Design and implementation of an adaptive neural network observer–based backstepping sliding mode controller for robot manipulators

The paper investigates a modified adaptive super-twisting sliding mode control (ASTSMC) for robotic manipulators with input saturation. To avoid singular perturbation while increasing the convergence rate, a modified sliding mode surface (SMS) is developed in this method. Using the proposed SMS, an ASTSMC is developed for robot manipulators, which not only achieves strong robustness but also ensures finite-time convergence. The boundary of lumped uncertainties cannot be easily obtained. A modified adaptive law is developed such that the boundaries of time-varying disturbance and its derivative are not required. Considering input saturation in practical cases, an ASTSMC with saturation compensation is proposed to reduce the effect of input saturation on tracking performances of robot manipulators. The finite-time convergence of the proposed scheme is analyzed. Through comparative simulations against two other sliding mode control schemes, the proposed method has been validated to possess strong adaptability, effectively adjusting control gains; simultaneously, it demonstrates robustness against disturbances and uncertainties.

RBFNN-based nonsingular fast terminal sliding mode control for robotic manipulators including actuator dynamics

ABSTRACTIn this article, we give some comments on the article ‘A new terminal sliding mode control for robotic manipulators’. The article presents a new terminal sliding mode control approach for global finite-time tracking of robotic manipulators. We point out a serious error occurred through the article, leading to the ineffectiveness of the proposed approach. A correction is proposed. Comparisons are presented.

This paper presents a novel adaptive fast-terminal neuro-sliding mode control (AFTN-SMC) for a two-link robot manipulator with unknown dynamics and external disturbances. The proposed controller is chattering-free and adaptive to the time-varying system uncertainties. Furthermore, the radial base function neural network (RBFNN) is employed to approximate the unknown state dynamics. The simulations have been completed in MATLAB, which illustrates the successful implementation of the proposed controller. The results showcased the effectiveness of the AFTN-SMC in achieving accurate tracking and stability, even in the presence of uncertainties and parameter variations. The incorporation of the RBFNN in the controller proved to be a valuable tool for approximating the unknown dynamics, enabling accurate estimation and control of the manipulator’s behavior. The research presented in this paper contributes to the advancement in control techniques for robot manipulators in diverse industrial and automation applications.

Adaptive second order terminal sliding mode controller for robotic manipulators

This article aims at the problem of trajectory tracking for industrial robotic manipulators with control backlash. An arctangent terminal sliding mode surface is developed to deal with the lumped disturbance and enhance the robustness of the system. A novel adaptive super‐twisting sliding mode control method is developed to achieve fast convergence and continuous control. The chattering in control law is surmounted by using super‐twisting method. The lumped disturbance with unknown upper bound is compensated with the help of the adaptive technique. Based on the Lyapunov stability theory, the sliding mode surface will be arrived in a finite time and the trajectory tracking error will converge to zero in a finite time. The feasibility of the proposed control scheme is validated through an example of a two‐link robotic manipulator.

In this paper, radial basis function network (RBFN) with sliding-mode controller (SMC) is designed to the joint position control of two-link robot manipulators for periodic motion and predefined trajectory tracking control. Radial basis function uses curve fitting mode to obtain the nonlinear mapping. The unavoidable learning procedure degrades its transient performance in the existence of disturbance. Sliding-mode control is effective in overcoming uncertainties and has a fast transient response, while the control effort is discontinuous and creates chattering. For this defect, a saturation function is utilized to improve it. The back-propagation (BP) algorithm and Lyapunov stability theorem are used to decide a suitable update law and sliding-mode switch gain, respectively. Thus, the satisfied performance will be obtained, which better than the controller with single RBFN controller, sliding mode controller. The simulated results of a two-link robotic manipulator for the joint frictions, changing link masses and adding external disturbances are provided to show that the effectiveness of the proposed control scheme.

This paper intends to design and develop an adaptive fuzzy sliding mode controller (SMC) for robotic manipulator. Since it is not viable to pair the SMC operations with the system model every time, this paper adopts a Fuzzy Inference System (FIS) to replace the system model. It effectively achieves the experimentation in two phases. Accordingly, in the first phase, it attains the accurate features of the system model based on varied samples to characterize the robotic manipulator. In the second stage, it represents the derived fuzzy rules based on adaptive fuzzy membership functions. Moreover, it establishes the self-adaptiveness using Grey Wolf Optimization (GWO) to attain the adaptive fuzzy membership functions. The analysis distinguishes the efficiency of the adopted technique with the optimal investigational scheme and the traditional schemes such as SMC, Fuzzy SMC (FSMC) and GWO-SMC. Moreover, the comparative analysis is also performed by including the noise and validates the effectiveness of the proposed and conventional models. Index Terms : Sliding Mode Control, Robot manipulators, Controller, Noise.

This paper presents a sliding mode controller for trajectory tracking of robotic manipulators with actuator faults. To achieve finite-time convergence of tracking errors and desirable tracking precision, a fast nonsingular terminal sliding mode controller is designed. The uncertainty caused by actuator faults is transformed into system disturbance which is compensated by introducing the dynamic gain technique. As a result, the prior knowledge about upper bound of system disturbance is not required. Moreover, the sign function is replaced by the saturation function in the control law, so the chattering phenomenon is attenuated. Finally, the designed controller is applied to control a two-link robotic manipulator in simulation, and results validate the effectiveness of the control scheme.

A sliding mode control based on motor angular speed control has been presented for a robot manipulator grasping a payload with mass variation. In order to guarantee the continuity of the control signals applied to the actuators of the robot manipulator, a sliding mode control with integral compensation is adopted. Improvement of robustness of the control system against payload mass variation is obtained by introducing a sliding mode feedforward signal. The control scheme is applied to a three joint robot manipulator, control performance both with payload torque compensation and without payload torque compensation are investigated. Simulation results show that the control scheme presented, is robust against payload mass variation and has satisfactory control performance.

Ahstract-This paper introduces a sliding mode control (SMC) strategy for robotic manipulators subject to uncertainties, disturbances, and input and output quantization. A continuous SMC method is proposed and a hysteretic quantizer with sector-bounded quantization errors is utilized to quantize the control input signal. Furthermore, a super-twisting algorithm (STA) based observer is adopted to estimate the unmeasured states by using quantized values of output signals. It is demonstrated that under the proposed SMC, the sliding variable can converge to a quasi sliding mode. Finally, a networked two-link robotic manipulator is used to verify the effectiveness of the proposed control method.

This paper develops a novel non-singular terminal sliding mode control scheme for trajectory tracking of robot manipulators in the presence of external disturbances and uncertainties. Firstly, with the introduction of two nonlinear terms, a newly terminal sliding surface is designed. Then utilizing this sliding surface, a novel non-singular terminal sliding mode controller is proposed to eliminate the reaching interval, singularity issue and subsequently with this controller, the finite time error convergence is also assured. In the proposed controller, radial basis function neural network is employed to approximate highly uncertain nonlinear dynamics of robot manipulators using update laws derived with Lyapunov approach. Meanwhile, the effects of approximation errors are attenuated with $$H_\infty $$ performance criterion by introducing a robust term into the controller. As a result of proposed approach, asymptotic convergence of tracking errors is achieved within finite time and the approximation errors are attenuated to desired levels. The numerical simulation result shows the effectiveness of proposed controller for the case of microbot type robot manipulator.

Nowadays the feedback linearization and backstepping techniques are introduced as methods for linearization of a system with coordinate transformation and nonlinear designing, respectively. The feedback linearization and backstepping techniques are robust methods, however this study indicates that combining of them and adding nonlinear disturbance observer increases the system robustness. In this paper, the system linearization with backstepping process has been studied. Combining of above mentioned techniques has been used for linearization in this method. The systems have been practically exposed to disturbances and uncertainties. Nonlinear disturbance observer has a good ability to estimate disturbances and nonlinear dynamics, so it is useful method for increasing performance of control methods, reducing the effects of disturbances and system uncertainties. The presented control method with nonlinear disturbance observer improves the system robustness against different types of uncertainties, so this method is a modified technique. The proposed design process consists of two steps: First, the nonlinear disturbance observer has been designed to estimate the uncertainties and external disturbances applied to system. Second, a controller has been designed using combined feedback linearization-backstepping method that used prior estimations to decrease the effects of external disturbances and uncertainties in the control input.

In recent years, robotic systems have been widely used in different applications, and this has motivated researchers to develop different control methods. A model-free, intelligent, robust control method for a nonlinear robotic manipulator system is proposed in this work. This paper presents a novel solution for the major drawbacks of the sliding mode control scheme, which are chattering. Prior knowledge is needed about the dynamic model of the controlled system and the upper bound of uncertainty. In this paper, a fuzzy-like PD controller with SMC (FLPDSM) is proposed. The fuzzy-like PD controller was designed according to fuzzy rules and membership functions based on the nominal model of the robot manipulator. A robust control term was added to the control signal to compensate for the system uncertainty, and external disturbances are compensated by adding an auxiliary robust term to the SMC control law. Two methods for designing robust control terms are proposed. The first proposed method assumes that the upper bound of system uncertainty is known although it cannot be exactly determined due to external disturbances and uncertainty. Hence, a second method was proposed that assumes this bound to be unknown, and an adaptive gain based on Lyapunov theory was used to derive the adaptation law. The Lyapunov second method was used to ensure the stability of the closed loop system. Performance tests on the proposed methods were implemented through simulation studies for the two-link robotic manipulator, and the test results were compared with the standard SMC to verify the effectiveness of the proposed method. A good trajectory tracking with a high robustness against parameter variations and external disturbances was observed under the presented control scheme.

This work proposes a non-singular fast terminal sliding mode control (NFTSMC) strategy based on the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm and a nonlinear disturbance observer (NDO) to address the issues of modeling errors, motion disturbances, and transmission friction in robotic manipulators. Firstly, a novel modular serial 5-DOF robotic manipulator configuration is designed, and its kinematic and dynamic models are established. Secondly, a nonlinear disturbance observer is employed to estimate the total disturbance of the system and apply feedforward compensation. Based on boundary layer technology, an improved NFTSMC method is proposed to accelerate the convergence of tracking errors, reduce chattering, and avoid singularity issues inherent in traditional terminal sliding mode control. The stability of the designed control system is proved using Lyapunov stability theory. Subsequently, a deep reinforcement learning (DRL) agent based on the TD3 algorithm is trained to adaptively adjust the control gains of the non-singular fast terminal sliding mode controller. The dynamic information of the robotic manipulator is used as the input to the TD3 agent, which searches for optimal controller parameters within a continuous action space. A composite reward function is designed to ensure the stable and efficient learning of the TD3 agent. Finally, the motion characteristics of three joints for the designed 5-DOF robotic manipulator are analyzed. The results show that compared to the non-singular fast terminal sliding mode control algorithm based on a nonlinear disturbance observer (NDONFT), the non-singular fast terminal sliding mode control algorithm integrating a nonlinear disturbance observer and the Twin Delayed Deep Deterministic Policy Gradient algorithm (TD3NDONFT) reduces the mean absolute error of position tracking for the three joints by 7.14%, 19.94%, and 6.14%, respectively, and reduces the mean absolute error of velocity tracking by 1.78%, 9.10%, and 2.11%, respectively. These results verify the effectiveness of the proposed algorithm in enhancing the trajectory tracking accuracy of the robotic manipulator under unknown time-varying disturbances and demonstrate its strong robustness against sudden disturbances.