Title :
Online learning and object recognition for AUV optical vision
Author :
Yuan, Xiaohai ; Hu, Zhen ; Chen, Jianping ; Chen, Rongsheng ; Liu, Peilin
Author_Institution :
China Ship Sci. Res. Center, Wuxi, China
Abstract :
Optical vision is very important for an AUV (autonomous underwater vehicle) to navigate, avoid obstacles and operate autonomously. A neural network for online learning and recognition is presented in the paper. The major attribute that distinguishes this ANN from others is its analysis speed. Another very important feature is the ability to dynamically change the “knowledge base”. Additionally, the ANN can cope with missing values in the data. The ANN is applied to AUV optical vision. An experiment shows that the ANN performs very well
Keywords :
feature extraction; learning (artificial intelligence); mobile robots; neural nets; object recognition; path planning; robot vision; underwater vehicles; analysis speed; autonomous underwater vehicle; knowledge base; navigation; obstacle avoidance; online learning; optical vision; Artificial neural networks; Biological neural networks; Feature extraction; Image processing; Navigation; Object recognition; Optical attenuators; Optical computing; Optical network units; Optical sensors;
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-5731-0
DOI :
10.1109/ICSMC.1999.816664