Authors:
Andreas Dieing, Gerd Baumann, Kevin Mehre, Martin Kehrer, Hans-Christian Reuss
Keywords:
force feedback, neural network, steering-feel, training and validation, Bayesian optimization
Abstract:
Dieing A.; Baumann D..-I.G.; Mehre K.; Kehrer D..-I.M. and Reuss P.D.H.-C. Optimization of the Steering Feel with Neural Networks for Force Feedback Systems In: Proceedings of the Driving Simulation Conference 2024 Europe VR, Driving Simulation Association, Strasbourg, France, 2024, pp. 153-160
Download .txt file
@inproceedings{Dieing2024,
title = {Optimization of the Steering Feel with Neural Networks for Force Feedback Systems},
author = {Andreas Dieing and Dr.-Ing. Gerd Baumann and Kevin Mehre and Dr.-Ing. Martin Kehrer and Prof. Dr. Hans-Christian Reuss},
editor = {Andras Kemeny and Jean-Rémy Chardonnet and Florent Colombet and Stéphane Espié},
isbn = {978-2-9573777-5-6},
year = {2024},
date = {2024-09-18},
booktitle = {Proceedings of the Driving Simulation Conference 2024 Europe VR},
pages = {153-160},
address = {Strasbourg, France},
organization = {Driving Simulation Association},
abstract = {The steering feel is a key component for a realistic driving experience in driving simulators with force feedback systems. Therefore, it’s necessary to generate a latency-free steering wheel torque, which depicts the real system behaviour. This publication presents a method how to generate a realistic steering feel for the on center area. The reduced steering model is extended with a neural network to build up a hybrid model that contains all necessary physical properties like the Lund-Grenoble friction model, cardan joints, inertias as well as the damping and friction forces on rack level. The parameters were identified through measurements with an electric power steering system on a test bench. The neural network adapts the physical model to depict the frequency dependence and parameter errors caused by inaccurate settings. The dataset, for the supervised learning approach, was measured by using a compact class vehicle with the same steering system as on the test bench and on-center driving maneuvers. The hyperparameters of the neural network are identified by using Bayesian optimization. This hybrid model structure helps to generate a more realistic steering torque and therefore maximizes the immersion in driving simulators.},
keywords = {},
}
Download .bib file
TY - CONF
TI - Optimization of the Steering Feel with Neural Networks for Force Feedback Systems
AU - Dieing, Andreas
AU - Baumann, Dr. -Ing. Gerd
AU - Mehre, Kevin
AU - Kehrer, Dr. -Ing. Martin
AU - Reuss, Prof. Dr. Hans-Christian
C1 - Strasbourg, France
C3 - Proceedings of the Driving Simulation Conference 2024 Europe VR
DA - 2024/09/18
PY - 2024
SP - 153
EP - 160
LA - en-US
PB - Driving Simulation Association
SN - 978-2-9573777-5-6
L2 - https://proceedings.driving-simulation.org/proceeding/dsc-2024/optimization-of-the-steering-feel-with-neural-networks-for-force-feedback-systems
ER -
Download .ris file
Cite this article
Copyright by the authors.
Licensee Driving Simulation Association.
Terms and Conditions for Downloading Driving Simulation Proceedings papers:
By downloading a scientific paper from proceedings.driving-simulation.org, you agree to the following terms and conditions:
- Copyright and Ownership:
The scientific paper is protected by copyright laws and is the intellectual property of the respective authors and publishers. All rights not expressly granted herein are reserved.
- Citation and Attribution:
If you use the scientific paper for research, presentations, or any other non-commercial purposes, you must provide appropriate citation and attribution to the original authors as per academic standards.
- Creative Commons:
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
- Disclaimer:
The Driving Simulation Association makes no representations or warranties regarding the accuracy, completeness, or suitability of the scientific paper for any particular purpose. The paper is provided as-is, without any warranties, express or implied. The Driving Simulation Association reserves the right to terminate or restrict access to the scientific paper at any time and without notice.