Please wait a minute...
浙江大学学报(工学版)  2022, Vol. 56 Issue (6): 1107-1118    DOI: 10.3785/j.issn.1008-973X.2022.06.007
智能机器人     
基于虚拟运动神经网络的六足机器人行为控制
朱雅光1,2(),刘春潮1,张亮1
1. 长安大学 道路施工技术与装备教育部重点实验室,陕西 西安 710064
2. 浙江大学 流体动力与机电系统国家重点实验室,浙江 杭州 310027
Behavior control of hexapod robot based on virtual motoneuron network
Ya-guang ZHU1,2(),Chun-chao LIU1,Liang ZHANG1
1. Key Laboratory of Road Construction Technology and Equipment of MOE, Chang'an University, Xi'an 710064, China
2. State Key Laboratory of Fluid Power and Mechatronic Systems, Hangzhou 310027, China
 全文: PDF(2980 KB)   HTML
摘要:

为了使腿足机器人适应性和行为能力提高,提出基于虚拟运动神经网络的六足机器人行为控制策略. 通过模拟生物神经?肌肉控制机制构建的腿足机器人行为运动神经控制架构,能够处理外部环境信息,调节神经信号强度,获得类似动物的信号处理和行为反应机制,实现机器人对环境的快速响应、机身与腿部的自适应调节. 实验结果表明,所提架构能够随环境变化自动调节神经信号强度,验证了机器人极强的环境自适应性和行为多样性.

关键词: 神经控制虚拟运动神经网络自适应灵活性行为多样性    
Abstract:

A behavior control strategy of the hexapod robots based on a virtual motoneuron network was proposed, in order to improve the adaptability and behavior ability of legged robots. By simulating the biological neural-muscle control mechanism, a behavioral motor neural control architecture for a legged robot was constructed, which could process the external environment information, adjust the neural signal intensity, obtain the signal processing and behavioral response mechanism similar to animals, realize the quickly response of the robot to the environment and the adaptive adjustment of the robot body and legs. Experiments results showed that the proposed mechanism made the intensity of neural signals automatically adjust with environmental changes. The strong adaptability to the environment and the behavioral diversity of the robot were verified.

Key words: neural control    virtual motoneuron network    adaption    flexibility    behavioral diversity
收稿日期: 2021-12-09 出版日期: 2022-06-30
CLC:  TP 24  
基金资助: 国家自然科学基金资助项目(51605039);陕西省重点研发计划国际合作项目(2020KW-064);流体动力与机电系统国家重点实验室开放基金资助项目(GZKF-201923);中央高校基本科研业务费专项资金资助项目(300102259308,300102259401)
作者简介: 朱雅光(1986—),男,教授,从事仿生机器人、腿足机器人、并联机器人、智能控制、自主导航和智能系统研究.orcid.org/0000-0001-9103-4211. E-mail: zhuyaguang@chd.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
朱雅光
刘春潮
张亮

引用本文:

朱雅光,刘春潮,张亮. 基于虚拟运动神经网络的六足机器人行为控制[J]. 浙江大学学报(工学版), 2022, 56(6): 1107-1118.

Ya-guang ZHU,Chun-chao LIU,Liang ZHANG. Behavior control of hexapod robot based on virtual motoneuron network. Journal of ZheJiang University (Engineering Science), 2022, 56(6): 1107-1118.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2022.06.007        https://www.zjujournals.com/eng/CN/Y2022/V56/I6/1107

图 1  自适应神经控制系统
图 2  中枢神经网络
图 3  虚拟运动神经网络
图 4  机身虚拟运动神经网络
图 5  单腿摆动态神经控制模块
图 6  感知神经网络
图 7  机身运动神经强度调节模块
图 8  腿部运动神经强度调节模块
图 9  肌肉调节因子对足端轨迹的影响
图 10  足端变轨迹实验
图 11  机器人的灵巧运动实验
图 12  机器人机身的应激避障实验
图 13  机器人腿部的主动避障实验
图 14  机器人腿部的应激避障实验
1 DELCOMYN F Insect walking and robotics[J]. Annual Review of Entomology, 2004, 49 (1): 51- 70
doi: 10.1146/annurev.ento.49.061802.123257
2 BAYRO-CORROCHANO E. Geometric algebra applications vol. II: robot modelling and control [M]. [S. l.]: Springer, 2020: 379-412.
3 AMROLLAH E, HENAFF P On the role of sensory feedbacks in Rowat–Selverston CPG to improve robot legged locomotion[J]. Frontiers in Neurorobotics, 2010, 4: 113
4 ROWAT P F, SELVERSTON A I Modeling the gastric mill central pattern generator of the lobster with a relaxation-oscillator network[J]. Journal of Neurophysiology, 1993, 70 (3): 1030- 1053
doi: 10.1152/jn.1993.70.3.1030
5 SCHILLING M, PASKARBEIT J, SCHMITZ J, et al. Grounding an internal body model of a hexapod walker control of curve walking in a biologically inspired robot [C]// IEEE/RSJ International Conference on Intelligent Robots and Systems. Vilamoura-Algarve: IEEE, 2012: 2762-2768.
6 SARTORI M, YAVUZ U S, FARINA D In vivo neuromechanics: decoding causal motor neuron behavior with resulting musculoskeletal function[J]. Scientific Reports, 2017, 7 (1): 13465
doi: 10.1038/s41598-017-13766-6
7 FARINA D, VUJAKLIJA I, SARTORI M, et al Man/machine interface based on the discharge timings of spinal motor neurons after targeted muscle sreinnervation[J]. Nature Biomedical Engineering, 2017, 1: 25
doi: 10.1038/s41551-016-0025
8 WANG T, GUO W, ZHA F, et al. Research on a central pattern generator bionic coupling control system of robot [C]// IEEE International Conference on Information and Automation. Harbin: IEEE, 2010: 723-728.
9 MANOONPONG P, PARLITZ U, WÖRGÖTTER F Neural control and adaptive neural forward models for insect-like, energy-efficient, and adaptable locomotion of walking machines[J]. Frontiers in Neural Circuits, 2013, 7: 12- 40
10 STEINGRUBE S, TIMME M, WÖRGÖTTER F, et al Self-organized adaptation of a simple neural circuit enables complex robot behaviour[J]. Nature Physics, 2010, 6 (3): 224- 230
doi: 10.1038/nphys1508
11 XIONG X, WÖRGÖTTER F, MANOONPONG P Adaptive and energy efficient walking in a hexapod robot under neuromechanical control and sensorimotor learning[J]. IEEE Transactions on Cybernetics, 2015, 46 (11): 2521- 2534
12 DÜRR V, ARENA P P, CRUSE H, et al Integrative biomimetics of autonomous hexapedal locomotion[J]. Frontiers in Neurorobotics, 2019, 13: 88
13 WANG Y, XUE X, CHEN B Matsuoka’s CPG with desired rhythmic signals for adaptive walking of humanoid robots[J]. IEEE Transactions on Cybernetics, 2018, 50 (2): 613- 626
14 WANG T, GUO W, LI M, et al CPG control for biped hopping robot in unpredictable environment[J]. Journal of Bionic Engineering, 2012, 9 (1): 29- 38
doi: 10.1016/S1672-6529(11)60094-2
15 OWAKI D, GODA M, MIYAZAWA S, et al A minimal model describing hexapedal interlimb coordination: the tegotae-based approach[J]. Frontiers in Neurorobotics, 2017, 11: 29- 42
doi: 10.3389/fnbot.2017.00029
16 OWAKI D, ISHIGURO A A quadruped robot exhibiting spontaneous gait transitions from walking to trotting to galloping[J]. Scientific Reports, 2017, 7 (1): 277
doi: 10.1038/s41598-017-00348-9
17 SANTOS C P, ALVES N, MORENO J C Biped locomotion control through a biomimetic CPG-based controller[J]. Journal of Intelligent and Robotic Systems, 2017, 85 (1): 47- 70
doi: 10.1007/s10846-016-0407-3
18 SUZUKI S, KANO T, IJSPEERT A J, et al Sprawling quadruped robot driven by decentralized control with cross-coupled sensory feedback between legs and trunk[J]. Frontiers in Neurorobotics, 2021, 14: 116
19 ZHU Y G, ZHANG L, MANOONPONG P. Generic mechanism for waveform regulation and synchronization of oscillators: an application for robot behavior diversity generation [J/OL]. IEEE Transactions on Cybernetics, 2020:1–13. [2021-12-09]. https://ieeexplore.ieee.org/abstract/document/9254119.
20 ZHU Y G, ZHANG L, GUO W J, et al. A simple and flexible movement control method for a hexapod walking robot [C]// 22nd International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines. Kuala Lumpur: [s. n.], 2019: 79-86.
21 ZHU Y G, ZHANG L, MANOONPONG P. Virtual motoneuron activation for goal-directed locomotion of a hexapod robot [C]// 2020 5th International Conference on Advanced Robotics and Mechatronics. Shenzhen: IEEE, 2020: 380-386.
22 ZHU Y G, WU Y S, LIU Q, et al A backward control based on σ-Hopf oscillator with decoupled parameters for smooth locomotion of bio-inspired legged robot[J]. Robotics and Autonomous Systems, 2018, 106: 165- 178
doi: 10.1016/j.robot.2018.05.009
23 ZHU Y G, ZHOU S J, GAO X D, et al Synchronization of non-linear oscillators for neurobiologically inspired control on a bionic parallel waist of legged robot[J]. Frontiers in Neurorobotics, 2019, 13: 59
doi: 10.3389/fnbot.2019.00059
24 DONG H, SANGOK S, JONGWOO L, et al High speed trot-running: implementation of a hierarchical controller using proprioceptive impedance control on the mit cheetah[J]. International Journal of Robotics Research, 2014, 33 (11): 1417- 1445
doi: 10.1177/0278364914532150
[1] 陈宏鑫,张北,王春香,杨明. 基于自适应随动机构的机器人目标跟随[J]. 浙江大学学报(工学版), 2022, 56(6): 1071-1078.
[2] 徐小高,夏莹杰,朱思雨,邝砾. 基于强化学习的多路口可变车道协同控制方法[J]. 浙江大学学报(工学版), 2022, 56(5): 987-994, 1005.
[3] 吴兰,王涵,李斌全,李崇阳,孔凡士. 基于自监督任务的多源无监督域适应法[J]. 浙江大学学报(工学版), 2022, 56(4): 754-763.
[4] 张科文,潘柏松. 考虑非线性模型不确定性的航天器自主交会控制[J]. 浙江大学学报(工学版), 2022, 56(4): 833-842.
[5] 于瑞,徐雪峰,周华,杨华勇. 基于改进切换增益自适应率的欠驱动USV滑模轨迹跟踪控制[J]. 浙江大学学报(工学版), 2022, 56(3): 436-443.
[6] 宋家成,闫茂德,杨盼盼,巨永锋,岳靖斐. 基于数据驱动的鲁棒反步自适应巡航控制[J]. 浙江大学学报(工学版), 2022, 56(3): 485-493.
[7] 李博群,杨家强. 用于SPMSM的自适应增量式无差拍预测电流控制算法[J]. 浙江大学学报(工学版), 2022, 56(3): 607-612.
[8] 王鑫,陈巧红,孙麒,贾宇波. 基于关系推理与门控机制的视觉问答方法[J]. 浙江大学学报(工学版), 2022, 56(1): 36-46.
[9] 宋晓晨,姚骁帆,叶尚军. 基于伪谱法的小型超音速无人机轨迹优化[J]. 浙江大学学报(工学版), 2022, 56(1): 193-201.
[10] 李曦,胡健,姚建勇,魏科鹏,王鹏飞,邢浩晨. 基于观测器摩擦补偿的机电系统高精度控制[J]. 浙江大学学报(工学版), 2021, 55(6): 1150-1158.
[11] 赵福林,张通,马光,陈哲,郭创新,张金江. 考虑源-荷波动的电力系统灵活性运行域研究[J]. 浙江大学学报(工学版), 2021, 55(5): 935-947.
[12] 王虹力,郭斌,刘思聪,刘佳琪,仵允港,於志文. 边端融合的终端情境自适应深度感知模型[J]. 浙江大学学报(工学版), 2021, 55(4): 626-638.
[13] 陈嘉映,李仲博,林小杰,刘荣,钟崴,俞自涛. 基于映射模型的城市热网热能输运灵活性研究[J]. 浙江大学学报(工学版), 2021, 55(11): 2125-2133.
[14] 黄靖,钟书远,文元桥,罗坤. 用于交通流预测的自适应图生成跳跃网络[J]. 浙江大学学报(工学版), 2021, 55(10): 1825-1833.
[15] 柏昀旭,陆新江,骆锐. 自适应上下文感知的目标追踪方法[J]. 浙江大学学报(工学版), 2021, 55(10): 1834-1846.