This paper focuses on the application of the intelligent control techniques (neural networks, fuzzy logic and genetic algorithms) anti their hybrid methods (neuro-fuzzy networks, neuro-genetic and fuzzy-genetic algorithms) in the area of humanoid robotic systems. This paper represents an attempt to give a report of the basic principles and concepts of intelligent control in humanoid robotics, with an outline of a number of recent algorithms used in advanced control of humanoid robots.

In this paper, a new method for selecting the appropriate compliance control parameters for robot machining tasks based on connectionist classification of unknown dynamic environments, is proposed. The method classifies the type of environment by using multilayer perceptron, and then, determines the control parameters for compliance control using the estimated characteristics. An important feature is that the process of pattern association can work in an on-line mode as a part of selected compliance control algorithm. Convergence process is improved by using evolutionary approach (genetic algorithms) in order to choose the optimal topology of the proposed multilayer perceptron. Compliant motion simulation experiments with robotic arm placed in contact with dynamic environment, described by the stiffness model and by the general impedance model, have been performed in order to verify the proposed approach.

In this paper, a new learning control algorithm based on neural network classification of unknown dynamic environment models and neural network learning of robot dynamic model is proposed. The method classifies characteristics of environments by using multilayer perceptrons, and then determines the control parameters for compliance control using the estimated characteristics. Simultaneously, using the second neural network the compensation of robot dynamic model uncertainties is accomplished. The classification capability of neural classifier is realized by efficient online training process. It is an important feature that the process of pattern classification can work in an online manner as a part of selected compliance control algorithm. Compliant motion simulation experiments have been performed in order to verify the proposed approach.

The major concern of this paper is the application of connectionist architectures for fast online learning of robot dynamic uncertainties which are used at the executive hierarchical control level in the case of robot contact tasks. The connectionist structures are integrated in the nonlearning control laws for contact tasks which enable simultaneous stabilization and good tracking performance of position and force. It has been shown that the problem of tracking a specified reference trajectory and specified force profile with a preset quality of their transient response can be efficiently solved by means of application of the four-layer perceptron. The four-layer perceptron as part of hybrid learning control algorithms through the process of synchronous training use fast learning rules and available sensor informations in order to improve robotic performance progressively for minimal possible number of learning epochs. Some simulation results of deburring process with robot MANUTEC r3 are shown to verify effectiveness of the proposed control learning algorithms.

A major objective in this paper is the application of connectionist architectures for fast and robust online learning of dynamic relations used in robot control at the executive hierarchical level. The proposed connectionist robot controllers as new feature use decomposition of robot dynamics in the space of internal robot coordinates. In this way, this method enables the training of neural networks on the simpler input-output relations with significant reduction of learning time. The proposed controller structure comprises a form of intelligent feedforward control in the frame of decentralized control algorithm with feedback-error or driving torque error learning method. The another important features of these new algorithms are fast and robust convergence properties because the problem of adjusting the weights of internal hidden units is considered as a problem of estimating parameters by recursive least square method and Kalman filter approach. From simulation examples of robot trajectory tracking it is shown that when a sufficiently trained network is desired, the learning speed of the proposed algorithms is faster than that of the standard back propagation algorithm.>

A major objective in this paper is the application of new connectionist structures for fast and robust online learning of internal robot dynamic relations used as part of impedance control strategies in the case of robot contact tasks. Using proposed connectionist structures, stabilization of robot motion and interaction force with environment is achieved. The proposed neural network models with their special topology are integrated in position-based impedance control, force-based impedance control and stabilizing impedance control. In this way, efficient dynamic compensation and fast learning properties of the control algorithm for contact tasks are enabled. The effectiveness of the learning method is shown by simulation experiments of robot deburring process.>

The application of connectionist architectures for fast and robust online learning of dynamic relations used in robot control at the executive hierarchical level is discussed. The proposed connectionist robot controllers use decomposition of robot dynamics. This method enables the training of neural networks on the simpler input/output relations with sigfnificant reduction of learning time. The other important features of these algorithms are fast and robust convergence properties because the problem of adjusting the weights of internal hidden units is considered as a problem of estimating parameters by the recursive least squares method and the extended Kalman filter approach. From simulation examples of robot trajectory tracking it is shows that when a sufficiently trained network is desired, the learning speed of the proposed algorithm is faster than that of the traditional backpropagation algorithms.>