Controlador PD con Compensación Neuro-Adaptable Aplicado a la Dinámica de un RMR Omnidireccional

Resumen: El esquema presentado en este artículo es un controlador neuro-adaptable para solucionar el problema de seguimiento de trayectoria de un robot móvil con ruedas mecanum omnidireccionales suponiendo incertidumbres paramétricas. Los pesos de la red neuronal artificial se actualizan en línea utilizando filtrado del error y leyes adaptables. El controlador neuro-adaptable se valida en simulación y se compara con un PID clásico obteniendo mejores resultados para el esquema propuesto.

¿Cómo citar?

S. Lopez, Miguel A. Llama & Ramon Garcia-Hernandez. Controlador PD con Compensación Neuro-Adaptable Aplicado a la Dinámica de un RMR Omnidireccional. Memorias del Congreso Nacional de Control Automático, pp. 803-808, 2019.

Palabras clave

Redes Neuronales, Robótica y Mecatrónica, Control de Sistemas No Lineales

• Alakshendra, V. y Chiddarwar, S.S. (2017a). Adaptive robust control of mecanum-wheeled mobile robot with uncertainties. Nonlinear Dynamics, 87(4), 2147–2169.
• Alakshendra, V. y Chiddarwar, S.S. (2017b). Simultaneous balancing and trajectory tracking control for an omnidirectional mobile robot with a cylinder using switching between two robust controllers. International Journal of Advanced Robotic Systems, 14(6), 1729881417738728. doi:10.1177/1729881417738728.
• Borisov, A.V., Kilin, A.A., y Mamaev, I.S. (2015). Dynamics and control of an omniwheel vehicle. Regular and Chaotic Dynamics, 20(2), 153–172.
• Campion, G., Bastin, G., y Dandrea-Novel, B. (1996). Structural properties and classification of kinematic and dynamic models of wheeled mobile robots. IEEE Transactions on Robotics and Automation, 12(1), 47– 62. doi:10.1109/70.481750.
• Chen, T., Xie, L., Han, Y., y Luo, J. (2018). Lane keeping control on mecanum wheeled omnidirectional vehicles using laser scanner. En 2018 Chinese Control And Decision Conference (CCDC), 3404–3409. doi: 10.1109/CCDC.2018.8407712.
• Dawson, D.M., Abdallah, C.T., y Lewis, F.L. (2003). Robot manipulator control: theory and practice. CRC Press.
• Ha, I.C. y Han, M.C. (2004). A robust control with a neural network structure for uncertain robot manipulator. KSME International Journal, 18(11), 1916. doi: 10.1007/BF02990433.
• Hendzel, Z. et al. (2017). Modelling of dynamics of a wheeled mobile robot with mecanum wheels with the use of Lagrange equations of the second kind. International Journal of Applied Mechanics and Engineering, 22(1), 81–99.
• Hernandez, D., Yu, W., y Moreno-Armendariz, M.A. (2011). Neural PD control with second-order sliding mode compensation for robot manipulators. En The 2011 International Joint Conference on Neural Networks, 2395–2402. doi:10.1109/IJCNN.2011.6033529.
• Kelly, R., Davila, V., y Perez, J. (2006). Control of Robot Manipulators in Joint Space. Advanced Textbooks in Control and Signal Processing. Springer London.
• Kwan, C., Dawson, D., y Lewis, F. (1995). Robust adaptive control of robots using neural network: global tracking stability. En Proceedings of 1995 34th IEEE Conference on Decision and Control, volumen 2, 1846– 1851. IEEE.
• Lewis, F.L. y Ge, S.S. (2006). Neural Networks in Feedback Control Systems, 791–825. John Wiley & Sons, Ltd. doi:10.1002/0471777455.ch19.
• Lewis, F.L., Yesildirak, A., y Jagannathan, S. (1998). Neural Network Control of Robot Manipulators and Nonlinear Systems. Taylor & Francis, Inc., Bristol, PA, USA.
• Lewis, F. (1999). Nonlinear network structures for feedback control. Asian Journal of Control, 1(4), 205–228.
• Lin, L.C. y Shih, H.Y. (2013). Modeling and adaptive control of an omni-mecanum-wheeled robot. Intelligent Control and Automation, 4(02), 166.
• Lu, X., Zhang, X., Zhang, G., y Jia, S. (2018). Design of adaptive sliding mode controller for fourmecanum wheel mobile robot. En 2018 37th Chinese Control Conference (CCC), 3983–3987. doi: 10.23919/ChiCC.2018.8483388.
• Montoya–Chairez, J., Santibáñez, V., y Moreno–Valenzuela, J. (2019). Adaptive control schemes applied to a control moment gyroscope of 2 degrees of freedom. Mechatronics, 57, 73 – 85. doi: https://doi.org/10.1016/j.mechatronics.2018.11.011.
• Moreno-Valenzuela, J., Aguilar-Avelar, C., PugaGuzm´an, S.A., y Santib´a˜nez, V. (2016). Adaptive neural network control for the trajectory tracking of the furuta pendulum. IEEE Transactions on Cybernetics, 46(12), 3439–3452. doi:10.1109/TCYB.2015.2509863.
• Ovalle, L., Ríos, H., Llama, M., Santibáñez, V., y Dzul, A. (2019). Omnidirectional mobile robot robust tracking: Sliding-mode output-based control approaches. Control Engineering Practice, 85, 50 – 58. doi: https://doi.org/10.1016/j.conengprac.2019.01.002.
• Selmic, R.R. y Lewis, F.L. (2000). Backlash compensation in nonlinear systems using dynamic inversion by neural networks. Asian Journal of Control, 2(2), 76–87.
• Siegwart, R., Nourbakhsh, I.R., y Scaramuzza, D. (2011). Introduction to autonomous mobile robots. MIT press.
• Slotine, J.J.E. y Li, W. (1987). On the adaptive control of robot manipulators. The International Journal of Robotics Research, 6(3), 49–59. doi: 10.1177/027836498700600303.
• Slotine, J. y Li, W. (1991). Applied Nonlinear Control. Prentice Hall. Sun, T., Pei, H., Pan, Y., Zhou, H., y Zhang, C. (2011). Neural network-based sliding mode adaptive control for robot manipulators. Neurocomputing, 74(14-15), 2377– 2384.
• Tsai, C., Tai, F., y Lee, Y. (2011). Motion controller design and embedded realization for mecanum wheeled omnidirectional robots. En 2011 9th World Congress on Intelligent Control and Automation, 546–551. doi: 10.1109/WCICA.2011.5970573.
• Viboonchaicheep, P., Shimada, A., y Kosaka, Y. (2003). Position rectification control for mecanum wheeled omni-directional vehicles. En IECON’03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468), volumen 1, 854–859 vol.1. doi:10.1109/IECON.2003.1280094.
• Wang, L., Chai, T., y Fang, Z. (2009). Neural-networkbased two-loop control of robotic manipulators including actuator dynamics in task space. Journal of Control Theory and Applications, 7(2), 112.