手机体育投注平台

Advertisement

Application of Artificial Neural Networks for Active Roll Control Based on Actor-Critic Reinforcement Learning

  • Matthias BahrEmail author
  • Sebastian Reicherts
  • Philipp Sieberg
  • Luca Morss
  • Dieter Schramm
Conference paper
  • 36 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1260)

Abstract

手机体育投注平台This work shows the application of artificial neural networks for the control task of the roll angle in passenger cars. The training of the artificial neural network is based on the specific actor-critic reinforcement learning training algorithm. It is implemented and trained utilizing the Python API for TensorFlow and set up in a co-simulation with the vehicle simulation realized in IPG CarMaker via MATLAB/Simulink to enable online learning. Subsequently it is validated in different representative driving maneuvers. For showing the practicability of the resulting neural controller it is also validated for different vehicle classes with respect to their corresponding structure, geometries and components. An analytical approach to adjust the resulting controller to various vehicle bodies dependent on physical correlations is presented.

Keywords

Artificial neural network Machine learning Actor-critic Reinforcement learning Active roll control Vehicle dynamics 

References

  1. 1.
    Sieberg, P., Schmid, M., Reicherts, S., Schramm, D.: Computation time optimization of a model-based predictive roll stabilization by neuro-fuzzy systems. In: Bargende, M., Reuss, H.-C., Wagner, A., Wiedemann, J. (eds.) 19. Internationales Stuttgarter Symposium, pp. 499–512. Springer, Wiesbaden (2019)
  2. 2.
    Boada, M., Boada, B., Gauchia Babe, A., Calvo, J., Diaz, V.: Active roll control using reinforcement learning for a single unit heavy vehicle. Int. J. Heavy Veh. Syst. 16(4), 412–430 (2009)
  3. 3.
    Fu, Z.-J., Li, B., Ning, X.-B., Xie, W.-D.: Online Adaptive optimal control of vehicle active suspension systems using single-network approximate dynamic programming. Math. Probl. Eng. 2017 (2017). 9 p.
  4. 4.
    Bahr, M., Reicherts, S., Sieberg, P., Morss, L., Schramm, D.: Development and validation of active roll control based on actor-critic neural network reinforcement learning. In: Proceedings of the 9th International Conference on Simulation and Modeling Methodologies, Technologies and Applications, pp. 36–46. SCITEPRESS, Prague (2019)
  5. 5.
    Schramm, D., Hiller, M., Bardini, R.: Vehicle Dynamics – Modeling and Simulation, 2nd edn. Springer, Heidelberg (2018)
  6. 6.
    Ammon, D.: Modellbildung und Systementwicklung in der Fahrzeugdynamik. Vieweg+Teubner, Stuttgart (2013)
  7. 7.
    Konda, V., Tsitsiklis, J.: Actor-critic algorithms. SIAM J. Control Optim. 42(4), 1143–1166 (2003)
  8. 8.
    Sutton, R., Barto, A.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press, London (2018)
  9. 9.
    Sutton, R., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: NIPS 1999 Proceedings of the 12th International Conference on Neural Information Processing Systems, pp. 1057–1063. The MIT Press, Cambridge (1999)
  10. 10.
    Szepesvári, C.: Algorithms for Reinforcement Learning, 1st edn. Morgan & Claypool Publishers, New York (2010)
  11. 11.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations, p. 13. arXiv.org, Ithaca New York (2015)
  12. 12.
    IPG Automotive’s Official Website. . Accessed 09 Feb 2019
  13. 13.
    MathWorks’ Official Website. . Accessed 09 Feb 2019
  14. 14.
    TensorFlow’s Official Website. . Accessed 09 Feb 2019
  15. 15.
    REGULATION (EC) No 139/2004. . Accessed 08 Dec 2019

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  • Matthias Bahr
    • 1
    Email author
  • Sebastian Reicherts
    • 2
  • Philipp Sieberg
    • 2
  • Luca Morss
    • 3
  • Dieter Schramm
    • 2
  1. 1.The Hydrogen and Fuel Cell Center ZBT GmbHDuisburgGermany
  2. 2.Chair of MechatronicsUniversity of Duisburg-EssenDuisburgGermany
  3. 3.Vodafone GmbHDusseldorfGermany

Personalised recommendations