Approximate Robust NMPC using Reinforcement Learning. Esfahani, H. N., Kordabad, A. B., & Gros, S. In 2021 European Control Conference (ECC), pages 132–137, Delft, Netherlands, June, 2021. IEEE. ![Approximate Robust NMPC using Reinforcement Learning [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex We present a Reinforcement Learning-based Robust Nonlinear Model Predictive Control (RL-RNMPC) framework for controlling nonlinear systems in the presence of disturbances and uncertainties. An approximate Robust Nonlinear Model Predictive Control (RNMPC) of low computational complexity is used in which the state trajectory uncertainty is modelled via ellipsoids. Reinforcement Learning is then used in order to handle the ellipsoidal approximation and improve the closed-loop performance of the scheme by adjusting the MPC parameters generating the ellipsoids. The approach is tested on a simulated Wheeled Mobile Robot (WMR) tracking a desired trajectory while avoiding static obstacles.
@inproceedings{esfahani_approximate_2021,
address = {Delft, Netherlands},
title = {Approximate {Robust} {NMPC} using {Reinforcement} {Learning}},
isbn = {978-94-6384-236-5},
url = {https://ieeexplore.ieee.org/document/9655129/},
doi = {10.23919/ECC54610.2021.9655129},
abstract = {We present a Reinforcement Learning-based Robust Nonlinear Model Predictive Control (RL-RNMPC) framework for controlling nonlinear systems in the presence of disturbances and uncertainties. An approximate Robust Nonlinear Model Predictive Control (RNMPC) of low computational complexity is used in which the state trajectory uncertainty is modelled via ellipsoids. Reinforcement Learning is then used in order to handle the ellipsoidal approximation and improve the closed-loop performance of the scheme by adjusting the MPC parameters generating the ellipsoids. The approach is tested on a simulated Wheeled Mobile Robot (WMR) tracking a desired trajectory while avoiding static obstacles.},
language = {en},
urldate = {2023-10-19},
booktitle = {2021 {European} {Control} {Conference} ({ECC})},
publisher = {IEEE},
author = {Esfahani, Hossein Nejatbakhsh and Kordabad, Arash Bahari and Gros, Sebastien},
month = jun,
year = {2021},
pages = {132--137},
}
Downloads: 0
{"_id":"ynjADtzdRSaD6mQYY","bibbaseid":"esfahani-kordabad-gros-approximaterobustnmpcusingreinforcementlearning-2021","author_short":["Esfahani, H. N.","Kordabad, A. B.","Gros, S."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Delft, Netherlands","title":"Approximate Robust NMPC using Reinforcement Learning","isbn":"978-94-6384-236-5","url":"https://ieeexplore.ieee.org/document/9655129/","doi":"10.23919/ECC54610.2021.9655129","abstract":"We present a Reinforcement Learning-based Robust Nonlinear Model Predictive Control (RL-RNMPC) framework for controlling nonlinear systems in the presence of disturbances and uncertainties. An approximate Robust Nonlinear Model Predictive Control (RNMPC) of low computational complexity is used in which the state trajectory uncertainty is modelled via ellipsoids. Reinforcement Learning is then used in order to handle the ellipsoidal approximation and improve the closed-loop performance of the scheme by adjusting the MPC parameters generating the ellipsoids. The approach is tested on a simulated Wheeled Mobile Robot (WMR) tracking a desired trajectory while avoiding static obstacles.","language":"en","urldate":"2023-10-19","booktitle":"2021 European Control Conference (ECC)","publisher":"IEEE","author":[{"propositions":[],"lastnames":["Esfahani"],"firstnames":["Hossein","Nejatbakhsh"],"suffixes":[]},{"propositions":[],"lastnames":["Kordabad"],"firstnames":["Arash","Bahari"],"suffixes":[]},{"propositions":[],"lastnames":["Gros"],"firstnames":["Sebastien"],"suffixes":[]}],"month":"June","year":"2021","pages":"132–137","bibtex":"@inproceedings{esfahani_approximate_2021,\n\taddress = {Delft, Netherlands},\n\ttitle = {Approximate {Robust} {NMPC} using {Reinforcement} {Learning}},\n\tisbn = {978-94-6384-236-5},\n\turl = {https://ieeexplore.ieee.org/document/9655129/},\n\tdoi = {10.23919/ECC54610.2021.9655129},\n\tabstract = {We present a Reinforcement Learning-based Robust Nonlinear Model Predictive Control (RL-RNMPC) framework for controlling nonlinear systems in the presence of disturbances and uncertainties. An approximate Robust Nonlinear Model Predictive Control (RNMPC) of low computational complexity is used in which the state trajectory uncertainty is modelled via ellipsoids. Reinforcement Learning is then used in order to handle the ellipsoidal approximation and improve the closed-loop performance of the scheme by adjusting the MPC parameters generating the ellipsoids. The approach is tested on a simulated Wheeled Mobile Robot (WMR) tracking a desired trajectory while avoiding static obstacles.},\n\tlanguage = {en},\n\turldate = {2023-10-19},\n\tbooktitle = {2021 {European} {Control} {Conference} ({ECC})},\n\tpublisher = {IEEE},\n\tauthor = {Esfahani, Hossein Nejatbakhsh and Kordabad, Arash Bahari and Gros, Sebastien},\n\tmonth = jun,\n\tyear = {2021},\n\tpages = {132--137},\n}\n\n","author_short":["Esfahani, H. N.","Kordabad, A. B.","Gros, S."],"key":"esfahani_approximate_2021","id":"esfahani_approximate_2021","bibbaseid":"esfahani-kordabad-gros-approximaterobustnmpcusingreinforcementlearning-2021","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/9655129/"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/victorjhu","dataSources":["CmHEoydhafhbkXXt5"],"keywords":[],"search_terms":["approximate","robust","nmpc","using","reinforcement","learning","esfahani","kordabad","gros"],"title":"Approximate Robust NMPC using Reinforcement Learning","year":2021}