Tackling the premature convergence problem in Monte-Carlo localization |
| |
Authors: | Gert Bart |
| |
Affiliation: | aArtificial Intelligence, Univesity of Groningen, The Netherlands, Postbus 407, 9700 AK Groningen, The Netherlands;bUnivesity of Amsterdam, The Netherlands, Spuistraat 210, 1012 VT Amsterdam, The Netherlands |
| |
Abstract: | Monte-Carlo localization uses particle filtering to estimate the position of the robot. The method is known to suffer from the loss of potential positions when there is ambiguity present in the environment. Since many indoor environments are highly symmetric, this problem of premature convergence is problematic for indoor robot navigation. It is, however, rarely studied in particle filters. We introduce a number of so-called niching methods used in genetic algorithms, and implement them on a particle filter for Monte-Carlo localization. The experiments show a significant improvement in the diversity maintaining performance of the particle filter. |
| |
Keywords: | Monte-Carlo localization Particle filter Premature convergence Niching Genetic algorithms |
本文献已被 ScienceDirect 等数据库收录! |
|