Balance control of robot with CMAC based Q-learning

The cerebellar model articulation controller (CMAC) neural network (NN) has advantages over fully connected NNs due to its increased structure. This paper attempts to provide a comprehensive treatment of CMAC NNs in closed-loop control applications. The function approximation capabilities of the CMAC NN are first rigorously established, and novel weight-update laws derived that guarantee the stability of the closed-loop system. The passivity properties of the CMAC under the specified tuning laws are examined and the relationship between passivity and closed-loop stability is derived. The utility of the CMAC NN in controlling a nonlinear system with unknown dynamics is demonstrated through numerical examples.

DC–DC converters are the devices which can convert a certain electrical voltage to another level of electrical voltage. They are very popularly used because of the high efficiency and small size. This paper proposes an intelligent power controller for the DC–DC converters via cerebella model articulation controller (CMAC) neural network approach. The proposed intelligent power controller is composed of a CMAC neural controller and a robust controller. The CMAC neural controller uses a CMAC neural network to online mimic an ideal controller, and the robust controller is designed to achieve L 2 tracking performance with desired attenuation level. Finally, a comparison among a PI control, adaptive neural control and the proposed intelligent power control is made. The experimental results are provided to demonstrate the proposed intelligent power controller can cope with the input voltage and load resistance variations to ensure the stability while providing fast transient response and simple computation.

This paper describes the application of cerebellar model articulation controller (CMAC) and B-spline neural networks to switched reluctance motor (SRM) torque estimation and control. Non-linear adaptive systems such as neural networks are well suited to learning the highly non-linear electromagnetic characteristics of the SRM for the purposes of linearisation and simplification of their control and a number of researchers have investigated their use in this context. CMAC and B-spline neural networks are particularly suited to this application area due to their potential for low-cost, high-speed implementation including the capability for real-time, on-line adaptation. CMAC and B-spline neural networks have successfully been applied both to torque ripple minimisation and to torque estimation in simulation and, implemented using FPGA technology, experimentally. This paper describes those applications with particular emphasis on the suitability of the CMAC and B-spline neural networks and gives details of their FPGA implementation.

The cerebellar model articulation controller (CMAC) neural network is an associative memory that is biologically inspired by the cerebellum, which is found in the brains of animals. In recent works, the kernel recursive least squares CMAC (KRLS---CMAC) was proposed as a superior alternative to the standard CMAC as it converges faster and does not require tuning of a learning rate parameter. One improvement to the standard CMAC that has been discussed in the literature is eligibility, and vector eligibility. With vector eligibility the CMAC is able to control online motion control problems that it could not previously, stabilize the system much faster, and converge to a more intelligent solution. This paper integrates vector eligibility with the KRLS---CMAC and shows how the combination is advantageous through two simulated control experiments.

The Cerebellar Model Articulation Controller (CMAC) neural network is an associative memory that is biologically inspired by the cerebellum, which is found in the brains of animals. The standard CMAC uses the least mean squares algorithm to train the weights. Recently, the recursive least squares (RLS) algorithm was proposed as a superior algorithm for training the CMAC online as it can converge in just one epoch, and does not require tuning of a learning rate. However, the RLS algorithm was found to be very computationally demanding as its computational complexity is dependent on the square of the number of weights required which can be huge for the CMAC. Here, we show a more efficient RLS algorithm that uses inverse QR decomposition and additionally provides a regularized solution, improving generalization. However, while the inverse QR decomposition based RLS algorithm reduces computation time significantly; it is still not fast enough for use in CMACs greater than two dimensions. To further improve efficiency we show that by using kernel methods the CMAC computational complexity can be transformed to become dependent on the number of unique training data. Additionally, it is shown how modeling error can be improved through use of higher order basis functions.

A control scheme of ANN-based PID controller is developed here to reach high precision tracking control for an electro-hydraulic servo system. The PID controller is used as a feedback controller to guarantee the system stability. The cerebellar model articulation controller (CMAC) neural network is used as a feed-forward compensator to identify the inverse system dynamics model. The CMAC and the PID controller are connected in parallel. The outputs of this paralleled controller are summed up as the total control action. A nonlinear tracking differentiator (NTD) is presented to yield high quality differential signals for the PID controller. The main task of this control algorithm is to make the error between the total control action and the output of the CMAC minimize by the CMAC learning algorithm. Thus the control action is formed by the CMAC. Numerical simulation results show comparing with conventional PID control strategy this proposed control scheme has an excellent system performance including high precision trajectory tracking ability and rejection of disturbance.

The present American Institute of Steel Construction specifications use the alignment charts and approximate formulas conveniently to determine some coefficients in design, such as moment gradient coefficient Cb for beams of I-shaped section and effective length factor K of columns. In these methods, the coefficients are unconservative when the boundary conditions are different from the development of specifications. The governing equations, numerical approaches, on the K and Cb coefficients provide more accurate results. The approaches, however, are not readily available for structural engineers to use in design. Applying neural network computing toward structural engineering problems has received increasing interest, with particular emphasis placed on supervised neural networks. The cerebellar model articulation controller (CMAC), one of the supervised neural network learning models, is mostly used in the domain of control. In this work, we use a newly developed Macro Structure CMAC (MS_CMAC) neural network learning model to aid steel structure design. The topology of the novel learning model is constructed by a number of time inversion CMACs as a tree structure. The learning performance of the MS_CMAC is first compared with a stand-alone time inversion CMAC using one structural engineering example. That comparison indicates not only superior prediction but also fast learning propriety for the MS_CMAC neural network learning model. In addition, the MS_CMAC neural network learning model is applied to two steel design problems. It is shown that the MS_CMAC not only can learn structural design problems within a reasonable central processing unit time but also can estimate more accurate coefficients than that estimated through alignment charts and approximate formulas in American Institute of Steel Construction specifications.

Load forecasting is an issue that needs to be addressed to prevent overloading and catastrophic blackouts in power grids. This paper proposes a dual cerebellar model articulation controller (CMAC) neural network which is able to give an accurate very short term prediction of the required load curve. This is the first time a CMAC algorithm has been employed for load forecasting. The paper depicts that the proposed method has the advantage of reduced training time and reduced computational requirements as compared to the other load forecasting techniques. The data of the south west interconnected system was employed to give load predictions whilst using the proposed dual CMAC and back propagation neural network. The performance evolution has shown that the proposed dual CMAC neural network works efficiently and accurately for very short term load forecasting scenarios as compared to other conventional load forecasting techniques.

This study employed a cerebellar model articulation controller (CMAC) neural network to conduct fault diagnoses on photovoltaic power generation systems. We composed a module array using 9 series and 2 parallel connections of SHARP NT-R5E3E 175 W photovoltaic modules. In addition, we used data that were outputted under various fault conditions as the training samples for the CMAC and used this model to conduct the module array fault diagnosis after completing the training. The results of the training process and simulations indicate that the method proposed in this study requires fewer number of training times compared to other methods. In addition to significantly increasing the accuracy rate of the fault diagnosis, this model features a short training duration because the training process only tunes the weights of the exited memory addresses. Therefore, the fault diagnosis is rapid, and the detection tolerance of the diagnosis system is enhanced.

This paper discusses adaptive control method used in high performance servo system based on Cerebellar Model Articulation Controller(CMAC). It analyzes the uncertain and nonlinear factors of the servo system, studies the modeling method using the frequency property of the system, and then uses an additional item to instead of the non-modeling factor. In the proposed control scheme, the CMAC controller is able to learn the unknown model dynamics, parameter variation and disturbance of the system on line. The model reference adaptive control (MRAC) scheme is used to give better solutions with online adaptation. It contemporarily improved the conception mapping algorithm of the Cerebellar Model Articulation Controller Neural Network(CMACNN), which gave a determined expression of the physical memory size and designed a physical memory address function. Experiment results verify that the proposed strategy can achieve high tracking precision for real-time position close-loop servo system.

The interpolation capabilities of the binary CMAC

This article originally analyses intelligent robust tracking for multi-arm fruit-harvesting mobile manipulators (MAFHMMs) with delayed angle-velocity uncertainties. The MAFHMMs are composed of two parts: a crawler-type mobile platform and a four-arm harvesting manipulator. The method proposed here does not require a matching condition for the non-linear uncertainties. A fuzzy cerebellar model articulation controller (CMAC) neural network system is used to approximate an unknown controlled system from the strategic manipulation of the model following the tracking errors. In addition, an adaptive robust compensator is presented to compensate for the uncertainties. Based on the Lyapunov stability theory and neural network approximation capability, several sufficient conditions are derived, which guarantee the convergence of the closed-loop error system. Both simulation and experimental results show the superior control performance of the proposed intelligent control method.

Cerebellar Model Articulation Controller (CMAC) is type of neural network inspired from part of the brain named cerebellum. It has long history in control applications, in simulated or in real-time implementations. MATLAB/Simulink is used for rapid building of CMAC neural network controller prototypes than can run in real-time. To run the controller in the same personal computer, QuaRC is used as real-time operating system that will execute controller task along Windows operating system. Hardware-in-the-loop architecture was used to test CMAC controller in real ball-and-beam physical plant from Quanser. Library of developed Simulink functional blocks enable easy exploration of different structural aspects of CMAC neural network controller, including selection of receptive field types, receptive field widths, Albus overlays, and fully interconnected multi-dimensional receptive fields. Same CMAC controller can be used also for controlling model of the plant, which can serve as means for controller to acquire knowledge before operating with real plant. CMAC controller learned to control the plant, and progressively became main control signal generator, while control signal from primary proportional-derivative controller almost vanished. Developed library can serve as easy startup for working with CMAC networks also for other types of applications.

This study entailed applying image-processing techniques and an intelligent control method to a wheeled mobile robot (WMR) for real-time trajectory recognition and tracking. The WMR was fitted with a charge-coupled device (CCD) camera to capture images of the environment, and the hue-saturation-intensity color space was used to classify the color features of the captured images. The WMR calculates the relative position of a target object by using image-processing and edge-detection algorithms. This paper proposes a cerebellar model articulation controller (CMAC) and adaptive CMAC to replace conventional proportional-integral-derivative (PID) controller for guiding the WMR to track a desired path. Moreover, using Lyapunov's stability theory to optimize the learning rate ensures that the proposed control system is stable. The tracking performance of several controllers used to track various path patterns were compared. Finally, according to the theoretical analysis, simulations, and experimental results of this study, the proposed control scheme is effective.

The design of an autonomous undersea vehicle (AUV) control system is a significant challenge in light of the highly uncertain nature of the ocean environment together with partially known nonlinear vehicle dynamics. The authors describe a neural network architecture called cerebellar model arithmetic computer (CMAC). CMAC is used to control a model of an autonomous underwater vehicle. The AUV model consists of two input parameters (the rudder and stern plane deflections) controlling six output parameters (forward velocity, vertical velocity, pitch angle, side velocity, roll angle, and yaw angle). Properties of CMAC and results of computer simulations for identification and control of the AUV model are presented. >