Identification of Subjective-Objective Vehicle Handling Links Using Neural Networks for the Foresight Vehicle 2002-01-1126
The paper describes the application of neural networks to understand the links between test drivers' subjective ratings of vehicle handling and measurable vehicle performance metrics as part of the Foresight Vehicle initiative. The shortcomings of classical linear methods used in previous studies (Crolla et al [1, 2 and 3]) are described along with the processes and developments made in a genetic algorithm based methodology used to find the predominantly non-linear links between subjective and objective handling. The techniques used were designed to make allowances for noise and other distractions inherent within drivers' subjective ratings. Further insights into the preferred ranges of the values of important vehicle handling metrics are presented.
Citation: King, R., Crolla, D., Ash, H., and Whitehead, J., "Identification of Subjective-Objective Vehicle Handling Links Using Neural Networks for the Foresight Vehicle," SAE Technical Paper 2002-01-1126, 2002, https://doi.org/10.4271/2002-01-1126. Download Citation
Author(s):
R. P. King, D. A. Crolla, H. A. S. Ash, J. Whitehead
Affiliated:
University of Leeds., MIRA Ltd.
Pages: 11
Event:
SAE 2002 World Congress & Exhibition
ISSN:
0148-7191
e-ISSN:
2688-3627
Also in:
Foresight Vehicle Technology: Design, ITS, Safety, Electronics, and Materials-SP-1695, SAE 2002 Transactions Journal of Passenger Cars - Electronic and Electrical Systems-V111-7
Related Topics:
Vehicle handling
Neural networks
Vehicle performance
Vehicle drivers
Vehicle networking
Mathematical models
SAE MOBILUS
Subscribers can view annotate, and download all of SAE's content.
Learn More »
