Validación del modelo de un vehículo autónomo guiado mediante un controlador inteligente

  1. Argente Mena, Javier 1
  2. Sierra Garcia, Jesus Enrique 2
  3. Santos Peña, Matilde 3
  1. 1 Facultad de Informática, Universidad Complutense de Madrid
  2. 2 a:1:{s:5:"es_ES";s:21:"Universidad de Burgos";}
  3. 3 Universidad Complutense de Madrid
    info

    Universidad Complutense de Madrid

    Madrid, España

    ROR 02p0gd045

Show affiliations +
Journal:
Jornadas de Automática
  1. Cruz Martín, Ana María (coord.)
  2. Arévalo Espejo, V. (coord.)
  3. Fernández Lozano, Juan Jesús (coord.)

ISSN: 3045-4093

Year of publication: 2024

Issue: 45

Type: Article

DOI: 10.17979/JA-CEA.2024.45.10910 DIALNET GOOGLE SCHOLAR lock_openOpen access editor

Abstract

In this work a conventional control, which has been tuned using a heuristic strategy, is applied to a model of an Automated Guided Vehicle (AGV). The dynamic model of the AGV has been extended by including the modeling of the motors, and the causality of the equations has been identified to facilitate its computational implementation. The genetic algorithm (GA) cost function used to adjust the trajectory tracking controller parameters has been defined based on two criteria: tracking error and penalizing the aggressiveness of the control action. By means of simulation it has been tested, on a sinusoidal trajectory, that the implemented control scheme, both speed and navigation, work correctly.

Bibliographic References

  • Abajo, M. R., Sierra-García, J. E., Santos, M., 2022. Evolutive tuning optimization of a pid controller for autonomous path-following robot. In: 16th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2021). Springer, pp. 451–460. DOI: https://doi.org/10.1007/978-3-030-87869-6_43
  • Espinosa, F., Santos, C., Sierra-García, J., 2020. Transporte multi-agv de una carga: estado del arte y propuesta centralizada. Revista Iberoamericana de Autom´atica e Inform´atica industrial 18 (1), 82–91. DOI: https://doi.org/10.4995/riai.2020.12846
  • Ghorbal, K., 2017. Modeling physics with differential-algebraic equations.
  • Martín Villalaba, C., Urquía Moraleda, A., 2018. Modeling and simulation in engineering using Modelica. Universidad Nacional de Educación a Distancia.
  • Moshayedi, A. J., Li, J., Sina, N., Chen, X., Liao, L., Gheisari, M., Xie, X., 2022. Simulation and validation of optimized pid controller in agv (automated guided vehicles) model using pso and bas algorithms. Computational Intelligence and Neuroscience 2022. DOI: https://doi.org/10.1155/2022/7799654
  • Reis, W. P. N. d., Couto, G. E., Junior, O. M., 2023. Automated guided vehicles position control: a systematic literature review. Journal of Intelligent Manufacturing 34 (4), 1483–1545. DOI: https://doi.org/10.1007/s10845-021-01893-x
  • Sánchez, R., Sierra-García, J. E., Santos, M., 2022. Modelado de un agv híbrido triciclo-diferencial. Revista Iberoamericana de Autom´atica e Informática industrial 19 (1), 84–95. DOI: https://doi.org/10.4995/riai.2021.14622
  • Sierra-Garcia, J. E., Santos, M., 2024a. Combining reinforcement learning and conventional control to improve automatic guided vehicles tracking of complex trajectories. Expert Systems 41 (2), e13076. DOI: https://doi.org/10.1111/exsy.13076
  • Sierra-Garcia, J. E., Santos, M., 2024b. Federated discrete reinforcement learning for automatic guided vehicle control. Future Generation Computer Systems 150, 78–89. DOI: https://doi.org/10.1016/j.future.2023.08.021
Data source: Dialnet