Intelligent control system for an industrial manipulator

In this chapter, two types of intelligent control systems are introduced. One is the adaptive learning technique for large-scale teaching signals. Recently various control methods as represented by PID control are used for robotic control. To cope with the requirements for high response and precision, advanced feedforward controllers such as gravity compensator, Coriolis/centrifugal force compensator and friction compensators have been built in the controller. Generally, it causes heavy computational load when calculating the compensating value within a short sampling period. To overcome the problem, integrated recurrent neural networks are applied as a feedforward controller for PUMA560 manipulator. The feedforward controller works instead of gravity and Coriolis/centrifugal force compensators. In the learning process of neural network by using back propagation algorithm, in general, the learning coefficient and gain of sigmoid function are tuned intuitively and empirically according to teaching signals. The tuning is complicated because of being conducted by trial and error. Especially, when the scale of teaching signal is large, the problem becomes crucial. To cope with the problem concerning the learning performance, a simple and adaptive learning technique for largescale teaching signals is proposed. The learning techniques and control effectiveness are evaluated through simulations using the dynamic model of PUMA560 manipulator. The other is the fine gain tuning technique for model-based robotic servo controllers using genetic algorithms. Resolved acceleration control method and computed torque control method are used for nonlinear control of industrial manipulators, which are composed of a model base portion and a servo portion. The servo portion is a closed-loop system with respect to the position and velocity. On the other hand, the model base portion has the inertia term, gravity term and centrifugal/Coriolis term, which works for canceling the nonlinearity of manipulator. In order to realize high control stability, the position and velocity feedback gains used in the servo portion should be tuned suitably. In the latter half of the chapter, a simple but effective fine tuning method after the manual tuning process is introduced for the position and velocity feedback gains in the servo portion. At the first step, the search space for the gains are roughly narrowed down by a controller designer, e.g., considering the critically damped condition. At the next step, the gains are finely tuned within the space by using genetic algorithms. The genetic algorithms search for the better combination of the position and velocity gains. Simulations are conducted using the dynamic model of PUMA560 manipulator to validate the effectiveness of the proposed method.