Learning Control For Robot Manipulators Research Articles

Intermittent Iterative Learning Control for Robot Manipulators Under Packet Dropouts

Intermittent Iterative Learning Control for Robot Manipulators Under Packet Dropouts

Adaptive learning control of robot manipulators via incremental hybrid neural network

A novel hybrid neural network based learning control method is proposed to improve trajectory tracking accuracy for complex robot manipulators in this paper. Firstly, a hybrid neural network is presented to improve the model accuracy and data efficiency, which is integrated by the Differential Newton-Euler Algorithm (DiffNEA) and Radial Basis Function Neural Network (RBFNN). In this hybrid neural network, the DiffNEA takes in charge of modeling the known rigid dynamics, while RBFNN takes in charge of capturing the unmodeled phenomena and external disturbances. Secondly, an incremental design method is proposed to determine optimal structure and parameters of the hybrid neural network. Thirdly, an adaptive learning controller based on the aforementioned hybrid neural network is designed to further reject the effects of unmodeled dynamics and external disturbances on trajectory tacking performance. Finally, experimental results are presented to validate the effectiveness of the proposed method.

Initial-Rectification Neuro-Adaptive Iterative Learning Control for Robot Manipulators With Input Deadzone and Nonzero Initial Errors

An initial-rectification adaptive iterative learning control scheme is proposed to solve the angle tracking problem of robot manipulators with input deadzone under nonzero initial errors. Lyapunov approach is utilized to design the controller. First, the initial-rectification auxiliary reference signal is constructed to overcome the obstacle caused by nonzero initial errors during ILC design. Second, adaptive ILC strategy and robust control strategy are adopted for dealing with deadzone nonlinearity. In addition, adaptive learning neural network is applied to approximate for uncertainties. The stability of closed-loop robotic system is rigorously proven by theoretical analysis. In the end, numerical simulation results are provided to verify the effectiveness of the proposed adaptive iterative learning control scheme.

Payload-adaptive iterative learning control for robotic manipulators

Abstract. The main purpose of the iterative learning control (ILC) method is to reduce the trajectory tracking error caused by an inaccurate model of the robot's dynamics. It estimates the tracking error and applies a learning operator to the output control signals to correct them. Today's ILC researchers are suggesting strategies for increasing the ILC's overall performance and minimizing the number of iterations required. When a payload (or a different end effector) is attached to a robotic manipulator, the dynamics of the robot change. When a new payload is added, even the most accurately approximated model of the dynamics will be altered. This will necessitate changes to the dynamics estimates, which may be avoided if the ILC process is used to control the system. When robotic manipulators are considered, this study analyses how the payload affects the dynamics and proposes ways to improve the ILC process. The study looks at the dynamics of a SCARA-type robot. Its inertia matrix is determined by the payload attached to it. The results show that the ILC method can correct for the estimated inertia matrix inaccuracy caused by the changing payload but at the cost of more iterations. Without any additional data of the payload's properties, the suggested technique may adjust and fine-tune the learning operator. On a preset reference trajectory, the payload adaptation process is empirically tested. When the same payload is mounted, the acquired adaptation improvements are then utilized for another desired trajectory. A computer simulation is also used to validate the suggested method. The suggested method increases the overall performance of ILC for industrial robotic manipulators with a set of similar trajectories but different types of end effectors or payloads.

Compound FAT-based prespecified performance learning control of robotic manipulators with actuator dynamics

In the framework of the backstepping algorithm, this article proposes a new function approximation technique (FAT)-based compound learning control law for electrically-driven robotic manipulators with output constraint. The Fourier series expansion is adopted in the learning-based design to approximate unknown terms in the system description. The accuracy of FAT approximation is also studied by defining an identification error, which is derived from a serial–parallel identifier. Furthermore, the output constraint is taken into account by integrating the error transformation, the performance function and the dynamic surface control in a compact framework. Following this idea, new compound adaptation laws are then constructed. The proposed compound learning controller confirms that all the signals of the overall system are uniformly ultimately bounded, ensuring the tracking error within the predefined bounds during operation. Different simulation scenarios applied to a robotic manipulator with motor dynamics illustrate the capability of the control algorithm.

Adaptive fuzzy logic with self-tuned membership functions based repetitive learning control of robotic manipulators

With increasing demand for using robotic manipulators in industrial applications, controllers specific for performing repeatable tasks are required. These controllers must also be robust to model uncertainties. To address this research issue, a repetitive learning control method fused with adaptive fuzzy logic techniques is designed. Specifically, modeling uncertainties are first modeled with a fuzzy logic network and an adaptive fuzzy logic strategy with online tuning is designed. The stability is investigated via Lyapunov type techniques where global uniform ultimate boundedness of closed loop system is guaranteed. Numerical simulation results obtained from a two degree of freedom robot manipulator model and experiments performed on a robot manipulator demonstrate the efficacy of the proposed control methodology.

Adaptive Iterative Learning Control for Robot Manipulators With Time-Varying Parameters and Arbitrary Initial Errors

In this paper, a novel error-tracking adaptive iterative learning control scheme is proposed to solve trajectory-tracking problem for a class of robot manipulators with time-varying parameters and arbitrary initial errors. Firstly, desired error trajectories are constructed for implementing error tracking strategy in the robotic systems, so as to relax the requirement of zero initial errors, which is usually assumed to be met in traditional iterative learning control algorithms. Secondly, with the help of reasonable parameterization to the robotic dynamics, the adaptive iterative control law is designed by using Lyapunov approach. Projection-free combined time-domain and iteration-domain adaptive learning strategy is adopted to estimate the unknown time-invariant parametric uncertainties, and difference learning strategy is adopted to estimate unknown time-varying parametric uncertainties. As the iteration number increases, the system error follows its desired error trajectory over the whole interval. As a result, system state can perfectly track the reference signal in the predetermined part interval. In the end, several numerical simulations are presented to demonstrate the effectiveness of the designed control scheme.

Real-time Machine Learning Control for Robotic Manipulator by LNB: Lion Naïve Bayes Algorithm

Real-time Machine Learning Control for Robotic Manipulator by LNB: Lion Naïve Bayes Algorithm

Virtual semi-active damping learning control for robot manipulators interacting with unknown environment

Position controllers are used for free motion, whereas force controllers are used for constrained motion of robotic manipulators. The hybrid controller switches between position and force control modes depending on whether the manipulator is in contact with the environment. To improve production efficiency, the velocity of contact between the manipulator and environment is not set to zero. However, the high impact force due to the nonzero contact velocity might damage the environment surface or manipulators. In this article, we propose a virtual semi-active damping learning method to suppress force overshoot without decreasing the contact velocity. Virtual semi-active damping is adjusted according to the manipulator position in force control. The limited-memory BFGS method is used to obtain the ideal impedance model for the unknown environment. By minimizing the defined cost function, we get the desired interaction performance. The correctness and effectiveness of the proposed method are verified by conducting simulations and experiments.

Robust Learning Control for Robot Manipulators With Random Initial Errors and Iteration-Varying Reference Trajectories

In this paper, we propose an error-tracking iterative learning control scheme to tackle the position tracking problem for robot manipulators with random initial errors and iteration-varying reference trajectories. Different from general usual ones, the control strategy in our work is to drive system errors perfectly track the desired error trajectories over the whole time interval as the iteration number increases, by which, the position trajectory and velocity trajectory can respectively track their reference trajectories during the predefined part operation interval. For fulfilling the control design, a new construction method of desired error trajectories is presented to remove the perfect initial resetting condition, which must be satisfied in most traditional iterative learning control algorithms. The uncertainties and disturbances in the robotic system dynamics are compensated by the robust approach and iterative learning approach, combinedly.

Neural Network-Based Adaptive Learning Control for Robot Manipulators With Arbitrary Initial Errors

In this paper, a neural network-based adaptive iterative learning control scheme is developed to solve the trajectory tracking problem for rigid robot manipulators with arbitrary initial errors. Time-varying boundary layers are used to relax the zero initial error condition which must be observed in traditional iterative learning control design, and adaptive learning neural networks are constructed to approximate uncertainties in robotic systems, whose optimal weights are estimated by using partial saturation difference learning method. For arbitrary bounded initial state errors, the tracking error of robot manipulators will asymptotically converge to a tunable residual set as the iteration number increases. An illustrative example and the comparisons are provided to demonstrate the effectiveness of the proposed neural network-based adaptive iterative learning control scheme.

Adaptive Iterative Learning Control of Robot Manipulators for Friction Compensation

Iterative learning control (ILC) has been well recognized for its ability to improve the tracking performance of systems that perform repetitive tasks. Its achievable performance, however, can be significantly degraded by the presence of non-repetitive disturbances which vary every iteration. Such may be a case for high-precision robot manipulators which are commonly subject to nonlinear and velocity-dependent friction forces. With a traditional PD-type ILC scheme, as joint velocities change along iterations, friction forces can vary substantially and deteriorate the performance of ILC. To address this problem, we propose an adaptive ILC algorithm, in which an adaptive friction compensation signal is introduced with ILC to adaptively identify the friction model over multiple iterations. Theoretical convergence analysis is provided with simulation verification on a 3-degree-of-freedom (DOF) planar manipulator. Experimental verification is also performed on a 5-DOF robot for silicon wafer handling. The verification results show that the proposed adaptive ILC approach can achieve significantly better tracking performance than traditional ILC methods.

Learning Control of Robot Manipulators in Task Space

AbstractTwo important properties of industrial tasks performed by robot manipulators, namely, periodicity (i.e., repetitive nature) of the task and the need for the task to be performed by the end‐effector, motivated this work. Not being able to utilize the robot manipulator dynamics due to uncertainties complicated the control design. In a seemingly novel departure from the existing works in the literature, the tracking problem is formulated in the task space and the control input torque is aimed to decrease the task space tracking error directly without making use of inverse kinematics at the position level. A repetitive learning controller is designed which “learns” the overall uncertainties in the robot manipulator dynamics. The stability of the closed‐loop system and asymptotic end‐effector tracking of a periodic desired trajectory are guaranteed via Lyapunov based analysis methods. Experiments performed on an in‐house developed robot manipulator are presented to illustrate the performance and viability of the proposed controller.

State Space Constrained Iterative Learning Control for Robotic Manipulators

AbstractReal‐life work operations of industrial robotic manipulators are performed within a constrained state space. Such operations most often require accurate planning and tracking a desired trajectory, where all the characteristics of the dynamic model are taken into consideration. This paper presents a general method and an efficient computational procedure for path planning with respect to state space constraints. Given a dynamic model of a robotic manipulator, the proposed solution takes into consideration the influence of all imprecisely measured model parameters, making use of iterative learning control (ILC). A major advantage of this solution is that it resolves the well‐known problem of interrupting the learning procedure due to a high transient tracking error or when the desired trajectory is planned closely to the state space boundaries. The numerical procedure elaborated here computes the robot arm motion to accurately track a desired trajectory in a constrained state space taking into consideration all the dynamic characteristics that influence the motion. Simulation results with a typical industrial robot arm demonstrate the robustness of the numerical procedure. In particular, the results extend the applicability of ILC in robot motion control and provide a means for improving the overall trajectory tracking performance of most robotic systems.

On the Development of Learning Control for Robotic Manipulators

Learning control for robotic manipulators has been developed over the past decade and to the best of the authors’ knowledge, it is still in its infant development stage; the authors believe that it will become one of the most promising directions in the control area in robotic manipulators. Learning control in robotic manipulators is mainly used to address the issue that the friction at the joints of robotic mechanisms and other uncertainties may exist in the dynamic models, which are very complex and may even be impossible to model mathematically. In this paper, the authors review and discuss the learning control in robotic manipulators and some issues in learning control for robotic manipulators are also illustrated. This review is able to give a general guideline for future research in learning control for robotic manipulators.

Linguistic Lyapunov reinforcement learning control for robotic manipulators

We propose a Lyapunov theory based linguistic reinforcement learning (RL) framework for stable tracking control of robotic manipulators. In particular, we employ Lyapunov theory to constrain fuzzy rule consequents for ensuring stability of the designed controller. Proposed fuzzy RL controller employs Lyapunov theory dictated rules for discovering an optimal yet stable control strategy for robotic manipulators. Furthermore, our proposed linguistic RL controller handles payload variations and external disturbances quite effectively. We validate linguistic Lyapunov RL controller on two benchmark control problems: (i) a standard two-link robotic arm manipulator, and (ii) a two link selective compliance assembly robotic arm (SCARA). Simulation results and comparison against (a) baseline fuzzy Q learning (FQL) controller, and (b) a recently proposed Lyapunov theory based Markov game controller showcases our controller's superior tracking performance and lower computational complexity. Furthermore, our controller exhibits high stability with disturbances and payload variations.

Iterative learning control for robotic manipulators: A bounded‐error algorithm

SUMMARYThis paper presents a model‐based nonlinear iterative learning control (NILC) for nonlinear multiple‐input and multiple‐output mechanical systems of robotic manipulators. An algorithm of a new strategy for the NILC implementation is proposed. This algorithm ensures that trajectory‐tracking errors of the proposed NILC, when implemented, are bounded by a given error norm bound. Both standard and bounded‐error learning control laws with feedback controllers attached are considered. The NILC synthesis is based on a dynamic model of a six degrees of freedom robotic manipulator. The dynamic model includes viscous and Coulomb friction and input generalized torques are bounded. With respect to the bounded‐error and standard learning processes applied to a virtual PUMA 560 robot (Unimation, Inc. Danburry, CT, USA), simulation results are presented in order to verify maximal tracking errors, convergence and applicability of the proposed learning control. Copyright © 2013 John Wiley & Sons, Ltd.

Velocity observer-based iterative learning control for robot manipulators

This article addresses the problem of designing an iterative learning control for trajectory tracking of rigid robot manipulators subject to external disturbances, and performing repetitive tasks, without using the velocity measurement. For solving this problem, a velocity observer having an iterative form is proposed to reconstruct the velocity signal in the control laws. Under assumptions that the disturbances are repetitive and the velocities are bounded, it has been shown that the whole control system (robot plus controller plus observer) is asymptotically stable and the observation error is globally asymptotically stable, over the whole finite time-interval when the iteration number tends to infinity. This proof is based upon the use of a Lyapunov-like positive definite sequence, which is shown to be monotonically decreasing under the proposed observer–controller schemes.

Simulation-based design of monotonically convergent iterative learning control for nonlinear systems

This paper deals with a simulation-based design of model-based iterative learning control (ILC) for multi-input, multi-output nonlinear time-varying systems. The main problem of the implementation of the nonlinear ILC in practice is possible inadmissible transient growth of the tracking error due to a non-monotonic convergence of the learning process. A model-based nonlinear closed-loop iterative learning control for robot manipulators is synthesized and its tuning depends on only four positive gains of both controllers - the feedback one and the learning one. A simulation-based approach for tuning the learning and feedback controllers is proposed to achieve fast and monotonic convergence of the presented ILC. In the case of excessive growth of transient errors this approach is the only way for learning gains tuning by using classical engineering techniques for practical online tuning of feedback gains

Adaptive Iterative Learning Control for Robot Manipulators with Initial Resetting Errors

In this paper, an adaptive iterative learning control is presented for robot manipulators with unknown parameters, performing repetitive tasks. In order to overcome the initial resetting errors, an auxiliary tracking error function is introduced. The adaptive algorithm is derived along the iteration axis to search for suitable parameter values. The technical analysis shows convergence of the tracking errors. Finally, simulation results are provided to illustrate the effectiveness of the proposed controller.