Jeong Hyun Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jeong Hyun Lee has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Jemin Hwangbo
KAIST
7 shared publications - Donghoon Youm
Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea
4 shared publications - Hyunsik Oh
Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea
4 shared publications - Gwanghyeon Ji
Robotics and Artificial Intelligence Laboratory, KAIST, Daejeon, Korea
3 shared publications - Hyeongjun Kim
Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea
3 shared publications - Juhyeok Mun
Robotics and Artificial Intelligence Lab, KAIST, Daejeon, South Korea
3 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14740-14747
PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14740-14747
PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation
- 23 September 2026
- Published by Springer Nature in Nature
- Vol. 658 (8135) , 372-379
A quadruped robot designed to complete a marathon on a single battery charge
Recent advances in legged robot control have expanded the potential for quadruped robots in real-world applications, such as rescue operations in disaster zones and mountainous regions1. However, practical deployment is hindered by the limited travel range per battery charge: a challenge compounded by the robots’ inherent structural characteristics. Unlike wheeled robots, quadrupeds continuously expend energy at their joints to support body weight and incur kinetic energy losses during intermittent foot–ground contact. Moreover, optimizing energy consumption is complicated by trade-offs among various physical effects2, necessitating a holistic approach encompassing both hardware and software components. Previous research has predominantly addressed isolated aspects of energy loss3,4,5,6. Here we show RAIBO2, an energy-efficient quadruped developed through a comprehensive analysis of its overall energy-loss model. Efficiency is enhanced through a force-transparent, lightweight mechanical hardware, a low-resistance motor driving circuit and a low-energy-dissipation locomotion policy. RAIBO2 completed a full marathon in 4 hours, 19 minutes and 52 seconds on a single battery charge7, achieving a total cost of transport of 0.25: surpassing the human benchmark of 0.37. Compared with existing quadrupeds, RAIBO2 offers more than three times the travel range per battery charge. This breakthrough in energy efficiency paves the way for extended outdoor applications in which prolonged battery life is critical.
- 23 September 2026
- Published by Springer Nature in Nature
- Vol. 658 (8135) , 372-379
A quadruped robot designed to complete a marathon on a single battery charge
Recent advances in legged robot control have expanded the potential for quadruped robots in real-world applications, such as rescue operations in disaster zones and mountainous regions1. However, practical deployment is hindered by the limited travel range per battery charge: a challenge compounded by the robots’ inherent structural characteristics. Unlike wheeled robots, quadrupeds continuously expend energy at their joints to support body weight and incur kinetic energy losses during intermittent foot–ground contact. Moreover, optimizing energy consumption is complicated by trade-offs among various physical effects2, necessitating a holistic approach encompassing both hardware and software components. Previous research has predominantly addressed isolated aspects of energy loss3,4,5,6. Here we show RAIBO2, an energy-efficient quadruped developed through a comprehensive analysis of its overall energy-loss model. Efficiency is enhanced through a force-transparent, lightweight mechanical hardware, a low-resistance motor driving circuit and a low-energy-dissipation locomotion policy. RAIBO2 completed a full marathon in 4 hours, 19 minutes and 52 seconds on a single battery charge7, achieving a total cost of transport of 0.25: surpassing the human benchmark of 0.37. Compared with existing quadrupeds, RAIBO2 offers more than three times the travel range per battery charge. This breakthrough in energy efficiency paves the way for extended outdoor applications in which prolonged battery life is critical.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12421-12428
Learning Quadrupedal Locomotion for a Heavy Hydraulic Robot Using an Actuator Model
The simulation-to-reality (sim-to-real) transfer of large-scale hydraulic robots presents a significant challenge in robotics because of the inherent slow control response and complex fluid dynamics. The complex dynamics result from the multiple interconnected cylinder structure and the difference in fluid rates of the cylinders. These characteristics complicate detailed simulation for all joints, making it unsuitable for reinforcement learning (RL) applications. In this work, we propose an analytical actuator model driven by hydraulic dynamics to represent the complicated actuators. The model predicts joint torques for all 12 actuators in under 1 $\mu$s, allowing rapid processing in RL environments. We compare our model with neural network-based actuator models and demonstrate the advantages of our model in data-limited scenarios. The locomotion policy trained in RL with our model is deployed on a hydraulic quadruped robot, BeTheX-Q, which is over 300 kg. This work is the first demonstration of a successful transfer of stable and robust command-tracking locomotion with RL on a heavy hydraulic quadruped robot, demonstrating advanced sim-to-real transferability.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12421-12428
Learning Quadrupedal Locomotion for a Heavy Hydraulic Robot Using an Actuator Model
The simulation-to-reality (sim-to-real) transfer of large-scale hydraulic robots presents a significant challenge in robotics because of the inherent slow control response and complex fluid dynamics. The complex dynamics result from the multiple interconnected cylinder structure and the difference in fluid rates of the cylinders. These characteristics complicate detailed simulation for all joints, making it unsuitable for reinforcement learning (RL) applications. In this work, we propose an analytical actuator model driven by hydraulic dynamics to represent the complicated actuators. The model predicts joint torques for all 12 actuators in under 1 $\mu$s, allowing rapid processing in RL environments. We compare our model with neural network-based actuator models and demonstrate the advantages of our model in data-limited scenarios. The locomotion policy trained in RL with our model is deployed on a hydraulic quadruped robot, BeTheX-Q, which is over 300 kg. This work is the first demonstration of a successful transfer of stable and robust command-tracking locomotion with RL on a heavy hydraulic quadruped robot, demonstrating advanced sim-to-real transferability.
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (11) , 10423-10430
Learning Semantic Traversability With Egocentric Video and Automated Annotation Strategy
For reliable autonomous robot navigation in urban settings, the robot must have the ability to identify semantically traversable terrains in the image based on the semantic understanding of the scene. This reasoning ability is based on semantic traversability, which is frequently achieved using semantic segmentation models fine-tuned on the testing domain. This fine-tuning process often involves manual data collection with the target robot and annotation by human labelers which is prohibitively expensive and unscalable. In this work, we present an effective methodology for training a semantic traversability estimator using egocentric videos and an automated annotation process. Egocentric videos are collected from a camera mounted on a pedestrian's chest. The dataset for training the semantic traversability estimator is then automatically generated by extracting semantically traversable regions in each video frame using a recent foundation model in image segmentation and its prompting technique. Extensive experiments with videos taken across several countries and cities, covering diverse urban scenarios, demonstrate the high scalability and generalizability of the proposed annotation method. Furthermore, performance analysis and real-world deployment for autonomous robot navigation showcase that the trained semantic traversability estimator is highly accurate, able to handle diverse camera viewpoints, computationally light, and real-world applicable.
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (11) , 10423-10430
Learning Semantic Traversability With Egocentric Video and Automated Annotation Strategy
For reliable autonomous robot navigation in urban settings, the robot must have the ability to identify semantically traversable terrains in the image based on the semantic understanding of the scene. This reasoning ability is based on semantic traversability, which is frequently achieved using semantic segmentation models fine-tuned on the testing domain. This fine-tuning process often involves manual data collection with the target robot and annotation by human labelers which is prohibitively expensive and unscalable. In this work, we present an effective methodology for training a semantic traversability estimator using egocentric videos and an automated annotation process. Egocentric videos are collected from a camera mounted on a pedestrian's chest. The dataset for training the semantic traversability estimator is then automatically generated by extracting semantically traversable regions in each video frame using a recent foundation model in image segmentation and its prompting technique. Extensive experiments with videos taken across several countries and cities, covering diverse urban scenarios, demonstrate the high scalability and generalizability of the proposed annotation method. Furthermore, performance analysis and real-world deployment for autonomous robot navigation showcase that the trained semantic traversability estimator is highly accurate, able to handle diverse camera viewpoints, computationally light, and real-world applicable.
- Top Cited Papers
- 14 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 40 (15523098) , 2984-3003
Not Only Rewards but Also Constraints: Applications on Legged Robot Locomotion
Several earlier studies have shown impressive control performance in complex robotic systems by designing the controller using a neural network and training it with model-free reinforcement learning. However, these outstanding controllers with natural motion style and high task performance are developed through extensive reward engineering, which is a highly laborious and time-consuming process of designing numerous reward terms and determining suitable reward coefficients. In this work, we propose a novel reinforcement learning framework for training neural network controllers for complex robotic systems consisting of both rewards and constraints . To let the engineers appropriately reflect their intent to constraints and handle them with minimal computation overhead, two constraint types and an efficient policy optimization algorithm are suggested. The learning framework is applied to train locomotion controllers for several legged robots with different morphology and physical attributes to traverse challenging terrains. Extensive simulation and real-world experiments demonstrate that performant controllers can be trained with significantly less reward engineering, by tuning only a single reward coefficient. Furthermore, a more straightforward and intuitive engineering process can be utilized, thanks to the interpretability and generalizability of constraints. The summary video is available at https://youtu.be/KAlm3yskhvM .
- 14 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 40 (15523098) , 2984-3003
Top Cited PapersNot Only Rewards but Also Constraints: Applications on Legged Robot Locomotion
Several earlier studies have shown impressive control performance in complex robotic systems by designing the controller using a neural network and training it with model-free reinforcement learning. However, these outstanding controllers with natural motion style and high task performance are developed through extensive reward engineering, which is a highly laborious and time-consuming process of designing numerous reward terms and determining suitable reward coefficients. In this work, we propose a novel reinforcement learning framework for training neural network controllers for complex robotic systems consisting of both rewards and constraints . To let the engineers appropriately reflect their intent to constraints and handle them with minimal computation overhead, two constraint types and an efficient policy optimization algorithm are suggested. The learning framework is applied to train locomotion controllers for several legged robots with different morphology and physical attributes to traverse challenging terrains. Extensive simulation and real-world experiments demonstrate that performant controllers can be trained with significantly less reward engineering, by tuning only a single reward coefficient. Furthermore, a more straightforward and intuitive engineering process can be utilized, thanks to the interpretability and generalizability of constraints. The summary video is available at https://youtu.be/KAlm3yskhvM .
- 29 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (5) , 4035-4042
Learning Vehicle Dynamics From Cropped Image Patches for Robot Navigation in Unpaved Outdoor Terrains
In the realm of autonomous mobile robots, safe navigation through unpaved outdoor environments remains a challenging task. Due to the high-dimensional nature of sensor data, extracting relevant information becomes a complex problem, which hinders adequate perception and path planning. Previous works have shown promising performances in extracting global features from full-sized images. However, they often face challenges in capturing essential local information. In this letter, we propose Crop-LSTM, which iteratively takes cropped image patches around the current robot's position and predicts the future position, orientation, and bumpiness. Our method performs local feature extraction by paying attention to corresponding image patches along the predicted robot trajectory in the 2D image plane. This enables more accurate predictions of the robot's future trajectory. With our wheeled mobile robot platform Raicart , we demonstrated the effectiveness of Crop-LSTM for point-goal navigation in an unpaved outdoor environment. Our method enabled safe and robust navigation using RGBD images in challenging unpaved outdoor terrains.
- 29 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (5) , 4035-4042
Learning Vehicle Dynamics From Cropped Image Patches for Robot Navigation in Unpaved Outdoor Terrains
In the realm of autonomous mobile robots, safe navigation through unpaved outdoor environments remains a challenging task. Due to the high-dimensional nature of sensor data, extracting relevant information becomes a complex problem, which hinders adequate perception and path planning. Previous works have shown promising performances in extracting global features from full-sized images. However, they often face challenges in capturing essential local information. In this letter, we propose Crop-LSTM, which iteratively takes cropped image patches around the current robot's position and predicts the future position, orientation, and bumpiness. Our method performs local feature extraction by paying attention to corresponding image patches along the predicted robot trajectory in the 2D image plane. This enables more accurate predictions of the robot's future trajectory. With our wheeled mobile robot platform Raicart , we demonstrated the effectiveness of Crop-LSTM for point-goal navigation in an unpaved outdoor environment. Our method enabled safe and robust navigation using RGBD images in challenging unpaved outdoor terrains.
- Top Cited Papers
- 25 January 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 8 (74) , eade2256
Learning quadrupedal locomotion on deformable terrain
Simulation-based reinforcement learning approaches are leading the next innovations in legged robot control. However, the resulting control policies are still not applicable on soft and deformable terrains, especially at high speed. The primary reason is that reinforcement learning approaches, in general, are not effective beyond the data distribution: The agent cannot perform well in environments that it has not experienced. To this end, we introduce a versatile and computationally efficient granular media model for reinforcement learning. Our model can be parameterized to represent diverse types of terrain from very soft beach sand to hard asphalt. In addition, we introduce an adaptive control architecture that can implicitly identify the terrain properties as the robot feels the terrain. The identified parameters are then used to boost the locomotion performance of the legged robot. We applied our techniques to the Raibo robot, a dynamic quadrupedal robot developed in-house. The trained networks demonstrated high-speed locomotion capabilities on deformable terrains: The robot was able to run on soft beach sand at 3.03 meters per second although the feet were completely buried in the sand during the stance phase. We also demonstrate its ability to generalize to different terrains by presenting running experiments on vinyl tile flooring, athletic track, grass, and a soft air mattress.
- 25 January 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 8 (74) , eade2256
Top Cited PapersLearning quadrupedal locomotion on deformable terrain
Simulation-based reinforcement learning approaches are leading the next innovations in legged robot control. However, the resulting control policies are still not applicable on soft and deformable terrains, especially at high speed. The primary reason is that reinforcement learning approaches, in general, are not effective beyond the data distribution: The agent cannot perform well in environments that it has not experienced. To this end, we introduce a versatile and computationally efficient granular media model for reinforcement learning. Our model can be parameterized to represent diverse types of terrain from very soft beach sand to hard asphalt. In addition, we introduce an adaptive control architecture that can implicitly identify the terrain properties as the robot feels the terrain. The identified parameters are then used to boost the locomotion performance of the legged robot. We applied our techniques to the Raibo robot, a dynamic quadrupedal robot developed in-house. The trained networks demonstrated high-speed locomotion capabilities on deformable terrains: The robot was able to run on soft beach sand at 3.03 meters per second although the feet were completely buried in the sand during the stance phase. We also demonstrate its ability to generalize to different terrains by presenting running experiments on vinyl tile flooring, athletic track, grass, and a soft air mattress.