Generation of Mission-Based Driving Cycles Using Behavioral Models Parameterized for Different Driver Categories
2023 (English)In: SAE technical paper series, ISSN 0148-7191, article id 2023-01-5033Article in journal (Refereed) Published
Abstract [en]
A methodology for the generation of representative driving cycles is proposed and evaluated. The proposed method combines traffic simulation and driving behavior modeling to generate mission-based driving cycles. Extensions to the existing behavioral model in a traffic simulation tool are suggested and parameterized for different driver categories to capture the effects of road geometry and variances between drivers. The evaluation results illustrate that the developed extensions significantly improve the match between driving data and the driving cycles generated by traffic simulation. Using model extensions parameterized for different driver categories, instead of only one average driver, provides the possibility to represent different driving behaviors and further improve the realism of the resulting driving cycles.
Place, publisher, year, edition, pages
Society of Automotive Engineers, 2023. article id 2023-01-5033
Keywords [en]
Behavioral model, Driver categories, Machine learning, Naturalistic driving data, Representative driving cycles, Road geometry, Behavioral research, Parameterization, Roads and streets, Driver category, Driving behaviors models, Driving cycle, Machine-learning, Parameterized, Representative driving cycle, Traffic simulations
National Category
Vehicle and Aerospace Engineering
Identifiers
URN: urn:nbn:se:vti:diva-19859DOI: 10.4271/2023-01-5033Scopus ID: 2-s2.0-85167570883OAI: oai:DiVA.org:vti-19859DiVA, id: diva2:1792441
2023-08-292023-08-292025-02-14Bibliographically approved