Robust Adaptive Fuzzy Neural Control of robot manipulators

This paper presents a robust Adaptive Fuzzy Neural Controller (AFNC) suitable for trajectory control of robot manipulators. The proposed controller has the following salient features: (1) Self-organizing fuzzy neural structure, i.e. fuzzy control rules can be generated or deleted automatically according to their significence to the control system and the complexity of the mapped system, and no predefined fuzzy rules are required; (2) Online learning, i.e. no prescribed training models are needed for online learning; (3) Fast learning speed, i.e. Generalized Dynamic Fuzzy Neural Network (GD-FNN) algorithm provides an efficient learning method. Moreover, weights of the AFNC are modified without using the Back-Propagation (BP) iteration method. Structure and parameters identification of the AFNC are done automatically and simultaneously without partitioning the input space and selecting initial parameters a priori; (4) Fast convergence of tracking error, i.e. manipulator joints can track the desired trajectory very quickly; (5) Adaptive control, i.e. structure and parameters of the AFNC can be self-adaptive in the presence of disturbances to maintain high control performance; (6) Robust control, i.e. asymptotic stability of the control system is established using Lyapunov theorem. Computer simulation studies were carried out and comparison of simulation results with some existing controllers demonstrate the flexibility, adaptability and good tracking performance of the proposed controller.