Stable neuro-adaptive control for robots with the upper bound estimation on the neural approximation errors

An indirect adaptive control approach is developed in this paper for robots with unknown nonlinear dynamics using neural networks (NNs). A key propert y of the proposed approach is that the actual joint angle values in the con trol law are replaced by the desired joint angles, angle velocities and acc elerators, and the bound on the NN reconstruction errors is assumed to be u nknown. Main theoretical results for designing such a neuro-controller are given, and the control performance of the proposed controller is verified w ith simulation studies.