Robust force/motion control of constrained robots using neural network

A robust neural network (NN) controller is proposed for the simultaneous force/motion control of constrained rigid robots. The NN weights here are tuned on‐line, with no off‐line learning phase required. Most importantly, we can guarantee the boundedness of constraint force errors, joint position tracking errors, and NN weights. When compared with adaptive controllers, we do not require linearity in the unknown parameters, and the tedious computation of the regression matrix. Novel passivity properties of the NN controller are stated and proven. ©1999 John Wiley & Sons, Inc.     

Robust neural-network control of rigid-link electrically drivenrobots

A robust neural-network (NN) controller is proposed for the motion control of rigid-link electrically driven (RLED) robots. Two-layer NN's are used to approximate two very complicated nonlinear functions. The main advantage of our approach is that the NN weights are tuned online, with no off-line learning phase required. Most importantly, we can guarantee the uniformly ultimately bounded (UUB) stability of tracking errors and NN weights. When compared with standard adaptive robot controllers, we do not require lengthy and tedious preliminary analysis to determine a regression matrix. The controller can be regarded as a universal reusable controller because the same controller can be applied to any type of RLED robots without any modifications.     

ROBUST NEURAL NETWORK CONTROL OF RIGID LINK FLEXIBLE-JOINT ROBOTS

A robust Neural Network (NN) controller is proposed for the motion control of rigid-link flexible-joint (RLFJ) robots. No weak joint elasticity assumption is needed. The NNs are used to approximate three very complicated nonlinear functions. Our NN approach requires no off-line learning phase, and no lengthy and tedious preliminary analysis to find the regression matrices. Most importantly, we can guarantee the uniformly ultimately bounded (UUB) stability of tracking errors and NN weights. The controller can be regarded as a universal reusable controller because the same controller can be directly applied to different RLFJ robots with different masses and lengths within the same class, for instance, of two-link revolute RLFJ robots.     

A direct NN‐approximation control for uncertain nonaffine systems with unknown control direction

In this paper, we present an adaptive neural network (NN) controller for uncertain nonaffine systems with unknown control direction. Most of the previous NN‐based controllers included a damping term in the adaptive law of NN weights to ensure the closed‐loop stability. The estimated error of the NN weights as well as the tracking error were therefore increased, relying not only on the size of the NN approximation error but also on the ideal NN weights. Compared with those, the proposed controller evades using the damping term through combining a novel adaptive algorithm and a switching mechanism to update the weights. The NN thus can directly approach a target controller with satisfactory accuracy even if the control direction is unknown. Stability analysis shows that the tracking error and the estimated error of NN weights both converge to small neighbors of 0 which solely depend on the NN approximation error. At last, simulations on a Duffing‐Holmes chaotic model show the effectiveness of the proposed controller in comparison to another NN‐based method.     

Decentralized sliding mode control for flexible link robots

A technique using augmented sliding mode control for robust, real-time control of flexible multiple link robots is presented. For the purpose of controller design, the n-link, n-joint robot is subdivided into n single joint, single link subsystems. A sliding surface for each subsystem is specified so as to be globally, asymptotically stable. Each sliding surface contains rigid-body angular velocity, angular displacement and flexible body generalized velocities. The flexible body generalized accelerations are treated as disturbances during the controller design. This has the advantage of not requiring explicit equations for the flexible body motion. The result is n single input, single output controllers acting at the n joints of the robot, controlling rigid body angular displacement and providing damping for flexible body modes. Furthermore, the n controllers can be operated in parallel so that compute speed is independent of the number of links, affording real-time, robust, control.     

Adaptive Control for Simultaneous Stabilization and Tracking of Unicycle Mobile Robots

A novel time‐varying adaptive controller at the torque level is proposed to simultaneously solve the stabilization and the tracking problem of unicycle mobile robots with unknown dynamic parameters. The idea underlying the controller is intuitively simple: rather than switching between two different types of controllers according to the a priori knowledge of the reference velocities being persistently exciting or not, a new time‐varying signal is introduced to make the single controller capable of adaptively, smoothly, and gradually converting between stabilizer and tracker depending on the instantaneous and past information of the reference velocities. Our control development is based on Lyapunov's direct method and the backstepping technique. Adaptive control techniques are used to deal with parametric uncertainties. The outstanding feature of our controller is computationally simple due to its full use of the existing results on stabilization and tracking control for unicycle robots. With our approach, robots can globally follow a large class of paths including a straight line, a circle, a path approaching a set‐point, or just a set‐point using a single controller. Simulation results for a unicycle‐type mobile robot are provided to illustrate the effectiveness of the proposed controller.     

Integrated design of a linear/neuro-adaptive controller in the presence of norm-bounded uncertainties

Adaptive neural controllers are often criticised for the lack of clear and easy design methodologies that relate adaptive neural network (NN) design parameters to performance requirements. This study proposes a methodology for the design of an integrated linear-adaptive model reference controller that guarantees component-wise boundedness of the tracking error within an a priori specified compact domain. The approach is based on the design of a robust invariant ellipsoidal set where both the NN reconstruction error and the neuro-adaptive control are considered as bounded persistent uncertainties. We show that all the performance and control requirements for the closed-loop system can be expressed as linear matrix inequality constraints. This brings the advantage that feasibility and optimal design parameters can be effectively computed while solving a linear optimisation problem. An advantage of the method is that it allows a systematic and quantitative evaluation of the interplay between the design parameters and their impact on the requirements. This produces an integrated linear/neuro-adaptive performance-oriented design methodology. A numerical example is used to illustrate the approach.     

Direct adaptive control for a class of discrete‐time unknown nonaffine nonlinear systems using neural networks

In this paper, a direct adaptive state‐feedback control approach is developed for a class of nonlinear systems in discrete‐time (DT) domain. We study MIMO unknown nonaffine nonlinear DT systems and employ a two‐layer NN to design the controller. By using the presented method, the NN approximation is able to cancel the nonlinearity of the unknown DT plant. Meanwhile, pretraining is not required, and the weights of NNs used in adaptive control are directly updated online. Moreover, unlike standard NN adaptive controllers yielding uniform ultimate boundedness results, the tracking error is guaranteed to be uniformly asymptotically stable by utilizing Lyapunov's direct method. Two illustrative examples are provided to demonstrate the effectiveness and the applicability of the theoretical results. Copyright © 2014 John Wiley & Sons, Ltd.     

A suite of robust controllers for the manipulation of microscale objects.

A suite of novel robust controllers is introduced for the pickup operation of microscale objects in a microelectromechanical system (MEMS). In MEMS, adhesive, surface tension, friction, and van der Waals forces are dominant. Moreover, these forces are typically unknown. The proposed robust controller overcomes the unknown contact dynamics and ensures its performance in the presence of actuator constraints by assuming that the upper bounds on these forces are known. On the other hand, for the robust adaptive critic-based neural network (NN) controller, the unknown dynamic forces are estimated online. It consists of an action NN for compensating the unknown system dynamics and a critic NN for approximating a certain strategic utility function and tuning the action NN weights. By using the Lyapunov approach, the uniform ultimate boundedness of the closed-loop manipulation error is shown for all the controllers for the pickup task. To imitate a practical system, a few system states are considered to be unavailable due to the presence of measurement noise. An output feedback version of the adaptive NN controller is proposed by exploiting the separation principle through a high-gain observer design. The problem of measurement noise is also overcome by constructing a reference system. Simulation results are presented and compared to substantiate the theoretical conclusions.     

Asymptotic Adaptive Neural Network Tracking Control of Nonholonomic Mobile Robot Formations

In this paper, asymptotically stable control laws are developed for leader–follower based formation control using backstepping in order to accommodate the dynamics of the robots and the formation. First, a kinematic controller is developed around control strategies for single mobile robots and the idea of virtual leaders. The virtual leader is replaced with a physical mobile robot leader, and an auxiliary velocity control law is developed in order to prove the global asymptotic stability of the followers which in turn allows the local asymptotic stability of the entire formation. A novel approach is taken in the development of the dynamical controller such that the torque control inputs for the follower robots include the dynamics of the follower robot as well as the dynamics of its leader, and two cases are considered—the case when the robot dynamics are known and the case when they are unknown. In the first case, a robust adaptive control term is utilized to account for unmodeled dynamics. For the latter, a robust adaptive term is augmented with a NN control law to achieve asymptotic tracking performance in contrast with most NN controllers where a bounded tracking error result is shown. Additionally, the NN approximation error is assumed to be a function of tracking errors instead of a constant upper bound, which is commonly found in the literature. The stability of the follower robots as well as the entire formation is demonstrated in each case using Lyapunov methods and numerical results are provided.     

On input‐to‐state stability of rigid‐body attitude control with quaternion representation

The concept of input‐to‐state stability (ISS) is important in robust control, as the state of an ISS system subject to disturbances can be stably regulated to a small region around the origin. In this study, the ISS property of the rigid‐body attitude system with quaternion representation is thoroughly investigated. It has been known that the closed loop with continuous controllers is not ISS with respect to arbitrarily small external disturbances. To deal with this problem, hybrid proportional‐derivative controllers with hysteresis are proposed to render the attitude system ISS. The controller is far from new, but it is investigated in a new aspect. To illustrate the applications of the results about ISS, 2 new robust hybrid controllers are designed. In the case of large bounded time‐varying disturbances, the hybrid proportional‐derivative controller is designed to incorporate a saturated high‐gain feedback term, and arbitrarily small ultimate bounds of the state can be obtained; in the case of constant disturbances, a hybrid adaptive controller is proposed, which is robust against small estimate error of inertia matrix. Finally, simulations are conducted to illustrate the effectiveness of the proposed control strategies.     

Robust H ∞ and adaptive tracking control against actuator faults with a linearised aircraft application

This article studies the problem of designing adaptive fault-tolerant H _∞ tracking controllers for a class of aircraft flight systems against general actuator faults and bounded perturbations. A robust adaptive state-feedback controller is constructed by a stabilising controller gain and an adaptive control gain function. Using mode-dependent Lyapunov functions, linear matrix inequality-based conditions are developed to find the controller gain such that disturbance attenuation performance is optimised. Adaptive control schemes are proposed to estimate the unknown controller parameters on-line for unparametrisable stuck faults and perturbation compensations. Based on Lyapunov stability theory, it is shown that the resulting closed-loop systems can guarantee asymptotic tracking with H _∞ performances in the presence of faults on actuators and perturbations. An application to a decoupled linearised dynamic aircraft system and its simulation results are given.     

Robust control of robot manipulators based on uncertainty and disturbance estimation

In this work, uncertainty and disturbance estimation (UDE) based robust trajectory tracking controller for rigid link manipulators was proposed. The UDE was employed to estimate the composite uncertainty that comprises the effects of system nonlinearities, external disturbances, and parametric uncertainties. A feedback linearization based controller was designed for trajectory tracking, and the same was augmented by the UDE‐estimated uncertainties to achieve robustness. The resulting controller however required measurement of joint velocities apart from the joint positions. To address the issue, an observer that employed the UDE‐estimated uncertainties for robustness was proposed, giving rise to the UDE‐based controller–observer structure. Closed‐loop stability of the overall system was established. The notable feature of the proposed design was that it neither required accurate plant model nor any information about the uncertainty. Also, the design needed only joint position measurements for its implementation. To demonstrate the effectiveness, simulation results of the proposed approach as applied to the trajectory tracking control of two‐link robotic manipulator and comparison of its performance with some of the well‐known existing controllers were presented. Lastly, hardware implementation of the proposed design for trajectory control of Quanser's single‐link flexible joint module was carried out, and it was shown that the proposed strategy offered a viable approach for designing implementable robust controllers for robots. Copyright © 2011 John Wiley & Sons, Ltd.     

Multilayer neural-net robot controller with guaranteed trackingperformance

A multilayer neural-net (NN) controller for a general serial-link rigid robot arm is developed. The structure of the NN controller is derived using a filtered error/passivity approach. No off-line learning phase is needed for the proposed NN controller and the weights are easily initialized. The nonlinear nature of the NN, plus NN functional reconstruction inaccuracies and robot disturbances, mean that the standard delta rule using backpropagation tuning does not suffice for closed-loop dynamic control. Novel online weight tuning algorithms, including correction terms to the delta rule plus an added robust signal, guarantee bounded tracking errors as well as bounded NN weights. Specific bounds are determined, and the tracking error bound can be made arbitrarily small by increasing a certain feedback gain. The correction terms involve a second-order forward-propagated wave in the backpropagation network. New NN properties including the notions of a passive NN, a dissipative NN, and a robust NN are introduced.     

Adaptive Neural Network Control For Smart Materials Robots Using Singular Perturbation Technique

In this paper, an adaptive neural network controller is presented for smart materials robots using Singular Perturbation techniques by modeling the flexible modes and their derivatives as the fast variables and link variables as slow variables. The neural network (NN) controller is to control the slow dynamics in order to eliminate the need tor the tedious dynamic modeling and the error prone process in obtaining the regressor matrix. In addition, inverse dynamic model evaluation is not required and the time‐consuming training process is avoided except for initializing the NNs based on the approximate function values at the initial posture at time t=0. The smart materials bonded along the links are used to active suppress the residue vibration. Simulation results have shown that the controller can control the system successfully and effectively.     

Neural-Network-Based State Feedback Control of a Nonlinear Discrete-Time System in Nonstrict Feedback Form

In this paper, a suite of adaptive neural network (NN) controllers is designed to deliver a desired tracking performance for the control of an unknown, second-order, nonlinear discrete-time system expressed in nonstrict feedback form. In the first approach, two feedforward NNs are employed in the controller with tracking error as the feedback variable whereas in the adaptive critic NN architecture, three feedforward NNs are used. In the adaptive critic architecture, two action NNs produce virtual and actual control inputs, respectively, whereas the third critic NN approximates certain strategic utility function and its output is employed for tuning action NN weights in order to attain the near-optimal control action. Both the NN control methods present a well-defined controller design and the noncausal problem in discrete-time backstepping design is avoided via NN approximation. A comparison between the controller methodologies is highlighted. The stability analysis of the closed-loop control schemes is demonstrated. The NN controller schemes do not require an offline learning phase and the NN weights can be initialized at zero or random. Results show that the performance of the proposed controller schemes is highly satisfactory while meeting the closed-loop stability.      

Autonomous mobile robots navigation using RBF neural compensator

This paper presents an approach to adaptive trajectory tracking of mobile robots which combines a feedback linearization based on a nominal model and a RBF-NN adaptive dynamic compensation. For a robot with uncertain dynamic parameters, two controllers are implemented separately: a kinematics controller and an inverse dynamics controller. The uncertainty in the nominal dynamics model is compensated by a neural adaptive feedback controller. The resulting adaptive controller is efficient and robust in the sense that it succeeds to achieve a good tracking performance with a small computational effort. The analysis of the RBF-NN approximation error on the control errors is included. Finally, the performance of the control system is verified through experiments.     

NEURAL NETWORK‐BASED OPTIMAL ADAPTIVE TRACKING USING GENETIC ALGORITHMS

This paper presents the use of neural networks (NNs) and genetic algorithms (GAs) to enhance the output tracking performance of partly known robotic systems. Two of the most potential approaches of adaptive control, i.e., the concept of variable structure control (VSC) and NN‐based adaptive control, are ingeniously combined using GAs to achieve high‐performance output tracking. GA is used to make the maximum use of different performance characteristics of two self‐adaptive NN modules by finding the switching function which best combines them. The method will be valid for any rigid revolute robot system. Computer simulations on our active binocular head are included for illustration and verification.     

Neural Network Adaptive Robust Control Of Siso Nonlinear Systems In A Normal Form

In this paper, performance oriented control laws are synthesized for a class of single‐input‐single‐output (SISO) n‐th order nonlinear systems in a normal form by integrating the neural networks (NNs) techniques and the adaptive robust control (ARC) design philosophy. All unknown but repeat‐able nonlinear functions in the system are approximated by the outputs of NNs to achieve a better model compensation for an improved performance. While all NN weights are tuned on‐line, discontinuous projections with fictitious bounds are used in the tuning law to achieve a controlled learning. Robust control terms are then constructed to attenuate model uncertainties for a guaranteed output tracking transient performance and a guaranteed final tracking accuracy. Furthermore, if the unknown nonlinear functions are in the functional ranges of the NNs and the ideal NN weights fall within the fictitious bounds, asymptotic output tracking is achieved to retain the perfect learning capability of NNs. The precision motion control of a linear motor drive system is used as a case study to illustrate the proposed NNARC strategy.