Machine learning to classify and predict objective and subjective assessments of vehicle dynamics: the case of steering feel

ABSTRACT

Objective measurements and computer-aided engineering simulations cannot be exploited to their full potential because of the high importance of driver feel in vehicle development. Furthermore, despite many studies, it is not easy to identify the relationship between objective metrics (OM) and subjective assessments (SA), a task further complicated by the fact that SA change between drivers and geographical locations or with time. This paper presents a method which uses two artificial neural networks built on top of each other that helps to close this gap. The first network, based solely on OM, generates a map that groups together similar vehicles, thus allowing a classification of measured vehicles to be visualised. This map objectively demonstrates that there exist brand and vehicle class identities. It also foresees the subjective characteristics of a new vehicle, based on its requirements, simulations and measurements. These characteristics are described by the neighbourhood of the new vehicle in the map, which is made up of known vehicles that are accompanied by word-clouds that enhance this description. This forecast is also extended to perform a sensitivity analysis of the tolerances in the requirements, as well as to validate previously published preferred range of steering feel metrics. The results suggest a few new modifications. Finally, the qualitative information given by this measurement-based classification is complemented with a second superimposed network. This network describes a regression surface that enables quantitative predictions, for example the SA of the steering feel of a new vehicle from its OM.

KEYWORDS:

• Objective metrics
• driver preference
• subjective assessments
• artificial neural network
• regression analysis
• steering feel
• vehicle dynamics

Acknowledgements

The authors would like to thank Volvo Car Corporation and all the people who have helped in collecting the data.

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

Gaspar L. Gil Gómez http://orcid.org/0000-0002-6699-1965

Mikael Nybacka http://orcid.org/0000-0002-2265-9004

Lars Drugge http://orcid.org/0000-0001-8928-0368

Additional information

Funding

The authors would also like to gratefully acknowledge the financial support received from TRENoP (Transport Research Environment with Novel Perspectives) at KTH (the Royal Institute of Technology) in Stockholm and the FFI – Strategic Vehicle Research and Innovation [2012-04609] funding programme.