Discrete-time neural network with two classes of bias noises for solving time-variant matrix inversion and application to robot tracking
It is well known that noise is inevitable in real world, especially in the case of solving time-variant matrix inversion. Therefore, it is more necessary to study the algorithm with bias noises to solve time-variant matrix inversion. This paper investigates discrete-time neural network with two classes of bias noises for solving time-variant matrix inversion, and its application to robot tracking based on the property of second-order differential equation. Firstly, the model is presented and some indispensable propaedeutics are given. Then, continuous-time and discrete-time neural network with two classes of bias noises is designed, respectively. Their convergence and finite-time stability are also theoretically analyzed. Finally, the proposed models are applied to a five-link robot tracking. Numerical simulations demonstrate the superiority and effectiveness of our method.
KeywordsDiscrete-time neural network Time-variant matrix inversion Bias noises Robot tracking
This work was supported by the National Science Foundation of China (61374028), the Key Scientific Research Foundation of Education Bureau of Henan Province, China (Grant No. 19A140021), and the 2016 Social science and economics’ association research topics in Henan Province (SKL-2016-3868). The paper has not been published and will not be submitted elsewhere for publication. In order to improve the quality of the article, with the consent of the original author and Zhiqiang Zhang, we invited Zhiqiang Zhang to revise the article. He added the finite-time stability to the revised paper.
Compliance with ethical standards
Conflict of interest
All authors declare that they have no conflict of interest.
- 1.Buss SR (2004) Introduction to inverse kinematics with Jacobian transpose. Pseudo inverse and damped least squares methods. Technical report. University of California, San DiegoGoogle Scholar
- 5.Chen J, Han D, Nie H, Cheng M (2014) Dual quaternion-based inverse kinematics of dexterous finger. J Vibroeng 16:2813–2820Google Scholar
- 6.Li S, Zhang Y (2018) Neural networks based single robot arm control for visual servoing. In: Neural networks for cooperative control of multiple robot arms. Springer, Singapore, pp 1–11Google Scholar
- 9.Bajodah AH (2013) Inertia-independent generalized dynamic inversion feedback control of spacecraft attitude maneuvers. Acta Astronaut 88:98–107Google Scholar
- 11.Zhang Y, Ge SS (2005) Design and analysis of a general recurrent neural network model for time-varying matrix inversion. IEEE Trans Neural Netw 16:1477–1490Google Scholar
- 12.Zhang Z, Zheng L, Weng J, Mao Y, Lu W, Xiao L (2018) A new varying-parameter recurrent neural-network for online solution of time-varying Sylvester equation. IEEE Trans Cybern 99:1–14Google Scholar
- 13.Miao P, Shen YJ, Xia XH (2014) Finite time dual neural networks with a tunable activation function for solving quadratic programming problems and its application. Neurocomputing 143:80–89Google Scholar
- 14.Miao P, Shen YJ, Li YJ, Bao L (2016) Finite-time recurrent neural networks for solving nonlinear optimization problems and their application. Neurocomputing 177:120–129Google Scholar
- 17.Zhang Y, Mu B, Zheng H (2013) Link between and comparison and combination of Zhang neural network and quasi-Newton BFGS method for time-varying quadratic minimization. IEEE Trans Cybern 43:490–503Google Scholar
- 18.Guo D, Zhang Y (2012) Zhang neural network, Getz–Marsden dynamic system, and discrete-time algorithms for time-varying matrix inversion with application to robots’ kinematic control. Neurocomputing 97:22–32Google Scholar
- 21.Li S, Chen S, Li B (2013) Accelerating a recurrent neural network to finite-time convergence for solving time-varying Sylvester equation by using a sign-bi-power activation function. Neural Process Lett 37:189–205Google Scholar
- 22.Miao P, Shen YJ, Huang YH, Wang YW (2015) Solving time-varying quadratic programs based on finite-time Zhang neural networks and their application to robot tracking. Neural Comput Appl 26(3):693–703Google Scholar
- 23.Hogan N, Sternad D (2009) Sensitivity of smoothness measures to movement duration, amplitude, and arrests. J Mot Behav 41(6):529–534Google Scholar
- 24.Balasubramanian S, Melendez-Calderon A, Burdet E (2012) A robust and sensitive metric for quantifying movement smoothness. IEEE Trans Biomed Eng 59(8):2126–2136Google Scholar
- 25.Balasubramanian S, Melendez-Calderon A, Roby-Brami A, Burdet E (2015) On the analysis of movement smoothness. J Neuroeng Rehab 12(1):112Google Scholar