Authors:
Ansgar Trächtler, Julia Timmermann, Keno Pape, Kevin Malena
Keywords:
Interactive Driving Simulation, LSTM, motion cueing, Physics-Guided Learning, Reference Prediction
Abstract:
Pape K.; Malena K.; Timmermann J. and Trächtler A. Learning-Based Acceleration Prediction for Real-Time Model Predictive Motion Cueing In: Proceedings of the Driving Simulation Conference 2026 Europe XR, Driving Simulation Association, Antibes, France, 2026, pp. 75 - 82
Download .txt file
@inproceedings{Pape2026,
title = {Learning-Based Acceleration Prediction for Real-Time Model Predictive Motion Cueing},
author = {Keno Pape and Kevin Malena and Julia Timmermann and Ansgar Trächtler},
editor = {Andras Kemeny and Jean-Rémy Chardonnet and Florent Colombet and Stéphane Espié},
doi = {https://doi.org/10.82157/dsa/2026/10},
isbn = {978-2-9573777-9-4},
year = {2026},
date = {2026-09-16},
booktitle = {Proceedings of the Driving Simulation Conference 2026 Europe XR},
volume = {11},
pages = {75 - 82},
address = {Antibes, France},
organization = {Driving Simulation Association},
abstract = {Interactive driving simulation relies on dynamic simulators whose motion systems are controlled by motion cueing algorithms. Model predictive motion cueing algorithms are particularly promising, but exploiting their full potential requires future motion references. These are not directly available because future vehicle motion depends on unknown driver intent. This paper introduces a hybrid predictor for longitudinal and lateral acceleration references that combines structured physics-based preview information with data-driven, driver-specific prediction. The framework comprises a rule- and physics-based SpeedPreviewer, physics-guided feature construction, and a long short-term memory (LSTM) predictor. It is evaluated in simulation regarding prediction accuracy, acceleration reproduction within the model predictive motion cueing algorithm, and real-time capability. The results show good prediction accuracy, consistent transfer to unseen road, and promising transfer to different driver types. Compared with a constant reference, the predictor improves acceleration reproduction, particularly in longitudinal dynamics, while meeting real-time requirements},
keywords = {},
}
Download .bib file
TY - CONF
TI - Learning-Based Acceleration Prediction for Real-Time Model Predictive Motion Cueing
AU - Pape, Keno
AU - Malena, Kevin
AU - Timmermann, Julia
AU - Trächtler, Ansgar
C1 - Antibes, France
C3 - Proceedings of the Driving Simulation Conference 2026 Europe XR
DA - 2026/09/16
PY - 2026
SP - 75
EP - 82
LA - en-US
PB - Driving Simulation Association
SN - 978-2-9573777-9-4
L2 - https://proceedings.driving-simulation.org/proceeding/dsc-2026/learning-based-acceleration-predictionfor-real-time-model-predictive-motion-cueing
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.