Neural networks for advanced control of robot manipulators

Abstract

Presents an approach and a systematic design methodology to adaptive motion control based on neural networks (NNs) for high-performance robot manipulators, for which stability conditions and performance evaluation are given. The neurocontroller includes a linear combination of a set of off-line trained NNs, and an update law of the linear combination coefficients to adjust robot dynamics and payload uncertain parameters. A procedure is presented to select the learning conditions for each NN in the bank. The proposed scheme, based on fixed NNs, is computationally more efficient than the case of using the learning capabilities of the neural network to be adapted, as that used in feedback architectures that need to propagate back control errors through the model to adjust the neurocontroller. A practical stability result for the neurocontrol system is given. That is, we prove that the control error converges asymptotically to a neighborhood of zero, whose size is evaluated and depends on the approximation error of the NN bank and the design parameters of the controller. In addition, a robust adaptive controller to NN learning errors is proposed, using a sign or saturation switching function in the control law, which leads to global asymptotic stability and zero convergence of control errors. Simulation results showing the practical feasibility and performance of the proposed approach to robotics are given.

Neural Network Grasping Controller for Continuum Robots

“…Specifically, the neural network is used to compensate for the nonlinear uncertain dynamics of the continuum robot manipulator while a nonlinear feedback controller [15] is used to provide semi-global asymptotic tracking. The advantage of the proposed control scheme compared to previous works is that semi-global asymptotic tracking can be proved, whereas most previous results for neural network control of robot manipulators [16]- [18] only prove ultimate boundedness of the tracking error.…”

Intelligent neural network design for nonlinear control using simultaneous perturbation stochastic approximation (SPSA) optimization

“…However, in the literature there are few examples of the application of SPSA in nonlinear control [3] [4]. For instance, recent studies address a wide range of possible application of NN-based controllers for robot manipulators highlighting its advantages in inverse kinematics problems [5]. It has been also shown that neural networks trained by the simultaneous perturbation stochastic approximation (SPSA) method guarantee closed-loop stability of the estimation in the control problem considered in [6].…”

Optimal Design of a RISE Feedback Controller for a 3-DOF Robot Manipulator Using Particle Swarm Optimization

“…Neural networks are almost able to approximate nonlinear continuous functions. They are therefore powerful tools to compensate for uncertainties, without knowing a complete knowledge of the plant [13]. Lewis et al proposed a multilayer neural network controller for a robot manipulator which guarantees trajectory tracking performance [14].…”