An active DoE method for the automated driving function ACC controller calibration Online publication date: Thu, 07-Apr-2022
by Su Zhou; Rucai Wang; Hans-Michael Koegeler; Jie Jin
International Journal of Powertrains (IJPT), Vol. 11, No. 1, 2022
Abstract: Generally, the calibration of an advanced driver assist system (ADAS) controller is carried out by an experienced operator, who tunes the most relevant parameters based on his experience. However, the calibration results are highly subjective, and could easily end up with a local optimum. To solve this problem, this paper studies an active design of experiment (DoE) calibration method for an adaptive cruise control (ACC) system controller, which needs to be calibrated with the targets of improving fuel efficiency and driving comfort. A statistical method was applied to arrange the simulation points of the most significant parameters. With the simulation results, the key performance indicator (KPI) models of the ACC system were built, to find the global optimum. Finally, the ACC controller was successfully calibrated with the least possible efforts and achieved a 19% reduction of fuel consumption and 49% improvement of driving comfort comparing to the ACC controller with the base set.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Powertrains (IJPT):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook