Artificial intelligence (AI) and data science techniques are integral to modern Engineering research, and this also holds for Automotive Engineering (AE). In this context, given the growing need to analyze relatively extensive datasets obtained from vehicle instrumentation and simulator use, this study aims to explore the relationship between drivers’ subjective assessments (SA) regarding vehicle dynamic behavior and its objective metrics (OM). To make this feasible, resources such as deep neural networks (DNN), virtual car models developed in VI-CarRealTime (VI-CRT) software, and 25 human drivers using a dynamic simulator with 9 degrees of freedom, the VI-Grade Driver in Motion (DiM) 150; were needed. By leveraging data from both virtual simulations and human drivers, the DNN demonstrated its ability to standardize vehicle evaluations across individuals with varying experience levels, ensuring a more consistent mapping between objective metrics and subjective assessments, and presenting satisfactory accuracy of around 90%. While one of the key outcomes of this paper is the capacity to evaluate the vehicle independently of driver subjectivity, another crucial one is the system’s ability to rely on less experienced drivers for vehicle classification. Also, another contribution is the significant reduction in vehicle development time and costs. Overall, this work advances vehicle evaluation by harmonizing subjective and objective assessments, fostering innovation in Automotive Engineering.
SchurmannRLionASchickB, et al. Objectification and prediction of the subjective criticality of axle damages using artificial neural networks as well as multibody- and real-time simulations. Int J Veh Perform2023; 9: 376–403.
2.
SeredynskiP. Multimatic opening new Michigan virtual vehicle-dynamics development center. SAE International, 2020.
3.
DiasCLandreJ. Vehicle dynamics response due to the adjustment of K&C parameters with the aid of a dynamic simulator with 9 DOF and a correlated virtual model. Proc Inst Mech Eng D: J Automob Eng2023; 237(10–11): 2616–2631.
4.
VI-GRADE. VI-Grade provides to FCA Latam and PUC Minas the first dynamic driving simulator to be ever installed in Latin America. VI-GRADE, 2021.
5.
Dell’AnnunziataGNArricaleVMFarroniF, et al. Estimation of vehicle longitudinal velocity with artificial neural network. Sensors2022; 22: 9516.
6.
PaszkielS. The use of facial expressions identified from the level of the EEG signal for controlling a mobile vehicle based on a state machine. In: SzewczykRZielińskiCKaliczyńskaM (eds.) Automation 2020: towards industry of the future. Springer, 2020, pp.227–238.
7.
SerjeDAcuñaE. Driving and flying simulators: a review on relevant considerations and trends. Transp Res Rec2022; 2676: 551–570.
8.
AoDLiJ. Subjective assessment for an advanced driver assistance system: a case study in China. J Intell Connect Veh2022; 5: 112–122.
9.
RaabeJFontanaFNeubeckJ, et al. Contribution to the objective evaluation of combined longitudinal and lateral vehicle dynamics in nonlinear driving range. SAE Int J Veh Dyn Stab NVH2023; 7(4): 533–554.
10.
KumarASällströmESebbenS, et al. Prediction of drivers’ subjective evaluation of vehicle reaction under aerodynamic excitations. Hum Factors2024; 66(5), 1600–1615.
11.
KimDJeongMBaeB, et al. Design of a human evaluator model for the ride comfort of vehicle on a speed bump using a neural artistic style extraction. Sensors2019; 19(24): 5407.
12.
ZhaoJLiuJYangL, et al. Exploring the relationships between subjective evaluations and objective metrics of vehicle dynamic performance. J Adv Transp2018; 2018: 2638474.
13.
KimDJeongMBaeB, et al. Design of a human evaluator model for the ride comfort of vehicle on a speed bump using a neural artistic style extraction. Sensors2019; 19: 5407.
14.
Gil GómezGLNybackaMDruggeL, et al. Machine learning to classify and predict objective and subjective assessments of vehicle dynamics: the case of steering feel. Veh Syst Dyn2018; 56: 150–171.
15.
DiasCARLandreJJúnior. The use of artificial intelligence in driver-in-the-loop simulation: a literature review. Aus J Mech Eng2025; 23(1), 161–169.
16.
GuastadisegniGDe PintoSCancelliD, et al. Ride analysis tools for passenger cars: objective and subjective evaluation techniques and correlation processes – a review. Veh Syst Dyn2024; 62(7), 1876–1902.
17.
PagliarecciNZimmerFBiroucheA, et al. Test methodology for the vehicle-tire handling performance evaluation: objectification of driver’s subjective assessment. IFAC-PapersOnLine2020; 53: 14394–14400.
18.
ZhangXTangSGuoK, et al. Vehicle handling indexes mining and consistency of subjective and objective evaluation. In: KlompMBruzeliusFNielsenJHillemyrA (eds.) Advances in dynamics of vehicles on roads and tracks. Springer, 2020, pp.1302–1312. Springer.
19.
AoDWongPKHuangW, et al. Analysis of co-relation between objective measurement and subjective assessment for dynamic comfort of vehicles. Int J of Automot Technol2020; 21: 1553–1567.
20.
ZhouWGuoXZhangC, et al. A novel objective evaluation method of drivability for passenger cars considering subjective and objective consistency. Proc Inst Mech Eng D: J Automob Eng2023; 237: 607–621.
21.
AshH. Correlation of subjective and objective handling of vehicle behaviour. PhD Thesis, University of Leeds, UK, 2002.
22.
GómezGNybackaMDruggeL, et al. Machine learning to classify and predict objective and subjective assessments of vehicle dynamics: the case of steering feel. Veh Syst Dyn2018; 56(1): 150–171.
23.
GómezGNybackaMBakkerE, et al. Objective metrics for vehicle handling and steering and their correlations with subjective assessments. Int J Automot Technol2016; 17: 777–794.
24.
JamsonA. Motion cueing in driving simulators for research applications. PhD Thesis, University of Leeds, UK, 2010.
25.
BruschettaMMinenD. Advanced features to make Dynamic Driving Simulators suitable for studies on Assisted and Autonomous Driving. In: Assisted and autonomous driving on driving simulators. Springer, 2019, pp. VD1, 1–14.
26.
VepaR. Flight dynamics, simulation, and control: for rigid and flexible aircraft, first. CRC Press, 2015.
27.
DiasC. Análise da taxa de esterçamento de um modelo automotivo correlacionado em K&C em um simulador driver-in-the-loop. MSc Thesis, Pontifícia Universidade Católica de Minas Gerais, Brazil, 2015.
28.
DiasCLandreJPimenta LF deC, et al. Braking system analysis with the aid of a dynamic vehicle simulator with nine degrees of freedom. Aus J Mech Eng2025; 23(3), 447–456.
29.
DiasCARLandreJJr. Have we reached satisfactory methodologies to approach the subjectivity in driver-in-the-loop simulators? A systematic review. Simulation2025; 101(10): 1077–1092.
30.
MancaR. Design and implementation of an Electric Power Steering system for a Formula Student Driverless vehicle. Master’s Thesis, Politecnico di Torino, Italy, 2020.
31.
MassaroMLimebeerDJN. Minimum-lap-time optimisation and simulation. Veh Syst Dyn2021; 59:1069–1113.
32.
NoviTLinigerACapitaniR, et al. Real-time control for at-limit handling driving on a predefined path. Veh Syst Dyn2020; 58: 1007–1036.
33.
Society of Automotive Engineers. SAE J 1441-2016: subjective rating scale for vehicle ride and handling. SAE J 1441-2016, 2016.
34.
AssegieTAElanangaiVPaulrajJS, et al. Evaluation of feature scaling for improving the performance of supervised learning methods. Bull Electric Eng Inform2023; 12: 1833–1838.
35.
GéronA. Hands-on machine learning with Scikit-learn and TensorFlow. O’Reilly Media, Inc., 2017.
36.
KoutsoukasAMonaghanKJLiX, et al. Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data. J Cheminform2017; 9: 1–13.
XiangXZengJDingX, et al. Research on vehicle comfort testing and evaluation based on the characterization of passenger motion sickness degree. In: BalochZPiccalugaPP (eds.) Third international conference on biomedical and intelligent systems (IC-BIS 2024), Nanchang, China, 22–24 March 2024, p 112. SPIE.
39.
QuezadaVNicolasM. Comprehensive assessment of comfort (motion sickness) in vehicles. Examensarbete för masterexamen. Master’s Thesis, Chalmers University of Technology, Sweden, 2024.
40.
LucasGKemenyAPaillotD, et al. A simulation sickness study on a driving simulator equipped with a vibration platform. Transp Res Part F Traffic Psychol Behav2020; 68: 15–22.
41.
Liu-HenkeXGollnerMJacobitzS, et al. Driving-simulator-in-the-loop—virtual function design with consideration of human behaviour. In: 2020 IEEE international symposium on systems engineering (ISSE), Vienna, Austria, 12 October–12 November 2020, pp.1–6. IEEE.
42.
CholletF. Deep learning with python. Manning Publications Co., 2018.
43.
UstebaySTurgutZAydinMA. Cyber attack detection by using neural network approaches: shallow neural network, deep neural network and autoencoder. In: GajPSawickiMKwiecieńA (eds.) Computer networks, Springer, 2019. pp.144–155.
44.
MengJDasguptaA. MEMS packaging reliability in board-level drop tests under severe shock and impact loading conditions—part II: fatigue damage modeling. IEEE Trans Compon Packaging Manuf Technol2016; 6: 1604–1614.
45.
BauDZhuJ-YStrobeltH, et al. Understanding the role of individual units in a deep neural network. Proc Natl Acad Sci U S A2020; 117: 30071–30078.
