[en] Radial Basis Function-Neural Networks are well-established function approximators. This paper presents an adaptive Gaussian RBF-NN with an extended learning-while controlling behaviour. The weights, function centres and widths are updated online based on a sliding mode control element. In this way, the need for fixing parameters a priori is overcome and the network is able to adapt to dynamically changing systems. The aim of this work is to present an extended adaptive neuro-controller for trajectory tracking of serial robots with unknown dynamics. The adaptive RBF-NN is used to approximate the unknown robot manipulator dynamics-function. It is combined with a conventional controller and a bio-inpsired extension for the control of a robot in the presence of switching constraints and discontinuous inputs. Its learned goal-directed output results from the complementary action of an actuator, A, and a prventer, P. The trigger is an incentive, I, based on the weighted perception of the enviornment. The concept is validated through simulations and implementation on a KUKA LWR4-robot.
Disciplines :
Sciences informatiques
Auteur, co-auteur :
KLECKER, Sophie ; University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Engineering Research Unit
HICHRI, Bassem ; University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Engineering Research Unit
PLAPPER, Peter ; University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Engineering Research Unit
Co-auteurs externes :
no
Langue du document :
Anglais
Titre :
Learning-While Controlling RBF-NN for Robot Dynamics Approximation in Neuro-Inspired Control of Switched Nonlinear Systems
Date de publication/diffusion :
2018
Nom de la manifestation :
27th International Conference on Artificial Neural Networks - ICANN 2018
Organisateur de la manifestation :
European Neural Network Society - ENNS
Lieu de la manifestation :
Rhodes, Grèce
Date de la manifestation :
from 04-10-2018 to 07-10-2018
Manifestation à portée :
International
Titre de l'ouvrage principal :
Artificial Neural Networks and Machine Learning; ICANN 2018 part 3
Micchelli, C.A.: Interpolation of scattered data: distance matrices and conditionally positive definite functions. Constr. Approximation 2, 11–22 (1986)
Bass, E., Lee, K.Y.: Robust control of nonlinear systems using norm-bounded neural networks. In: IEEE World Congress Computer Intelligence (Neural Networks part), pp. 2524–2529 (1994)
Van Cuong, P., Nan, W.Y.: Adaptive trajectory tracking neural network control with robust compensator for robot manipulators. Neural Comput. Appl. 27(2), 525–536 (2015). https://doi.org/10.1007/s00521-015-1873-4
Yu, L., Fei, S., Huang, J., Gao, Y.: Trajectory switching control of robotic manipulators based on RBF neural networks. Circuits Syst. Signal Process. 33, 1119–1133 (2014)
Tao, Y., Zheng, J., Lin, Y.: A sliding mode control-based on a RBF neural network for deburring industry robotic systems. Int. J. Adv. Robotic Syst. 13(1), 13–18 (2016). https://doi.org/10.5772/62002
Wang, L., Chai, T., Zhai, L.: Neural-network-based terminal sliding-mode control of robotic manipulators including actuator dynamics. IEEE Trans. Ind. Electron. 56(9), 3296–3304 (2009)
Ren, X., Rad, A.B., Lewis, F.L.: Neural network-based compensation control of robot manipulators with unknown dynamics. In: American Control Conference, pp. 13–18 (2007)
Otte, S., Zwiener, A., Butz, M.V.: Inherently constraint-aware control of many-joint robot arms with inverse recurrent models. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, Alessandro E.P. (eds.) ICANN 2017. LNCS, vol. 10613, pp. 262–270. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68600-4_31
He, W., Dong, Y.: Adaptive fuzzy neural network control for a constrained robot using impedance learning. IEEE Trans. Neural Netw. Learn. Syst. 29(4), 1174–1186 (2018)
Klecker, S., Hichri, B., Plapper, P.: Neuro-inspired reward-based tracking control for robotic manipulators with unknown dynamics. In: 2nd International Conference on Robotics and Automation Engineering, pp. 21–25 (2017)
Krabbes, M., Döschner, C.: Modelling of robot dynamics based on a multi-dimensional RBF-like neural network. In: IEEE International Conference on Information, Intelligence, and Systems (1999)
Kringelbach, M.L., Berridge, K.C.: Neuroscience of reward, motivation, and drive. In: Recent Developments in Neuroscience Research on Human Motivation, Advances in Motivation and Achievement, vol. 19, pp. 23–35 (2017)
Balkenius, C., Moren, J.: Emotional learning: a computational model of the amygdala. Int. J. Cybern. Syst. 32(6), 611–636 (2001)
Merrick, K.E.: Intrinsic motivation and introspection in reinforcement learning. IEEE Trans. Auton. Mental Develop. 4, 315–329 (2012)
Racca, M., Pajarinen, J., Montebelli, A., Kyrki, V.: Learning in-contact control strategies from demonstration. In: IROS (2016)
