Control Scheme For Robot Manipulators Research Articles

Lifelong deep learning‐based control of robot manipulators

SummaryThis study proposes a lifelong deep learning control scheme for robotic manipulators with bounded disturbances. This scheme involves the use of an online tunable deep neural network (DNN) to approximate the unknown nonlinear dynamics of the robot. The control scheme is developed by using a singular value decomposition‐based direct tracking error‐driven approach, which is utilized to derive the weight update laws for the DNN. To avoid catastrophic forgetting in multi‐task scenarios and to ensure lifelong learning (LL), a novel online LL scheme based on elastic weight consolidation is included in the DNN weight‐tuning laws. Our results demonstrate that the resulting closed‐loop system is uniformly ultimately bounded while the forgetting is reduced. To demonstrate the effectiveness of our approach, we provide simulation results comparing it with the conventional single‐layer NN approach and confirm its theoretical claims. The cumulative effect of the error and control input in the multitasking system shows a 43% improvement in performance by using the proposed LL‐based DNN control over recent literature.

Uncalibrated Adaptive Visual Servoing of Robotic Manipulators with Uncertainties in Kinematics and Dynamics

In the study, we propose a novel adaptive visual servoing control scheme for robotic manipulators with kinematic and dynamic uncertainties, where the camera used is uncalibrated, which implies that its intrinsic and extrinsic parameters are unavailable for measurement. For our scheme, a depth-independent composite Jacobian matrix is constructed to make visual parameters and robotic physical parameters appear linearly in a parametrized uniform form so that an adaptive algorithm can be developed to estimate their values. With the raised adaptive algorithm, the potential singularity of the Jacobian matrix can be well circumvented by updating estimated parameters in an appropriate tiny range of actual values. With our scheme, the asymptotic convergence of the image tracking error to zero is established successfully, in addition to the signal boundedness of the closed-loop system. The effectiveness of the proposed scheme is confirmed by simulation results based on a 6-DOF PUMA manipulator.

Adaptive fault-tolerant visual control of robot manipulators using an uncalibrated camera

In this paper, we propose an adaptive fault-tolerant visual control scheme for robotic manipulators with possible actuator failures in an uncalibrated environment. Most existing visual control approaches for robot system do not take into account actuator failures, which may prominently affect the transient performance of the system in practice. In order to moderate the detrimental and adverse effects of actuator failures on the system, a new adaptive algorithm is proposed to compensate stuck-type failures occurred in actuators. Moreover, by proposing a decoupling method, the uncertain parameter model of actuator failure is successfully separated from the dynamics model while the two models are coupled in most existing results [e.g., (Rugthum and Tao in Robotica 34(7):1529–1552, 2016; Rugthum in: International conference on engineering, applied sciences, and technology (ICEAST), pp 1–4, 2018)]. And the stability of the dynamic system and the convergence of the image error are proved by the Lyapunov analysis method. Finally, the effectiveness of the proposed control scheme is verified by comparing and analysing the tracking performance of the 3-DOF manipulator under different failure parameters.

Dual-Loop Optimal Control of a Robot Manipulator and Its Application in Warehouse Automation

The goal of this work is to develop the next generation of coordinated optimal planning and control schemes for real-world robotic applications, with cost-effective intelligent robots that can safely and robustly perform the tasks at hand. This article presents a dual-loop optimal hierarchical control scheme for robotic manipulators consisting of outer and inner loops. The outer kinematic control loop in the operational space provides a joint velocity reference signal to the inner one. The kinematic control is formulated as a closed-loop optimal control approach to trajectory generation where the desired target (possibly time-varying) is obtained by acting upon the feedback from the actual state of the robot. The kinematic control is obtained using a closed-form analytic solution of the Hamilton–Jacobi–Bellman (HJB) equation. The proposed methodology defines the task in terms of the integral cost function, which results in a global optimal solution. The inner dynamic control loop consists of a neural network (NN)-based adaptive critic (AC) optimal tracking control scheme. The online NN approximator-based dynamic controller learns the infinite-horizon cost function related to inner loop error dynamics in continuous time and calculates the corresponding optimal control input to minimize the cost function forward in time. The stability and the performance of the proposed control scheme are shown theoretically via the Lyapunov approach and also verified experimentally using a 7-DOF Barrett WAM robot manipulator. The warehousing applications of the proposed dual-loop control scheme have been demonstrated experimentally in an exact warehouse setting. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This article was motivated by our previous experiences in the Amazon Robotics Challenge (ARC) competitions as a participant. Although the major lessons from those events revealed many important issues toward warehouse automation both from robotic vision and grasping aspects, the application aspects of control engineering to solution for these real-world problems could significantly benefit the today’s highly automated society. The intention of this article is to address this situation by designing a cost-effective robot manipulator control scheme by optimizing robot manipulation trajectories in the outer loop along with the actuator input in the inner loop. Therefore, we propose a dual-loop optimal control scheme for robotic manipulations under a cost-optimal framework with guaranteed stability proof via the Lyapunov approach. This results in smoother trajectories with cost-effective control actuator inputs than the state-of-the-art methods. We believe that this work can be beneficial for academic and industrial research to design more advanced and optimized solutions in this domain.

Barrier Lyapunov function-based robot control with an augmented neural network approximator

PurposeConsidering the complexity of dynamic and friction modeling, this paper aims to develop an adaptive trajectory tracking control scheme for robot manipulators in a universal unmodeled method, avoiding complicated modeling processes.Design/methodology/approachAn augmented neural network (NN) constituted of radial basis function neural networks (RBFNNs) and additional sigmoid-jump activation function (SJF) neurons is introduced to approximate complicated dynamics of the system: the RBFNNs estimate the continuous dynamic term and SJF neurons handle the discontinuous friction torques. Moreover, the control algorithm is designed based on Barrier Lyapunov Function (BLF) to constrain output error.FindingsLyapunov stability analysis demonstrates the exponential stability of the closed-loop system and guarantees the tracking errors within predefined boundaries. The introduction of SJFs alleviates the limitation of RBFNNs on discontinuous function approximation. Owing to the fast learning speed of RBFNNs and jump response of SJFs, this modified NN approximator can reconstruct the system model accurately at a low compute cost, and thereby better tracking performance can be obtained. Experiments conducted on a manipulator verify the improvement and superiority of the proposed scheme in tracking performance and uncertainty compensation compared to a standard NN control scheme.Originality/valueAn enhanced NN approximator constituted of RBFNN and additional SJF neurons is presented which can compensate the continuous dynamic and discontinuous friction simultaneously. This control algorithm has potential usages in high-performance robots with unknown dynamic and variable friction. Furthermore, it is the first time to combine the augmented NN approximator with BLF. After more exact model compensation, a smaller tracking error is realized and a more stringent constraint of output error can be implemented. The proposed control scheme is applicable to some constraint occasion like an exoskeleton and surgical robot.

Admittance Force Tracking Control Schemes for Robot Manipulators under Uncertain Environment and Dynamics

Admittance Force Tracking Control Schemes for Robot Manipulators under Uncertain Environment and Dynamics

Finite-Time Tracking Controller Design of Perturbed Robotic Manipulator Based on Adaptive Second-Order Sliding Mode Control Method

This article presents an adaptive finite time second-order sliding mode tracking control scheme for robotic manipulators. A new control law is suggested to force the trajectories of the robot manipulator to move from all initial conditions to proportional-integral-derivative switching surface in the finite time and stay on it. Moreover, the adaptation law rejects the requirement of knowledge about upper bound of the external perturbations. It is difficult to exactly determine the upper bound of the perturbations in the practical systems, such as robot manipulators. Unlike the existing methods, the new adaptive finite time second-order sliding mode tracker for $n$ -link robot manipulators enables accurate tracking control, robust performance and parameter tuning. The suggested approach presents the design of a robust controller such that the tracking errors of robot manipulator can reach the equilibrium in the finite time. Through the combination of the finite time tracker and disturbance observer, the position tracking purpose of manipulator joints is accurately performed not only in the nominal environment, but also in the existence of different types of perturbations. The robustness performance and effectiveness of the offered technique are studied in simulation and experimental results.

Fuzzy descriptor tracking control with guaranteed L∞ error-bound for robot manipulators

This paper is concerned with the nonlinear tracking control design for robot manipulators. In spite of the rich literature in the field, the problem has not yet been addressed adequately due to the lack of an effective control design. Using a descriptor fuzzy model-based framework, we propose a new approach to design a feedback-feedforward control scheme for robot manipulators in a general form. The goal is to guarantee a small level of an [Formula: see text] gain specification to improve the tracking performance while significantly reducing the numerical complexity for real-time implementation. Based on Lyapunov stability arguments, the control design is formulated as a convex optimization problem involving linear matrix inequalities. Numerical experiments performed with a high-fidelity manipulator benchmark model, embedded in the Simscape MultibodyTM environment, demonstrate the effectiveness of the proposed control solution over existing standard approaches.

An Observer-Based Neural Adaptive $PID^2$ Controller for Robot Manipulators Including Motor Dynamics With a Prescribed Performance

This article proposes a novel prescribed performance-based neural adaptive control scheme for robot manipulators including motor dynamics under model uncertainties without velocity, acceleration, and input current measurements. The prescribed performance function approach is used to transform a constrained tracking problem of the robot model including motor dynamics into an unconstrained third-order error model in Euler-Lagrange form which inherits all properties of the robot dynamics. Then, a projection-type neural adaptive PID <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> controller (a PID controller with the second-order derivative) in conjunction with a velocity-acceleration observer is proposed. Lyapunov's direct method is used to prove that the tracking and state observation errors are semiglobally uniformly ultimately bounded and converge to a small ball around the origin with a prescribed overshoot/undershoot, convergence rate, and final tracking accuracy. Finally, simulation, experimental results on a SCARA robot and comparative studies verify that the proposed controller is effective for the joint position trajectory tracking of robot manipulators in the industrial automation with minimum measurement and hardware requirements.

A generalized adaptive stiffness control scheme for robot manipulators with bounded inputs

AbstractIn general, indirect force control schemes (stiffness, impedance, etc.) assume that robot actuators can provide any torque value to achieve the goal of interaction control. This study attempts to regulate robot–environment interaction by generating bounded control signals and to avoid accurate knowledge of the parameters associated with gravitational effects and the stiffness of the environment. To achieve this aim, a generalized and saturating adaptive stiffness control scheme in task‐space is proposed. For the purpose of this work, the interaction or contact between the end‐effector of a robot manipulator and the environment is modeled as a vector of bounded spring‐like forces. The proposed control approach has a proportional‐derivative structure with static model‐based compensation of gravitational and interaction forces, which it achieves by including a regressor‐based adaptive term. As a theoretical basis to support the proposal, Lyapunov's stability analysis of the closed‐loop equilibrium vector is presented. Finally, the suitability of the proposed stiffness control scheme for interaction tasks is verified through simulations and experimental tests by using three‐degree‐of‐freedom robotic arms.

Neural-Learning-Based Force Sensorless Admittance Control for Robots With Input Deadzone

This article presents a neural network based admittance control scheme for robotic manipulators when interacting with the unknown environment in the presence of the actuator deadzone without needing force sensing. A compliant behavior of robotic manipulators in response to external torques from the unknown environment is achieved by admittance control. Inspired by broad learning system, a flatted neural network structure using radial basis function (RBF) with incremental learning algorithm is proposed to estimate the external torque, which can avoid retraining process if the system is modeled insufficiently. To deal with uncertainties in the robot system, an adaptive neural controller with dynamic learning framework is developed to ensure the tracking performance. Experiments on the Baxter robot have been implemented to test the effectiveness of the proposed method.

Adaptive Predefined Performance Neural Control for Robotic Manipulators with Unknown Dead Zone

This paper proposes an adaptive predefined performance neural control scheme for robotic manipulators in the presence of nonlinear dead zone. A neural network (NN) is utilized to estimate the model uncertainties and unknown dynamics. An improved funnel function is designed to guarantee the transient behavior of the tracking error. The proposed funnel function can release the assumption on the conventional funnel control. Then, an adaptive predefined performance neural controller is proposed for robotic manipulators, while the tracking errors fall within a prescribed funnel boundary. The closed-loop system stability is proved via Lyapunov function. Finally, the numerical simulation results based on a 2-DOF robotic manipulator illustrate the control effect of the presented approach.

Composite Learning Enhanced Neural Control for Robot Manipulator With Output Error Constraints

This article presents a control scheme for robot manipulators with the consideration of output error constraints, unknown dynamics, and bounded disturbances. A modified virtual input variable in the second stage design of the dynamic surface control scheme is proposed, which can enhance the robustness of the controller. Bounded disturbances due to the situations that the base is not well fixed if the robot manipulator is mounted at a mobile platform are considered and suppressed. Besides, the detailed implementation process of the composite learning laws adopted for enhancing the radial basis function neural network is presented. Lyapunov stability analysis verifies that the proposed control scheme ensures the trajectory tracking errors stay within predefined boundaries and parameter estimate errors converge without a stringent condition termed persistent excitation. Experimental results show the superiority of the proposed controller regarding parameter estimation and tracking capabilities.

Stiff and safe task-space position and attitude controller for robotic manipulators

This paper proposes a stiff and safe task-space position and attitude control scheme for robotic manipulators. This study extends the work of Kikuuwe et al’s. (2006) velocity-bounding proxy-based sliding mode control by explicitly addressing the attitude part. The proposed controller has a Jacobian-based structure, which realizes smooth trajectories when the desired attitude is far rotated from the actual attitude. It also imposes arbitrary magnitude limits on the end-effector velocity, angular velocity, and each actuator force without sacrificing a stiffness, which is the same level as a high-gain PID position control below the limits. The benefit of the proposed controller becomes apparent after the robot yields to external forces due to force saturations, when the robot makes contact with obstacles. In such a situation, if the external forces disappear, the controller generates overdamped resuming motion from large tracking errors. The proposed controller can be expected to enhance the safety of robotic applications for the human–robot interaction. The proposed method is validated by experiments employing a six-degree of freedom industrial manipulator.

A 3D Path Following Control Scheme for Robot Manipulators

We describe a novel path following control scheme for robot manipulators where constant tool velocity of travel on a surface is desirable. The path following scheme is applicable to general situations where the surface geometry is typically given in terms of measured data from a sensor. Considering the measured data points as control points, we utilize a cubic spline interpolation to generate a closed-form geometric description for the 3D path. Since joint velocity control is quite common in many industrial robots and most surface finishing tasks require travel with constant velocity along the path, we consider a 3D kinematic model for the end-effector with control inputs as rate of change of orientation and translational velocity that is locally tangent to the surface along the path. By utilizing a path variable and the tangent vector along the path, we formulate a converging path as the path that is traversed from a given robot end-effector position to the desired path and subsequent travel on the desired path on the surface. To evaluate the performance of the scheme, we have conducted a number of real-time experiments on a six degree-of-freedom industrial robot for several paths which can be employed for sanding of structures or deburring of large industrial cast parts and gears.

A family of hyperbolic-type control schemes for robot manipulators

A family of hyperbolic-type control schemes for robot manipulators

Force Sensorless Admittance Control With Neural Learning for Robots With Actuator Saturation

In this paper, we present a sensorless admittance control scheme for robotic manipulators to interact with unknown environments in the presence of actuator saturation. The external environment is defined as linear models with unknown dynamics. Using admittance control, the robotic manipulator is controlled to be compliant with external torque from the environment. The external torque acted on the end-effector is estimated by using a disturbance observer based on generalized momentum. The model uncertainties are solved by using radial basis neural networks (NNs). To guarantee the tracking performance and tackle the effect of actuator saturation, an adaptive NN controller integrating an auxiliary system is designed to handle the actuator saturation. By employing Lyapunov stability theory, the stability of the closed-loop system is achieved. The experiments on the Baxter robot are implemented to verify the effectiveness of the proposed method.

An adaptive robust control scheme for robot manipulators with unknown backlash nonlinearity in gears

This paper presents an adaptive robust control algorithm for the nonlinear dynamics of robot manipulators with unknown backlash in gears. The basic nonlinear model of a serial manipulator robot is used for the controller design, and this is combined with the nonlinear proposed dead zone model, based on the input and output torque. The main idea of providing this model is to achieve a dynamic model of the system considering the backlash of the robot joint gears, and having less complexity such that the developed controller does not need the inverse backlash model. The adaptive robust controller is developed, without using the inverse backlash model. The proposed controller is designed based on an unknown dead zone parameter and it guarantees the stability and path tracking of the robot trajectory with unknown dead zone parameter in the desired range. Numerical simulations are conducted to show the effectiveness of the proposed controller. Finally, the efficiency and capability of the proposed controller in dealing with the unknown backlash nonlinearities in gears of the manipulator are demonstrated by experimental results with a five-bar manipulator.

Fault Tolerant Control Scheme for Robotic Manipulators Affected by Torque Faults

A Fault Tolerant Control (FTC) scheme for robotic manipulators affected by actuator faults is proposed in this paper. The actuator fault consists in an unknown partial joint torque reduction, which causes a loss of the desired end-effector motion. The FTC scheme includes a Fault Detection and Diagnosis (FDD) system based on a first-order sliding mode observer, in order to detect and estimate the joint torque fault. The estimated fault is mapped into a kinematic deviation of the motion of the end effector from the desired one, and compensated at the level of the kinematic controller. Simulation results demonstrate the effectiveness of the proposed scheme for a planar manipulator affected by two types of actuator faults, namely bias fault and partial torque fault.

Saturating Stiffness Control of Robot Manipulators with Bounded Inputs

Abstract A saturating stiffness control scheme for robot manipulators with bounded torque inputs is proposed. The control law is assumed to be a PD-type controller, and the corresponding Lyapunov stability analysis of the closed-loop equilibrium point is presented. The interaction between the robot manipulator and the environment is modeled as spring-like contact forces. The proper behavior of the closed-loop system is validated using a three degree-of-freedom robotic arm.