A Reinforcement Learning Modular Control Architecture for Fully Automated Vehicles

  • Jorge Villagrá
  • Vicente Milanés
  • Joshué Pérez
  • Jorge Godoy
  • Enrique Onieva
  • Javier Alonso
  • Carlos González
  • Teresa de Pedro
  • Ricardo Garcia
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6928)

Abstract

This paper proposes a modular and generic architecture to deal with Global Chassis Control. Reinforcement learning is coupled with intelligent PID controllers and an optimal tire effort allocation algorithm to obtain a general, robust, adaptable, efficient and safe control architecture for any kind of automated wheeled vehicle.

Keywords

Active Suspension Advanced Driving Assistance System Fault Tolerant Control Vehicle System Dynamics Control Allocation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chou, H., D’Andréa-Novel, B.: Global vehicle control using differential braking torques and active suspension forces. Vehicle System Dynamics 43(4), 261–284 (2005)CrossRefGoogle Scholar
  2. 2.
    Fliess, M., Join, C.: Intelligent PID Controllers. In: Proc. of 16th Mediterrean Conf. on Control and Automation, Ajaccio, France (2008)Google Scholar
  3. 3.
    Ono, E., Hattoria, Y., Muragishia, Y., Koibuchi, K.: Vehicle dynamics integrated control for four-wheel-distributed steering and four-wheel-distributed traction/braking systems. Vehicle System Dynamics 44(2), 139–151 (2006)CrossRefGoogle Scholar
  4. 4.
    Poussot-Vassal, C., Sename, O., Dugard, L.: A LPV/H ∞  Global Chassis Controller for handling improvements involving braking and steering systems. In: IEEE 47th Conference on Decision and Control, pp. 5366–5371 (2008)Google Scholar
  5. 5.
    Suzumura, M., Fukatani, K., Asada, H.: Current State of and Prospects for the Vehicle Dynamics Integrated Management System (VDIM). Toyota Technical Review 55(222) (2007)Google Scholar
  6. 6.
    Svendenius, J., Gäfvert, M.: A semi-empirical dynamic tire model for combined-slip forces. Vehicle System Dynamics 44(2), 189–208 (2006)CrossRefGoogle Scholar
  7. 7.
    Tondel, P., Johansen, T.A.: Control allocation for yaw stabilization in automotive vehicles using multiparametric nonlinear programming. In: Proc. of the American Control Conference, June 8-10, pp. 453–458 (2005)Google Scholar
  8. 8.
    Villagra, J., d’Andrea-Novel, B., Mounier, H., Pengov, M.: Flatness-Based Vehicle Steering Control Strategy With SDRE Feedback Gains Tuned Via a Sensitivity Approach. IEEE Transactions on Control Systems Technology 15(3), 554–565 (2007)CrossRefGoogle Scholar
  9. 9.
    Villagra, J., Milanes, V., Pérez, J., de Pedro, T.: Control basado en pid inteligentes: Aplicación al control de crucero de un vehículo a bajas velocidades. Revista Iberoamericana de Automática e Informática Industrial 7(4), 44–52 (2010)Google Scholar
  10. 10.
    Wang, X.S., Cheng, Y.H., Sun, W.: A Proposal of Adaptive PID Controller Based on Reinforcement Learning. Journal of China University of Mining and Technology 17(1), 40–44 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Jorge Villagrá
    • 1
  • Vicente Milanés
    • 1
  • Joshué Pérez
    • 1
  • Jorge Godoy
    • 1
  • Enrique Onieva
    • 1
  • Javier Alonso
    • 1
  • Carlos González
    • 1
  • Teresa de Pedro
    • 1
  • Ricardo Garcia
    • 1
  1. 1.Autopia Program, Center for Automation and RoboticsUPM-CSICMadridSpain

Personalised recommendations