Hostname: page-component-848d4c4894-sjtt6 Total loading time: 0 Render date: 2024-06-14T16:01:35.511Z Has data issue: false hasContentIssue false
  • English
  • Français

Minimizing occupant loads in vehicle crashes through reinforcement learning-based restraint system design: assessing performance and transferability

Published online by Cambridge University Press:  16 May 2024

Janis Mathieu ,
Parul Gupta ,
Michael Di Roberto  and
Michael Vielhaber
Janis Mathieu*
Affiliation:
Porsche Engineering Group GmbH, Germany Saarland University, Germany
Parul Gupta
Affiliation:
Ilmenau University of Technology, Germany
Michael Di Roberto
Affiliation:
Porsche Engineering Group GmbH, Germany
Michael Vielhaber
Affiliation:
Saarland University, Germany
*
janis.mathieu@porsche-engineering.de

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

The optimization of mechanical behavior in safety systems during crash scenarios consistently poses challenges in vehicle development. Hence, a reinforcement learning-based approach for optimizing restraint systems in frontal impacts is proposed. The trained agent, which adjusts five parameters simultaneously, is capable of minimizing loads on a seen and unseen anthropomorphic test device on the co-driver position and is thus able of transferring knowledge. A hundred times higher rate of convergence to reach a similar optimum compared to a global optimization algorithm has been achieved.

Keywords

data-driven designcomputational design methodsoccupant safetyoptimization
Type
Artificial Intelligence and Data-Driven Design
Information
Proceedings of the Design Society , Volume 4: DESIGN 2024 , May 2024 , pp. 2139 - 2148
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2024.

References

Beyer, F., Schneider, D. and Schumacher, A. (2021), “Finding three-dimensional layouts for crashworthiness load cases using the graph and heuristic based topology optimization”, Structural and Multidisciplinary Optimization, Vol. 63, pp. 1-15. https://doi.org/10.1007/s00158-020-02768-0CrossRefGoogle Scholar
Beysolow, T. II (2019), Applied Reinforcement Learning with Python, Apress, New York. https://doi.org/10.1007/978-1-4842-5127-0CrossRefGoogle Scholar
Brown, N., Garland, A., Fadel, G. and Li, G. (2022), “Deep reinforcement learning for engineering design through topology optimization of elementally discretized design domains”, Materials & Design, Vol. 218, pp. 110672. https://doi.org/10.1016/j.matdes.2022.110672CrossRefGoogle Scholar
Gonter, M., Knoll, P., Leschke, A., Seiffert, U. and Weinert, F. (2021), “Fahrzeugsicherheit”, In: Pischinger, S. and Seiffert, U. (Ed.), Vieweg Handbuch Kraftfahrzeugtechnik. ATZ/MTZ-Fachbuch, Springer Vieweg, Wiesbaden, pp. 1073-1160. https://doi.org/10.1007/978-3-658-25557-2_9Google Scholar
Hayashi, K. and Ohsaki, M. (2020), “Reinforcement learning for optimum design of a plane frame under static loads”, Engineering with Computers, Vol. 37, pp. 1999–2011. https://doi.org/10.1007/s00366-019-00926-7CrossRefGoogle Scholar
Hayashi, K. and Ohsaki, M. (2022), “Graph-based reinforcement learning for discrete cross-section optimization of planar steel frames”, Advanced Engineering Informatics, Vol. 51, pp. 101512. https://doi.org/10.1016/j.aei.2021.101512.CrossRefGoogle Scholar
Horii, H. (2017), “Multi-objective Optimization of Vehicle Occupant Restraint System by Using Evolutionary Algorithm with Response Surface Model”, International Journal of Computational Methods and Experimental Measurements, Vol. 5, No. 2, pp. 163-173. https://doi.org/10.2495/CMEM-V5-N2-163-170CrossRefGoogle Scholar
Huang, Y., Zhou, Q., Zhang, X. and Wang, C. (2015), “Optimization study of occupant restraint system concerning variations in occupant size and crash severity in frontal collisions”, International Journal of Vehicle Safety, Vol. 8. https://doi.org/10.1504/IJVS.2015.074373CrossRefGoogle Scholar
Joodaki, H., Gepner, B. and Kerrigan, J. (2021), “Leveraging machine learning for predicting human body model response in restraint design simulations”, Computer Methods in Biomechanics and Biomedical Engineering, Vol. 24, No. 6, pp. 597-611. https://doi.org/10.1080/10255842.2020.1841754CrossRefGoogle ScholarPubMed
Kracker, D., Dhanasekaran, R. K., Schumacher, A. and Garcke, J. (2023), “Method for automated detection of outliers in crash simulations”, International Journal of Crashworthiness, Vol. 28, No. 1, pp. 96–107. https://doi.org/10.1080/13588265.2022.2074634CrossRefGoogle Scholar
Langen, T., Falk, K., and Mansouri, M. (2022), “A Systems Thinking Approach to Data-Driven Product Development”, Proceedings of the Design Society, Vol. 2: DESIGN2022, May 2022, The Design Society, Glasgow, pp. 1915-1924. https://doi.org/10.1017/pds.2022.194CrossRefGoogle Scholar
Muhl, P., Rudolf, S. (2022), “Data-Driven Calibration of Thermal Management Control Systems of an Electric Sports Car”, 31. Aachen Colloquium Sustainable Mobility, Aachen, 2022.Google Scholar
Rabus, M., Belaid, M. K., Maurer, S., and Hiermaier, A., S. (2022), “Development of a model for the prediction of occupant loads in vehicle crashes: introduction of the Real Occupant Load Criterion for Prediction (ROLCp)”, Automotive and Engine Technology, Vol. 7, No. 3–4, pp. 229–244, Dec. 2022. https://doi.org/10.1007/s41104-022-00111-xCrossRefGoogle Scholar
Rudolf, T., Schürmann, T., Skull, M., Schwab, S. and Hohmann, S. (2022), “Data-Driven Automotive Development: Federated Reinforcement Learning for Calibration and Control”, 22. Internationales Stuttgarter Symposium, Springer Fachmedien, Wiesbaden, pp. 369–384. https://doi.org/10.1007/978-3-658-37009-1_26CrossRefGoogle Scholar
Schuhmacher, A. (2020), Optimierung mechanischer Strukturen, (3rd ed.), Springer Vieweg Berlin Heidelberg, Berlin. https://doi.org/10.1007/978-3-662-60328-4CrossRefGoogle Scholar
Sutton, S. and Barto, A. (2018), Reinforcement Learning: An Introduction, (2nd ed.), A Bradford Book, Cambridge.Google Scholar
Thiele, M., Mullerschön, H., van den Hove, M. and Mlekusch, B. (2006), “Optimization of an Adaptive Restraint System Using LS-OPT and Visual Exploration of the Design Space Using D-SPEX”, 9th International LS-DYNA Users Conference, Detroit, 2006.Google Scholar
Trilling, J., Schumacher, A. and Zhou, M. (2022), “Einsatz von Reinforcement Learning zur lokalen Versteifung von Extrusionsprofilen in Crashlastfällen”, Zeitschrift für numerische Simulation und angrenzende Gebiete, NAFEMS-Online-Magazin, Vol. 62, pp. 59-70, Feb. 2022.Google Scholar
Trilling, J., Schuhmacher, A., Zhou, M. (2022), “Einsatz von Reinforcement Learning zur lokalen Versteigung von Extrusionsprofilen in Crashlaställen”, NAFEMS Magazin, Vol. 61,Google Scholar
Xue, Z., Parashar, S., Li, G. and Fu, Y. (2012), “Optimization Strategies to Explore Multiple Optimal Solutions and Its Application to Restraint System Design”, SAE International Journal of Passenger Cars - Mechanical Systems, Vol. 5, No. 1, pp. 540–551. https://doi.org/10.4271/2012-01-0578CrossRefGoogle Scholar