Title :
Accurate local positioning using visual landmarks from a panoramic sensor
Author :
Thompson, Simon ; Zelinsky, Alexander
Author_Institution :
Res. Sch. of Inf. Sci. & Eng., Australian Nat. Univ., Canberra, ACT, Australia
Abstract :
Presents a method for representing places using a set of visual landmarks from a panoramic sensor that allows for accurate local positioning while still providing efficient global localisation. For each place landmarks are selected for their local uniqueness in the panoramic visual field and their dynamic reliability over a turn back and look movement. During this movement, the depth of landmarks is also estimated using a bearing only SLAM approach. Accurate local position tracking within places equal to that of laser range finder systems is obtained by the application of the condensation algorithm over individual places. A topological map of such places is built and both global localisation and position tracking experiments are carried out
Keywords :
mobile robots; path planning; position control; probability; robot vision; topology; accurate local positioning; bearing only SLAM approach; condensation algorithm; dynamic reliability; global localisation; local uniqueness; panoramic sensor; position tracking; topological map; turn back and look movement; visual landmarks; Data mining; Image sensors; Insects; Machine vision; Navigation; Robot sensing systems; Robot vision systems; Sensor phenomena and characterization; Sensor systems; Simultaneous localization and mapping;
Conference_Titel :
Robotics and Automation, 2002. Proceedings. ICRA '02. IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7272-7
DOI :
10.1109/ROBOT.2002.1013632