Reinforcement Learning Control of a Flexible Two-Link Manipulator: An Experimental Investigation

He, Wei; Gao, Hejia; Zhou, Chen; Yang, Chenguang; Li, Zhijun

doi:10.1109/tsmc.2020.2975232

Cited by 161 publications

(68 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[44], [19], optimize control [39], neural network control [13], [35], [10], learning-based control methods [31], [14] for flexible fire-rescue ladders, and validating the simulation results to provide more accurate simulations [5], [3], and further giving experiments [18].…”

Section: Discussionmentioning

confidence: 99%

Vibration suppression and angle tracking of a fire-rescue ladder

Feng

Zhang

et al. 2020

Nonlinear Dyn

View full text Add to dashboard Cite

This paper mainly considers vibration suppression and angle tracking of a fire-rescue ladder system. The dynamical model is regarded as a segmented Euler-Bernoulli beam with gravity and tip mass, described by a set of motion equations and boundary conditions. Based on the nonlinear Euler-Bernoulli beam model, two active boundary controllers are proposed to achieve the control objectives. The elastic deflection and the angular error in the closed-loop system are proven to converge exponentially to a small neighborhood of zero. Numerical simulations based on finite difference method verify the effectiveness and the ascendancy of active boundary controllers.

show abstract

Section: Discussionmentioning

confidence: 99%

Vibration suppression and angle tracking of a fire-rescue ladder

Feng

Zhang

et al. 2020

Nonlinear Dyn

View full text Add to dashboard Cite

show abstract

“…As a result, the iterative algorithm can be considered by the Bellman error with solving the optimization problem. For designing the ARL scheme in linear dynamical systems [31] and in nonlinear systems [32,40], the methods are realized to find the optimal control input being Kronecker product and approximating neural networks (NNs), respectively. Furthermore, this technique is extended for several situations, such as goal representation heuristic dynamic programming (GRHDP) with the multivariable tracking scheme [35] and uncertain discrete-time systems by using NNs [33].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Reinforcement Learning-Enhanced Motion/Force Control Strategy for Multirobot Systems

Nam

Khanh

Nguyen

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper presents an adaptive reinforcement learning- (ARL-) based motion/force tracking control scheme consisting of the optimal motion dynamic control law and force control scheme for multimanipulator systems. Specifically, a new additional term and appropriate state vector are employed in designing the ARL technique for time-varying dynamical systems with online actor/critic algorithm to be established by minimizing the squared Bellman error. Additionally, the force control law is designed after obtaining the computation of constraint force coefficient by the Moore–Penrose pseudo-inverse matrix. The tracking effectiveness of the ARL-based optimal control is verified in the closed-loop system by theoretical analysis. Finally, simulation studies are conducted on a system of three manipulators to validate the physical realization of the proposed optimal tracking control design.

show abstract

“…Many scholars have applied many advanced control strategies to the control of the uncertain systems. 34–41…”

Section: Introductionmentioning

confidence: 99%

A novel hierarchical nonlinear proportional-integral fast terminal sliding mode control for PMSM drives

Peng

Zhang

2021

Advances in Mechanical Engineering

View full text Add to dashboard Cite

This study proposes a novel hierarchical nonlinear proportional-integral fast terminal sliding mode (HNLPIFTSM) control for permanent magnet synchronous motor (PMSM) speed regulation system. A new type of sliding surface called HNLPIFTSM surface, which combines the benefits of a nonlinear proportional-integral (PI) sliding mode surface and a fast terminal sliding mode (FTSM) surface, is proposed to enhance the robustness and improved the dynamic response, whilst preserving the great property of the conventional hierarchical fast terminal sliding mode (HFTSM) control strategy. The proposed HNLPIFTSM surface uses the novel nonlinear PI sliding mode surface as its inner loop and uses the FTSM surface as its outer loop. Meanwhile, an extended state observer (ESO) is used to estimate the uncertain terms of the PMSM speed regulation system. Furthermore, the stability of the closed-loop control system under the ESO and the HNLPIFTSM control strategy is proved by the Lyapunov stability theorem. Finally, the simulations and experimental demonstrations verify the effectiveness and superiorities of our proposed HNLPIFTSM control strategy over the conventional HFTSM control strategy.

show abstract

Reinforcement Learning Control of a Flexible Two-Link Manipulator: An Experimental Investigation

Cited by 161 publications

References 60 publications

Vibration suppression and angle tracking of a fire-rescue ladder

Vibration suppression and angle tracking of a fire-rescue ladder

Adaptive Reinforcement Learning-Enhanced Motion/Force Control Strategy for Multirobot Systems

A novel hierarchical nonlinear proportional-integral fast terminal sliding mode control for PMSM drives

Contact Info

Product

Resources

About