期刊文献+

一种带有实时视觉特征学习的自主发育机器人探索 被引量:6

An Exploration of Autonomous Developing Robot with Real Time Vision Learning
在线阅读 下载PDF
导出
摘要 能根据实时的环境如人一样进行自主发育学习是近年刚刚提出的、根据生物和认知的原理的一个新思想,因提出的方法复杂度高,所需的机器人平台的要求也比较高,在研究了增量获取特征和自主发育算法的基础上,把视觉特征抽取和自主发育结合在一起,通过一定的简化,形成能在简单的平台上实现的简化系统.经实验模拟证实该系统能够实时抽取视频图像的特征并实现移动机器人对环境的主动辨别和认知. Autonomous Mental Development proposed in recent years is a new idea based on biokgy and cognition principles, which can automatically follow the real environment. Because this method is more complicated, it needs a robot plant with high computation ability and large storage capacity. Based on incremental learning and Autonomous Mental Development theory, it combines the vision learning with autonomous development algorithm to establish a simpler system. Simulation results show that the system can extract vision features in real-time and make a mobile robot recognize the environment automatically.
出处 《复旦学报(自然科学版)》 CAS CSCD 北大核心 2005年第6期964-970,共7页 Journal of Fudan University:Natural Science
基金 国家自然科学基金资助项目(60171036)
关键词 机器人视觉 直观无协方差增量主元分析 分级判别回归 自主心智发育 machine vision candid covariance-free incremental principal component analysis (CCIPCA) hierarchical diseriminant regression (HDR) autonomous mental development (AMD)
  • 相关文献

参考文献9

  • 1Brooks R A.A robust layered control system for a mobile robot [J].IEEE Journal of Robotics and Automation,1986,2(1):14-23.
  • 2Gomi T.Evolutionary Robotics:From Intelligent Robotis to Artificial Life(ER'98) [M].Canada:AAI Books,1998.
  • 3Weng J.Learning in image analysis and beyond:Development[A].Visual Communication and Image Processing[C].New York:Marcel Dekker,1998.
  • 4Weng J,McClelland J,Pentland A.Autonomous mental development by robots and animals [J].Science,2001,291:599-600.
  • 5Hwang W S,Weng J.Hierarchical discriminant regression [J].IEEE Trans on Pattern Analysis and Machine Intelligence,2000,22:1277-1293.
  • 6Weng J,Zhang Y,Hwang W S.Candid covariance-free incremental principal component analysis [J].IEEE Trans Pattern Analysis and Machine Intelligence,2003,25(8):1034-1040.
  • 7Oja E,Karhunen J.On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix [J].J Math Analysis and Application,1985,106:69-84.
  • 8Sanger T D.Optimal unsupervised learning in a single-layer linear feedforward neural network [J].IEEE Trans Neural Networks,1989,2:459-473.
  • 9Zhang N,Weng J,Zhang Z.A developing sensory mapping for robots [EB/OL].http://ieeexplore.ieee.org/ iel5/7906/21803/01011723.pdf,2002-06-15/2005-03-01.

同被引文献91

引证文献6

二级引证文献26

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