Title :
MARVEL: a system that recognizes world locations with stereo vision
Author :
Braunegg, David J.
Author_Institution :
Artificial Intelligence Lab., MIT, Cambridge, MA, USA
Abstract :
To use a world model, a mobile robot must be able to determine its own position in the world. MARVEL, a system that builds and maintains its own models of world locations and uses these models to recognize its world position from stereo vision input, supports truly autonomous navigation. MARVEL is designed to be robust with respect to input errors and to respond to a gradually changing world by updating its world location models. In over 1000 recognition tests using real-world data, MARVEL yielded a false negative rate under 10% with zero false positives
Keywords :
computer vision; computerised pattern recognition; mobile robots; MARVEL; autonomous navigation; mobile robot; real-world data; recognition tests; stereo vision; world locations; world model; Artificial intelligence; Contracts; Image recognition; Laboratories; Mobile robots; Navigation; Robot kinematics; Robustness; Stereo vision; System testing;
Conference_Titel :
Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on
Conference_Location :
Maui, HI
Print_ISBN :
0-8186-2148-6
DOI :
10.1109/CVPR.1991.139780