Data-driven design of switching reference governors for brake-by-wire applications

Andrea Sassella; Valentina Breschi; Simone Formentin

Data-driven design of switching reference governors for brake-by-wire applications

Andrea Sassella
, Valentina Breschi
, Simone Formentin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Nowadays, data are ubiquitous in control design and data-driven approaches are in constant evolution. By following such a trend, in this paper we propose an approach for the direct data-driven design of switching reference governors for nonlinear plants and we apply it within a brake-by-wire application. The braking system is assumed to be pre-stabilized via a simple unknown controller attaining unsatisfactory performance in terms of output tracking and actuator effort. Hence, the reference governor is used to improve the overall closed-loop behavior, resulting into safer maneuvering. Preliminary results on a simulation setup show the effectiveness of the proposed strategy, thus motivating further investigation on the topic.

Original language	English
Title of host publication	Proceedings of the 3rd Conference on Learning for Dynamics and Control
Publisher	PMLR
Pages	99-110
Number of pages	12
Publication status	Published - 2021
Externally published	Yes
Event	3rd Annual Conference on Learning for DynamIcs & Control, L4DC 2021 - Zurich, Switzerland Duration: 7 Jun 2021 → 8 Jun 2021 Conference number: 3 https://l4dc.ethz.ch/

Publication series

Name	Proceedings of Machine Learning Research
Publisher	PMLR
Volume	144
ISSN (Electronic)	2640-3498

Conference

Conference	3rd Annual Conference on Learning for DynamIcs & Control, L4DC 2021
Abbreviated title	L4DC 2021
Country/Territory	Switzerland
City	Zurich
Period	7/06/21 → 8/06/21
Internet address	https://l4dc.ethz.ch/

Keywords

Data-driven control
Brake-by-wire applications
Switching control
Reference governor
data-driven control
Hierarchical control
braking control

Access to Document

https://proceedings.mlr.press/v144/sassella21a.html

Cite this

@inproceedings{67f231a34cca481894c7d75019e7b143,

title = "Data-driven design of switching reference governors for brake-by-wire applications",

abstract = "Nowadays, data are ubiquitous in control design and data-driven approaches are in constant evolution. By following such a trend, in this paper we propose an approach for the direct data-driven design of switching reference governors for nonlinear plants and we apply it within a brake-by-wire application. The braking system is assumed to be pre-stabilized via a simple unknown controller attaining unsatisfactory performance in terms of output tracking and actuator effort. Hence, the reference governor is used to improve the overall closed-loop behavior, resulting into safer maneuvering. Preliminary results on a simulation setup show the effectiveness of the proposed strategy, thus motivating further investigation on the topic.",

keywords = "Data-driven control, Brake-by-wire applications, Switching control, Reference governor, data-driven control, Hierarchical control, braking control",

author = "Andrea Sassella and Valentina Breschi and Simone Formentin",

year = "2021",

language = "English",

series = "Proceedings of Machine Learning Research",

publisher = "PMLR",

pages = "99--110",

booktitle = "Proceedings of the 3rd Conference on Learning for Dynamics and Control",

note = "3rd Annual Conference on Learning for DynamIcs \& Control, L4DC 2021, L4DC 2021 ; Conference date: 07-06-2021 Through 08-06-2021",

url = "https://l4dc.ethz.ch/",

}

Sassella, A, Breschi, V & Formentin, S 2021, Data-driven design of switching reference governors for brake-by-wire applications. in Proceedings of the 3rd Conference on Learning for Dynamics and Control. Proceedings of Machine Learning Research, vol. 144, PMLR, pp. 99-110, 3rd Annual Conference on Learning for DynamIcs & Control, L4DC 2021, Zurich, Switzerland, 7/06/21. <https://proceedings.mlr.press/v144/sassella21a.html>

Data-driven design of switching reference governors for brake-by-wire applications. / Sassella, Andrea; Breschi, Valentina; Formentin, Simone.
Proceedings of the 3rd Conference on Learning for Dynamics and Control. PMLR, 2021. p. 99-110 (Proceedings of Machine Learning Research; Vol. 144).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Data-driven design of switching reference governors for brake-by-wire applications

AU - Sassella, Andrea

AU - Breschi, Valentina

AU - Formentin, Simone

N1 - Conference code: 3

PY - 2021

Y1 - 2021

N2 - Nowadays, data are ubiquitous in control design and data-driven approaches are in constant evolution. By following such a trend, in this paper we propose an approach for the direct data-driven design of switching reference governors for nonlinear plants and we apply it within a brake-by-wire application. The braking system is assumed to be pre-stabilized via a simple unknown controller attaining unsatisfactory performance in terms of output tracking and actuator effort. Hence, the reference governor is used to improve the overall closed-loop behavior, resulting into safer maneuvering. Preliminary results on a simulation setup show the effectiveness of the proposed strategy, thus motivating further investigation on the topic.

AB - Nowadays, data are ubiquitous in control design and data-driven approaches are in constant evolution. By following such a trend, in this paper we propose an approach for the direct data-driven design of switching reference governors for nonlinear plants and we apply it within a brake-by-wire application. The braking system is assumed to be pre-stabilized via a simple unknown controller attaining unsatisfactory performance in terms of output tracking and actuator effort. Hence, the reference governor is used to improve the overall closed-loop behavior, resulting into safer maneuvering. Preliminary results on a simulation setup show the effectiveness of the proposed strategy, thus motivating further investigation on the topic.

KW - Data-driven control

KW - Brake-by-wire applications

KW - Switching control

KW - Reference governor

KW - data-driven control

KW - Hierarchical control

KW - braking control

UR - https://www.scopus.com/pages/publications/85131956446

M3 - Conference contribution

T3 - Proceedings of Machine Learning Research

SP - 99

EP - 110

BT - Proceedings of the 3rd Conference on Learning for Dynamics and Control

PB - PMLR

T2 - 3rd Annual Conference on Learning for DynamIcs & Control, L4DC 2021

Y2 - 7 June 2021 through 8 June 2021

ER -

Data-driven design of switching reference governors for brake-by-wire applications

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this