Publications

See also Google Scholar.

1. Precise SE(3) End-Effector Tracking in Whole-Body Humanoid Control
   Joohwan Seo, Xiaofeng Guo, Jinkun Cao, Roberto Horowitz, Rocky Duan, Guanya Shi, Koushil Sreenath
   arXiv preprint arXiv:2610.09479, 2026
   arXivproject website
2. CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration
   Hyunjin Park, Jebeom Chae, Minwoo Park, Sunghyun Park, Hanjun Yoo, Seoyeon Choi, Soochul Yoo, Joohwan Seo, Sarmad Idrees, Jae-Sang Hyun, Jongmin Lee, Roberto Horowitz, Youngwoon Lee, Jongeun Choi
   arXiv preprint arXiv:2609.34782, 2026
   arXiv
3. Partially Equivariant Reinforcement Learning in Symmetry-breaking Environments
   Junwoo Chang, Minwoo Park, Joohwan Seo, Roberto Horowitz, Jongmin Lee, Jongeun Choi
   International Conference on Learning Representations (ICLR) 2026
4. EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Policy for Spatially Generalizable Contact-rich Tasks
   Joohwan Seo, Arvind Kruthiventy, Soomi Lee, Megan Teng, Xiang Zhang, Seoyeon Choi, Jongeun Choi, Roberto Horowitz
   arXiv preprint arXiv:2507.10961, 2025
   arXivproject website
5. Geometric Formulation of Unified Force-Impedance Control on SE(3) for Robotic Manipulators
   Joohwan Seo, Nikhil P.S. Prakash, Soomi Lee, Arvind Kruthiventy, Megan Teng, Jongeun Choi, Roberto Horowitz
   arXiv preprint arXiv:2504.17080, 2025
   arXiv
6. SE(3)-Equivariant Robot Learning and Control: A Tutorial Survey
   Joohwan Seo, Soochul Yoo, Junwoo Chang, Hyunseok An, Hyunwoo Ryu, Soomi Lee, Arvind Kruthiventy, Jongeun Choi, Roberto Horowitz
   International Journal of Control, Automation and Systems (IJCAS), 2025
   SpringerarXiv
7. Deep Geometric Potential Functions for Tracking on Manifolds
   Nikhil P.S. Prakash, Joohwan Seo, Koushil Sreenath, Jongeun Choi, Roberto Horowitz
   IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024, Abu Dhabi, UAE
8. Variable Impedance Control using Deep Geometric Potential Fields
   Nikhil P.S. Prakash, Joohwan Seo, Koushil Sreenath, Jongeun Choi, Roberto Horowitz
   Modeling, Estimation, and Control Conference (MECC) 2024, Chicago, USA
9. Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation
   Hyunwoo Ryu, Jiwoo Kim, Junwoo Chang, Hyun Seok Ahn, Joohwan Seo, Taehan Kim, Jongeun Choi, Roberto Horowitz
   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 Highlight
10. A Comparison between Lie Group- and Lie Algebra-based Potential Functions for Geometric Impedance Control
    Joohwan Seo, Nikhil P.S. Prakash, Jongeun Choi, Roberto Horowitz
    American Control Conference (ACC) 2024, Toronto, Canada
11. Contact-rich SE(3)-Equivariant Robot Manipulation Task Learning via Geometric Impedance Control
    Joohwan Seo, Nikhil P.S. Prakash, Xiang Zhang, Changhao Wang, Jongeun Choi, Masayoshi Tomizuka, Roberto Horowitz
    IEEE Robotics and Automation Letters 9.2 (2024): 1508–1515 (presented at IROS 2024)
    arXivproject website
12. Denoising Heat-inspired Diffusion with Insulators for Collision Free Motion Planning
    Junwoo Chang, Hyunwoo Ryu, Jiwoo Kim, Soochul Yoo, Joohwan Seo, Nikhil P.S. Prakash, Jongeun Choi, Roberto Horowitz
    NeurIPS 2023 Workshop
13. Clustering Techniques for Stable Linear Dynamical Systems with Applications to Hard Disk Drives
    Nikhil Potu Surya Prakash, Joohwan Seo, Jongeun Choi, Roberto Horowitz
    IFAC Modeling, Estimation and Control Conference (MECC) 2023, Lake Tahoe, USA
14. Geometric Impedance Control on SE(3) for Robotic Manipulators
    Joohwan Seo, Nikhil P.S. Prakash, Alexander Rose, Roberto Horowitz
    IFAC World Congress 2023, Yokohama, Japan
    Scholar
15. Data-Driven Track Following Control for Dual Stage-Actuator Hard Disk Drives
    Nikhil P.S. Prakash, Joohwan Seo, Alexander Rose, Roberto Horowitz
    IFAC World Congress 2023, Yokohama, Japan
16. Robotic Manipulation Learning with Equivariant Descriptor Fields: Generative Modeling, Bi-equivariance, Steerability, and Locality
    Jiwoo Kim, Hyunwoo Ryu, Jongeun Choi, Joohwan Seo, Nikhil P.S. Prakash, Ruolin Li, Roberto Horowitz
    Robotics: Science and Systems (RSS) 2023 Workshop, Daegu, Korea
    Scholar
17. Output Feedback Control Design for Quadrotor using Recursive Least Square Dynamic Inversion
    Seongwon Lee, Joohwan Seo, Joonho Lee, Connor J. Boss, Jongeun Choi
    Mechatronics 92 (2023): 102981
18. Suspension Control Strategies using Switched Soft Actor-Critic Models for Real Roads
    Hwanmoo Yong, Joohwan Seo, Jaeyoung Kim, Myounghoe Kim, Jongeun Choi
    IEEE Transactions on Industrial Electronics 70.1 (2022): 824–832
19. Safety-critical Control with Nonaffine Control Inputs via a Relaxed Control Barrier Function for an Autonomous Vehicle
    Joohwan Seo, Joonho Lee, Eunkyu Baik, Roberto Horowitz, Jongeun Choi
    IEEE Robotics and Automation Letters 7.2 (2022): 1944–1951 (presented at ICRA 2022)
    IEEE
20. Output Feedback Control Design using Extended High-Gain Observers and Dynamic Inversion with Projection for a Small Scaled Helicopter
    Joonho Lee, Joohwan Seo, Jongeun Choi
    Automatica 133 (2021): 109883
21. State Reconstruction in a Nonlinear Vehicle Suspension System using Deep Neural Networks
    Hwanmoo Yong, Joohwan Seo, Jungkyu Kim, Jongeun Choi
    Nonlinear Dynamics 105 (2021): 439–455
22. Vision-based Uncertainty-aware Lane Keeping Strategy using Deep Reinforcement Learning
    Myounghoe Kim, Joohwan Seo, Mingoo Lee, Jongeun Choi
    Journal of Dynamic Systems, Measurement, and Control 143.8 (2021): 084503
23. Nonaffine Helicopter Control Design and Implementation based on a Robust Explicit Nonlinear Model Predictive Control
    Joohwan Seo, Seongwon Lee, Joonho Lee, Jongeun Choi
    IEEE Transactions on Control Systems Technology 30.2 (2021): 811–818
24. Output Feedback Control Synthesis for a Helicopter using Explicit Nonlinear Model Predictive Control, Dynamic Inversion, and Extended High-Gain Observers
    Joohwan Seo, Jongeun Choi
    ASME Dynamic Systems and Control Conference (DSCC) 2019, Park City, USA

Invited Talks & Presentations

Geometric Learning and Control on SE(3) for Robotic Manipulators (with EquiContact)

• AAI Seminar @ Seoul National University (Prof. Namhoon Cho), 09/26/2025 · Video
• Robot & AI Seminar @ Yonsei University (Prof. Jongeun Choi), 06/23/2025

Geometric Learning and Control on SE(3) for Robotic Manipulators

• Centre for Autonomous and Cyber-Physical Systems @ Cranfield University (Prof. Namhoon Cho), 07/23/2024
• Hong Kong Center for Construction Robotics (HKCRC), 03/19/2024
• Control Seminar Series @ UC Berkeley Mechanical Engineering, 03/01/2024
  with Prof. Koushil Sreenath, Negar Mehr, Kameshwar Poolla, Mark Mueller, and Francesco Borrelli
• Hybrid Robotics Lab @ UC Berkeley (Prof. Koushil Sreenath), 12/02/2023
• Stanford x Berkeley Korean Research Conference, 11/04/2023
• Korea Institutes x Berkeley International Research Forum, 10/23/2023

Workshop & Poster Presentations

• “EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Policy for Spatially Generalizable Contact-rich Tasks”
  2nd Workshop on Dexterous Manipulation @ CoRL 2025, Seoul, South Korea
• “Contact-rich SE(3) Equivariant Robot Manipulation Task Learning via Geometric Impedance Control”
  Equivariant Robotics: The Role of Symmetry Across Perception, Estimation, and Control, Workshop @ IROS 2024
  Best Poster AwardIEEE RAS Technical Committee for Computer & Robot Vision
• “Contact-rich SE(3) Equivariant Robot Manipulation Task Learning via Geometric Impedance Control”
  From Geometry to General Autonomy of Robotic Systems, Workshop @ IROS 2024
• “SE(3) Equivariant Vision-based Skill Acquisition for Robotic Manipulation in Contact-rich Environments”
  Berkeley DeepDrive (BDD) Workshop 2024

Conference Presentations

• “Geometric Formulation of Unified Force-Impedance Control on SE(3) for Robotic Manipulators” (GUFIC) — IFAC World Congress 2026, Busan, Korea
• “Deep Geometric Potential Functions for Tracking on Manifolds” — IROS 2024, Abu Dhabi, UAE
• “Contact-rich SE(3)-Equivariant Robot Manipulation Task Learning via Geometric Impedance Control” — IROS 2024, Abu Dhabi, UAE
• “Variable Impedance Control using Deep Geometric Potential Fields” — MECC 2024, Chicago, USA
• “A Comparison between Lie Group- and Lie Algebra-based Potential Functions for Geometric Impedance Control” — ACC 2024, Toronto, Canada
• “Geometric Impedance Control on SE(3) for Robotic Manipulators” — IFAC World Congress 2023, Yokohama, Japan
• “Safety-critical Control with Nonaffine Control Inputs via a Relaxed Control Barrier Function for an Autonomous Vehicle” — ICRA 2022, Philadelphia, USA
• “Output Feedback Control Synthesis for a Helicopter using Explicit Nonlinear MPC, Dynamic Inversion and Extended High-Gain Observers” — DSCC 2019, Park City, USA