Adaptive Critic Neural Networks for Identification of Wheeled Mobile Robot
A new applications of adaptive critic identifier for wheeled mobile robot is presented. In this approach the architecture of adaptive critic identifier contains a neural network (NN) based adaptive critic element (ACE) generating the reinforcement signal to tune the associative search element (ASE), which is applied to approximate nonlinear functions of the mobile robot. The proposed system identification that can guarantee tracking performance and stability is derived from the Lyapunov stability theory. Computer simulation have been conducted to illustrate the performance of the proposed solution by a series of experiments on the emulator of wheeled mobile robot Pioneer-2DX.
KeywordsMobile Robot Lyapunov Stability Theory Layer Neural Network Wheel Mobile Robot Adaptive Critic
Unable to display preview. Download preview PDF.
- 1.Barto, A.G., Sutton, R.S., Anderson, W.: Neuron-like adaptive elements can solve difficult learning con-trol problems. IEEE Trans, on Systems, Man, and Cy-bernetics 13(5), 834–846 (1983)Google Scholar
- 2.Giergiel, J., Hendzel, Z., Zylski, W.: Modelling and Control of Wheeled Mobile Robots (in Polish), WNT, Warsaw (2002)Google Scholar
- 4.Lewis, F.L., Jagannathan, S., Yesildirek, A.: Neural network control of robot manipulators and nonlinear systems. Taylor and Francis, London (1999)Google Scholar
- 6.Liu, G.P.: Nonlinear identification and control. In: Advances in Industrial Control, Springer, Heidelberg (2001)Google Scholar
- 8.Sutton, R.S., Barto, A.G.: Reinforcement Learning, An Introduction. MIT Press, Cambridge (1999)Google Scholar