Design of an adaptive fuzzy-neural inference system-based control approach for robotic manipulators

This paper proposes an adaptive fuzzy-neural inference system (ANFIS)-based control approach for a six degrees of freedom (6-DoF) robotic manipulator. Its main objective is to guarantee the error convergence of the controlled system in the presence of uncertainties and unknown disturbances. The suggested controller is a parallel combination of an ANFIS network with a proportional-integral-derivative (PID) controller. The ANFIS system is used as an estimator to approximate a part of the system and then applied as the feedback linearization in the suggested control structure. The convergence of system errors to zero was proven using Barbalat’s lemma. The suggested control law combines the simplicity and ease of implementation of PID control with the estimation properties of ANFIS networks. The suggested approach was evaluated using a simulation study and further validated experimentally using the 6-DoF IRB-120 robotic manipulator (IRB-120-RM). The obtained results confirmed its superior performance and suitability for practical implementation to industrial actuators. •Suggestion of a PID-based adaptive neuro‐fuzzy inference system approach;•Capability for formulation, estimation and elimination of the system uncertainties and disturbances compared to the ordinary ANFIS structure;•Analyzing and proving the zero-convergence error and asymptotic stability of the controlled system, which is not possible for the normal ANFIS structure;•Satisfaction of asymptotic convergence of the system errors to the origin by using the Barbalat’s lemma, since the control system is time-variant.