@inproceedings{joung2026agiledp,title={Agile{DP}: Quantizing Diffusion Policy via Dynamic Scaling and Reweighted Distillation},author={Joung, Jiyeon and Lee, Seungseop and Kim, Namyoon and Jang, Keunwoo},booktitle={10th Annual Conference on Robot Learning},year={2026},url={https://openreview.net/forum?id=Gr9nFtFTjn},show_all_authors={true}}
We propose CSC-MPPI, a novel constrained Model Predictive Path Integral framework that integrates DBSCAN clustering for reliable obstacle avoidance in robot navigation tasks.
@inproceedings{park2025cscmppi,title={CSC-MPPI: A Novel Constrained MPPI Framework with DBSCAN for Reliable Obstacle Avoidance},author={Park, Leesai and Jang, Keunwoo and Kim, Sanghyun},booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},year={2025},pages={19645--19652},doi={10.1109/IROS60139.2025.11246839}}
We describe a robotic avatar system developed for the ANA Avatar XPRIZE Finals, featuring intuitive teleoperation interfaces and whole-body control for tele-existence applications.
@article{park2025avatar,title={Intuitive and Interactive Robotic Avatar System for Tele-Existence: TEAM SNU in the ANA Avatar XPRIZE Finals},author={Park, Beomyeong and Kim, Donghyeon and Lim, Daegyu and Park, Suhan and Ahn, Junewhee and Kim, Seungyeon and Shin, Jaeyong and Sung, Eunho and Sim, Jaehoon and Kim, Junhyung and Kim, Myeong-Ju and Cha, Junhyeok and Park, Gyeongjae and Lee, Hokyun and You, Seungbin and Jang, Keunwoo and Kim, Seung-Hun and Schwartz, Mathew and Park, Jaeheung},journal={International Journal of Social Robotics},year={2025},volume={17},pages={379--407},doi={10.1007/s12369-024-01152-y}}
We present a whole-body motion planning approach for a dual-arm mobile manipulator that compensates for the reaction force exerted by a door during traversal, enabling robust door-opening behavior.
@inproceedings{kim2024dualarm,title={Whole-body Motion Planning of Dual-Arm Mobile Manipulator for Compensating for Door Reaction Force},author={Kim, Yujin and Jang, Keunwoo},booktitle={2nd Workshop on Mobile Manipulation and Embodied Intelligence at ICRA 2024},year={2024},}
We propose a subspace-wise hybrid reinforcement learning approach for articulated object manipulation, combining model-based and model-free methods to enable efficient policy learning for complex manipulation tasks.
@article{kim2024subspace,title={Subspace-wise Hybrid Reinforcement Learning for Articulated Object Manipulation},author={Kim, Yujin and Choi, Sol and You, Bum-Jae and Jang, Keunwoo and Lee, Yisoo},journal={arXiv preprint arXiv:2412.08522},year={2024},}
2023
Thesis
Thesis
Task-Oriented Whole-Body Motion Generation Strategy of Mobile Manipulator for Considering Kinematic and Dynamic Constraints
This dissertation presents a task-oriented whole-body motion generation strategy for mobile manipulators, addressing kinematic and dynamic constraints through hierarchical quadratic programming frameworks.
@phdthesis{jang2023thesis,title={Task-Oriented Whole-Body Motion Generation Strategy of Mobile Manipulator for Considering Kinematic and Dynamic Constraints},author={Jang, Keunwoo},school={Seoul National University},year={2023},}
We present a motion planning framework for mobile manipulators that enables navigation including door traversal. The system integrates whole-body control with task planning to handle the complex constraints of door interaction.
@article{jang2023door,title={Motion Planning of Mobile Manipulator for Navigation Including Door Traversal},author={Jang, Keunwoo and Kim, Sanghyun and Park, Jaeheung},journal={IEEE Robotics and Automation Letters},year={2023},volume={8},number={7},pages={4147--4154},doi={10.1109/LRA.2023.3279612}}
We present a motion planning approach for closed-chain constraints using a probabilistic roadmap with improved connectivity, enabling reliable planning for robots with kinematic loops such as parallel manipulators.
@article{jang2022closedchain,title={Motion Planning for Closed-Chain Constraints Based on Probabilistic Roadmap With Improved Connectivity},author={Jang, Keunwoo and Baek, Jiyeong and Park, Suhan and Park, Jaeheung},journal={IEEE/ASME Transactions on Mechatronics},year={2022},volume={27},number={4},pages={2035--2043},doi={10.1109/TMECH.2022.3175260}}
We propose a weighted hierarchical quadratic programming (W-HQP) approach that assigns individual joint weights for each task priority level, enabling more flexible and intuitive whole-body robot control.
@article{jang2022weighted,title={Weighted Hierarchical Quadratic Programming: Assigning Individual Joint Weights for Each Task Priority},author={Jang, Keunwoo and Kim, Sanghyun and Park, Suhan and Kim, Junhyung and Park, Jaeheung},journal={Intelligent Service Robotics},year={2022},volume={15},number={4},pages={475--486},doi={10.1007/s11370-022-00431-9}}
We present a contact state estimation method for peg-in-hole assembly tasks using a Gaussian Mixture Model, enabling robust estimation of contact states during precision assembly operations.
@article{lee2022contact,title={Contact State Estimation for Peg-in-Hole Assembly Using Gaussian Mixture Model},author={Lee, Haeseong and Park, Suhan and Jang, Keunwoo and Kim, Seungyeon and Park, Jaeheung},journal={IEEE Robotics and Automation Letters},year={2022},volume={7},number={2},pages={3349--3356},doi={10.1109/LRA.2022.3146949}}
We present a complete robotic furniture assembly system that integrates task abstraction, motion planning, and whole-body control to autonomously assemble furniture from components.
@article{park2022furniture,title={Robotic Furniture Assembly: Task Abstraction, Motion Planning, and Control},author={Park, Suhan and Lee, Haeseong and Kim, Seungyeon and Baek, Jiyeong and Jang, Keunwoo and Kim, Hyoung Cheol and Kim, Myeongsoo and Park, Jaeheung},journal={Intelligent Service Robotics},year={2022},volume={15},number={4},pages={441--457},doi={10.1007/s11370-022-00427-5}}
An encyclopedia entry covering the fundamentals, kinematics, redundancy resolution, and control of redundant manipulators.
@incollection{park2021redundant,title={Redundant Manipulators},author={Park, Jaeheung and Jang, Keunwoo},booktitle={Encyclopedia of Robotics},year={2021},publisher={Springer},doi={10.1007/978-3-642-41610-1_186-1}}
We propose a regularized hierarchical quadratic programming (R-HQP) approach for real-time whole-body motion generation, ensuring robust and stable solutions in the presence of singularities and conflicting task constraints.
@article{hong2021regularized,title={Regularized Hierarchical Quadratic Program for Real-Time Whole-Body Motion Generation},author={Hong, Seongil and Jang, Keunwoo and Kim, Sanghyun and Park, Jaeheung},journal={IEEE/ASME Transactions on Mechatronics},year={2021},volume={26},number={4},pages={2115--2126},doi={10.1109/TMECH.2020.3032522}}
We present a reactive self-collision avoidance framework for a differentially driven mobile manipulator based on hierarchical quadratic programming, enabling real-time safe operation in dynamic environments.
@article{jang2021collision,title={Reactive Self-Collision Avoidance for a Differentially Driven Mobile Manipulator},author={Jang, Keunwoo and Kim, Sanghyun and Park, Jaeheung},journal={Sensors},year={2021},volume={21},number={3},pages={890},doi={10.3390/s21030890}}
We present a search trajectory method with twisting motion for dual peg-in-hole assembly tasks, enabling reliable insertion despite positional and angular uncertainties using compliant motion strategies.
@article{lee2021search,title={Search Trajectory with Twisting Motion for Dual Peg-in-Hole Assembly},author={Lee, Haeseong and Lee, Sang Yup and Jang, Keunwoo and Kim, Seungyeon and Ko, Jongseong and Park, Jaeheung},journal={Intelligent Service Robotics},year={2021},volume={14},number={4},pages={597--609},doi={10.1007/s11370-021-00382-7}}
@inproceedings{lee2021bolt,title={볼트와 체결 도구의 끼임 극복을 위한 제어 전략},author={Lee, Haeseong and Kim, Sanghyun and Park, Suhan and Jang, Keunwoo and Park, Jaeheung},booktitle={한국로봇종합학술대회 (KROC 2021)},year={2021},}
We present a continuous task transition approach for robot controllers based on hierarchical quadratic programming (HQP), enabling smooth switching between task priorities during robot motion.
@article{kim2019continuous,title={Continuous Task Transition Approach for Robot Controller Based on Hierarchical Quadratic Programming},author={Kim, Sanghyun and Jang, Keunwoo and Park, Suhan and Lee, Yisoo and Lee, Sang Yup and Park, Jaeheung},journal={IEEE Robotics and Automation Letters},year={2019},volume={4},number={2},pages={1603--1610},doi={10.1109/LRA.2019.2896769}}
We propose a whole-body control framework for non-holonomic mobile manipulators using HQP with continuous task transition, enabling coordinated base and arm motion under multiple task priorities.
@inproceedings{kim2019wholebody,title={Whole-body Control of Non-holonomic Mobile Manipulator Based on Hierarchical Quadratic Programming and Continuous Task Transition},author={Kim, Sanghyun and Jang, Keunwoo and Park, Suhan and Lee, Yisoo and Lee, Sang Yup and Park, Jaeheung},booktitle={4th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)},year={2019},pages={414--419},doi={10.1109/ICARM.2019.8834269}}
We propose a unified framework for overcoming motion constraints of robots using a task transition algorithm, enabling seamless switching between different task objectives under various kinematic and dynamic constraints.
@article{jang2018unified,title={A Unified Framework for Overcoming Motion Constraints of Robots Using Task Transition Algorithm},author={Jang, Keunwoo and Kim, Sanghyun and Park, Suhan and Park, Jaeheung},journal={Journal of Korea Robotics Society},year={2018},volume={13},number={2},pages={129--140},doi={10.7746/JKROS.2018.13.2.129}}
