Adaptive Neuro-Fuzzy Inference System based control of six DOF robot manipulator

Abstract

The dynamics of robot manipulators are highly nonlinear with strong couplings existing between joints and are frequently subjected to structured and unstructured uncertainties. Fuzzy Logic Controller can very well describe the desired system behavior with simple "if-then" relations owing the designer to derive "if-then" rules manually by trial and error. On the other hand, Neural Networks perform function approximation of a system but cannot interpret the solution obtained neither check if its solution is plausible. The two approaches are complementary. Combining them, Neural Networks will allow learning capability while Fuzzy-Logic will bring knowledge representation (Neuro-Fuzzy). This paper presents the control of six degrees of freedom robot arm (PUMA Robot) using Adaptive Neuro Fuzzy Inference System (ANFIS) based PD plus I controller. Numerical simulation using the dynamic model of six DOF robot arm shows the effectiveness of the approach in trajectory tracking problems. Comparative evaluation with respect to PID, Fuzzy PD+I controls are presented to validate the controller design. The results presented emphasize that a satisfactory tracking precision could be achieved using ANFIS controller than PID and Fuzzy PD+I controllers

Sliding Mode Control (SMC) of Robot Manipulator via Intelligent Controllers

“…In [49], Alavandar has proven ANFIS PID when compared with PID or fuzzy PID controller on a six DOF manipulator. This paper considers the ANFIS structure with first order Sugeno model containing 49 rules.…”

“…(b) L 2 norm of control effort of joint angles in joint spaces is defined as Fig. 2 ANFIS procedure [49] J. Inst. Eng.…”

“…In ANFIS, learning capabilities of the neural networks are brought to fuzzy inference systems. In many research publications [46][47][48][49], ANFIS based controller has proven itself when compared to other classical controllers. According to Jang [50], ANFIS can be employed to model the nonlinear systems.…”

Adaptive Line Trajectory Identification of Industrial 5-DOF Robot Arm Using Neural MIMO NARX Model

“…The input signals θ 1 ,θ 2 , θ 3 , θ 4 and θ 5 (or q 1 (k), q 2 (k), q 3 (k), q 4 (k), q 5 (k) in zdomain) represented five joint-angles which are needed to be applied to the five joints of the industrial robot arm when we apply a linear trajectory represented by output signals (x,y) corresponding the Cartesian coordinates of the end-effecter of the industrial 5-DOF robot arm. Therefore, the chosen output Cartesian coordinates (x,y) are to formulate a linear trajectory of the robot arm's end-effecter.…”

“…(Srinivasan et al 2008) applied neuro-fuzzy method to solve the kinematic solution of industrial robot arm. (Alavandar S. et al 2008) applied ANFIS based on PD plus I controller to the dynamic model of 6-DOF robot manipulator. (Hasan 2010) adopted an application of neuro-fuzzy method to the solution of the inverse kinematics problem for serial robot manipulators.…”