The Experts below are selected from a list of 48522 Experts worldwide ranked by ideXlab platform

Lunan Zheng - One of the best experts on this subject based on the ideXlab platform.

  • three recurrent neural networks and three numerical methods for solving a repetitive motion planning scheme of redundant robot manipulators
    IEEE-ASME Transactions on Mechatronics, 2017
    Co-Authors: Zhijun Zhang, Lunan Zheng
    Abstract:

    Three neural networks and three numerical methods are investigated, developed, and compared to solve a repetitive motion planning (RMP) scheme for remedying joint-drift problems of redundant robot manipulators. Three recurrent neural networks, i.e., a dual neural network, a linear variational inequality (LVI)-based primal-dual neural network, and a simplified LVI-based primal-dual neural network, are recurrent and real time, and they do not need to be trained in advance. Three numerical methods, i.e., the 94LVI method, the E47 method, and the M4 method, are time discrete and ready to conduct in Digital Computers. All these solutions have global linear convergence. Computer simulations and physical robot experiments verify that they are all effective to solve the RMP scheme. The comparisons show that neural networks are more accurate and faster than numerical methods on the same simulated condition under the majority normal circumstances. Furthermore, numerical methods are easy to be applied in Digital Computers since they are time discrete.

  • three recurrent neural networks and three numerical methods for solving a repetitive motion planning scheme of redundant robot manipulators
    IEEE-ASME Transactions on Mechatronics, 2017
    Co-Authors: Zhijun Zhang, Lunan Zheng, Junming Yu, Yuanqing Li, Zhu Liang Yu
    Abstract:

    Three neural networks and three numerical methods are investigated, developed, and compared to solve a repetitive motion planning (RMP) scheme for remedying joint-drift problems of redundant robot manipulators. Three recurrent neural networks, i.e., a dual neural network, a linear variational inequality (LVI)-based primal-dual neural network, and a simplified LVI-based primal-dual neural network, are recurrent and real time, and they do not need to be trained in advance. Three numerical methods, i.e., the 94LVI method, the E47 method, and the M4 method, are time discrete and ready to conduct in Digital Computers. All these solutions have global linear convergence. Computer simulations and physical robot experiments verify that they are all effective to solve the RMP scheme. The comparisons show that neural networks are more accurate and faster than numerical methods on the same simulated condition under the majority normal circumstances. Furthermore, numerical methods are easy to be applied in Digital Computers since they are time discrete.

Zhijun Zhang - One of the best experts on this subject based on the ideXlab platform.

  • three recurrent neural networks and three numerical methods for solving a repetitive motion planning scheme of redundant robot manipulators
    IEEE-ASME Transactions on Mechatronics, 2017
    Co-Authors: Zhijun Zhang, Lunan Zheng
    Abstract:

    Three neural networks and three numerical methods are investigated, developed, and compared to solve a repetitive motion planning (RMP) scheme for remedying joint-drift problems of redundant robot manipulators. Three recurrent neural networks, i.e., a dual neural network, a linear variational inequality (LVI)-based primal-dual neural network, and a simplified LVI-based primal-dual neural network, are recurrent and real time, and they do not need to be trained in advance. Three numerical methods, i.e., the 94LVI method, the E47 method, and the M4 method, are time discrete and ready to conduct in Digital Computers. All these solutions have global linear convergence. Computer simulations and physical robot experiments verify that they are all effective to solve the RMP scheme. The comparisons show that neural networks are more accurate and faster than numerical methods on the same simulated condition under the majority normal circumstances. Furthermore, numerical methods are easy to be applied in Digital Computers since they are time discrete.

  • three recurrent neural networks and three numerical methods for solving a repetitive motion planning scheme of redundant robot manipulators
    IEEE-ASME Transactions on Mechatronics, 2017
    Co-Authors: Zhijun Zhang, Lunan Zheng, Junming Yu, Yuanqing Li, Zhu Liang Yu
    Abstract:

    Three neural networks and three numerical methods are investigated, developed, and compared to solve a repetitive motion planning (RMP) scheme for remedying joint-drift problems of redundant robot manipulators. Three recurrent neural networks, i.e., a dual neural network, a linear variational inequality (LVI)-based primal-dual neural network, and a simplified LVI-based primal-dual neural network, are recurrent and real time, and they do not need to be trained in advance. Three numerical methods, i.e., the 94LVI method, the E47 method, and the M4 method, are time discrete and ready to conduct in Digital Computers. All these solutions have global linear convergence. Computer simulations and physical robot experiments verify that they are all effective to solve the RMP scheme. The comparisons show that neural networks are more accurate and faster than numerical methods on the same simulated condition under the majority normal circumstances. Furthermore, numerical methods are easy to be applied in Digital Computers since they are time discrete.

Shixing Wang - One of the best experts on this subject based on the ideXlab platform.

  • neural control of hypersonic flight vehicle model via time scale decomposition with throttle setting constraint
    Nonlinear Dynamics, 2013
    Co-Authors: Zhongke Shi, Chenguang Yang, Shixing Wang
    Abstract:

    Considering the use of Digital Computers and samplers in the control circuitry, this paper describes the controller design in discrete time for the longitudinal dynamics of a generic hypersonic flight vehicle (HFV) with Neural Network (NN). Motivated by time-scale decomposition, the states are decomposed into slow dynamics of velocity, altitude and fast dynamics of attitude angles. By command transformation, the reference command for γ−θp−q subsystem is derived from h−γ subsystem. Furthermore, to simplify the backstepping design, we propose the controller for γ−θp−q subsystem from prediction function without virtual controller. For the velocity subsystem, the throttle setting constraint is considered and new NN adaption law is designed by auxiliary error dynamics. The uniformly ultimately boundedness (UUB) of the system is proved by Lyapunov stability method. Simulation results show the effectiveness of the proposed algorithm.

  • Discrete flight path angle tracking control of hypersonic flight vehicles via multi-rate sampling
    Proceedings of 2012 UKACC International Conference on Control, 2012
    Co-Authors: Bin Xu, Chenguang Yang, Jing Li, Danwei Wang, Shixing Wang
    Abstract:

    This paper presents the flight path angle tracking control of the longitudinal dynamics of a generic hypersonic flight vehicle(HFV). Due to the use of Digital Computers and microprocessors for controls applications, the discrete hypersonic flight control is investigated. The altitude command is transformed into the flight path angle information. The back-stepping scheme is applied for the attitude subsystem which includes flight path angle, pitch angle and pitch rate. The virtual control is designed with nominal feedback and Neural Network (NN) approximation. To use the information of throttle setting, the multi-rate sampling method is employed for the two subsystems where the velocity subsystem is considered as slow dynamics. Under the proposed controller, the semiglobal uniform ultimate boundedness (SGUUB) stability is guaranteed. The simulation is presented to show the effectiveness of the proposed control approach.

Aniruddha Datta - One of the best experts on this subject based on the ideXlab platform.

  • Adaptive internal model control: the discrete-time case
    International Journal of Adaptive Control and Signal Processing, 2001
    Co-Authors: Guillermo J. Silva, Aniruddha Datta
    Abstract:

    This paper considers the design and analysis of a discrete-time H2 optimal robust adaptive controller based on the internal model control structure. The certainty equivalence principle of adaptive control is used to combine a discrete-time robust adaptive law with a discrete-time H2 internal model controller to obtain a discrete-time adaptive H2 internal model control scheme with provable guarantees of stability and robustness. The approach used parallels the earlier results obtained for the continuous-time case. Nevertheless, there are some differences which, together with the widespread use of Digital Computers for controls applications, justifies a separate exposition. Copyright © 2001 John Wiley & Sons, Ltd.

  • Adaptive internal model control: the discrete-time case
    Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251), 1999
    Co-Authors: Guillermo J. Silva, Aniruddha Datta
    Abstract:

    This paper considers the design and analysis of a discrete-time H/sub 2/ optimal robust adaptive controller based on the internal model control structure. The certainty equivalence principle of adaptive control is used to combine a discrete-time robust adaptive law with a discrete-time H/sub 2/ internal model controller to obtain a discrete-time adaptive H/sub 2/ internal model control scheme with provable guarantees of stability and robustness. The approach used parallels the earlier results obtained for the continuous-time case. Nevertheless, there are some differences which, together with the widespread use of Digital Computers for controls applications, justifies a separate exposition.

Zhu Liang Yu - One of the best experts on this subject based on the ideXlab platform.

  • three recurrent neural networks and three numerical methods for solving a repetitive motion planning scheme of redundant robot manipulators
    IEEE-ASME Transactions on Mechatronics, 2017
    Co-Authors: Zhijun Zhang, Lunan Zheng, Junming Yu, Yuanqing Li, Zhu Liang Yu
    Abstract:

    Three neural networks and three numerical methods are investigated, developed, and compared to solve a repetitive motion planning (RMP) scheme for remedying joint-drift problems of redundant robot manipulators. Three recurrent neural networks, i.e., a dual neural network, a linear variational inequality (LVI)-based primal-dual neural network, and a simplified LVI-based primal-dual neural network, are recurrent and real time, and they do not need to be trained in advance. Three numerical methods, i.e., the 94LVI method, the E47 method, and the M4 method, are time discrete and ready to conduct in Digital Computers. All these solutions have global linear convergence. Computer simulations and physical robot experiments verify that they are all effective to solve the RMP scheme. The comparisons show that neural networks are more accurate and faster than numerical methods on the same simulated condition under the majority normal circumstances. Furthermore, numerical methods are easy to be applied in Digital Computers since they are time discrete.