Title :
NN-based environment recognition of pipeline robot
Author :
Zhou Xiao ; Tiansheng, Lu ; Zhijun, Li
Author_Institution :
Shanghai Jiaotong Univ., China
Abstract :
Aimed at the environment recognition problem of pipeline robot in bent pipes this paper constructs the characteristic rotating vector description of images and uses RBF neural network to recognize the direction of turn. Experiments prove that the speed and accuracy of the algorithms can meet the requirement of visual servo control in pipeline robot
Keywords :
computational complexity; image recognition; mobile robots; neurocontrollers; radial basis function networks; robot vision; servomechanisms; NN-based environment recognition; RBF neural network; bent pipes; pipeline robot; rotating vector image description; visual servo control; Image recognition; Neodymium; Neural networks; Pipelines; Robots; Servomechanisms;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location :
Hefei
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.863445
