Localisation, i.e., estimating a robot pose relative to a map of an environment, is one of the most important problems in mobile robotics. The literature offers several possible approaches to deal with such task, and optimal algorithms can be devised relying on particular constraints (linear state equations, Gaussian posterior density, etc.). Here, we propose a preliminary study for an algorithm able to approximate a large number of probability distributions when a map of the environment is available. This work improves the particle filters strategies presented in literature, reducing the number of particles needed to solve the localisation problem. The algorithm relies upon a suitable clustering of the particle set and a genetic approach for the resampling step
Gasparri, A., Panzieri, S., Pascucci, F., Ulivi, G. (2006). Genetic approach for a localisation problem based upon Particle Filters. In Proceedings of. 8th International IFAC Symposium on Robot Control, 2006. (pp.272-277) [10.3182/20060906-3-IT-2910.00047].
Genetic approach for a localisation problem based upon Particle Filters
GASPARRI, ANDREA;PANZIERI, Stefano;PASCUCCI, Federica;ULIVI, Giovanni
2006-01-01
Abstract
Localisation, i.e., estimating a robot pose relative to a map of an environment, is one of the most important problems in mobile robotics. The literature offers several possible approaches to deal with such task, and optimal algorithms can be devised relying on particular constraints (linear state equations, Gaussian posterior density, etc.). Here, we propose a preliminary study for an algorithm able to approximate a large number of probability distributions when a map of the environment is available. This work improves the particle filters strategies presented in literature, reducing the number of particles needed to solve the localisation problem. The algorithm relies upon a suitable clustering of the particle set and a genetic approach for the resampling stepI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.