Koopman Model Predictive Control for Eco-Driving of Automated Vehicles

Koopman Model Predictive Control for Eco-Driving of Automated Vehicles. Gupta, S., Shen, D., Karbowski, D., & Rousseau, A. In 2022 American Control Conference (ACC), Atlanta, GA, USA, June, 2022. IEEE. ANL

Paper doi abstract bibtex 20 downloads

In this paper, we develop a data-driven process for building a model predictive control (MPC) for eco-driving of automated vehicles. The process involves performing system identification in which the non-linear vehicle dynamics model is approximated by the Koopman operator, a linear predictor of higher state-dimension, in a data-driven framework. This approach allows us to formulate the eco-driving problem in a constrained quadratic program that leads to a computationally fast MPC. The MPC is then implemented as a closed-loop control of an electric vehicle in numerical simulations for demonstration.

@inproceedings{gupta_koopman_2022,
	address = {Atlanta, GA, USA},
	title = {Koopman {Model} {Predictive} {Control} for {Eco}-{Driving} of {Automated} {Vehicles}},
	url = {https://anl.box.com/s/767hekd8hze41g96eaj3eqcea1cr5jzk},
	doi = {https://doi.org/10.23919/ACC53348.2022.9867636},
	abstract = {In this paper, we develop a data-driven process for building a model predictive control (MPC) for eco-driving of automated vehicles. The process involves performing system identification in which the non-linear vehicle dynamics model is approximated by the Koopman operator, a linear predictor of higher state-dimension, in a data-driven framework. This approach allows us to formulate the eco-driving problem in a constrained quadratic program that leads to a computationally fast MPC. The MPC is then implemented as a closed-loop control of an electric vehicle in numerical simulations for demonstration.},
	booktitle = {2022 {American} {Control} {Conference} ({ACC})},
	publisher = {IEEE},
	author = {Gupta, Shobhit and Shen, Daliang and Karbowski, Dominik and Rousseau, Aymeric},
	month = jun,
	year = {2022},
	note = {ANL},
	keywords = {Connected and Automated Vehicles, DOE SMART, RoadRunner, Vehicle control},
}

Downloads: 20

{"_id":"iAz9sxZ25L4Sg43hR","bibbaseid":"gupta-shen-karbowski-rousseau-koopmanmodelpredictivecontrolforecodrivingofautomatedvehicles-2022","author_short":["Gupta, S.","Shen, D.","Karbowski, D.","Rousseau, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Atlanta, GA, USA","title":"Koopman Model Predictive Control for Eco-Driving of Automated Vehicles","url":"https://anl.box.com/s/767hekd8hze41g96eaj3eqcea1cr5jzk","doi":"https://doi.org/10.23919/ACC53348.2022.9867636","abstract":"In this paper, we develop a data-driven process for building a model predictive control (MPC) for eco-driving of automated vehicles. The process involves performing system identification in which the non-linear vehicle dynamics model is approximated by the Koopman operator, a linear predictor of higher state-dimension, in a data-driven framework. This approach allows us to formulate the eco-driving problem in a constrained quadratic program that leads to a computationally fast MPC. The MPC is then implemented as a closed-loop control of an electric vehicle in numerical simulations for demonstration.","booktitle":"2022 American Control Conference (ACC)","publisher":"IEEE","author":[{"propositions":[],"lastnames":["Gupta"],"firstnames":["Shobhit"],"suffixes":[]},{"propositions":[],"lastnames":["Shen"],"firstnames":["Daliang"],"suffixes":[]},{"propositions":[],"lastnames":["Karbowski"],"firstnames":["Dominik"],"suffixes":[]},{"propositions":[],"lastnames":["Rousseau"],"firstnames":["Aymeric"],"suffixes":[]}],"month":"June","year":"2022","note":"ANL","keywords":"Connected and Automated Vehicles, DOE SMART, RoadRunner, Vehicle control","bibtex":"@inproceedings{gupta_koopman_2022,\n\taddress = {Atlanta, GA, USA},\n\ttitle = {Koopman {Model} {Predictive} {Control} for {Eco}-{Driving} of {Automated} {Vehicles}},\n\turl = {https://anl.box.com/s/767hekd8hze41g96eaj3eqcea1cr5jzk},\n\tdoi = {https://doi.org/10.23919/ACC53348.2022.9867636},\n\tabstract = {In this paper, we develop a data-driven process for building a model predictive control (MPC) for eco-driving of automated vehicles. The process involves performing system identification in which the non-linear vehicle dynamics model is approximated by the Koopman operator, a linear predictor of higher state-dimension, in a data-driven framework. This approach allows us to formulate the eco-driving problem in a constrained quadratic program that leads to a computationally fast MPC. The MPC is then implemented as a closed-loop control of an electric vehicle in numerical simulations for demonstration.},\n\tbooktitle = {2022 {American} {Control} {Conference} ({ACC})},\n\tpublisher = {IEEE},\n\tauthor = {Gupta, Shobhit and Shen, Daliang and Karbowski, Dominik and Rousseau, Aymeric},\n\tmonth = jun,\n\tyear = {2022},\n\tnote = {ANL},\n\tkeywords = {Connected and Automated Vehicles, DOE SMART, RoadRunner, Vehicle control},\n}\n\n","author_short":["Gupta, S.","Shen, D.","Karbowski, D.","Rousseau, A."],"key":"gupta_koopman_2022","id":"gupta_koopman_2022","bibbaseid":"gupta-shen-karbowski-rousseau-koopmanmodelpredictivecontrolforecodrivingofautomatedvehicles-2022","role":"author","urls":{"Paper":"https://anl.box.com/s/767hekd8hze41g96eaj3eqcea1cr5jzk"},"keyword":["Connected and Automated Vehicles","DOE SMART","RoadRunner","Vehicle control"],"metadata":{"authorlinks":{}},"downloads":20},"bibtype":"inproceedings","biburl":"https://api.zotero.org/groups/2254223/items?key=Bbol5AZSx3A5fDcmq91mfOKd&format=bibtex&limit=100","dataSources":["Emhp3E5GZrDSaunEJ","qc6TuRNtLYeLyawhB","cGgmoLgbNTEZGWgPE","YAe24F3YNSozTyd4w","8NTJjnAGyZ5qTfMug"],"keywords":["connected and automated vehicles","doe smart","roadrunner","vehicle control"],"search_terms":["koopman","model","predictive","control","eco","driving","automated","vehicles","gupta","shen","karbowski","rousseau"],"title":"Koopman Model Predictive Control for Eco-Driving of Automated Vehicles","year":2022,"downloads":20}