Disturbance Observer-Based Neural Network Control of Cooperative Multiple Manipulators With Input Saturation

He, Wei; Sun, Yiming; Yan, Zichen; Yang, Chenguang; Li, Zhijun; Kaynak, Okyay

doi:10.1109/tnnls.2019.2923241

Cited by 101 publications

(55 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, such adaptive design is here introduced for strengthening adaptability and robustness of the coordinated saturation planning and TSMC tracking control scheme. As well, due to its powerful approaching capacity, high convergence rate and superior approaching precision, radical basis function neural network (RBFNN) technique [38,39,40] is utilized for identifying lumped uncertainties including of both sudden change and gradual change uncertainties.…”

Section: Literature Reviewmentioning

confidence: 99%

RBFNN based terminal sliding mode adaptive control for electric ground vehicles after tire blowout on expressway

Yang

Yue

Liu

et al. 2020

Applied Soft Computing

View full text Add to dashboard Cite

This paper proposes a radial basis function neural network (RBFNN) based terminal sliding mode control scheme for electric ground vehicles subject to tire blowout on expressway in presence of tire nonlinearities, unmodeled dynamics and external disturbances. For enhancing the longitudinal and lateral stability of the vehicle after tire blowout, a saturated velocity planner is firstly constructed for tracking the original motion trajectory, by which the longitudinal velocity and yaw rate saturation constraints can be effectively handled. Afterwards, a terminal sliding mode controller (TSMC) is designed for tracking the planned velocity signals because of its inherent finite time convergence rate and superior steady-state property, by which the adverse dynamic behaviors can be timely suppressed. Further, to strengthen the adaptability and robustness of the control scheme, a RBFNN approximator is developed for identifying the lumped uncertainty, such as tire nonlinearities, unmodeled dynamics and external disturbances, etc., and then compensated into the controller. Lastly, simulations with front-right tire blowout on expressway are performed to validate the effectiveness and efficiency of presented control scheme and methods, and the comprehensive performance of TSMC+RBFNN and TSMC schemes in maintaining original trajectory tracking capacity is evaluated and discussed.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

RBFNN based terminal sliding mode adaptive control for electric ground vehicles after tire blowout on expressway

Yang

Yue

Liu

et al. 2020

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…Adoption of a single channel to estimate complicated dynamics of robots under diverse working conditions however limited their performances especially for large disturbances in high working frequencies [38][39]. This drawback could be overcome by integrating nominal system models into the disturbance techniques [40][41]. Although ones lost little effort to build up the simple model, it is worth achieving higher control performances with this combination.…”

Section: Introductionmentioning

confidence: 99%

A Precise Neural-Disturbance Learning Controller of Constrained Robotic Manipulators

Xuan

Bae

2021

IEEE Access

View full text Add to dashboard Cite

An adaptive robust controller is introduced for high-precision tracking control problems of robotic manipulators with output constraints. A nonlinear function is employed to transform the constrained control objective to new free variables that are then synthesized using a sliding-mode-like function as an indirect control mission. A robust nonlinear control signal is derived to ensure the boundedness of the main control objective without violation of physical output constraints. The control performance is improved by adopting a neural-network model with conditioned nonlinear learning laws to deal with nonlinear uncertainties and disturbances inside the system dynamics. A disturbanceobserver-based control signal is additionally properly injected into the neural nonlinear system to eliminate the approximation error for achieving asymptotically tracking control accuracy. Performance of the overall control system is validated by intensive theoretical proofs and comparative simulation results.

show abstract

“…Lin et al [15] developed fuzzy Gaussian mixture models to approximate the objects' shape for robot manipulator grasping tasks under unknown environments, and the model has a good grasp quality. He et al [16] proposed a disturbance-observer-based control strategy to approximate unknown parameters and disturbance for multimanipulator robots and validated on a dual-arm cooperative robot (Baxter).…”

Section: Introductionmentioning

confidence: 99%

Disturbance-Observer-Based Fuzzy Control for a Robot Manipulator Using an EMG-Driven Neuromusculoskeletal Model

Zhang

et al. 2020

Complexity

View full text Add to dashboard Cite

Robot manipulators have been extensively used in complex environments to complete diverse tasks. The teleoperation control based on human-like adaptivity in the robot manipulator is a growing and challenging field. This paper developed a disturbance-observer-based fuzzy control framework for a robot manipulator using an electromyography- (EMG-) driven neuromusculoskeletal (NMS) model. The motion intention (desired torque) was estimated by the EMG-driven NMS model with EMG signals and joint angles from the user. The desired torque was transmitted into the desired velocity for the robot manipulator system through an admittance filter. In the robot manipulator system, a fuzzy logic system, utilizing an integral Lyapunov function, was applied for robot manipulator systems subject to model uncertainties and external disturbances. To compensate for the external disturbances, fuzzy approximation errors, and nonlinear dynamics, a disturbance observer was integrated into the controller. The developed control algorithm was validated with a 2-DOFs robot manipulator in simulation. The results indicate the proposed control framework is effective and crucial for the applications in robot manipulator control.

show abstract

Disturbance Observer-Based Neural Network Control of Cooperative Multiple Manipulators With Input Saturation

Cited by 101 publications

References 74 publications

RBFNN based terminal sliding mode adaptive control for electric ground vehicles after tire blowout on expressway

RBFNN based terminal sliding mode adaptive control for electric ground vehicles after tire blowout on expressway

A Precise Neural-Disturbance Learning Controller of Constrained Robotic Manipulators

Disturbance-Observer-Based Fuzzy Control for a Robot Manipulator Using an EMG-Driven Neuromusculoskeletal Model

Contact Info

Product

Resources

About