MOTION CONTROL OF FLEXIBLE ROBOTIC ARMS BASED ON CEREBELLAR SPIKING NEURAL NETWORK

Zhang Touming; Han Fang; Wang Qingyun

doi:10.6052/0459-1879-24-560

Volume 57 Issue 4

Apr. 2025

Turn off MathJax

Article Contents

Abstract

References

Chinese Journal of Theoretical and Applied Mechanics > 2025 > 57(4): 997-1007. > DOI: 10.6052/0459-1879-24-560 CSTR: 32045.14.0459-1879-24-560

Zhang Touming, Han Fang, Wang Qingyun. Motion control of flexible robotic arms based on cerebellar spiking neural network. Chinese Journal of Theoretical and Applied Mechanics, 2025, 57(4): 997-1007. DOI: 10.6052/0459-1879-24-560

Citation:

PDF (3021 KB)

MOTION CONTROL OF FLEXIBLE ROBOTIC ARMS BASED ON CEREBELLAR SPIKING NEURAL NETWORK

Zhang Touming^*,
Han Fang^{*, †, ,},
Wang Qingyun^{†, **}

*.
College of Information Science and Technology, Donghua University, Shanghai 201620, China
†.
Ningxia Basic Science Research Center of Mathematics, College of Mathematics and Statistics, Ningxia University, Yinchuan 750021, China
**.
Department of Dynamics and Control, Beihang University, Beijing 100191, China

Received Date: December 03, 2024
Accepted Date: March 04, 2025
Available Online: March 04, 2025
Published Date: March 08, 2025

Graphical Abstract

Abstract

Abstract

Due to the soft characteristics of its own material, the flexible robotic arm is very susceptible to the uncertainty interference in the environment, which leads to unexpected deformation and affects the control accuracy. To address this situation, this paper draws on the cerebellum's regulation of motion and adaptation to the environment in the human body, and builds a cerebellar spiking neural network model for corrective control of the motion behavior of flexible robotic arms under environmental disturbances. Firstly, a multi-degree-of-freedom flexible robotic arm model is built based on the piecewise constant curvature (PCC) method, which has moving joints and rotating joints and can realize the motion behaviors of stretching and bending; and the inverse kinematic model of the robotic arm is obtained by using the sequential quadratic programming (SQP) algorithm to approximate the computation, so as to solve the desired joint parameters corresponding to the desired trajectory. Then, drawing on the neural system structure and adaptive function of the cerebellar cortex, the synaptic plasticity rule between the granular cell layer and the Purkinje cell layer is modeled to fully construct the cerebellar spiking neural network model. Finally, this paper investigates the motion effect of the flexible robotic arm to complete the circular trajectory and the “figure-eight” trajectory under the environmental interference, and finds that compared with the direct open-loop control of the motion results without the cerebellar model, the trajectory error of the flexible robotic arm end-effector under the control of the cerebellar spiking neural network has been reduced by 95% and 96%, which demonstrates the effectiveness of the cerebellar spiking neural network model in enhancing the flexible robotic arm's resistance to uncertainty interference. Compared to traditional control methods, this approach is more biologically interpretable and provides a brain-inspired intelligent method for the motion control of flexible robotic arms under uncertainty perturbation.
- cerebellum,
- flexible robotic arm,
- spiking neural network,
- adaptability

FullText(HTML)

References (31)

References

[1]	Monje Micharet CA, Laschi C. Editorial: Advances in modeling and control of soft robots. Frontiers in Robotics and AI, 2021, 8: 706514 doi: 10.3389/frobt.2021.706514
[2]	王海涛, 彭熙凤, 林本末. 软体机器人研究进展. 华南理工大学学报(自然科学版), 2020, 48(2): 94-106 (Wang Haitao, Peng Xifeng, Lin Benmo. Research progress on soft robotics. South China University of Technology (Natural Science Edition), 2020, 48(2): 94-106 (in Chinese) Wang Haitao, Peng Xifeng, Lin Benmo. Research progress on soft robotics. South China University of Technology (Natural Science Edition), 2020, 48(2): 94-106 (in Chinese)
[3]	Marchese AD, Onal CD, Rus D. Autonomous soft robotic fish capable of escape maneuvers using fluidic elastomer actuators. Soft Robotics, 2014, 1(1): 75-87 doi: 10.1089/soro.2013.0009
[4]	Calisti M, Giorelli M, Levy G, et al. An octopus-bioinspired solution to movement and manipulation for soft robots. Bioinspiration & Biomimetics, 2011, 6(3): 036002
[5]	Mustaza SM, Elsayed Y, Lekakou C, et al. Dynamic modeling of fiber-reinforced soft manipulator: A visco-hyperelastic material-based continuum mechanics approach. Soft Robotics, 2019, 6(3): 305-317 doi: 10.1089/soro.2018.0032
[6]	Wang HS, Yang BH, Liu YT, et al. Visual servoing of soft robot manipulator in constrained environments with an adaptive controller. IEEE/ASME Transactions on Mechatronics, 2017, 22(1): 41-50 doi: 10.1109/TMECH.2016.2613410
[7]	Lindenroth L, Stoyanov D, Rhode K, et al. Toward intrinsic force sensing and control in parallel soft robots. IEEE/ASME Transactions on Mechatronics, 2023, 28(1): 80-91 doi: 10.1109/TMECH.2022.3210065
[8]	Piqué F, Kalidindi HT, Fruzzetti L, et al. Controlling soft robotic arms using continual learning. IEEE Robotics and Automation Letters, 2022, 7(2): 5469-5476 doi: 10.1109/LRA.2022.3157369
[9]	Robinson RM, Kothera CS, Sanner RM, et al. Nonlinear control of robotic manipulators driven by pneumatic artificial muscles. IEEE/ASME Transactions on Mechatronics, 2016, 21(1): 55-68 doi: 10.1109/TMECH.2015.2483520
[10]	Kawato M, Ohmae S, Hoang H, et al. 50 years since the Marr, Ito, and Albus models of the cerebellum. Neuroscience, 2021, 462: 151-174 doi: 10.1016/j.neuroscience.2020.06.019
[11]	Vijayan A, Diwakar S. A cerebellum inspired spiking neural network as a multi-model for pattern classification and robotic trajectory prediction. Frontiers in Neuroscience, 2022, 16: 909146 doi: 10.3389/fnins.2022.909146
[12]	Chen XY, Zhu WX, Liang WY, et al. Control of antagonistic mcKibben muscles via a bio-inspired approach. Journal of Bionic Engineering, 2022, 19(6): 1771-1789 doi: 10.1007/s42235-022-00225-w
[13]	Zhang Y, Huang PY, You B, et al. Design and motion simulation of a soft robot for crawling in pipes. Applied Bionics and Biomechanics, 2023, 2023: 1-8
[14]	Keyvanara M, Goshtasbi A, Kuling IA. A geometric approach towards inverse kinematics of soft extensible pneumatic actuators intended for trajectory tracking. Sensors, 2023, 23(15): 6882 doi: 10.3390/s23156882
[15]	朱永辉, 张胜文, 支辰羽等. 基于SQP算法的厢舱类产品快速设计技术研究. 机械设计, 2024, 41(S1): 64-69 (Zhu Yonghui, Zhang Shengwen, Zhi Chenyu, et al. Research on rapid design technology of cabin products based on SQP algorithm. Journal of Mechanical Design, 2024, 41(S1): 64-69 (in Chinese) Zhu Yonghui, Zhang Shengwen, Zhi Chenyu, et al. Research on rapid design technology of cabin products based on SQP algorithm. Journal of Mechanical Design, 2024, 41(S1): 64-69 (in Chinese)
[16]	Zahra O, Tolu S, Tolu S, et al. A bio-inspired mechanism for learning robot motion from mirrored human demonstrations. Frontiers in Neurorobotics, 2022, 16: 826410 doi: 10.3389/fnbot.2022.826410
[17]	Marr D, Thach WT. From the Retina to the Neocortex: Selected Papers of David Marr. Boston, MA: Birkhäuser Boston, 1991: 11-50
[18]	刘印. 基于监督学习的小脑脉冲神经网络模型. [硕士论文]. 大连: 大连理工大学, 2021 (Liu Yin. A cerebellar spiking neural network model based on supervised learning. [Master Thesis]. Dalian: Dalian University of Technology, 2021 (in Chinese) Liu Yin. A cerebellar spiking neural network model based on supervised learning. [Master Thesis]. Dalian: Dalian University of Technology, 2021 (in Chinese)
[19]	Thanawalla AR, Chen AI, Azim E. The cerebellar nuclei and dexterous limb movements. Neuroscience, 2020, 450: 168-183 doi: 10.1016/j.neuroscience.2020.06.046
[20]	Antonietti A, Martina D, Casellato C, et al. Control of a humanoid NAO robot by an adaptive bioinspired cerebellar module in 3D motion tasks. Computational Intelligence and Neuroscience, 2019, 2019(1): 4862157
[21]	Pimentel JM, Moioli RC, De Araujo MFP, et al. An integrated neurorobotics model of the cerebellar-basal ganglia circuitry. International Journal of Neural Systems, 2023, 33(11): 2350059 doi: 10.1142/S0129065723500594
[22]	Takahashi M, Shinoda Y. Neural circuits of inputs and outputs of the cerebellar cortex and nuclei. Neuroscience, 2021, 462: 70-88 doi: 10.1016/j.neuroscience.2020.07.051
[23]	Yamazaki K, Vo-Ho VK, Bulsara D, et al. Spiking neural networks and their applications: a review. Brain Sciences, 2022, 12(7): 863 doi: 10.3390/brainsci12070863
[24]	Abadía I, Naveros F, Garrido JA, et al. On robot compliance: a cerebellar control approach. IEEE Transactions on Cybernetics, 2021, 51(5): 2476-2489 doi: 10.1109/TCYB.2019.2945498
[25]	郝新宇, 王江, 邓斌等. 可用于机械臂控制的小脑脉冲神经元网络研究与FPGA实现. 控制与决策, 2023, 38(3): 631-644 (Hao Xinyu, Wang Jiang, Deng Bin, et al. Research and FPGA implementation of cerebellar spiking neural network for robot arm control. Journal of Control and Decision, 2023, 38(3): 631-644 (in Chinese) Hao Xinyu, Wang Jiang, Deng Bin, et al. Research and FPGA implementation of cerebellar spiking neural network for robot arm control. Journal of Control and Decision, 2023, 38(3): 631-644 (in Chinese)
[26]	Bruel A, Abadia I, Collin T, et al. The spinal cord facilitates cerebellar upper limb motor learning and control; inputs from neuromusculoskeletal simulation. PLOS Computational Biology, 2024, 20(1): e1011008 doi: 10.1371/journal.pcbi.1011008
[27]	Liu Y, Liu R, Wang JX, et al. A cerebellum-inspired spiking neural model with adapting rate neurons. IEEE Transactions on Cognitive and Developmental Systems, 2023, 15(3): 1628-1638 doi: 10.1109/TCDS.2023.3237776
[28]	Xie M, Muscinelli SP, Decker Harris K, et al. Task-dependent optimal representations for cerebellar learning. Elife, 2023, 12: e82914 doi: 10.7554/eLife.82914
[29]	Sparavigna AC. Entropy in image analysis. Entropy, 2019, 21(5): 502 doi: 10.3390/e21050502
[30]	方五益, 郭晛, 黎亮等. 柔性铰柔性杆机器人动力学建模、仿真和控制. 力学学报, 2020, 52(4): 965-974 (Fang Wuyi, Guo Xian, Li Liang, et al. Dynamics modeling, simulation, and control of robots with flexible joints and flexible links. Chinese Journal of Theoretical and Applied Mechanics, 2020, 52(4): 965-974 (in Chinese) doi: 10.6052/0459-1879-20-067 Fang Wuyi, Guo Xian, Li Liang, et al. Dynamics modeling, simulation, and control of robots with flexible joints and flexible links. Chinese Journal of Theoretical and Applied Mechanics, 2020, 52(4): 965-974 (in Chinese) doi: 10.6052/0459-1879-20-067
[31]	任峰, 都军民, 李广华. 降低圆柱升力脉动的智能自适应旋转控制. 力学学报, 2024, 56(4): 972-979 (Ren Feng, Du Junmin, Li Guanghua. Intelligent self-adaptive control for mitigating lift fluctuations of a circular cylinder. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(4): 972-979 (in Chinese) doi: 10.6052/0459-1879-23-449 Ren Feng, Du Junmin, Li Guanghua. Intelligent self-adaptive control for mitigating lift fluctuations of a circular cylinder. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(4): 972-979 (in Chinese) doi: 10.6052/0459-1879-23-449

[1]	Zhang Linghai, Zhou Bin, Luo Yi, Feng Jun. AN ADAPTIVE COLLOCATION POINT ALGORITHM FOR PHYSICS-INFORMED NEURAL NETWORKS[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(10): 3069-3083. DOI: 10.6052/0459-1879-24-244
[2]	Ren Feng, Du Junmin, Li Guanghua. INTELLIGENT SELF-ADAPTIVE CONTROL FOR MITIGATING LIFT FLUCTUATIONS OF A CIRCULAR CYLINDER[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(4): 972-979. DOI: 10.6052/0459-1879-23-449
[3]	Chen Xiang, Cheng Shuo, Zhao Wanzhong, Wang Chunyan, Jiang Rui. EXTENSION-DECISION-BASED ADAPTIVE COLLISION AVOIDANCE CONTROL FOR VEHICLES[J]. Chinese Journal of Theoretical and Applied Mechanics, 2023, 55(1): 213-222. DOI: 10.6052/0459-1879-22-347
[4]	Liu Hongquan, Chen Shaolin, Sun Xiaoying, Wu Shaoheng. VULNERABILITY ANALYSIS OF NPP EQUIPMENT BASED ON NEURAL NETWORK[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(7): 2059-2070. DOI: 10.6052/0459-1879-21-466
[5]	Xu Dengke, Dong Xu, Xu Ruize, Li Jia, Sun Dakun, Sun Xiaofeng. RESEARCH PROGRESS OF ADAPTIVE CONTROL METHODS FOR COMPRESSOR FLOW STABILITY[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(3): 559-576. DOI: 10.6052/0459-1879-21-560
[6]	Shao Yulong, Duan Qinglin, Gao Xin, Li Xikui, Zhang Hongwu. ADAPTIVE CONSISTENT HIGH ORDER ELEMENT-FREE GALERKIN METHOD[J]. Chinese Journal of Theoretical and Applied Mechanics, 2017, 49(1): 105-116. DOI: 10.6052/0459-1879-16-252
[7]	Hongzhe Dai Wei Zhao Wei Wang. An efficient adaptive importance samping method for structural reliability analysis[J]. Chinese Journal of Theoretical and Applied Mechanics, 2011, 43(6): 1133-1140. DOI: 10.6052/0459-1879-2011-6-lxxb2010-805
[8]	Shengli Xu, Gengdong Cheng. Material design of permeability coefficient based on adaptive mesh[J]. Chinese Journal of Theoretical and Applied Mechanics, 2010, 42(2): 238-244. DOI: 10.6052/0459-1879-2010-2-2008-730
[9]	AN ADAPTIVE CONTROL STRATEGY FOR DIRECTING CHAOTIC MOTION TO PERIODIC MOTION[J]. Chinese Journal of Theoretical and Applied Mechanics, 1997, 29(5): 631-635. DOI: 10.6052/0459-1879-1997-5-1995-277
[10]	CONSTRUCTION OF AN ADAPTIVE HYBRID FORM OF TVD SCHEMES[J]. Chinese Journal of Theoretical and Applied Mechanics, 1995, 27(6): 647-652. DOI: 10.6052/0459-1879-1995-6-1995-480

Cited By

Cited by

Periodical cited type(1)

王鹏欢，汤名锴，王森林. 激光选区熔化成形多层级Gyroid点阵结构的力学性能研究. 力学学报. 2025(01): 148-161 .

本站查看

Other cited types(0)

Get Citation

PDF

XML

Article Metrics

Article views (127) PDF downloads (38) Cited by(1)

MOTION CONTROL OF FLEXIBLE ROBOTIC ARMS BASED ON CEREBELLAR SPIKING NEURAL NETWORK