Output feedback control of rigid robots using dynamic neural networks

A neural network controller for constrained robot manipulators is presented. A feedforward neural network is used to adaptively compensate for the uncertainties in the robot dynamics. Training signals are proposed for the feedforward neural network controller. The neural network weights are tuned online, with no online learning phase required. It is shown that the controller is able to deal with the uncertainties of the robot which include modelled undertainties (dynamic parameter uncertainties, etc.) as well as unmodelled uncertainties (frictions, etc.). The suggested controller is simple in structure and can be implemented easily. The controller has the proportional-integral (PI) type force feedback control structure with a low proportional force feedback gain. Detailed experimental results show the effectiveness of the proposed controller.

In this paper, a new nonlinear controller for a quadrotor unmanned aerial vehicle (UAV) is proposed using neural networks (NNs) and output feedback. The assumption on the availability of UAV dynamics is not always practical, especially in an outdoor environment. Therefore, in this work, an NN is introduced to learn the complete dynamics of the UAV online, including uncertain nonlinear terms like aerodynamic friction and blade flapping. Although a quadrotor UAV is underactuated, a novel NN virtual control input scheme is proposed which allows all six degrees of freedom (DOF) of the UAV to be controlled using only four control inputs. Furthermore, an NN observer is introduced to estimate the translational and angular velocities of the UAV, and an output feedback control law is developed in which only the position and the attitude of the UAV are considered measurable. It is shown using Lyapunov theory that the position, orientation, and velocity tracking errors, the virtual control and observer estimation errors, and the NN weight estimation errors for each NN are all semiglobally uniformly ultimately bounded (SGUUB) in the presence of bounded disturbances and NN functional reconstruction errors while simultaneously relaxing the separation principle. The effectiveness of proposed output feedback control scheme is then demonstrated in the presence of unknown nonlinear dynamics and disturbances, and simulation results are included to demonstrate the theoretical conjecture.

SummaryThis paper addresses the neural network (NN) output feedback formation tracking control of nonholonomic wheeled mobile robots (WMRs) with limited voltage input. A desired formation is achieved based on the leader–follower strategy utilizing hyperbolic tangent saturation functions to reduce the risk of actuator saturation. The controller is developed by incorporating the high-gain observer and radial basis function (RBF) NNs using the inverse dynamics control technique. The high-gain observer is introduced to estimate velocities of the followers. The RBF NN preserves the robustness of the proposed controller against uncertain nonlinearities. The adaptive laws are also combined by a robust control term to estimate the weights of RBF NN, approximation errors, and bounds of unknown time-variant environmental disturbances. A Lyapunov-based stability analysis proves that all signals of the closed-loop system are bounded, and tracking errors are uniformly ultimately bounded. Finally, some simulations are carried out to show the effectiveness of the proposed controller for a number of WMRs.

A new class of adaptive nonlinear H∞ control systems for nonlinear and time-varying processes which include nonlinear parametric models approximated by neural networks (NN), is proposed in this manuscript. Those control schemes are derived as solutions of particular nonlinear H∞control problems, where unknown system parameters, approximation and algorithmic errors in NN, and estimation errors of layer weights in NN, are regarded as exogenous disturbances to the processes, and thus, in the resulting control systems, the L2 gains from those uncertain elements to generalized outputs are made less than γ (> 0) (the prescribed positive constants). The resulting control systems are bounded for arbitrarily large but bounded variations of time-varying parameters and layer weights, and modeling and algorithmic errors in NN approximators.

In this paper, stable adaptive neural network (NN) control, a combination of weighted one-step-ahead control and adaptive NN is developed for a class of multi-input-multi-output (MIMO) nonaffine nonlinear discrete-time systems. The weighted one-step-ahead control is designed to stabilize the nominal linear system, while the adaptive NN compensator is introduced to deal with the nonlinearities. Under the assumption that the inverse control gain matrix has an either positive definite or negative definite symmetric part, the obstacle in NN weights tuning for the MIMO systems is transformed to unknown control direction problem for single-input-single-output (SISO) system. Discrete Nussbaum gain is introduced into the NN weights adaptation law to overcome the unknown control direction problem. It is proved that all signals of the closed-loop system are bounded, while the tracking error converges to a compact set. Simulation result illustrates the effectiveness of the proposed control.

Chapter 20 - Neural Network Approximation of Piecewise Continuous Functions: Application to Friction Compensation

In this paper, we present experimental validation of a novel method for controlling a robotic manipulator using an experience-based Neural Network (NN) controller derived from Deterministic Learning (DL) techniques. Studies are performed on simulated and real-world environments to quantify performance of this controller compared (as a baseline case) to traditional methods such as Proportional-Integral-Derivative (PID) control. Both of these controller types (NN and PID) are integrated into a 7 Degrees of Freedom (DOF) manipulator system, having the controller available to use on all 7 joints simultaneously. The NN controller utilizes adaptive learning strategies focusing on the state-feedback case. The learning algorithms train Radial Basis Function Neural Networks (RBFNN) to enhance tracking performance along a non-linear recurrent reference trajectory. With convergence of NN weights within the RBFNN, the unmodeled manipulator dynamics are guaranteed to be identified and stored for use with the experience-based algorithms without online adaptation. This paper details the process of integrating a NN controller with system state feedback and employing learning/experience based algorithms in a manner that host system computations are not affected beyond a pre-determined sampling rate.

In this paper, the design of a neural network (NN) based adaptive model-based event-triggered control of an uncertain single input single output (SISO) nonlinear discrete time system in affine form is presented. The controller uses an adaptive estimator consisting of a single-layer NN not only to approximate the internal dynamics of an affine nonlinear discrete-time system but also to provide an estimate of the state vector during inter event interval. The NN weights of the adaptive NN estimator are tuned in a aperiodic manner at the event trigger instants unlike periodic updates in standard adaptive neural network (NN) control. A dead zone operator is used to reset the event trigger error to zero as long as the system states continue to remain in a bounded region due to NN reconstruction errors. Lyapunov method is used to derive the event trigger condition, prove uniform ultimate boundedness (UUB) of the NN weight estimation error and system states.

Robust adaptive NN control of dynamically positioned vessels under input constraints

Nowadays, due to many limitations in reality, the optimization of tracking precision and convergence time has attracted the attention of researchers in robotics community. In this article, a fixed-time adaptive neural network (NN) controller is proposed for unknown robot manipulators. A switching mechanism is integrated into the control design such that the semiglobal stability of the conventional NN control systems can be extended to global stability. The time-varying barrier Lyapunov function and the fixed-time control technique are incorporated into the controller design to guarantee the prescribed motion constraints and the fixed-time convergence simultaneously. Compared with some existing fixed-time NN control algorithms, the assumption that NN weight should be upper bounded can be relaxed in our work. Finally, the simulation and experiment studies are respectively carried out based on an unknown 2-degree of freedom robot and a Baxter robot to demonstrate the effectiveness and superiority of the proposed control scheme.

A robust adaptive neural network controller is presented for flexible joint robots using feedback linearization techniques. The controller is based on an approach of using an additional neural network to provide adaptive enhancements to a bask fixed nonlinear controller which can be either neural-network-based or model-used. The weights of the additional neural network are updated on-line based on direct adaptive techniques. It is shown that if Gaussian radial basis function networks are used for the additional neural network, uniformly stable adaptation is assured and asymptotic tracking of the position reference signal is achieved. Intensive computer simulations on a two-link flexible joint robot have shown that the controller can belter handle dynamical model changes and parameter uncertainties than the conventional feedback linearization controller

Robust vibration control of smart composite beams using neural networks was studied. Linear quadratic Gaussian with loop transfer recovery (LQG/LTR) methodology was used to design a robust controller on the basis of the state space model of the system. The state space model of the system was obtained using the finite-element method and mode superposition. The finite-element model was based on a higher-order shear deformation theory which included the lateral strains. The mode superposition method was used to transform the coupled finite-element equations of motion in the physical coordinates into a set of reduced uncoupled equations in the modal coordinates. The performance of the LQG/LTR controller was verified for various arbitrary initial conditions. A system of neural networks was then trained to emulate the robust controller. The neural network system was trained using the backpropagation algorithm. After suitable training, the NN (neural network) controller was shown to effectively control the vibrations of the composite beam. A robustness study including the effects of tip mass, structural parameter variation, and loss of a sensor input was performed. The NN controller is shown to provide robustness and control capabilities equivalent to that of the LQG/LTR controller.

In this paper, an adaptive neural network (NN) output feedback control is investigated for incommensurate fractional-order permanent magnet synchronous motors under the condition of input saturation. First, a NN state observer is presented to obtain the ‘virtual estimate’ of angle speed, where the unknown function is approximated by the NN. Then, in order to solve the input saturation problem, an auxiliary system is developed under fractional-order framework. Next, the command filtered technology with an error compensation mechanism is used to handle the ‘explosion of complexity’ in backstepping and remove the filtering errors. In addition, the frequency distributed model is utilized such that the Lyapunov theory is available in the backstepping design and the system stability is demonstrated. Finally, numerical simulations confirm the availability of the proposed design.

In this note, robust adaptive neural network (NN) control scheme is constructed for a class of unknown nonlinear systems with drift terms. The robust adaptive NN control laws are developed using backstepping technique which does not require the unknown parameters to be linear parametrizable and no regression matrices are needed. All the signals in the resulting closed-loop system are proved to be ultimately uniform bounded, and the system states are guaranteed to converge to zero.Keywordsadaptive controlbacksteppingneural networknonlinear system

The present paper investigates an advanced control system of the wind energy conversion using an Artificial Neural Network (ANN) controller, which is developed in two modes: the offline mode, required for testing different sets of neural network parameters to find the optimal neural network controller (structure, activation function, and training algorithm), and the online mode where the optimal ANN controller is used in the five-phase PMSG based wind turbine system. The required data to generate the ANN model is obtained from a conventional PI controller. The controller inputs are the error between reference and actual speed (e), and the error change (de = e(k)-e(k-1)). As for the ANN output, it is the decreasing or increasing electromagnetic torque (dTe*). The studied neural network controller has been tested and validated using different wind speed values. Results and analysis are presented, and the contribution has been demonstrated.