期刊文献+

面向机器人教育的智能小车设计 被引量:1

Intelligent Car Design for Robot Education
下载PDF
导出
摘要 目前国内机器人教育多以理论为主,实践机会较少,需要提供经济、适用的实验装置来引导学生接触人工智能算法及机器人控制。该智能小车以AT-SAMD21G18A芯片作为核心,利用4个光敏电阻采集光线强度信息,选取人工神经网络作为控制算法,驱动两个直流减速步进电机执行运动指令,实现趋光和避光的功能。实验结果表明,该装置虽然结构简单但涵盖了人工神经网络和机器人应用的基础知识,为机器人实验教学提供了一种低成本、可扩展的硬件支撑。 At present,robot education is mostly based on theory and has fewer practical opportunities.It is necessary to provide cheap and applicable experimental devices to guide students to contact artificial intelligence algorithms and robot control applications.The intelligent car takes ATSAMD21G18A chip as the core,four photoresistors are used to collect light intensity information,and artificial neural network is selected as control algorithm to drive two DC deceleration stepping motors to execute motion commands,so as to realize the function of robot's phototaxis and antiphototaxis.The experimental results show that although the device is simple in structure,it can still penetrate the basic knowledge of artificial neural network and robot application,providing a low-cost and scalable hardware support for robot experimental teaching.
作者 张晓华 白娟 Zhang Xiaohua;Bai Juan(School of Physics and Electronics,North China University of Water Resources and Electric Power,Zhengzhou,450046,China;School of Information Engineering,North China University of Water Resources and Electric Power,Zhengzhou,450046,China)
出处 《中国现代教育装备》 2021年第17期8-11,共4页 China Modern Educational Equipment
基金 华北水利水电大学博士启动基金项目“基于半张量积的布尔网络机器人的控制研究”(编号:40722) 华北水利水电大学一流本科课程建设基金项目“线上线下混合式一流课程《嵌入式系统》”(编号:2020-90) 华北水利水电大学2017年度校级教育教学改革项目“‘互联网+虚拟化’的教学模式研究与实践--以《嵌入式系统》课程为例”。
关键词 人工智能 光线强度 神经网络 机器人教育 artificial intelligence light intensity neural network robot education
  • 相关文献

参考文献12

二级参考文献86

  • 1姚文山.光敏电阻器原理及检测方法[J].家电检修技术,2007(19):61-61. 被引量:3
  • 2殷蔚明,谢靖,许鸿文,任雁胜.普及机器人教育:工科高校创新教育的一剂良方[J].成功,2007(8):160-161. 被引量:6
  • 3李鸣华.机器人教育的教学设计[J].中国电化教育,2007(8):98-101. 被引量:24
  • 4胡寿松.自动控制原理[M].北京:科学出版社,2009.
  • 5常见生,石要武.检测与转换技术[M].北京:机械工业出版社,2008:187-188.
  • 6BENGIO Y, DELALLEAU O. On the expressive power of deep archi- tectures[ C ]//Proc of the 14th International Conference on Discovery Science. Berlin : Springer-Verlag, 2011 : 18 - 36.
  • 7BENGIO Y. Leaming deep architectures for AI[ J]. Foundations and Trends in Machine Learning ,2009,2 ( 1 ) : 1-127.
  • 8HINTON G,OSINDERO S,TEH Y. A fast learning algorithm for deep belief nets [ J ]. Neural Computation ,2006,18 (7) : 1527-1554.
  • 9BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks [ C ]//Proc of the 12th Annual Conference on Neural Information Processing System. 2006:153-160.
  • 10LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning ap- plied to document recognition[ J]. Proceedings of the iEEE, 1998, 86( 11 ) :2278-2324.

共引文献782

同被引文献3

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部