PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Biologically inspired path execution using SURF flow in robot navigation
Xavier Perez-Sala, Cecilio Angulo and Sergio Escalera
Lecture Notes in Computer Science Volume 6692, pp. 581-588, 2011. ISSN 0302-9743

Abstract

An exportable and robust system using only camera images is proposed for path execution in robot navigation. Motion information is extracted in the form of optical flow from SURF robust descriptors of consecutive frames, so the method is called SURF flow. This information is used to correct robot displacement when a straight forward path command is sent to the robot, but it is not really executed due to several robot and environmental concerns. The proposed system has been successfully tested on the legged robot Aibo.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:8608
Deposited By:Cecilio Angulo
Deposited On:13 February 2012