Byeongho Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Byeongho Lee has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Frank Chongwoo Park
Seoul National University
4 shared publications - Junsu Ha
Department of Mechanical Engineering, Seoul National University, Seoul, South Korea
3 shared publications - Duckhyun Suh
LIG Defense & Aerospace, Seongnam 13488, Republic of Korea
2 shared publications - Sungjun Shim2 shared publications
- Yonghyeon Lee
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
2 shared publications - Younghun Kim
Seoul National University
2 shared publications
Latest Publications
- 28 February 2026
- Published by The Korea Robotics Society in Journal of Korea Robotics Society
- Vol. 21 (1) , 26-32
Improving Reinforcement Learning-Based Indoor Exploration Through Uncertainty Estimation
- 28 February 2026
- Published by The Korea Robotics Society in Journal of Korea Robotics Society
- Vol. 21 (1) , 26-32
Improving Reinforcement Learning-Based Indoor Exploration Through Uncertainty Estimation
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42 (15523098) , 713-733
Behavior-Controllable Stable Dynamics Models on Riemannian Configuration Manifolds
Due to their stability and robustness properties, Stable Dynamical Systems (SDS) have received considerable attention as a means of representing motions in learning from demonstration tasks. Designing vector fields that fit complex trajectories while ensuring stability still remains a key challenge; although recent deep learning-based methods have shown substantial progress in this direction, their tendency to overfit to demonstration trajectories often leads to undesirable behaviors, particularly as tasks deviate from demonstrations. At a fundamental level, the only reliable way to address this lack of generalization is to provide supervision in out-of-demonstration regions. Focusing on two types of general behaviors, mimicking and contracting, we propose a Behavior-Controllable Stable Dynamics Model (BCSDM), a one-parameter family of SDS that allows users to adjust the system's overall behavior depending on user intent. We show how to extend BCSDM to accommodate demonstrations of multiple tasks, and also propose a Deep Operator Vector Field (DeepOVec) for memory-efficient encoding of multiple dynamical systems. Extensive experiments on tasks that involve mimicking or contracting behaviors demonstrate the advantages of BCSDMs over existing state-of-the-art SDS learning methods.
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42 (15523098) , 713-733
Behavior-Controllable Stable Dynamics Models on Riemannian Configuration Manifolds
Due to their stability and robustness properties, Stable Dynamical Systems (SDS) have received considerable attention as a means of representing motions in learning from demonstration tasks. Designing vector fields that fit complex trajectories while ensuring stability still remains a key challenge; although recent deep learning-based methods have shown substantial progress in this direction, their tendency to overfit to demonstration trajectories often leads to undesirable behaviors, particularly as tasks deviate from demonstrations. At a fundamental level, the only reliable way to address this lack of generalization is to provide supervision in out-of-demonstration regions. Focusing on two types of general behaviors, mimicking and contracting, we propose a Behavior-Controllable Stable Dynamics Model (BCSDM), a one-parameter family of SDS that allows users to adjust the system's overall behavior depending on user intent. We show how to extend BCSDM to accommodate demonstrations of multiple tasks, and also propose a Deep Operator Vector Field (DeepOVec) for memory-efficient encoding of multiple dynamical systems. Extensive experiments on tasks that involve mimicking or contracting behaviors demonstrate the advantages of BCSDMs over existing state-of-the-art SDS learning methods.
- 29 August 2025
- Published by The Korea Robotics Society in Journal of Korea Robotics Society
- Vol. 20 (3) , 464-470
A Random 2D Environment Generation Framework for Learning-Based Navigation in Office Buildings
- 29 August 2025
- Published by The Korea Robotics Society in Journal of Korea Robotics Society
- Vol. 20 (3) , 464-470
A Random 2D Environment Generation Framework for Learning-Based Navigation in Office Buildings
- 30 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. PP, 1-8
Motion Manifold Flow Primitives for Task-Conditioned Trajectory Generation Under Complex Task-Motion Dependencies
Effective movement primitives should be capable of encoding and generating a rich repertoire of trajectories conditioned on task-defining parameters such as vision or language inputs. While recent methods based on the motion manifold hypothesis, which assumes that a set of trajectories lies on a lower-dimensional nonlinear subspace, address challenges such as limited dataset size and the high dimensionality of trajectory data, they often struggle to capture complex task-motion dependencies, i.e., when motion distributions shift drastically with task variations. To address this, we introduce Motion Manifold Flow Primitives (MMFP), a framework that decouples the training of the motion manifold from task-conditioned distributions. Specifically, we employ flow matching models, state-of-the-art conditional deep generative models, to learn task-conditioned distributions in the latent coordinate space of the learned motion manifold. Experiments are conducted on language-guided trajectory generation tasks, where many-to-many text-motion correspondences introduce complex task-motion dependencies, highlighting MMFP's superiority over existing methods.
- 30 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. PP, 1-8
Motion Manifold Flow Primitives for Task-Conditioned Trajectory Generation Under Complex Task-Motion Dependencies
Effective movement primitives should be capable of encoding and generating a rich repertoire of trajectories conditioned on task-defining parameters such as vision or language inputs. While recent methods based on the motion manifold hypothesis, which assumes that a set of trajectories lies on a lower-dimensional nonlinear subspace, address challenges such as limited dataset size and the high dimensionality of trajectory data, they often struggle to capture complex task-motion dependencies, i.e., when motion distributions shift drastically with task variations. To address this, we introduce Motion Manifold Flow Primitives (MMFP), a framework that decouples the training of the motion manifold from task-conditioned distributions. Specifically, we employ flow matching models, state-of-the-art conditional deep generative models, to learn task-conditioned distributions in the latent coordinate space of the learned motion manifold. Experiments are conducted on language-guided trajectory generation tasks, where many-to-many text-motion correspondences introduce complex task-motion dependencies, highlighting MMFP's superiority over existing methods.