IEEE/CAA Journal of Automatica Sinica
Citation:  N. Tan, P. Yu, Z. Y. Zhong, and F. L. Ni, “A new noisetolerant dualneuralnetwork scheme for robust kinematic control of robotic arms with unknown models,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 10, pp. 1778–1791, Oct. 2022. doi: 10.1109/JAS.2022.105869 
Taking advantage of their inherent dexterity, robotic arms are competent in completing many tasks efficiently. As a result of the modeling complexity and kinematic uncertainty of robotic arms, modelfree control paradigm has been proposed and investigated extensively. However, robust modelfree control of robotic arms in the presence of noise interference remains a problem worth studying. In this paper, we first propose a new kind of zeroing neural network (ZNN), i.e., integrationenhanced noisetolerant ZNN (IENTZNN) with integrationenhanced noisetolerant capability. Then, a unified dual IENTZNN scheme based on the proposed IENTZNN is presented for the kinematic control problem of both rigidlink and continuum robotic arms, which improves the performance of robotic arms with the disturbance of noise, without knowing the structural parameters of the robotic arms. The finitetime convergence and robustness of the proposed control scheme are proven by theoretical analysis. Finally, simulation studies and experimental demonstrations verify that the proposed control scheme is feasible in the kinematic control of different robotic arms and can achieve better results in terms of accuracy and robustness.
[1] 
C. Duriez, “Control of elastic soft robots based on realtime finite element method,” in Proc. IEEE Int. Conf. Robotics and Automation, 2013, pp. 3982–3987.

[2] 
M. Giorelli, F. Renda, M. Calisti, A. Arienti, G. Ferri, and C. Laschi, “Neural network and Jacobian method for solving the inverse statics of a cabledriven soft arm with nonconstant curvature,” IEEE Trans. Robotics, vol. 31, no. 4, pp. 823–834, 2015. doi: 10.1109/TRO.2015.2428511

[3] 
Y. Jin, Y. Wang, X. Chen, Z. Wang, X. Liu, H. Jiang, and X. Chen, “Modelless feedback control for soft manipulators,” in Proc. IEEE Int. Conf. Intelligent Robots and Systems, 2017, pp. 2916–2922.

[4] 
E. Coevoet, A. Escande, and C. Duriez, “Optimizationbased inverse model of soft robots with contact handling,” IEEE Robotics and Automation Letters, vol. 2, no. 3, pp. 1413–1419, 2017. doi: 10.1109/LRA.2017.2669367

[5] 
D. Guo and Y. Zhang, “A new inequalitybased obstacleavoidance MVN scheme and its application to redundant robot manipulators,” IEEE Trans. Systems,Man and Cybernetics Part C: Applications and Reviews, vol. 42, no. 6, pp. 1326–1340, 2012. doi: 10.1109/TSMCC.2012.2183868

[6] 
L. Jin, S. Li, L. Xiao, R. Lu, and B. Liao, “Cooperative motion generation in a distributed network of redundant robot manipulators with noises,” IEEE Trans. Systems,Man,and Cybernetics: Systems, vol. 48, no. 10, pp. 1715–1724, 2018. doi: 10.1109/TSMC.2017.2693400

[7] 
A. H. Khan, Z. Shao, S. Li, Q. Wang, and N. Guan, “Which is the best PID variant for pneumatic soft robots an experimental study?” IEEE/CAA J. Autom. Sinica, vol. 7, no. 2, pp. 451–460, 2020. doi: 10.1109/JAS.2020.1003045

[8] 
S. Wang, J. Housden, T. Bai, H. Liu, J. Back, D. Singh, K. Rhode, Z. G. Hou, and F.Y. Wang, “Robotic intraoperative ultrasound: Virtual environments and parallel systems,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 5, pp. 1095–1106, 2021. doi: 10.1109/JAS.2021.1003985

[9] 
D. Guo and Y. Zhang, “Lifunction activated ZNN with finitetime convergence applied to redundantmanipulator kinematic control via timevarying Jacobian matrix pseudoinversion,” Applied Soft Computing J., vol. 24, pp. 158–168, 2014. doi: 10.1016/j.asoc.2014.06.045

[10] 
Z. Zhang, L. Zheng, J. Yu, Y. Li, and Z. Yu, “Three recurrent neural networks and three numerical methods for solving a repetitive motion planning scheme of redundant robot manipulators,” IEEE/ASME Trans. Mechatronics, vol. 22, no. 3, pp. 1423–1434, 2017. doi: 10.1109/TMECH.2017.2683561

[11] 
S. CobosGuzman, D. Palmer, and D. Axinte, “Kinematic model to control the endeffector of a continuum robot for multiaxis processing,” Robotica, vol. 35, no. 1, pp. 224–240, 2017. doi: 10.1017/S0263574715000946

[12] 
V. Falkenhahn, A. Hildebrandt, R. Neumann, and O. Sawodny, “Dynamic control of the bionic handling assistant,” IEEE/ASME Trans. Mechatronics, vol. 22, no. 1, pp. 6–17, 2017. doi: 10.1109/TMECH.2016.2605820

[13] 
W. Chang, Y. Li, and S. Tong, “Adaptive fuzzy backstepping tracking control for flexible robotic manipulator,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 12, pp. 1923–1930, 2021. doi: 10.1109/JAS.2017.7510886

[14] 
Z. Li, S. Li, and X. Luo, “An overview of calibration technology of industrial robots,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 1, pp. 23–36, 2021. doi: 10.1109/JAS.2020.1003381

[15] 
M. C. Yip and D. B. Camarillo, “Modelless feedback control of continuum manipulators in constrained environments,” IEEE Trans. Robotics, vol. 30, no. 4, pp. 880–889, 2014. doi: 10.1109/TRO.2014.2309194

[16] 
M. C. Yip and D. B. Camarillo, “Modelless hybrid position/force control: A minimalist approach for continuum manipulators in unknown, constrained environments,” IEEE Robotics and Automation Letters, vol. 1, no. 2, pp. 844–851, 2016. doi: 10.1109/LRA.2016.2526062

[17] 
H. T. Kalidindi, T. G. Thuruthel, C. Laschi, and E. Falotico, “Cerebelluminspired approach for adaptive kinematic control of soft robots,” in Proc. IEEE Int. Conf. Soft Robotics, 2019, pp. 684–689.

[18] 
M. Yang, Y. Zhang, Z. Zhang, and H. Hu, “Adaptive discrete ZND models for tracking control of redundant manipulator,” IEEE Trans. Industrial Informatics, 2020. DOI: 10.1109/TII.2020.2976844

[19] 
K. H. Lee, D. K. Fu, M. C. Leong, M. Chow, H. C. Fu, K. Althoefer, K. Y. Sze, C. K. Yeung, and K. W. Kwok, “Nonparametric online learning control for soft continuum robot: An enabling technique for effective endoscopic navigation,” Soft Robotics, vol. 4, no. 4, pp. 324–337, 2017. doi: 10.1089/soro.2016.0065

[20] 
T. G. Thuruthel, E. Falotico, M. Manti, A. Pratesi, M. Cianchetti, and C. Laschi, “Learning closed loop kinematic controllers for continuum manipulators in unstructured environments,” Soft Robotics, vol. 4, no. 3, pp. 285–296, 2017. doi: 10.1089/soro.2016.0051

[21] 
M. Li, R. Kang, D. T. Branson, and J. S. Dai, “Modelfree control for continuum robots based on an adaptive Kalman filter,” IEEE/ASME Trans. Mechatronics, vol. 23, no. 1, pp. 286–297, 2018. doi: 10.1109/TMECH.2017.2775663

[22] 
X. Luo, Y. Yuan, M. Zhou, Z. Liu, and M. Shang, “Nonnegative latent factor model based on βdivergence for recommender systems,” IEEE Trans. Systems,Man,and Cybernetics: Systems, vol. 51, no. 8, pp. 4612–4623, 2021. doi: 10.1109/TSMC.2019.2931468

[23] 
Z. Zhang, Z. Li, Y. Zhang, Y. Luo, and Y. Li, “Neuraldynamicmethodbased dualarm CMG scheme with timevarying constraints applied to humanoid robots,” IEEE Trans. Neural Networks and Learning Systems, vol. 26, no. 12, pp. 3251–3262, 2015. doi: 10.1109/TNNLS.2015.2469147

[24] 
D. Chen, Y. Zhang, and S. Li, “Tracking control of robot manipulators with unknown models: A Jacobianmatrixadaption method,” IEEE Trans. Industrial Informatics, vol. 14, no. 7, pp. 3044–3053, 2018. doi: 10.1109/TII.2017.2766455

[25] 
J. Li, Y. Zhang, S. Li, and M. Mao, “New discretizationformulabased zeroing dynamics for realtime tracking control of serial and parallel manipulators,” IEEE Trans. Industrial Informatics, vol. 14, no. 8, pp. 3416–3425, 2018. doi: 10.1109/TII.2017.2780892

[26] 
L. Xiao, B. Liao, S. Li, Z. Zhang, L. Ding, and L. Jin, “Design and analysis of FTZNN applied to the realtime solution of a nonstationary Lyapunov equation and tracking control of a wheeled mobile manipulator,” IEEE Trans. Industrial Informatics, vol. 14, no. 1, pp. 98–105, 2018. doi: 10.1109/TII.2017.2717020

[27] 
H. Lu, L. Jin, X. Luo, B. Liao, D. Guo, and L. Xiao, “RNN for solving perturbed timevarying underdetermined linear system with double bound limits on residual errors and state variables,” IEEE Trans. Industrial Informatics, vol. 15, no. 11, pp. 5931–5942, 2019. doi: 10.1109/TII.2019.2909142

[28] 
S. Lyu and C. C. Cheah, “Datadriven learning for robot control with unknown Jacobian,” Automatica, vol. 120, p. 109120, 2020.

[29] 
Y. Zhang and D. Guo, Zhang Functions and Various Models. Berlin, Germany: SpringerVerlag, 2015.

[30] 
D. Chen and Y. Zhang, “Robust zeroing neuraldynamics and its timevarying disturbances suppression model applied to mobile robot manipulators,” IEEE Trans. Neural Networks and Learning Systems, vol. 29, no. 9, pp. 4385–4397, 2018. doi: 10.1109/TNNLS.2017.2764529

[31] 
Z. Xie, L. Jin, X. Luo, B. Hu, and S. Li, “An accelerationlevel datadriven repetitive motion planning scheme for kinematic control of robots with unknown structure,” IEEE Trans. Systems,Man,and Cybernetics: Systems, pp. 1–13, 2021.

[32] 
G. Zong, H. Ren, and H. R. Karimi, “Eventtriggered communication and annular finitetime H _{∞} filtering for networked switched systems,” IEEE Trans. Cybernetics, vol. 51, no. 1, pp. 309–317, 2021. doi: 10.1109/TCYB.2020.3010917

[33] 
H. Ren, G. Zong, and T. Li, “Eventtriggered finitetime control for networked switched linear systems with asynchronous switching,” IEEE Trans. Systems,Man,and Cybernetics: Systems, vol. 48, no. 11, pp. 1874–1884, 2018. doi: 10.1109/TSMC.2017.2789186

[34] 
Z. Zhao and Z. Liu, “Finitetime convergence disturbance rejection control for a flexible Timoshenko manipulator,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 1, pp. 157–168, 2021. doi: 10.1109/JAS.2020.1003378

[35] 
B. Liao, Y. Zhang, and L. Jin, “Taylor O(h^{3}) discretization of ZNN models for dynamic equalityconstrained quadratic programming with application to manipulators,” IEEE Trans. Neural Networks and Learning Systems, vol. 27, no. 2, pp. 225–237, 2016. doi: 10.1109/TNNLS.2015.2435014

[36] 
L. Jin, Y. Zhang, S. Li, and Y. Zhang, “Noisetolerant ZNN models for solving timevarying zerofinding problems: A controltheoretic approach,” IEEE Trans. Autom. Control, vol. 62, no. 2, pp. 992–997, 2017. doi: 10.1109/TAC.2016.2566880

[37] 
L. Xiao, B. Liao, S. Li, and K. Chen, “Nonlinear recurrent neural networks for finitetime solution of general timevarying linear matrix equations,” Neural Networks, vol. 98, pp. 102–113, 2018. doi: 10.1016/j.neunet.2017.11.011

[38] 
L. Xiao, L. Jia, Y. Zhang, Z. Hu, and J. Dai, “Finitetime convergence and robustness analysis of two nonlinear activated ZNN models for timevarying linear matrix equations,” IEEE Access, vol. 7, pp. 135133–135144, 2019. doi: 10.1109/ACCESS.2019.2941961

[39] 
W. Li, L. Xiao, and B. Liao, “A finitetime convergent and noiserejection recurrent neural network and its discretization for dynamic nonlinear equations solving,” IEEE Trans. Cybernetics, vol. 50, no. 7, pp. 3195–3207, 2020. doi: 10.1109/TCYB.2019.2906263

[40] 
Q. Xiang, W. Li, B. Liao, and Z. Huang, “Noiseresistant discretetime neural dynamics for computing timedependent Lyapunov equation,” IEEE Access, vol. 6, pp. 45359–45371, 2018. doi: 10.1109/ACCESS.2018.2863736

[41] 
W. Li, “Design and analysis of a novel finitetime convergent and noisetolerant recurrent neural network for timevariant matrix inversion,” IEEE Trans. Systems,Man,and Cybernetics: Systems, vol. 50, no. 11, pp. 4362–4376, 2020. doi: 10.1109/TSMC.2018.2853598

[42] 
L. Xiao, “Design and analysis of robust nonlinear neural dynamics for solving dynamic nonlinear equation within finite time,” Nonlinear Dynamics, vol. 96, no. 4, pp. 2437–2447, 2019. doi: 10.1007/s11071019049328

[43] 
Z. Tan, W. Li, L. Xiao, and Y. Hu, “New varyingparameter ZNN models with finitetime convergence and noise suppression for timevarying matrix moorepenrose inversion,” IEEE Trans. Neural Networks and Learning Systems, vol. PP, no. 1, pp. 1–13, 2019.

[44] 
L. Xiao, Y. Zhang, J. Dai, K. Chen, S. Yang, W. Li, B. Liao, L. Ding, and J. Li, “A new noisetolerant and predefinedtime ZNN model for timedependent matrix inversion,” Neural Networks, vol. 117, pp. 124–134, 2019. doi: 10.1016/j.neunet.2019.05.005

[45] 
Z. Tan, Y. Hu, L. Xiao, and K. Chen, “Robustness analysis and robotic application of combined function activated RNN for timevarying matrix pseudo inversion,” IEEE Access, vol. 7, pp. 33434–33440, 2019. doi: 10.1109/ACCESS.2019.2904605

[46] 
L. Jin, Y. Zhang, and S. Li, “Integrationenhanced Zhang neural network for realtimevarying matrix inversion in the presence of various kinds of noises,” IEEE Trans. Neural Networks and Learning Systems, vol. 27, no. 12, pp. 2615–2627, 2016. doi: 10.1109/TNNLS.2015.2497715

[47] 
K. Imagawa, T. Emaru, Y. Hoshino, and Y. Kobayashi, “Estimation of velocity and acceleration by nonlinear filter based on sliding mode and application to control system,” in Proc. 3rd Asia Int. Symposium Mechatronics, 2018, pp. 226–231.

[48] 
J. Yang, J. Na, H. Yu, G. Gao, and X. Wang, “Unknown system dynamics estimator for motion control of nonlinear robotic systems,” IEEE Trans. Industrial Electronics, vol. 67, no. 5, pp. 3850–3859, 2020. doi: 10.1109/TIE.2019.2920604

[49] 
G. Li, D. Song, S. Xu, L. Sun, and J. Liu, “A hybrid model and modelfree position control for a reconfigurable manipulator,” IEEE/ASME Trans. Mechatronics, vol. 24, no. 2, pp. 785–795, 2019. doi: 10.1109/TMECH.2019.2893227

[50] 
N. Tan, P. Yu, X. Zhang, and T. Wang, “Modelfree motion control of continuum robots based on a zeroing neurodynamic approach,” Neural Networks, vol. 133, pp. 21–31, 2021. doi: 10.1016/j.neunet.2020.10.005
