Title :
Vision-based fast and reactive Monte-Carlo localization
Author :
Rofer, Thomas ; Jungel, M.
Author_Institution :
Bremer Inst. fur Sichere Syst., Bremen Univ., Germany
Abstract :
This paper presents a fast approach for vision-based self-localization in RoboCup. The vision system extracts the features required for localization without processing the whole image and is a fist step towards independence of lighting conditions. In the field of self-localization, some new ideas are added to the well-known Monte Carlo localization approach that increase both stability and reactivity, while keeping the processing time low.
Keywords :
Monte Carlo methods; feature extraction; image processing; mobile robots; path planning; robot vision; Monte Carlo localization; RoboCup; feature extraction; lighting condition independence; vision system; vision-based self-localization; Cameras; Feature extraction; Head; Image resolution; Machine vision; Mobile robots; Orbital robotics; Robot sensing systems; Robot vision systems; Stability;
Conference_Titel :
Robotics and Automation, 2003. Proceedings. ICRA '03. IEEE International Conference on
Print_ISBN :
0-7803-7736-2
DOI :
10.1109/ROBOT.2003.1241700
