Vision-based neural predictive tracking control for multi-manipulator systems with parametric uncertainty

Wu, Jinhui; Jin, Zhehao; Liu, Andong

doi:10.1016/j.isatra.2020.10.057

Cited by 24 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notice that regulating r(t) and s(t) confirms the regulation of e o (t) and xo (t), respectively. According to (29) the control signals u, v (from (34)) and so h(t) is bounded that guarantees boundedness of ẍo in (21). The following equation, obtained from ( 20), (29), and (34), shows that internal force errors are bounded.…”

Section: Stability Analysismentioning

confidence: 99%

See 1 more Smart Citation

An observer-based output tracking controller for electrically driven cooperative multiple manipulators with adaptive Bernstein-type approximator

Izadbakhsh

2021

Robotica

View full text Add to dashboard Cite

Thisarticle presents an observer-based output tracking control method for electrically actuated cooperative multiple manipulators using Bernstein-type operators as a universal approximator. This efficient mathematical tool represents lumped uncertainty, including external perturbations and unmodeled dynamics. Then, adaptive laws are derived through the stability analysis to tune the polynomial coefficients. It is confirmed that all the position and force tracking errors are uniformly ultimately bounded using the Lyapunov stability theorem. The theoretical achievements are validated by applying the proposed observer-based controller to a cooperative robotic system comprised of two manipulators transporting a rigid object. The outcomes of the introduced method are also compared to RBFNN, which is a powerful state-of-the-art approximator. The results demonstrate the efficacy of the introduced adaptive control approach in controlling the system even in the presence of disturbances and uncertainties.

show abstract

Section: Stability Analysismentioning

confidence: 99%

“…A Metaheuristic approach is utilized to optimize the controller. Reference [21] dealt with the tracking problem of cooperative manipulators by presenting a predictive control scheme based on neural networks. The uncertainties are regarded as the disturbance in this research, and an extended observer is designed to attenuate its effect.…”

Section: Introductionmentioning

confidence: 99%

An observer-based output tracking controller for electrically driven cooperative multiple manipulators with adaptive Bernstein-type approximator

Izadbakhsh

2021

Robotica

View full text Add to dashboard Cite

show abstract

“…A predictive controller utilizing neural networks has been proposed to handle the cooperative arms tracking problem. 17 The uncertainty is treated as a perturbation in this work, and an extended observer is applied to suppress its effect. A fuzzy sliding mode control strategy has been advised for the problem of moving an item by the cooperative arms.…”

Section: Introductionmentioning

confidence: 99%

Cooperative multiple elastic‐joint arms control using the (p, q)‐analogue of Bernstein operators as the uncertainty approximator

Bayat

Izadbakhsh

2023

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This paper presents the position-force tracking control problem of cooperative multiple elastic-joint robotic arms, encountering model nonlinearities, unknown perturbations, and dynamic uncertainties. To this mean, an adaptive function approximation technique (FAT) is proposed, authorizing the reference trajectory to be tracked by the object. This potential originates from the universal approximation feature of the FAT-based methodologies. The (p, q)-analogue of the Bernstein operators is utilized for this purpose. Since the systems' parameters are not precisely known, adaptive laws are employed for adjusting the uncertainty coefficients. The Lyapunov stability theorem assures that all signals in the error space remain uniformly ultimately bounded (UUB). In the end, two elastic-joint arms carrying a rigid object are utilized for validation of the theoretical outcomes. The suggested strategy is also compared to the Chebyshev neural network (CNN). The results show the benefit of the existing method, managing the system even in the presence of disturbances and uncertainties with lower tuning parameters compared with CNN.

show abstract

“…This is appropriate if both the precise cutting path and trajectory are irrelevant to the task, but is insufficient for cases where geometric or safety concerns mandate explicit control over the path, such as cutting of battery components. Examples of recent learning-based predictive path following studies are Yang et al (2021) and Wu et al (2021) . Yang et al (2021) consider a general path following control framework using a Gaussian process (GP) estimator to adapt to external disturbances.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, although non-parametric uncertain disturbance is considered, the method is not robust to system parametric uncertainty. Wu et al (2021) propose a predictive tracking control method based on a neural network, robust to parametric uncertainties. However, the paper employs a simple RNN dynamic model; this could be improved upon by considering improved architectures such as the LSTM as addressed in Mitsioni et al (2019) .…”

Section: Introductionmentioning

confidence: 99%

Vision-Guided MPC for Robotic Path Following Using Learned Memory-Augmented Model

Rastegarpanah

Hathaway

2021

Front. Robot. AI

View full text Add to dashboard Cite

The control of the interaction between the robot and environment, following a predefined geometric surface path with high accuracy, is a fundamental problem for contact-rich tasks such as machining, polishing, or grinding. Flexible path-following control presents numerous applications in emerging industry fields such as disassembly and recycling, where the control system must adapt to a range of dissimilar object classes, where the properties of the environment are uncertain. We present an end-to-end framework for trajectory-independent robotic path following for contact-rich tasks in the presence of parametric uncertainties. We formulate a combination of model predictive control with image-based path planning and real-time visual feedback, based on a learned state-space dynamic model. For modeling the dynamics of the robot-environment system during contact, we introduce the application of the differentiable neural computer, a type of memory augmented neural network (MANN). Although MANNs have been as yet unexplored in a control context, we demonstrate a reduction in RMS error of ∼21.0% compared with an equivalent Long Short-Term Memory (LSTM) architecture. Our framework was validated in simulation, demonstrating the ability to generalize to materials previously unseen in the training dataset.

show abstract

Vision-based neural predictive tracking control for multi-manipulator systems with parametric uncertainty

Cited by 24 publications

References 35 publications

An observer-based output tracking controller for electrically driven cooperative multiple manipulators with adaptive Bernstein-type approximator

An observer-based output tracking controller for electrically driven cooperative multiple manipulators with adaptive Bernstein-type approximator

Cooperative multiple elastic‐joint arms control using the (p, q)‐analogue of Bernstein operators as the uncertainty approximator

Vision-Guided MPC for Robotic Path Following Using Learned Memory-Augmented Model

Contact Info

Product

Resources

About