Recently, various control methods represented by proportional-integral-derivative （PID） control are used for robotic control. To cope with the requirements for high response and precision, advanced feedforward contr...Recently, various control methods represented by proportional-integral-derivative （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. In this paper, 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 the neural network by using back propagation algorithm, the learning coefficient and gain of sigmoid function are tuned intuitively and empirically according to teaching signals. The tuning is complicated because it is being conducted by trial and error. Especially, when the scale of teaching signal is large, the problem becomes crucial. To cope with the problem which concerns the learning performance, a simple and adaptive learning technique for large scale teaching signals is proposed. The learning techniques and control effectiveness are evaluated through simulations using the dynamic model of PUMA560 manipulator.展开更多
In this paper, A Novel Stochastic Algorithm using Pythagorean means for minimization of the objective function is described. The algorithm is initially tested with Rastrigin’s function and compared with Genetic algor...In this paper, A Novel Stochastic Algorithm using Pythagorean means for minimization of the objective function is described. The algorithm is initially tested with Rastrigin’s function and compared with Genetic algorithm results for the function with the same initial conditions. After this, it is used in tuning the gains of fuzzy PD + I controller for trajectory control of PUMA 560 robot manipulator. The results are again verified with the results of genetic algorithm.展开更多
基金supported by Grant-in-Aid for Scientific Research(C) (No. 20560248) of Japan
文摘Recently, various control methods represented by proportional-integral-derivative （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. In this paper, 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 the neural network by using back propagation algorithm, the learning coefficient and gain of sigmoid function are tuned intuitively and empirically according to teaching signals. The tuning is complicated because it is being conducted by trial and error. Especially, when the scale of teaching signal is large, the problem becomes crucial. To cope with the problem which concerns the learning performance, a simple and adaptive learning technique for large scale teaching signals is proposed. The learning techniques and control effectiveness are evaluated through simulations using the dynamic model of PUMA560 manipulator.
文摘In this paper, A Novel Stochastic Algorithm using Pythagorean means for minimization of the objective function is described. The algorithm is initially tested with Rastrigin’s function and compared with Genetic algorithm results for the function with the same initial conditions. After this, it is used in tuning the gains of fuzzy PD + I controller for trajectory control of PUMA 560 robot manipulator. The results are again verified with the results of genetic algorithm.
