Authors:
Stefan Hörmann, Eduard Comulada Simpson, Mohammad Bahram
Keywords:
steering wheel torque modeling, neural networks
Abstract:
On the road the driver is provided with a force feedback through the steering wheel, enabling him or her to perceive road conditions. In order to develop a realistic driving simulation environment a viable steering wheel torque model is a key factor. In contrast to state-of-the-art steering wheel torque models a novel machine learning-based approach is employed. This novel approach does not rely on expert knowledge for dependency identification and parameter tuning since the proposed generic model adapts to the parameters of a specific car type automatically via training. We demonstrate how a steering wheel torque model is generated using neural networks supplied with training data, which was recorded from selected predefined driving maneuvers. The proposed model shows superior generalization performance since the predefined maneuvers allow the model to accurately predict the torque for unknown inputs. With the help of a novel evaluation method based on the perception threshold of the steering wheel torque, the overall percentage of test data causing noticeable errors amounts to 6.6%. Our proposed approach allows the adoption of the generic steering wheel torque model to any given car type with manageable effort.
Hörmann S.; Comulada Simpson E. and Bahram M. A generic Steering Wheel Torque Model using Neural Networks In: Proceedings of the Driving Simulation Conference 2017 Europe VR, Driving Simulation Association, Stuttgart, Germany, 2017, pp. 43-50
Download .txt file
@inproceedings{Hörmann2017,
title = {A generic Steering Wheel Torque Model using Neural Networks},
author = {Stefan Hörmann and Comulada Simpson, Eduard and Mohammad Bahram},
editor = {Andras Kemeny and Florent Colombet and Frédéric Merienne and Stéphane Espié},
issn = {0769-0266},
year = {2017},
date = {2017-09-06},
booktitle = {Proceedings of the Driving Simulation Conference 2017 Europe VR},
pages = {43-50},
address = {Stuttgart, Germany},
organization = {Driving Simulation Association},
abstract = {On the road the driver is provided with a force feedback through the steering wheel, enabling him or her to perceive road conditions. In order to develop a realistic driving simulation environment a viable steering wheel torque model is a key factor. In contrast to state-of-the-art steering wheel torque models a novel machine learning-based approach is employed. This novel approach does not rely on expert knowledge for dependency identification and parameter tuning since the proposed generic model adapts to the parameters of a specific car type automatically via training. We demonstrate how a steering wheel torque model is generated using neural networks supplied with training data, which was recorded from selected predefined driving maneuvers. The proposed model shows superior generalization performance since the predefined maneuvers allow the model to accurately predict the torque for unknown inputs. With the help of a novel evaluation method based on the perception threshold of the steering wheel torque, the overall percentage of test data causing noticeable errors amounts to 6.6%. Our proposed approach allows the adoption of the generic steering wheel torque model to any given car type with manageable effort.},
keywords = {neural networks, steering wheel torque modeling},
}
Download .bib file
TY - CONF
TI - A generic Steering Wheel Torque Model using Neural Networks
AU - Hörmann, Stefan
AU - Comulada Simpson, Eduard
AU - Bahram, Mohammad
C1 - Stuttgart, Germany
C3 - Proceedings of the Driving Simulation Conference 2017 Europe VR
DA - 2017/09/06
PY - 2017
SP - 43
EP - 50
LA - en-US
PB - Driving Simulation Association
SN - 0769-0266
L2 - https://proceedings.driving-simulation.org/proceeding/dsc-2017/a-generic-steering-wheel-torque-model-using-neural-networks
ER -
Download .ris file
Cite this article
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:
- Personal Use Only:
The scientific paper provided on this website is solely for personal, educational, and non-commercial use. You may download and use the paper for your own reference and research purposes only.
- No Reproduction or Distribution:
You may not reproduce, distribute, transmit, publish, or otherwise make the paper available to any third party in any form, whether for commercial or non-commercial purposes, without the express written consent of the Driving Simulation Association.
- 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.
- No Modification:
You may not modify, alter, or adapt the content of the scientific paper in any way.
- 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.