Title
Vision-based 3-D trajectory tracking for unknown environments
Abstract
This paper describes a vision-based system for 3-D localization of a mobile robot in a natural environment. The system includes a mountable head with three on-board charge-coupled device cameras that can be installed on the robot. The main emphasis of this paper is on the ability to estimate the motion of the robot independently from any prior scene knowledge, landmark, or extra sensory devices. Distinctive scene features are identified using a novel algorithm, and their 3-D locations are estimated with high accuracy by a stereo algorithm. Using new two-stage feature tracking and iterative motion estimation in a symbiotic manner, precise motion vectors are obtained. The 3-D positions of scene features and the robot are refined by a Kalman filtering approach with a complete error-propagation modeling scheme. Experimental results show that good tracking and localization can be achieved using the proposed vision system.
Year
DOI
Venue
2006
10.1109/TRO.2005.858856
IEEE Transactions on Robotics
Keywords
Field
DocType
Kalman filters,covariance matrices,iterative methods,mobile robots,motion estimation,path planning,robot vision,3D localization,Kalman filtering,complete error-propagation modeling scheme,covariance matrix,extra sensory devices,iterative motion estimation,mobile robot,mountable head,onboard charge-coupled device cameras,prior scene knowledge,stereo algorithm,two-stage feature tracking,unknown environments,vision-based 3D trajectory tracking,Feature-based tracking,robot vision,three-dimensional (3-D) localization,three-dimensional (3-D) trajectory tracking,vision-based tracking,visual motion tracking,visual trajectory tracking
Motion planning,Computer vision,Motion control,Machine vision,Control theory,Kalman filter,Artificial intelligence,Motion estimation,Robot,Mathematics,Robotics,Mobile robot
Journal
Volume
Issue
ISSN
22
1
1552-3098
Citations 
PageRank 
References 
26
1.18
31
Authors
3
Name
Order
Citations
PageRank
Parvaneh Saeedi118320.02
Peter D. Lawrence211140.88
D. G. Lowe3157181413.60