Marcel Menner

- Phone: 617-621-7525
- Email:
-
Position:
Research / Technical Staff
Research Scientist -
Education:
Ph.D., ETH Zurich, 2020 -
Research Areas:
External Links:
Marcel's Quick Links
-
Biography
Marcel's research interests include optimization-based control, machine learning, learning from human interactions, as well as their applications to vehicles and robots. During his Ph.D. research, he developed data-based control methodologies for improving the operation of dynamical systems.
-
Recent News & Events
-
NEWS MERL researchers present 10 papers at the American Control Conference (ACC) Date: May 31, 2023 - June 2, 2023
Where: San Diego, CA
MERL Contacts: Karl Berntorp; Ankush Chakrabarty; Vedang M. Deshpande; Stefano Di Cairano; Marcus Greiff; Devesh K. Jha; Christopher R. Laughman; Marcel Menner; Rien Quirynen; Arvind Raghunathan; Diego Romeres; Abraham P. Vinod; Yebin Wang; Avishai Weiss
Research Areas: Control, Machine Learning, OptimizationBrief- MERL will present 10 papers at the American Control Conference (ACC) in San Diego, CA, with topics including autonomous-vehicle decision making and control, physics-informed machine learning, motion planning, control subject to nonconvex chance constraints, and optimal power management. Two talks are part of tutorial sessions.
MERL will also be present at the conference as a sponsor, with a booth for discussing with researchers and students, and hosting a special session at lunch with highlights of MERL research and work philosophy.
- MERL will present 10 papers at the American Control Conference (ACC) in San Diego, CA, with topics including autonomous-vehicle decision making and control, physics-informed machine learning, motion planning, control subject to nonconvex chance constraints, and optimal power management. Two talks are part of tutorial sessions.
-
TALK [MERL Seminar Series 2023] Dr. Michael Muehlebach presents talk titled Learning and Dynamical Systems Date & Time: Tuesday, April 11, 2023; 11:00 AM
Speaker: Michael Muehlebach, Max Planck Institute for Intelligent Systems
MERL Host: Marcel Menner
Research Areas: Control, Dynamical Systems, Machine Learning, Optimization, RoboticsAbstractThe talk will be divided into two parts. The first part of the talk introduces a class of first-order methods for constrained optimization that are based on an analogy to non-smooth dynamical systems. The key underlying idea is to express constraints in terms of velocities instead of positions, which has the algorithmic consequence that optimizations over feasible sets at each iteration are replaced with optimizations over local, sparse convex approximations. This results is a simplified suite of algorithms and an expanded range of possible applications in machine learning. In the second part of my talk, I will present a robot learning algorithm for trajectory tracking. The method incorporates prior knowledge about the system dynamics and by optimizing over feedforward actions, the risk of instability during deployment is mitigated. The algorithm will be evaluated on a ping-pong playing robot that is actuated by soft pneumatic muscles.
See All News & Events for Marcel -
-
MERL Publications
- "Friction-Adaptive Stochastic Nonlinear Model Predictive Control for Autonomous Vehicles", Vehicle System Dynamics, May 2023.BibTeX TR2023-064 PDF
- @article{Vaskov2023may2,
- author = {Vaskov, Sean and Quirynen, Rien and Menner, Marcel and Berntorp, Karl},
- title = {Friction-Adaptive Stochastic Nonlinear Model Predictive Control for Autonomous Vehicles},
- journal = {Vehicle System Dynamics},
- year = 2023,
- month = may,
- url = {https://www.merl.com/publications/TR2023-064}
- }
, - "Gaussian Processes with State-Dependent Noise for Stochastic Control", arXiv, May 2023. ,
- "Automated Controller Calibration by Kalman Filtering", IEEE Transactions on Control Systems Technology, April 2023.BibTeX TR2023-022 PDF
- @article{Menner2023apr,
- author = {Menner, Marcel and Berntorp, Karl and Di Cairano, Stefano},
- title = {Automated Controller Calibration by Kalman Filtering},
- journal = {IEEE Transactions on Control Systems Technology},
- year = 2023,
- month = apr,
- url = {https://www.merl.com/publications/TR2023-022}
- }
, - "Learning Optimization-based Control Policies Directly from Digital Twin Simulations", IEEE Conference on Control Technology and Applications (CCTA), DOI: 10.1109/CCTA49430.2022.9966077, August 2022, pp. 895-900.BibTeX TR2022-108 PDF
- @inproceedings{Menner2022aug,
- author = {Menner, Marcel and Chakrabarty, Ankush and Berntorp, Karl and Di Cairano, Stefano},
- title = {Learning Optimization-based Control Policies Directly from Digital Twin Simulations},
- booktitle = {IEEE Conference on Control Technology and Applications (CCTA)},
- year = 2022,
- pages = {895--900},
- month = aug,
- doi = {10.1109/CCTA49430.2022.9966077},
- url = {https://www.merl.com/publications/TR2022-108}
- }
, - "Location and Driver-Specific Vehicle Adaptation Using Crowdsourced Data", European Control Conference (ECC), DOI: 10.23919/ECC55457.2022.9838135, July 2022, pp. 769-774.BibTeX TR2022-095 PDF
- @inproceedings{Menner2022jul,
- author = {Menner, Marcel and Ma, Ziyi and Berntorp, Karl and Di Cairano, Stefano},
- title = {Location and Driver-Specific Vehicle Adaptation Using Crowdsourced Data},
- booktitle = {European Control Conference (ECC)},
- year = 2022,
- pages = {769--774},
- month = jul,
- doi = {10.23919/ECC55457.2022.9838135},
- url = {https://www.merl.com/publications/TR2022-095}
- }
,
- "Friction-Adaptive Stochastic Nonlinear Model Predictive Control for Autonomous Vehicles", Vehicle System Dynamics, May 2023.
-
Other Publications
- "Learning-based model predictive control: Toward safe learning in control", Annual Review of Control, Robotics, and Autonomous Systems, Vol. 3, pp. 269-296, 2020.BibTeX
- @Article{hewing2020learning,
- author = {Hewing, Lukas and Wabersich, Kim P and Menner, Marcel and Zeilinger, Melanie N},
- title = {Learning-based model predictive control: Toward safe learning in control},
- journal = {Annual Review of Control, Robotics, and Autonomous Systems},
- year = 2020,
- volume = 3,
- pages = {269--296}
- }
, - "Using Human Ratings for Feedback Control: A Supervised Learning Approach With Application to Rehabilitation Robotics", IEEE Transactions on Robotics, Vol. 36, No. 3, pp. 789-801, 2020.BibTeX
- @Article{menner2020using,
- author = {Menner, Marcel and Neuner, Lukas and L{\"u}nenburger, Lars and Zeilinger, Melanie N},
- title = {Using Human Ratings for Feedback Control: A Supervised Learning Approach With Application to Rehabilitation Robotics},
- journal = {IEEE Transactions on Robotics},
- year = 2020,
- volume = 36,
- number = 3,
- pages = {789--801}
- }
, - "Constrained inverse optimal control with application to a human manipulation task", IEEE Transactions on Control Systems Technology, 2019.BibTeX
- @Article{menner2019constrained,
- author = {Menner, Marcel and Worsnop, Peter and Zeilinger, Melanie N},
- title = {Constrained inverse optimal control with application to a human manipulation task},
- journal = {IEEE Transactions on Control Systems Technology},
- year = 2019
- }
, - "Robust Design of Adaptive Output Feedback Controllers for Direct Feedthrough Systems", Journal of Guidance, Control, and Dynamics, Vol. 41, No. 9, pp. 1919-1928, 2018.BibTeX
- @Article{menner2018robust,
- author = {Menner, Marcel and Annaswamy, Anuradha M and Holzapfel, Florian},
- title = {Robust Design of Adaptive Output Feedback Controllers for Direct Feedthrough Systems},
- journal = {Journal of Guidance, Control, and Dynamics},
- year = 2018,
- volume = 41,
- number = 9,
- pages = {1919--1928}
- }
,
- "Learning-based model predictive control: Toward safe learning in control", Annual Review of Control, Robotics, and Autonomous Systems, Vol. 3, pp. 269-296, 2020.
-
Videos
-
MERL Issued Patents
-
Title: "Adaptive Control of Autonomous or Semi-Autonomous Vehicle"
Inventors: Berntorp, Karl; Di Cairano, Stefano; Menner, Marcel
Patent No.: 11,327,492
Issue Date: May 10, 2022
-
Title: "Adaptive Control of Autonomous or Semi-Autonomous Vehicle"