Lie group and Lie algebra, geometric and impedance control, group equivariance and symmetry, and diffusion models for robotic manipulation and motion planning.
Achievement of joint research
Seo, J., Prakash, N. P. S., Choi, J., & Horowitz, R. (2024). A Comparison Between Lie Group-and Lie Algebra-Based Potential Functions for Geometric Impedance Control. arXiv preprint arXiv:2401.13190.
Ryu, H., Kim, J., An, H., Chang, J., Seo, J., Kim, T., ..., Choi, J. & Horowitz, R. (2024). Diffusion-edfs: Bi-equivariant denoising generative modeling on se (3) for visual robotic manipulation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 18007-18018).
Seo, J., Prakash, N. P., Zhang, X., Wang, C., Choi, J., Tomizuka, M., & Horowitz, R. (2023). Contact-rich se (3)-equivariant robot manipulation task learning via geometric impedance control. IEEE Robotics and Automation Letters.
Chang, J., Ryu, H., Kim, J., Yoo, S., Choi, J., Seo, J., Prakash, N., ... & Horowitz, R. (2023). Denoising heat-inspired diffusion with insulators for collision free motion planning. NeurIPS 2023 Workshop on Diffusion Models
Kim, J., Ryu, H., Choi, J., Seo, J., Prakash, N. P. S., Li, R., & Horowitz, R. (2023). Robotic manipulation learning with equivariant descriptor fields: Generative modeling, bi-equivariance, steerability, and locality. In RSS 2023 Workshop on Symmetries in Robot Learning.
Seo, J., Lee, J., Baek, E., Horowitz, R., & Choi, J. (2022). Safety-critical control with nonaffine control inputs via a relaxed control barrier function for an autonomous vehicle. IEEE Robotics and Automation Letters, 7(2), 1944-1951.
Collaborators
Professor Roberto Horowitz, Ph.D., Distinguished Professor of Mechanical Engineering, James Fife Endowed Chair, Department of Mechanical Engineering, University of California, Berkeley
Professor Masayoshi Tomizuka, Cheryl and John Neerhout, Jr. Distinguished Professor, Distinguished Professor of Mechanical Engineering, Associate Dean, Faculty, Department of Mechanical Engineering, University of California, Berkeley
Joohwan Seo, Ph.D. Candidate, Department of Mechanical Engineering, University of California, Berkeley
Nikhil Potu Surya Prakash, Ph.D. Apple, Department of Mechanical Engineering, University of California, Berkeley
Ruolin Li, Ph.D. a Gabilan Assistant Professor, Department of Civil and Environmental Engineering at University of Southern California
Changhao Wang, Ph.D., Researcher at Meta Fundamental AI Research (FAIR) in Menlo Park
Michigan State University Center for Orthopedic Research (MSUCOR)
Research Topic
Patient-specific system identification, human motor control and rehabilitation using inverse optimal control, predictive modeling, physical human-robot interaction, and machine learning.
Achievement of joint research
Ramadan A, Choi J, Cholewicki J, Reeves NP, Popovich JM, Radcliffe CJ. Feasibility of incorporating test-retest reliability and model diversity in identification of key neuromuscular pathways during head position tracking. IEEE transactions on neural systems and rehabilitation engineering. 2019 Jan 10;27(2):275-82.
Ramadan A, Choi J, Radcliffe CJ, Popovich JM, Reeves NP. Inferring Control Intent During Seated Balance Using Inverse Model Predictive Control. IEEE Robotics and Automation Letters. 2018 Dec 12;4(2):224-30.
Ramadan A, Boss C, Choi J, Reeves NP, Cholewicki J, Popovich JM, Radcliffe CJ. Selecting sensitive parameter subsets in dynamical models with application to biomechanical system identification. Journal of biomechanical engineering. 2018 Jul 1;140(7):074503.
Ijaz A, Choi J. Anomaly detection of electromyographic signals. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2018 Mar 8;26(4):770-9.
Ramadan A, Cholewicki J, Radcliffe CJ, Popovich Jr JM, Reeves NP, Choi J. Reliability of assessing postural control during seated balancing using a physical human-robot interaction. Journal of biomechanics. 2017 Nov 7;64:198-205.
Ramadan A, Choi J, Radcliffe CJ, Cholewicki J, Reeves NP, Popovich JM. Robotic solutions to facilitate studying human motor control. In2017 14th IEEE International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2017 Jun 28 (pp. 174-178).
Ramadan A, Choi J, Radcliffe CJ. Inferring human subject motor control intent using inverse MPC. In2016 IEEE American Control Conference (ACC) 2016 Jul 6 (pp. 5791-5796).
Collaborators
Professor Jacek Cholewicki, Ph.D., Walter F. Patenge Chair, Director for the Michigan State University Center for Orthopedic Research (MSUCOR), College of Osteopathic Medicine, Department of Osteopathic Surgical Specialties, Michigan State University
Professor John Popovich, PhD, DPT, ATC, Assistant Professor, College of Osteopathic Medicine, Department of Osteopathic Surgical Specialties, Michigan State University
N. Peter Reeves, Ph.D., Associate Professor, College of Osteopathic Medicine, Department of Osteopathic Surgical Specialties, Michigan State University
Professor Clark Radcliffe, Ph.D., Professor Emeritus, College of Engineering, Department of Mechanical Engineering, Michigan State University
Ahmed Ramadan, Ph.D., Posdoc at University of Maryland School of Medicine in Baltimore.
Computational cardio-mechanics and Bayesian statistics group.
Research Topic
Bayesian patient-specific calibration of the computational model. Predictive biomedical modeling. Patient-specific machine learning.
Achievement of joint research
Zhang L, Jiang Z, Choi J, Lim CY, Maiti T, Baek S. Patient-Specific Prediction of Abdominal Aortic Aneurysm Expansion using Bayesian Calibration. IEEE journal of biomedical and health informatics. 2019 Jan 30.
Do HN, Ijaz A, Gharahi H, Zambrano B, Choi J, Lee W, Baek S. Prediction of Abdominal Aortic Aneurysm Growth Using Dynamical Gaussian Process Implicit Surface. IEEE Transactions on Biomedical Engineering. 2018 Jul 2;66(3):609-22.
Zhang L, Lim CY, Maiti T, Li Y, Choi J, Bozoki A, Zhu DC, Key Laboratory of Applied Statistics of the Ministry of Education (KLAS), for the Alzheimer’s Disease Neuroimaging Initiative. Analysis of conversion of Alzheimer’s disease using a multi-state Markov model. Statistical methods in medical research. 2018 Jan 1:0962280218786525.
Collaborators
University of Michigan
Professor C. Alberto Figueroa, Ph.D.,, Edward B. Diethrich Professor of Surgery, Professor, Biomedical Engineering
Computational Vascular Biomechanics Lab., University of Michigan
MSU Biomedical Engineering
Professor Seungik Baek, Ph.D.,, Cardiovascular and Tissue Mechanics Research Lab., Department of Mechanical Engineering, Michigan State University
Professor Lik Chuan Lee, Ph.D.,, Experimental and theoretical modeling for biomechanical research lab., Department of Mechanical Engineering, Michigan State University
MSU Statistics and Probability
Professor Tapabrata (Taps) Maiti, MSU Foundation professor, Ph.D.,, Department of Statistics and Probability, Michigan State University
MSU and GM control theory group
Research Topic
We try to establish a theoretical framework that can deal with nonlinear control design based on high-gain observers under measurement noise, using stochastic approximation and the ordinary differential equation (ODE) analysis techniques.
Achievement of joint research
Boss CJ, Lee J, Choi J. Uncertainty and Disturbance Estimation for Quadrotor Control Using Extended High-Gain Observers: Experimental Implementation. InASME 2017 Dynamic Systems and Control Conference 2017 Oct 11 (pp. V002T01A003-V002T01A003). American Society of Mechanical Engineers
Boss CJ, Lee J, De Aguiar CC, Choi J. Implementation of state and disturbance estimation for quadrotor control using extended high-gain observers. InASME 2016 Dynamic Systems and Control Conference 2016 Oct 12 (pp. V002T17A006-V002T17A006). American Society of Mechanical Engineers.
Lee J, Choi J, Khalil HK. New implementation of high-gain observers in the presence of measurement noise using stochastic approximation. In2016 IEEE European Control Conference (ECC) 2016 Jun 29 (pp. 1740-1745).
Collaborators
Professor Hassan K. Khalil, Ph.D., University Distinguished Professor, Department of Electrical & Computer Engineering (ECE), Michigan State University
Joonho Lee, Ph.D., General Motors Tech Center, Warren, MI 48092
University of Waterloo, Canada
Research Topic
Multi-Sensory Reinforcement Learning (RL) for Synthesis of Dexterous Manipulation Skills Using Anthropomorphic Robot Arm and Hand
Achievement of joint research
Yang S, Jeon S, Choi J. Level-set based greedy algorithm with sequential gaussian process regression for implicit surface estimation. InASME 2016 Dynamic Systems and Control Conference 2016 Oct 12 (pp. V002T25A001-V002T25A001). American Society of Mechanical Engineers.
Collaborators
Professor Jeon Soo, Ph.D., Department of Mechanical and Mechatronics, University of Waterloo
University of British Columbia, Canada
Research Topic
We collaborate with the Control Engineering Laboratory (CEL) at the University of British Columbia to carry out research in control theory and its applications to engineering and science. Current research in CEL is focused in the areas of control-oriented modeling and system identification, robust and optimal control system design, and control applications in mechanical and mechatronics systems.
Achievement of joint research
Andrew White, Jongeun Choi, Ryozo Nagamune, and Guoming Zhu, “Gain-Scheduling Control of Port-Fuel-Injection Processes”, Control Engineering Practice, Volume 19, Issue 4, Pages 380-394, April 2011.
Richard Conway, Jongeun Choi, Ryozo Nagamune, and Roberto Horowitz “Robust Track-Following Controller Design in Hard Disk Drives based on Parameter Dependent Lyapunov Functions”, IEEE Transactions on Magnetics, Volume 46, Number 4, Pages 1060-1068, April 2010.
Jongeun Choi, Ryozo Nagamune, and Roberto Horowitz, “Multiple Robust Track-Following Controller Design in Hard Disk Drives”, the Special Issue on Intelligent Control and Its Applications to Hard Disk Drives for the International Journal of Adaptive Control and Signal Processing 2008, Volume 22, Number 4, Pages 359-373, Published online 22 August 2007.
Ryozo Nagamune and Jongeun Choi, “Parameter Reduction of Estimated Model Sets for Robust Control”, Journal of Dynamic Systems, Measurement, and Control, Volume 132, Issue 2, Pages 021002(10), March 2010.
Ryozo Nagamune and Jongeun Choi “Parameter Reduction of Nonlinear Least-Squares Estimates via Nonconvex Optimization”, in the Proceedings of the American Control Conference (ACC) 2008.
Ryozo Nagamune and Jongeun Choi “Parameter Reduction of Nonlinear Least-Squares Estimates via Singular Value Decomposition”, in the Proceedings of the 17th International Federation of Automatic Control (IFAC) World Congress 2008.
Jongeun Choi, Ryozo Nagamune and Roberto Horowitz, “Multiple Robust Controller Design based on Parameter Dependent Lyapunov Functions.” Proceedings of the 17th International Symposium on Mathematical Theory of Networks and Systems (MTNS), Kyoto, Japan, July 24-28, 2006.
Jongeun Choi, Ryozo Nagamune and Roberto Horowitz, “Synthesis of Multiple Robust Controllers for Parametric Uncertain LTI Systems”, Proceedings of the 25th American Control Conference (ACC) June 14 to 16, 2006, Minneapolis, Minnesota, USA.
Collaborators
Jongeun Choi, Ryozo Nagamune and Roberto Horowitz, “Synthesis of Multiple Robust Controllers for Parametric Uncertain LTI Systems”, Proceedings of the 25th American Control Conference (ACC) June 14 to 16, 2006, Minneapolis, Minnesota, USA.