首页 > 过刊浏览>2017年第31卷第9期 >1459-1466. DOI:10.13382/j.jemi.2017.09.017
PDF HTML阅读 XML下载 导出引用 引用提醒
基于ARM-Linux的爬壁机器人控制器研究
作者:
作者单位:

1． 天津理工大学电气电子工程学院 天津市复杂系统控制理论及应用重点实验室天津300384;2． 天津广播电视台传输发射部天津300072

中图分类号:

TP108.4

基金项目:

天津市科技支撑重大科技工程专项基金（14ZCDGSF00028）、天津市高等学校创新团队培养计划（TD125015）资助项目


Research on controller of wallclimbing robot based on ARMLinux
Author:
Affiliation:

1. School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin Key Laboratory of Complex System Control Theory and Application, Tianjin 300384, China; 2. Transmission and Launch Department, Tianjin Radio and TV Station, Tianjin 300072, China

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [15]
    • |
  • 相似文献 [20]
    • |
  • 引证文献
    • | |
  • 文章评论
    摘要:

    针对人工船舶除锈的效率低、危险性高、成本高等问题，研制出爬壁机器人进行船舶除锈。采用了上、下位机的分布式控制方案，对基于ARMLinux的爬壁机器人控制器进行研究，包括遥感器、比较器及其组成电路。通过引用强化学习算法QLeaning算法，实现了爬壁机器人的强化学习循迹，改进了传统PID等算法无法针对环境进行最优化动作策略选择的缺点，提高爬壁机器人在不同环境下循迹的准确性。实验结果表明，基于ARMLinux的爬壁机器人控制系统性能较好，可以满足控制器要求。

    Abstract:

    Aiming at the low efficiency, high risk and high cost in manual ship descaling, the wallclimbing robot is developed. This paper adopts the distributed control scheme of host and slave machine to research the controller of the wallclimbing robot based on ARMLinux, including the sensor, the comparator, and the composition of the circuit. By using the reinforcement learning algorithm QLeaning algorithm, the reinforcement learning tracking of wallclimbing robot is realized. The weakness that traditional PID and other algorithms that can't optimize the action strategy for environment are improved and the wallclimbing robot in different environments tracking accuracy is raised. The experiment results show that the control system of the wallclimbing robot based on ARMLinux can perform better and meet the requirements of the controller.

    参考文献
    [1]王兴如,弓永军,衣正尧,等. 超高压水射流船舶爬壁除锈机器人力学特性分析[J]. 机床与液压,2008, 36 (10):6770. WANG X R,GONG Y J,YI ZH Y, et al，Analysis of wall rust removal robot mechanical properties of ultra high pressure water jet ship climb[J].Machine and Hydraulic,2008,36(10):6770.
    [2]HUANG H C, LI D H, XUE Z,et al. Design and performance analysis of a tracked wallclimbing robot for ship inspection in shipbuilding[J]. Ocean Engineering,2017,131:5963.
    [3]丁问司,汪兴潮,唐昌滔. 永磁吸附履带式船舶爬壁机器人结构设计[J]. 机床与液压,2016, 44 (6):611. DING W S,WANG X CH,TANG CH T.The structure design of the permanent magnet adsorption tracked wall climbing robot[J]. Machine and Hydraulic，2016, 44(6):611.
    [4]孔庆,马凤伟,周文婷.手动机器人控制系统设计[J]. 中国科技信息， 2012(14) : 1520. KONG Q,MA F W,ZHOU W T.Design of manual robot control system [J].China Science and Technology Information, 2012(14) : 1520.
    [5]林文建,钟杭,黎福海,等. 两轮自平衡机器人控制系统设计与实现[J]. 电子测量与仪器学报,2013,27(8):750759. LIN W J,ZHONG H,LI F H, et al.Design and implementation of two wheeled self balancing robot control system[J].Journal of Electronic Measurement and Instrumentation,2013,27(8):750759.
    [6]李易难,牛燕雄,杨露. 基于DSP+FPGA视频图像采集处理系统的设计[J]. 电子测量技术,2014,37(1):5861. LI Y N,NIU Y X,YANG L.Design of video image acquisition and processing system based on DSP+FPGA[J]. Electronic Measurement Technology,2014,37(1):5861.
    [7]何宏,赵磊,张志宏. 基于ARMLinux的爬壁机器人远程自动控制系统[J]. 国外电子测量技术,2016,35(12):5660. HE H,ZHAO L,ZHANG ZH H.Remote automatic control system of wall climbing robot based on ARMLinux[J].Foreign Electronic Measurement Technology,2016,35(12):5660.
    [8]于乃功,默凡凡. 基于深度自动编码器与Q学习的移动机器人路径规划方法[J]. 北京工业大学学报,2016, 42 (5) :668673. YU N G,MO F F.Path planning method for mobile robot based on depth encoder and Qlearning.[J].Journal of Beijing University of Technology,2016, 42 (5) :668673.
    [9]POURPANAH F,TAN C J,LIM C P,et al.A Qlearningbased multiagent system for data classification[J]. Applied Soft Computing,2016(52):7779.
    [10]WEI Q L,LIU D R. A novel policy iteration based deterministic Qlearning for discretetime nonlinear systems[J]. Science China:Information Sciences,2015,58(12):147161.
    [11]杨旭东，刘全，李瑾. 一种基于资格迹的并行强化学习算法[J].苏州大学学报:自然科学版,2012，28 (1):2633. YANG X D,LIU Q,LI J.A parallel reinforcement learning algorithm based on trace [J].Journal of Soochow University: Natural Science Edition,2012，28 (1):2633.
    [12]朱洁瑛. 基于迭代学习控制算法的网络机器人控制系统[J]. 计算机安全, 2013(7) : 5862.ZHU J Y.Networked robot control system based on iterative learning control algorithm [J].Computer security, 2013(7) :5862
    [13]宋志章. 基于Linux移动机器人控制系统设计[J]. 微计算机信息, 2008, 24(29):240241. SONG ZH ZH. Linux based mobile robot control system design [J]. Microcomputer Information, 2008,24(29) : 240241
    [14]黄刚. 实时修正偏移量的循迹机器人控制系统研究与实现[J]. 仪器仪表学报,2015,36(11):25382547. HUANG G.Research and implementation of control system of robot tracking realtime offset correction[J]. Chinese Journal of Scientific Instrument, 2015,36(11):25382547.
    [15]谢其玲. 一款教育机器人控制系统设计[J]. 科技风, 2014(24):7474. XIE Q L.An educational robot control system design [J]. Science and Technology Wind， 2014(24):7474.
    引证文献
引用本文

贾云辉,张志宏,何宏.基于ARM-Linux的爬壁机器人控制器研究[J].电子测量与仪器学报,2017,31(9):1459-1466

复制
分享
文章指标
  • 点击次数:3507
  • 下载次数: 7794
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2017-11-06
文章二维码
您是第  5538030   位访问者
主管单位：中国科学技术协会
主办单位：中国电子学会
地址：北京市东城区北河沿大街79号
电话：010-53389339
电子测量与仪器学报 ® 2025 版权所有