and mild-hybrid system, GT-POWER simulation environment was integrated with a SI turbulent combustion model and 48V MHSG model with actual part specifications. The combustion model is essential for in-cylinder pressure-based control; thus, it is calibrated with actual engine experimental data. The modeling results demonstrate the precise accuracy of the engine cylinder pressures and of quantities such as MAF, MAP, BMEP, and IMEP. The proposed control algorithm also showed remarkable control performance, achieved by instantaneous torque calculation and dynamic compensation, with a 99% maximum reduction rate of engine torque deviation under target CDA operations.