Research Papers

Improved Neural Network Control Approach for a Humanoid Arm

[+] Author and Article Information
Xinhua Liu

School of Mechatronics Engineering,
China University of Mining and Technology,
Xuzhou 211006, China
e-mail: liuxinhua@cumt.edu.cn

Xiaohui Zhang

School of Mechatronics Engineering,
China University of Mining and Technology,
Xuzhou 211006, China
e-mail: xh_zhang@cumt.edu.cn

Reza Malekian

Department of Computer Science
and Media Technology,
Malmö University,
Malmö 20506, Sweden
e-mail: reza.malekian@ieee.org

Th. Sarkodie-Gyan

College of Engineering,
University of Texas,
500 West University Avenue,
El Paso, TX 79968
e-mail: tsarkodi@utep.edu

Zhixiong Li

School of Engineering,
Ocean University of China,
Tsingdao 266100, China;
School of Mechanical, Materials,
Mechatronic and Biomedical Engineering,
University of Wollongong,
Wollongong, NSW 2522, Australia
e-mail: zhixiong_li@uow.edu.au

1Corresponding author.

Contributed by the Dynamic Systems Division of ASME for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT,AND CONTROL. Manuscript received November 25, 2018; final manuscript received May 7, 2019; published online June 13, 2019. Assoc. Editor: Mohammad A. Ayoubi.

J. Dyn. Sys., Meas., Control 141(10), 101009 (Jun 13, 2019) (13 pages) Paper No: DS-18-1525; doi: 10.1115/1.4043761 History: Received November 25, 2018; Revised May 07, 2019

This study extended the knowledge over the improvement of the control performance for a seven degrees-of-freedom (7DOF) humanoid arm. An improved adaptive Gaussian radius basic function neural network (RBFNN) approach was proposed to ensure the reliability and stability of the humanoid arm control. Considering model uncertainties, the established dynamic model for the humanoid arm was divided into a nominal model and an error model. The error model was approximated by the RBFNN learning to compensate the uncertainties. The contribution of this study mainly concentrates on employing fruit fly optimization algorithm (FOA) to optimize the basic width parameter of the RBFNN, which can enhance the capability of the error approximation speed. Additionally, the output weights of the neural network were adjusted using the Lyapunov stability theory to improve the robustness of the RBFN-based error model. The simulation and experiment results demonstrate that the proposed approach is able to optimize the system state with less tracking errors, regulate the uncertain nonlinear dynamic characteristics, and effectively reduce unexpected interferences.

Copyright © 2019 by ASME
Your Session has timed out. Please sign back in to continue.


Paik, J. K. , Shin, B. H. , Bang, Y. B. , and Shim, Y. B. , 2012, “ Development of an Anthropomorphic Robotic Arm and Hand for Interactive Humanoids,” J. Biol. Eng., 9(2), pp. 133–142.
Hoekstra, A. , Morgan, J. , Lurain, J. , Buttin, B. , Singh, D. , Schink, J. , and Lowe, M. , 2009, “ Robotic Surgery in Gynecologic Oncology: Impact on Fellowship Training,” Gynecol. Oncol., 114(2), pp. 168–172. [CrossRef] [PubMed]
Hirukawa, H. , 2007, “ Walking Biped Humanoids That Perform Manual Labour,” Philos. Trans., 365(1850), pp. 65–77. [CrossRef]
Zhou, L. , and Bai, S. , 2015, “ A New Approach to Design of a Lightweight Anthropomorphic Arm for Service Applications,” ASME J. Mech. Rob., 7(3), p. 031001. [CrossRef]
Sun, J. , and Zhang, W. , 2012, “ A Novel Coupled and Self-Adaptive Under-Actuated Multi-Fingered Hand With Gear–Rack–Slider Mechanism,” J. Manuf. Syst., 31(1), pp. 42–49. [CrossRef]
Driver, T. A. , and Shen, X. , 2014, “ Design and Control of a Sleeve Muscle-Actuated Robotic Elbow,” ASME J. Dyn. Syst. Meas. Control, 136(4), p. 041023. [CrossRef]
Controzzi, M. , Cipriani, C. , Jehenne, B. , Donati, M. , and Carrozza, M. C. , 2010, “ Bio-Inspired Mechanical Design of a Tendon-Driven Dexterous Prosthetic Hand,” Annual International Conference of the IEEE Engineering in Medicine and Biology (IEMBS), Buenos Aires, Argentina, Aug. 31–Sept. 4, pp. 499–502.
Liu, H. , Cui, S. , Liu, Y. , Ren, Y. , and Sun, Y. , 2018, “ Design and Vibration Suppression Control of a Modular Elastic Joint,” Sensors, 18(6), p. 1869. [CrossRef]
Kargov, A. , Asfour, T. , Pylatiuk, C. , and Oberle, R. , 2005, “ Development of an Anthropomorphic Hand for a Mobile Assistive Robot,” 9th International Conference on Rehabilitation Robotics (ICORR), Chicago, IL, June 28–July 1, pp. 182–186.
Wu, Q. C. , Wang, X. S. , and Du, F. P. , 2016, “ Analytical Inverse Kinematic Resolution of a Redundant Exoskeleton for Upper-Limb Rehabilitation,” Int. J. Human. Rob., 13(3), p. 1550042. [CrossRef]
Artemiadis, P. K. , Katsiaris, P. T. , and Kyriakopoulos, K. J. , 2010, “ A Biomimetic Approach to Inverse Kinematics for a Redundant Robot Arm,” Auton. Rob., 29(3–4), pp. 293–308. [CrossRef]
Mohan, V. , and Morasso, P. , 2011, “ Passive Motion Paradigm: An Alternative to Optimal Control,” Front. Neurorob., 5, p. 4. [CrossRef]
Bhat, A. A. , Akkaladevi, S. C. , Mohan, V. , Eitzinger, C. , and Morasso, P. , 2017, “ Towards a Learnt Neural Body Schema for Dexterous Coordination of Action in Humanoid and Industrial Robots,” Auton. Rob., 41(4), pp. 945–966. [CrossRef]
Wang, Y. , Shi, R. , and Wang, H. , 2013, “ Dynamic Modeling and Fuzzy Self-Tuning Disturbance Decoupling Control for a 3-Dof Serial-Parallel Hybrid Humanoid Arm,” Adv. Mech. Eng., 12, p. 286074. [CrossRef]
Otani, T. , Hashimoto, K. , Miyamae, S. , Ueta, H. , Natsuhara, A. , Sakaguchi, M. , Kawakami, Y. , Lim, H.-O. , and Takanishi, A. , 2018, “ Upper-Body Control and Mechanism of Humanoids to Compensate for Angular Momentum in the Yaw Direction Based on Human Running,” Appl. Sci., 8(1), pp. 44–56. [CrossRef]
Zhao, Y. , and Cheah, C. C. , 2009, “ Neural Network Control of Multifingered Robot Hands Using Visual Feedback,” IEEE Trans. Neural Network, 20(5), pp. 758–767. [CrossRef]
Sanner, R. M. , and Slotine, J. E. , 1992, “ Gaussian Networks for Direct Adaptive Control,” IEEE Trans. Neural Network, 3(6), pp. 837–863. [CrossRef]
Yoshikawa, T. , 2010, “ Multifingered Robot Hands: Control for Grasping and Manipulation,” Annu. Rev. Control, 34(2), pp. 199–208. [CrossRef]
Hemmi, D. , Herrmann, G. , Na, J. , and Mahyuddin, M. N. , 2015, “ Adaptive Optimal Tracking Control Applied for a Humanoid Robot Arm,” IEEE International Symposium on Intelligent Control (ISIC), Sydney, NSW, Australia, Sept. 21–23, pp. 35–40.
Simonidis, C. , and Seemann, W. , 2008, “ Recursive Control of a 7 Dof Robotic Arm,” PAMM, 8(1), pp. 10919–10920. [CrossRef]
Schroder, J. , Kawamura, K. , and Gockel, T. , 2003, “ Improved Control of a Humanoid Arm Driven by Pneumatic Actuators,” IEEE-RAS International Conference on Humanoid Robots (Humanoids), Las Vegas, NV, Oct. 27–31, pp. 1–18.
Liu, Z. , Chen, C. , Zhang, Y. , and Chen, C. L. P. , 2015, “ Adaptive Neural Control for Dual-Arm Coordination of Humanoid Robot With Unknown Nonlinearities in Output Mechanism,” IEEE Trans. Cybern., 45(3), p. 521. [CrossRef] [PubMed]
Kondak, K. , Hommel, G. , Stanczyk, B. , and Buss, M. , 2005, “ Robust Motion Control for Robotic Systems Using Sliding Mode,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Edmonton, AB, Canada, Aug. 2–6, pp. 2375–2380.
Van Tran, T. , Wang, Y. N. , Ao, H. L. , and Khac Truong, T. , 2015, “ Sliding Mode Control Based on Chemical Reaction Optimization and Radial Basis Functional Link Net for De-Icing Robot Manipulator,” ASME J. Dyn. Syst. Meas. Control, 137(5), p. 051009. [CrossRef]
Ahn, M. S. , Cho, S. H. , Oh, C. Y. , Lee, S. R. , and Yi, H. , 2017, “ Intelligent Controlof Humanoid Manipulation With Uncertain Weight Objects,” Int. J. Adv. Rob. Syst., 14(3) (epub).
Shibuya, Y. , and Maru, N. , 2009, “ Control of 6 DOF Arm of the Humanoid Robot by Linear Visual Servoing,” IEEE International Symposium on Industrial Electronics (ISIE), Seoul, South Korea, July 5–8, pp. 1791–1796.
Su, Y. , and Zheng, C. , 2019, “ Fixed-Time Inverse Dynamics Control for Robot Manipulators,” ASME J. Dyn. Syst. Meas. Control, 141(6), p. 064502. [CrossRef]
Liu, X. H. , Zheng, X. H. , Li, S. P. , Chen, X. H. , and Wang, Z. B. , 2015, “ Improved Adaptive Neural Network Control for Humanoid Robot Hand in Workspace,” J. Mech. Eng. Sci. Technol., 229(5), pp. 869–881. [CrossRef]
Yao, J. , Wang, X. , Hu, S. , and Fu, W. , 2011, “ Adaline Neural Network-Based Adaptive Inverse Control for an Electro-Hydraulic Servo System,” J. Vib. Control, 17(13), pp. 2007–2014. [CrossRef]
Sefriti, S. , Boumhidi, J. , Naoual, R. , and Boumhidi, Y. , 2012, “ Adaptive Neural Network Sliding Mode Control for Electrically-Driven Robot Manipulators,” Control Eng. Appl. Inf., 14(4), pp. 27–32.
Salahshoor, K. , Zakeri, S. , and Sefat, M. H. , 2013, “ Stabilization of Gas-Lift Oil Wells by a Nonlinear Model Predictive Control Scheme Based on Adaptive Neural Network Models,” Eng. Appl. Artif. Intell., 26(8), pp. 1902–1910. [CrossRef]
Guzey, H. M. , Xu, H. , and Jagannathan, S. , 2015, “ Neural Network-Based Adaptive Optimal Consensus Control of Leaderless Networked Mobile Robots,” IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), Orlando, FL, Dec. 9–12 pp. 295–300.
Mehraeen, S. , Jagannathan, S. , and Crow, M. L. , 2012, “ Decentralized State Feedback and Near Optimal Adaptive Neural Network Control of Interconnected Nonlinear Discrete-Time Systems,” 49th IEEE Conference on Decision and Control (CDC), Atlanta, GA, Dec. 15–17, pp. 6406–6411.
Zhang, Z. J. , Yan, Z. Y. , and Fu, T. Z. , 2018, “ Varying-Parameter RNN by Finite-Time Functions for Solving Joint-Drift Problems of Redundant Robot Manipulators,” IEEE Trans. Ind. Inf., 14(12), pp. 5359–5367. [CrossRef]
Cook, D. F. , Ragsdale, C. T. , and Major, R. L. , 2000, “ Combining a Neural Network With a Genetic Algorithm for Process Parameter Optimization,” Eng. Appl. Artif. Intell., 13(4), pp. 391–396. [CrossRef]
Xu, Y. Y. , Wang, Y. , and Xue, D. B. , 2018, “ Neural Network Control Optimization and Simulation of Robot Arm,” Chin. J. Constr. Mach., 16(5), pp. 44–48 (in Chinese).
Li, X. , Nishiguchi, J. , Minami, M. , and Matsuno, T. , 2015, “ Iterative Calculation Method for Constraint Motion by Extended Newton-Euler Method and Application for Forward Dynamics,” Eighth IEEE/SICE International Symposium on System Integration (SII), Nagoya, Japan, Dec. 11–13, pp. 313–319.
Luo, L. , Wang, S. , Mo, J. , and Cai, J. , 2006, “ On the Modeling and Composite Control of Flexible Parallel Mechanism,” Int. J. Adv. Manuf. Technol., 29(7–8), pp. 786–793. [CrossRef]
Chen, C. S. , 2008, “ Dynamic Structure Neural-Fuzzy Networks for Robust Adaptive Control of Robot Manipulators,” IEEE Trans. Ind. Electron., 55(9), pp. 3402–3414. [CrossRef]
Zhu, D. , Mei, T. , and Luo, M. , 2009, “ Adaptive Sliding Mode Control for Robots Based on Fuzzy Support Vector Machines,” International Conference on Mechatronics and Automation (ICMA), Changchun, China, Aug. 9–12, pp. 3469–3474.
Sepasi, D. , Nagamune, R. , and Sassani, F. , 2012, “ Tracking Control of Flexible Ball Screw Drives With Runout Effect and Mass Variation,” IEEE Trans. Ind. Electron., 59(2), pp. 1248–1256. [CrossRef]
Sage, H. G. , Mathelin, M. F. D. , and Ostertag, E. , 1999, “ Robust Control of Robot Manipulators: A Survey,” Int. J. Control, 72(16), pp. 1498–1522. [CrossRef]
Lu, S. Y. , Zhou, Q. H. , and Li, Q. B. , 2014, “ RBF Neural Network Used on Universal Intelligent Monitoring System in Heavy Machinery,” Appl. Mech. Mater., 556–562, pp. 3242–3245. [CrossRef]
Moody, J. , and Darken, C. J. , 1989, “ Fast Learning in Networks of Locally-Tuned Processing Units,” Neural Comput., 1(2), pp. 281–294. [CrossRef]
Huang, S. , and Tan, K. K. , 2012, “ Intelligent Friction Modeling and Compensation Using Neural Network Approximations,” IEEE Trans. Ind. Electron., 59(8), pp. 3342–3349. [CrossRef]
Qu, J. , Zhang, F. , Fu, Y. , Li, G. , and Guo, S. , 2017, “ Adaptive Neural Network Visual Servoing of Dual-Arm Robot for Cyclic Motion,” Ind. Rob., 44(2), pp. 210–221. [CrossRef]
Li, Y. L. , Huang, P. W. , and Xie, T. , 2013, “ A Research on Adaptive Neural Network Control Strategy of Vehicle Yaw Stability,” Fourth International Conference on Intelligent Systems Design and Engineering Applications (ISDEA), Zhangjiajie, China, Nov. 6–7, pp. 48–51.
Wei, M. , and Chen, G. , 2011, “ Adaptive RBF Neural Network Sliding Mode Control for Ship Course Control System,” Third International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMC), Zhejiang, China, Aug. 26–27, pp. 27–30.
Pan, W. T. , 2012, “ A New Fruit Fly Optimization Algorithm: Taking the Financial Distress Model as an Example,” Knowl.-Based Syst., 26(2), pp. 69–74. [CrossRef]


Grahic Jump Location
Fig. 1

Three-dimensional model of the 7DOF humanoid arm and D–H coordinate system

Grahic Jump Location
Fig. 2

Graphic description of the fruit fly group food searching procedure

Grahic Jump Location
Fig. 5

Schematic diagram of the proposed control system

Grahic Jump Location
Fig. 6

FOA optimization curve

Grahic Jump Location
Fig. 7

Tracked trajectories of the joint variable set in the simulation

Grahic Jump Location
Fig. 8

Approximation of f using (a) traditional RBFNN and (b) proposed FOA+RBFNN

Grahic Jump Location
Fig. 9

Control experiment platform of the humanoid arm

Grahic Jump Location
Fig. 10

Tracked trajectory of each joint variable

Grahic Jump Location
Fig. 11

Trajectory tracking errors of the joint variable set



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In