Title :
An approach to appearance-based simultaneous localization and map building (SLAM)
Author :
Lee, Chun-Fan ; Sowmya, Arcot
Author_Institution :
Sch. of Comput Sci. & Eng., Univ. of New South Wales, Australia
Abstract :
Current robotic localization and SLAM algorithms are restricted to simple geometric features such as lines and corners as landmarks. The richness of the information provided by visual perception has not been fully explored. This paper presents a vision based SLAM algorithm which utilizes visual information with minimal prior assumptions.
Keywords :
Kalman filters; artificial intelligence; mobile robots; navigation; appearance based simultaneous localization and map building; autonomous mobile robot; extended Kalman filter; geometric features; robotic localization; vision based SLAM algorithms; Content addressable storage; Intelligent sensors; Mobile robots; Navigation; Predictive models; Robot kinematics; Robot sensing systems; Robustness; Simultaneous localization and mapping; Visual perception;
Conference_Titel :
Robotics, Automation and Mechatronics, 2004 IEEE Conference on
Print_ISBN :
0-7803-8645-0
DOI :
10.1109/RAMECH.2004.1438030
