Adaptive neural network control of coordinated manipulators

Woon, L.C.; Ge, Shuzhi Sam; Chen, Xiaoqi; Zhang, C.

doi:10.1002/(sici)1097-4563(199904)16:4<195::aid-rob1>3.0.co;2-r

Cited by 18 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This means that the accuracy could be further improved by prolonging the training phase. An optimized learning rule replacing equations (15) will reduce the number of training iterations by increasing the rate of convergence of E. The fact that the errors for low SNRs and very low flow velocities are nearly independent of the number of hidden units suggests that we face a theoretical limit that we cannot overcome by increasing h. The error for the flow velocity is fairly constant over the range of u y . This means that the percentage errors are large at low flow velocities.…”

Section: Discussionmentioning

confidence: 99%

Neural network data analysis for laser-induced thermal acoustics

Schlamp

Hornung

Cummings

2000

Meas. Sci. Technol.

View full text Add to dashboard Cite

Abstract.A general, analytical closed-form solution for laser-induced thermal acoustic (LITA) signals using homodyne or heterodyne detection and using electrostrictive and thermal gratings is derived. A one-hidden-layer feed-forward neural network is trained using back-propagation learning and a steepest descent learning rule to extract the speed of sound and flow velocity from a heterodyne LITA signal. The effect of the network size on the performance is demonstrated. The accuracy is determined with a second set of LITA signals that were not used during the training phase. The accuracy is found to be better than that of a conventional frequency decomposition technique while being computationally as efficient. This data analysis method is robust with respect to noise, numerically stable and fast enough for real-time data analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Neural network data analysis for laser-induced thermal acoustics

Schlamp

Hornung

Cummings

2000

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…It can be seen that the whole system contains 3n variables. However, because the dual-arm robots and the object are rigid and have no relative position, only n variables are independent of each other [33]. Further, to analyze the dynamic characteristics of the whole dual-arm system, it is necessary to establish the relationship between the joint variable q and object position x o , so that only x o is included in the comprehensive dynamic model.…”

Section: Comprehensive Dynamics Of Dual-arm Systemmentioning

confidence: 99%

“…The weight and inertia of the object are m a = 1kg and I 3 = 0.3kg, respectively. The Jacobian matrix J e and the grasping matrix J o are shown in [32,33].…”

Section: Simulation Studymentioning

confidence: 99%

Neuroadaptive cooperative control for dual-arm robots tracking with state constraints and torque optimization

Cao

Chen

2022

Preprint

View full text Add to dashboard Cite

This paper studies cooperative control for dual-arm robots with state constraints and torque optimization. Firstly, the centralized comprehensive dynamic model of the dual-arm robots with the grasped object is established in the Cartesian coordinate system, and then the motion of the system is analyzed using the property that the sum of internal forces is zero. Secondly, to deal with the state constraints, a constraint transformation function is constructed involving the system state and the constraint boundary, with which the state constraints are satisfied as long as the new transformed system states are bounded. Then, a neuro-adaptive cooperative control scheme is designed with the non-unique pseudo-inverse grasping matrix. Finally, an energy function is built and the control is determined uniquely using the torque optimality principle. The significant advantages of this paper are described as follows:(i) Different from the traditional barrier-Lyapunov function for dealing with state constraints, where the satisfaction of feasibility conditions is required, here this condition is avoided by the introduction of constraint transformation function and system transformation technology. (ii) The torque optimization eliminates the requirement for calculating the inverse of the grasping matrix with insufficient rank and the control input is determined uniquely.

show abstract

“…where X 0 can be chosen as ½z 1 ; _ z 1 ; y d ; _ y d ; € y d T , which can be found the same with X in MANNBS. Substituting equation (39) into equation (28) and the MANNBS control law can be rewritten as…”

Section: Adaptive Neural Backstepping Sliding-mode Controller (Annbs) Designmentioning

confidence: 99%

“…More studies with online neural learning and adaptation can be found elsewhere. [28][29][30] Besides, radial basis function (RBF) NN-enhanced estimator and observer were developed 31,32 to estimate system uncertainty and obtain the leader manipulator's acceleration and control torque online. As for sliding-mode controllers, Wang et al 33 proposed a decentralized position synchronized force control scheme.…”

Section: Introductionmentioning

confidence: 99%

A model weighted adaptive neural backstepping sliding-mode controller for cooperative manipulator system

Wang

2017

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Since dynamic model can be obtained through various approaches with certain different accuracies, the accuracy of model in simulation plant compared to reality is found to be influential but seldom concerned under robotic cooperation. This may result in acceptable simulation but unsatisfactory practical application. Based on different dynamics' demands or accuracies, an inverse model-based backstepping sliding-mode controller and another model-free controller are derived using feedforward radial basis function neural networks to compensate the uncertain dynamics of the system. Modelbased algorithm is found to provide much more satisfactory contribution than that of model free. Thus, a model weight is introduced to adjust contribution of inverse dynamics and neural compensation, and a novel model weighted adaptive neural backstepping sliding-mode controller is proposed to cope with different dynamics' demands or accuracies. The neural networks require no off-line learning and it is shown that they can deal well with the dynamic uncertainty, joint friction, and external disturbances. With Lyapunov stability approach, these controllers are proved to be robust, both position/force convergence and tracking stability are guaranteed. Simulation and analysis indicate that these controllers provide good tracking performance in position and internal force. Moreover, the model weighted controller achieves better tracking accuracy and stability under various degrees of model errors.

show abstract

Adaptive neural network control of coordinated manipulators

Cited by 18 publications

References 23 publications

Neural network data analysis for laser-induced thermal acoustics

Neural network data analysis for laser-induced thermal acoustics

Neuroadaptive cooperative control for dual-arm robots tracking with state constraints and torque optimization

A model weighted adaptive neural backstepping sliding-mode controller for cooperative manipulator system

Contact Info

Product

Resources

About