The robot localization problem is a key problem in making truly autonomous robots. If a robot does not know where it is, it can be difficult to determine what to do next. Monte Carlo Localization as a well known localization algorithm represents a robot's belief by a set of weighted samples. This set of samples approximates the posterior probability of where the robot is located. Our method presents an extension to the MCL algorithm when localizing in highly symmetrical environments; a situation where MCL is often unable to correctly track equally probable poses for the robot. The sample sets in MCL often become impoverished when samples are generated in several locations. Our approach incorporates the idea of clustering the samples and organizes them considering to their orientation. Experimental results show our method is able to successfully determine the position of the robot in symmetric environment, while ordinary MCL often fails.
Robot localization in symmetric environment
2010-01-01
Electronic Theses and Dissertations
Theses
Electronic Resource
English
DDC: | 629 |
Efficient use of 3d environment models for mobile robot simulation and localization
BASE | 2010
|