Multilayer neural-net robot controller with guaranteed tracking performance


LEWIS F., Yesildirek A., LIU K.

IEEE TRANSACTIONS ON NEURAL NETWORKS, vol.7, no.2, pp.388-399, 1996 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 7 Issue: 2
  • Publication Date: 1996
  • Doi Number: 10.1109/72.485674
  • Journal Name: IEEE TRANSACTIONS ON NEURAL NETWORKS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Computer & Applied Sciences
  • Page Numbers: pp.388-399
  • Yıldız Technical University Affiliated: No

Abstract

A multilayer neural-net (NN) controller for a general serial-link rigid robot arm is developed. The structure of the NN controller is derived using a filtered error/passivity approach. No off-line learning phase is needed for the proposed NN controller and the weights are easily initialized. The nonlinear nature of the NN, plus NN functional reconstruction inaccuracies and robot disturbances, mean that the standard delta rule using backpropagation tuning does not suffice for closed-loop dynamic control. Novel on-line weight tuning algorithms, including correction terms to the delta rule plus an added robustifying signal, guarantee bounded tracking errors as well as bounded NN weights. Specific bounds are determined, and the tracking error bound can be made arbitrarily small by increasing a certain feedback gain. The correction terms involve a second-order forward-propagated wave in the backprop network. New NN properties including the notions of a passive NN, a dissipative NN, and a robust NN are introduced.