Visual Feedback Fuzzy Control for a Robot Manipulator Based on SVR Learning

doi:10.16182/j.issn1004731x.joss.2020-FZ0337E

Abstract

Abstract: A fuzzy controller based on SVR learning is proposed for uncalibrated robot visual servoing. In this paper, a fuzzy controller is used to directly construct the nonlinear mapping between image features and robot joint motion. The fuzzy basis function of the fuzzy controller is taken as the kernel function of an SVR and the equivalent relationship between the SVR and the fuzzy controller is established. The learned support vector from the SVR is used as the rule of the fuzzy controller. Since all rules are learned from the data, there is no need to manually design the rules. The proposed method fully utilizes the good generalization ability of SVR in small sample learning, and the experimental results show that the proposed visual servoing controller has good performance in precision and convergence.

Key words: visual servoing, robot, fuzzy control, SVR

CLC Number:

TP24

Zhang Xianxia, Zhang Jinqiang, Li Zhiyuan, Ma Shiwei, Yang Banghua. Visual Feedback Fuzzy Control for a Robot Manipulator Based on SVR Learning[J]. Journal of System Simulation, 2020, 32(10): 1997-2009.

References 33

[1]	Malis E.Contributions à la modélisation et à lacommande en asservissement visuel[D]. Master's thesis, France: Universite de Rennes 1, IRISA, 1998.
[2]	Lippiello V, Siciliano B, Villani L.Position-based visual servoing in industrialmultirobot cells using a hybrid camera configuration[J]. IEEE Trans. Robot (S1552-3098), 2007, 23(1): 73-86.
[3]	Assa A, Farrokh J S.A robust vision-based sensor fusion approach for real-time pose estimation[J]. IEEE Trans. Syst., Man, Cybern. B, Cybern (S1083-4419), 2014, 44(2): 217-227.
[4]	Chaumette F, Hutchinson S.Visual servo control. I. Basic approaches[J]. IEEE Robotics & Automation Magazine (S1070-9932), 2006, 13(4): 82-90.
[5]	Hutchinson S, Hager G, Corke P.A tutorial on visual servo control[J]. IEEE Trans. Robot. Automat (S2374-958X), 1996, 12(5): 651-670.
[6]	Malis E, Chaumette F, Boudet S.2 1/2 D visual servoing[J]. IEEE Transactions on Robotics & Automation (S2374-958X), 2002, 15(2): 238-250.
[7]	Malis E, Chaumette F.Theoretical improvements in the stability analysis of a new class of model-free visual servoing methods[J]. IEEE Trans. Robot. Automat (S2374-958X), 2002, 18(2): 176-186.
[8]	Miljkovi¢ Z, Miti¢ M, Lazarevi¢ M, et al.Neural network Reinforcement Learning for visual control of robot manipulators[J]. Expert Syst. Appl.(S0957-4174), 2013, 40(5): 1721-1736.
[9]	Liu M, Pradalier C, Siegwart R.Visual homing from scale with an uncalibrated omnidirectional camera[J]. IEEE Transactions on Robotics (S2374-958X), 2013, 29(6): 1353-1365.
[10]	Wang H S, Liu Y H, Chen W D.Uncalibrated visual tracking control without visual velocity[J]. IEEE Transactions on Control Systems Technology,(S1050-4729), 2010, 18(6): 1359-1370.
[11]	Hua C C, Wang Y Q, Guan X P.Visual tracking control for an uncalibrated robot system with unknown camera parameters[J]. Robotics and Computer-Integrated Manufacturing (S0020-7721), 2014, 30(1): 19-24.
[12]	Hashimoto H, Kubota T, Sato M, et al.Visual control of robotic manipulator based on neural networks[J]. IEEE Transactions on Industrial Electronics (S0278-0046), 1992, 39(6): 490-496.
[13]	Stanley K, Wu Q M J, Jerbi A, et al. Neural network-based vision guided robotics[C]. IEEE International Conference on Robotics and Automation, 1999. Proceedings. IEEE, Detroit, MI, USA: IEEE Press 2002, 1: 281-286.
[14]	Albus J S.A new approach to manipulator control: The cerebellar model articulation controller (CMAC)[J]. J. Dyn. Syst., Meas., Control (S0022-0434), 1975, 97(3): 220-227.
[15]	Albus J S.Data storage in the cerebellar model articulation controller (CMAC)[J]. J. Dyn. Syst., Meas., Control (S0022-0434), 1975, 97(3): 228-233.
[16]	Miljkovi¢ Z, Miti¢ M, Lazarevi¢ M, et al.Neural network Reinforcement Learning for visual control of robot manipulators[J]. Expert Syst. Appl.(S0957-4174), 2013, 40(5): 1721-1736.
[17]	Shi H, Li X, Hwang K S, et al.Decoupled visual servoing with fuzzy Q-learning[J]. IEEE Trans. Ind. Informat.(S1941-0050), 2018, 14(1): 241-252.
[18]	Bateux Q, Marchand E, Leitner J, et al.Visual Servoing from Deep Neural Networks[C]. Conference: Cambridge MA, USA: RSS Workshop, 2017.
[19]	Siradjuddin I, Behera L, Mcginnity T M, et al.Image-Based Visual Servoing of a 7-DOF Robot Manipulator Using an Adaptive Distributed Fuzzy PD Controller[J]. IEEE/ASME Transactions on Mechatronics,(S1941-014X), 2014, 19(2): 512-523.
[20]	Ahn K K, Anh H P H. Inverse double narx fuzzy modeling for system identification[J]. IEEE/ASME Transactions on Mechatronics (S1941-014X), 2009, 15(1): 136-148.
[21]	Liu Y J, Wang W, Tong S C, et al.Robust adaptive tracking control for nonlinear systems based on bounds of fuzzy approximation parameters[J]. IEEE Trans. Syst., Man, Cybern. A, Syst., Humans (S1558-2426), 2010, 40(1): 170-184.
[22]	Gueaieb W, Karray F, Al-Sharhan S.A robust adaptive fuzzy position/force control scheme for cooperative manipulators[J]. IEEE Trans. Control Syst. Technol.(S1558-0865), 2003, 11(4): 516-528.
[23]	Goncalves P, Mendoca L, Sousa J, et al.Uncalibrated eye to hand visual servoing using inverse fuzzy models[J]. IEEE Trans. Fuzzy Syst.(S1941-0034), 2008, 16(2): 341-353.
[24]	Wang F, Liu Z, Zhang Y, et al.Adaptive fuzzy visual tracking control for manipulator with quantized saturation input[J]. Nonlinear Dynamics (S0924-090X), 2017, 89(3): 1-18.
[25]	Liu Z, Wang F, Zhang Y.Adaptive Visual Tracking Control for Manipulator With Actuator Fuzzy Dead-Zone Constraint and Unmodeled Dynamic[J]. IEEE Transactions on Systems Man & Cybernetics Systems (S2168-2232), 2015, 45(10): 1301-1312.
[26]	Tanaka K, Sugeno M.Stability analysis and design of fuzzy control systems[J]. Fuzzy Sets Syst.(S0165-0114), 1992, 45(2): 135-156.
[27]	Xiu Z H, Ren G.Stability analysis and systematic design of Takagi_Sugeno fuzzy control systems[J]. Fuzzy Sets Syst.(S0165-0114), 2006, 151(1): 119-138.
[28]	Wai R, Lin Y.Adaptive moving target tracking control of vision based mobile robot via dynamic Petri recurrent fuzzy neural network[J]. IEEE Trans. Fuzzy Syst.(S1941-0034), 2013, 21(4): 688-701.
[29]	Wai R J, Chen P C.Robust neural-fuzzy-network control for robot manipulator including actuator dynamics[J]. IEEE Trans. Ind. Electron.(S1557-9948), 2006, 53(4): 1328-1349.
[30]	Pan W, Lyu M, Hwang K S, et al.A Neuro-Fuzzy Visual Servoing Controller for an Articulated Manipulator[J]. IEEE Access (S2169-3536), 2018, 6: 3346-3357.
[31]	Suh I H, Kim T W.Fuzzy membership function based neural networks with applications to the visual servoing of robot manipulators[J]. IEEE Transactions on Fuzzy Systems (S1941-0034), 1994, 2(3): 203-220.
[32]	Burges C J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining Knowl. Discovery (S1384-5810), 1998, 2(2): 121-167.
[33]	Vapnik V.Statistical Learning Theory[M]. New York, USA: Wiley, 1998.