Stable adaptive systems
Robust implicit self-tuning regulator: convergence and stability
Automatica (Journal of IFAC)
Adaptive Control: The Model Reference Approach
Adaptive Control: The Model Reference Approach
Control of Robot Manipulators
Multilayer discrete-time neural-net controller with guaranteed performance
IEEE Transactions on Neural Networks
Neural net robot controller with guaranteed tracking performance
IEEE Transactions on Neural Networks
Preventing bursting in approximate-adaptive control when using local basis functions
Fuzzy Sets and Systems
A new robust weight update for multilayer-perceptron adaptive control
Control and Intelligent Systems
| Hi-index | 0.00 |
Neural network (NN) controllers for the robust back stepping control ofrobotic systems in both continuous and discrete-time are presented. Controlaction is employed to achieve tracking performance for unknown nonlinearsystem. Tuning methods are derived for the NN based on delta rule. Novelweight tuning algorithms for the NN are obtained that are similar toϵ-modification in the case of continuous-timeadaptive control. Uniform ultimate boundedness of the tracking error and theweight estimates are presented without using the persistency of excitation(PE) condition. Certainty equivalence is not used and regression matrix isnot computed. No learning phase is needed for the NN and initialization ofthe network weights is straightforward. Simulation results justify thetheoretical conclusions.