Hostname: page-component-6bf8c574d5-gr6zb Total loading time: 0 Render date: 2025-02-27T14:02:29.245Z Has data issue: false hasContentIssue false
  • English
  • Français

Adaptive optimization for virtual model control of quadruped robots based on BP neural network

Published online by Cambridge University Press:  26 February 2025

Jianwen Liu Open the ORCID record for Jianwen Liu [Opens in a new window] ,
Xiaojun Xu ,
Wenhao Wang ,
Yuanjiang Tang  and
Shengyang Lu
Jianwen Liu*
Affiliation:
College of Intelligent Science, National University of Defense Technology, Changsha, PR China
Xiaojun Xu
Affiliation:
College of Intelligent Science, National University of Defense Technology, Changsha, PR China
Wenhao Wang
Affiliation:
College of Intelligent Science, National University of Defense Technology, Changsha, PR China
Yuanjiang Tang
Affiliation:
College of Intelligent Science, National University of Defense Technology, Changsha, PR China
Shengyang Lu
Affiliation:
College of Intelligent Science, National University of Defense Technology, Changsha, PR China
*
Corresponding author: Jianwen Liu; Email: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

The virtual model control (VMC) method establishes a direct correlation model between the end-effector and the main body by selecting appropriate virtual mechanical components. This approach facilitates direct force control while circumventing the necessity for complex dynamic modeling. However, the simplification inherent in this modeling can result in inaccuracies in the calculation of joint driving torques, ultimately diminishing control precision. Moreover, VMC typically depends on predefined models for control, which constrains its adaptability in dynamically complex environments and under varying movement conditions. To address these limitations, this paper proposes the BP-VMC method, which is based on a backpropagation neural network (BPNN). Initially, a quadruped robot model was established through kinematic analysis. Subsequently, a decomposed VMC model was developed, and BPNN was introduced to facilitate the adaptive tuning of virtual parameters. This approach resulted in the creation of a virtual mechanical component model with adaptive capabilities, compensating for errors arising from simplified modeling. Finally, a simulation control system was constructed based on the BP-VMC control framework to validate the optimization of control performance. Simulation experiments demonstrated that, in comparison to traditional VMC methods, the BP-VMC method exhibits enhanced control accuracy and stability, achieving a 30% reduction in trajectory tracking error, a 40% reduction in velocity tracking error, and a 20–30% improvement in instability indices across various working conditions. This evidence underscores the BP-VMC method’s robust adaptability in dynamic environments.

Keywords

quadruped robotvirtual model controlBP neural networkparameter adaptationcontrol of robotic systems
Type
Research Article
Information
Robotica , First View , pp. 1 - 33
Copyright
© The Author(s), 2025. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Gor, M. M., Pathak, P. M., Samantaray, A. K., Yang, J. M., Kwak, S.W., “Control oriented model-based simulation and experimental studies on a compliant legged quadruped robot,” Robot. Auton. Syst. 72(C), 217–234 (2015).CrossRefGoogle Scholar
Hamid, T. and Nasser, M., “A study on quadruped mobile robots,” Mech. Mach. Theory 190, 105448 (2023).Google Scholar
Jiandong, C., Jinzhu, Z., Wang, T., M. Jiahao, L. Senlin and L. Miao, “Mechanism design and dynamic switching modal control of the wheel-legged separation quadruped robot,” Robotica 42(3), 660–683 (2024).Google Scholar
Kousik, S., Rahul, S., Annigeri, A. R., U. B. Praveen Kumar and M. N. Bharath, “Performance analysis of quadruped robot designed with Desai’s walking leg mechanism,” Aust. J. Mech. Eng. 22(2), 282–295 (2024).Google Scholar
Amir, I., Yuan, G. and Yan, G., “Provably stabilizing controllers for quadrupedal robot locomotion on dynamic rigid platforms,” IEEE/ASME Trans. Mechatron. 25(4), 2035–2044 (2020).Google Scholar
De Paula Daniel, T., Paciencia, G. E. and Mauricio, B.-V., “Dynamic modeling and simulation of a torque-controlled spatial quadruped robot,” Robotica 42(8), 1–20 (2024).Google Scholar
Huaizhi, Z., Junhui, Z., Jiang, L., Z. Kun, S. Jun, L. Zhenyu, W. Ke, W. Yanli and X. Bing, “Bionic lightweight design of limb leg units for hydraulic quadruped robots by additive manufacturing and topology optimization,” Bio-Des. Manuf. 7(1), 1–13 (2024).Google Scholar
Akshit, S., Vijay, M., Krishnan, V., M. Sandeep and M. D. Arun, “Formation control and trajectory tracking of nonholonomic mobile robots,” IEEE Trans. Control Syst. Trans. 26(6), 2250–2258 (2018).Google Scholar
Fan, Y. A., Pei, Z. C., Wang, C., Li, M., Tang, Z. Y., Liu, Q. H.“A review of quadruped robots: Structure, control, and autonomous motion,” Adv. Intell. Syst. 6(6) (2024).CrossRefGoogle Scholar
Hui, C., Yibin, L., Song, R., Z. Guoteng, Z. Qin, L. Song, H. Jinmian, X. Yaxian, Y. Ming, Z. Guoxuan and Y. Zhiyuan, “A survey of the development of quadruped robots : Joint configuration, dynamic locomotion control method and mobile manipulation approach,” Biomimetic Intell. Rob. 1(1), 9–21 (2022).Google Scholar
Shengyang, L., Yue, J., Lei, Z. and Xiaojun, X., “Adaptive differential steering strategy for distributed driving unmanned ground vehicle with variable configurations based on modified localized modelling sliding mode control,” ISA Trans. 151, 391–408 (2024).Google Scholar
Xiaojun, X., Shengyang, L., Jiang, Y., L. Jianwen and Z. Lei, “Driving strategy of unmanned ground vehicle under split-docking road conditions based on improved EKF and PID-modified SMC,” Adv. Eng. Inf. 62(Part C), 102830 (2024).Google Scholar
Takeuchi, H., “Development of MEL HORSE”. In: 19th Annual Conference of the Robotics Society of Japan (RSJ2001), Tokyo, Japan, September 18-20 (2001).Google Scholar
Yoneda, R. K. K. and Hirose, S., “Shigeo Hirose “Feedforward and feedback trot gait control for quadruped walking vehicle,” Auton. Rob. 12(2), 157–172 (2002).Google Scholar
Raibert Marc, H. and Sutherland Ivan, E., “Machines that walk,” Sci. Am. 248(1), 44–53 (1983).CrossRefGoogle Scholar
Raibert Marc, H. and Tello Ernest, R., “Legged robots that balance,” IEEE Exp. 1(4), 89 (1986).CrossRefGoogle Scholar
Pratt, J. and Dilworth, P., “Virtual Model Control of a Bipedal Walking Robot,” In: Proceedings of International Conference on Robotics and Automation, Albuquerque, NM, USA (1997).Google Scholar
Aizhen, X., Teng, C., Rong, X., Z. Guoteng, L. Yibin and F. Yong, “A robust and compliant framework for legged mobile manipulators using virtual model control and whole-body control,” Rob. Auton. Syst. 164 (C), 104411 (2023).Google Scholar
Yasuhiro, F., Hiroshi, K. and Cohen Avis, H., “Adaptive dynamic walking of a quadruped robot on irregular terrain based on biological concepts,” Int. J. Rob. Res. 22(3-4), 187–202 (2003).Google Scholar
Hiroshi, K., Yasuhiro, F. and Cohen Avis, H., “Adaptive dynamic walking of a quadruped robot on natural ground based on biological concepts,” Int. J. Rob. Res. 26(5), 475–490 (2007).Google Scholar
Linlin, S., Wei, W. and Jianqiang, Y., “Active Impact Motion for a Quadruped Robot,” In: 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE), Hong Kong, China (2020).Google Scholar
Michele, F., Amina, K., Aubakir, B., Giuseppina, G., Alessio Mauro, F., Matteo, B.“A neuromorphic control architecture for a biped robot,” Rob. Auton. Syst. 120(0), 103244 (2019).Google Scholar
Xin, J., Tao, S. and Kai, S., “Design of an Effective Trajectory Control Method for Quadruped Robot ia Neural Network,” In: 2018 13th World Congress On Intelligent Control and Automation (WCICA), Changsha, China (2018).Google Scholar
Shangyu, W., Xianqing, L. and Linqi, Y., “Balance control of an inverted pendulum on a quadruped robot by reinforcement learning,” J. Phys. Conf. Ser. 2187(1), 012024 (2022).Google Scholar
Ji, Q., Haibo, G., Su, H., H. Liangliang, S. Bo, H. Mingying, Y. Haitao and D. Zongquan, “Reinforcement learning-based stable jump control method for asteroid-exploration quadruped robots,” Aerospace Sci. Technol. 142(11) (Part B), 108689 (2023).Google Scholar
Sibo, G., Shangke, L., Hongyin, Z. and Donglin, W., “Continual reinforcement learning for quadruped robot locomotion,” Entropy 26(1), 93 (2024).Google Scholar
Chew, C.-M. and Pratt, G. A., “Dynamic bipedal walking assisted by learning,” Robotica 20(5), 477–491 (2002).CrossRefGoogle Scholar
Gerardo, B., Powell Matthew, J., Katz, B., D. Carlo Jared, W. M. Patrick and K. Sangbae, “MIT Cheetah 3: Design and Control of a Robust, Dynamic Quadruped Robot,” In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain (2018).Google Scholar
Di Carlo, J., Wensing Patrick, M., Katz, B., B. Gerardo and K. Sangbae, “Dynamic Locomotion in the MIT Cheetah 3 Through Convex Model-Predictive Control,” In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain (2018).Google Scholar
Zhang, G. T., Rong, X. W., Hui, C., Y. B. Li and B. Li, “Torso motion control and toe trajectory generation of a trotting quadruped robot based on virtual model control,” Adv. Rob. 30(4), 284–297 (2016).CrossRefGoogle Scholar
Chen, T., Sun, X. B., Xu, Z., Y. B. Li, X. W. Rong and L. L. Zhou, “A trot and flying trot control method for quadruped robot based on optimal foot force distribution,” J. Bionic Eng. 16(4), 621–632 (2019).CrossRefGoogle Scholar
Sabri, B., “On the implementation of Fuzzy VMC for an under actuated system,” IEEE Access 7, 163578–163588 (2019).Google Scholar
Li, Y. Y. X., Xu, Z., Yu, Y., Xu, J. and Xiao, F., “Design of trot gait parameters planning system for parallel quadruped robot based on virtual model controller and fuzzy neural network,” ISA Trans. 157, 510–529 (2024).Google Scholar
Xie, H. X., Ahmadi, M., Shang, J. Z. and Luo, Z. R., “An intuitive approach for quadruped robot trotting based on virtual model control,” Proc. Inst. Mech. Eng. Part I: J. Syst. Control Eng. 229(4), 342–355 (2015).Google Scholar
Bhaskar, S. V., Manish, R. and Nandi, G. C., “Biometric gait identification based on a multilayer perceptron,” Rob. Auton. Syst. 65(1), 65–75 (2015).Google Scholar
Robert, H.-N., “Theory of the backpropagation neural network,” Neural Netw. 1(1Suppl), 445 (1988).Google Scholar
Basheer, I. A. and Hajmeer, M., “Artificial neural networks: Fundamentals, computing, design, and application.,” J. Microbiol. Methods 43(1), 3–31 (2000).CrossRefGoogle ScholarPubMed
Yue, Z., Yue, G., Sun, Q., T. Yuan, M. Liheng and G. Feng, “A real-time low-computation cost human-following framework in outdoor environment for legged robots,” Rob. Auton. Syst. 146 (C), 103899 (2021).Google Scholar
Guangrong, C., Sheng, G., Bowen, H. and Junzheng, W., “Virtual model control for quadruped robots,” IEEE Access 8, 140736–140751 (2020).Google Scholar
Zhong, S. Y. Y. and Yulong, Y., “Motion VMC method of quadruped robot based on adaptive fuzzy algorithm,” Appl. Sci. Technol. 49(1), 53–58 (2022).Google Scholar
Deme, T. T., Manavaalan, G., Halder, K., V. H. Kumar, P. S. Sundar, J. Nishant, J. F. Orlando Maria and H. Y. Vijay, “Trajectory tracking control of a mobile robot using fuzzy logic controller with optimal parameters,” Robotica 42(8), 1–24 (2024).Google Scholar
Ming, Y., Haigang, D., Feng, X., L. Peigang, L. Yanfei and L. Haiyang, “Improved dynamic windows approach based on energy consumption management and fuzzy logic control for local path planning of mobile robots,” Comput. Ind. Eng. 187, 109767 (2024).Google Scholar
Zhijun, H., “Simulation of football based on PID controller and BP neural network,” Microprocess. Microsyst. 81, 103695 (2021).Google Scholar
Ming-Li, Z., Yi-Jie, Z., Xiao-Long, H. and Zheng-Jie, G., “Adaptive PID control and its application based on a double-layer BP neural network," Processes, 9(1475), 1475 (2021).Google Scholar
Yunkang, Z., Xiaohui, H., Faming, S. and Xiangpo, Z., “Research on the optimization of the PID control method for an EOD robotic manipulator using the PSO algorithm for BP neural networks,” Actuators 13(10), 386 (2024).Google Scholar