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。
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 ARMLinux,including the sensor,the comparator,and the composition of the circuit. By using the reinforcement learning algorithm QLeaning 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.
作者
贾云辉
张志宏
何宏
Jia Yunhui Zhang Zhihong He Hong(School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin Key Laboratory of Complex System Control Theory and Application, Tianjin 300384, China Transmission and Launch Department, Tianjin Radio and TV Station, Tianjin 300072, China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2017年第9期1459-1466,共8页
Journal of Electronic Measurement and Instrumentation
基金
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
