Cognitive Learning Methods for Mass Eccentricity Identification of Unmanned Bicycles

doi:10.3901/JME.2024.23.140

Abstract

Abstract: Body mass eccentricity plays an important role in course tracking performance of unmanned bicycle. In order to realize online recognition of body mass eccentricity, a cognitive learning method for mass eccentricity recognition of unmanned bicycle is proposed. In this method, the influence of vehicle mass eccentricity on the linear trajectory is considered, and the inverse mapping relationship between the vehicle body yaw trajectory and mass eccentricity is used to construct the state evaluation function based on the vehicle body heading angle and heading angle integral. A reactive cognitive learning algorithm is introduced to construct a normal distribution learning mechanism, and the expected value and standard deviation of the learning automaton are iteratively updated. The results of iterative learning are compensated into the balance controller to realize the online identification of mass eccentricity of the unmanned bicycle. The results of numerical simulation and prototype experiment show that after 2 to 3 rounds of iterative learning (each round learning time is 20 s) under different load conditions, the absolute error of body mass eccentricity identification is maintained within 0.01 rad, the relative error is less than 10%, and the method has certain anti-interference ability. The research results can provide some theoretical support and technical reference for the follow-up research on course and trajectory tracking of unmanned bicycles.

Key words: unmanned bicycle, mass eccentricity, online recognition, cognitive learning, heading trajectory

CLC Number:

TP242

HUANG Yonghua, LIANG Ziyan, ZHUANG Wei, YANG Haiyang. Cognitive Learning Methods for Mass Eccentricity Identification of Unmanned Bicycles[J]. Journal of Mechanical Engineering, 2024, 60(23): 140-151.

References

[1] JONES D E H. The stability of the bicycle[J]. Physics Today，1970，23(4)：34-40.
[2] KOOIJMAN J，MEIJAARD J P，PAPADOPOULOS J M，et al. A bicycle can be self-stable without gyroscopic or caster effects[J]. Science，2011，332(6027)：339-342.
[3] 艾红，童璐，李成荣. 无机械辅助结构自行车机器人控制仿真及实现[J]. 信息与控制，2019(2)：187-193. AI Hong，TONG Lu，LI Chengrong. Control simulation and implementation of a bicycle robot without a mechanically assisted structure[J]. Information and Control，2019(2)：187-193.
[4] HUANG Y H，LIAO Q Z，GUO L，et al. Simple realization of balanced motions under different speeds for a mechanical regulator-free bicycle robot[J]. Robotica，2014，72(9)：1-15.
[5] HUANG Y H，LIAO Q Z，GUO L，et al. Balanced motions realization for a mechanical regulators free and front-wheel drive bicycle robot under zero forward speed[J]. International Journal of Advanced Robotic Systems，2013，10(317)：1-9.
[6] YONGLI Z，LIU Y，YI G. Model analysis of unmanned bicycle and variable gain lqr control[C]// 2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). IEEE，2020，9：1196-1200.
[7] BAQUERO M，CORTES J，ARCOS J，et al. A robust two-stage active disturbance rejection control for the stabilization of a riderless bicycle[J]. Multibody System Dynamics，2019，45(1)：7-35.
[8] ZHANG K，YIN D. A control approach adaptive to load and road slope for electric power assisted bicycle[C]// Chinese Control Conference (CCC)，Dalian，China，2017：3414-3418.
[9] 庄未，杨继伟，黄用华，等. 考虑车轮纵向滑动的无人自行车平衡控制实现[J]. 信息与控制，2022，51(5)：587-595. ZHUANG Wei，YANG Jiwei，HUANG Yonghua，et al. The realization of balance control of an unmanned bicycle by considering wheels’ longitudinal sliding[J]. Information and Control，2022，51(5)：587-595.
[10] HASHEMNIA S，SHARIAT P M，MAHJOOB M J. Unmanned bicycle balancing via Lyapunov rule-based fuzzy control[J]. Multibody System Dynamics，2014，31：147-168.
[11] 李艳，王涵. 基于复合控制的自行车机器人平衡控制[J]. 现代电子技术，2019，42(2)：177-182. LI Yan，WANG Han. Balance control of bicycle robot based on compound control[J]. Modern Electronics Technique，2019，42(2)：177-182.
[12] 李凯，周璟成. 基于图像分析的质心和转动惯量测量方法[J]. 力学与实践，2021，43(5)：771-775. LI Kai，ZHOU Jingcheng. Center of mass and moment of inertia measurement method based on image analysis[J]. Mechanics in Engineering，2021，43(5)：771-775.
[13] 王若琳，胡翔，余烨，等. 基于扭摆的落体质心与光心距离的高精度测量[J]. 仪器仪表学报，2022，43(8)：85-92. WANG Ruolin，HU Xiang，YU Ye，et al. High-precision measurement of the distance between the mass center and the optical center of falling body based on the pendulum system[J]. Chinese Journal of Scientific Instrument，2022，43(8)：85-92.
[14] 倪庆乐，王雨时，闻泉，等. 基于三维造型的复杂形状零部件质心位置测量[J]. 兵器装备工程学报，2016，37(4)：66-68. NI Qingle，WANG Yushi，WEN Quan，et al. Measurement of centroid position for parts with complex shape based on three-dimensional modeling techniques[J]. Journal of Ordnance Equipment Engineering，2016，37(4)：66-68.
[15] 郭亚内. 多轴车辆质心测量方法分析[J]. 黑龙江科学，2019，10(14)：70-71. GUO Yanei. Analysis of centroid measurement method for multi-axle vehicles[J]. Heilongjiang Science，2019，10(14)：70-71.
[16] 赵传松，任红格，史涛，等. 内在动机轮式倒立摆反应式认知系统[J]. 浙江大学学报，2018，52(6)：1073-1080. ZHAO Chuansong，REN Hongge，SHI Tao，et al. Wheeled inverted pendulum reactive cognitive system with internal motivation[J]. Journal of Zhejiang University，2018，52(6)：1073-1080.
[17] QURESHI A H，NAKAMURA Y，YOSHIKAWA Y，et al. Intrinsically motivated reinforcement learning for human–robot interaction in the real-world[J]. Neural Networks，2018(107)：170-186.
[18] 阮晓钢，张家辉，黄静，等. 一种结合内在动机理论的移动机器人环境认知模型[J]. 控制与决策，2021， 36(9)：2211-2217. RUAN Xiaogang，ZHANG Jiahui，HUANG Jing，et al. An environment cognition model combined with intrinsic motivation for mobile robots[J]. Control and Decision，2021，36(9)：2211-2217.
[19] KOOIJMAN J，SCHWAD A L，MEIJAARD J P. Experimental validation of a model of an uncontrolled bicycle[J]. Multibody System Dynamics，2008，19(1/2)：115-132.