## KLD-Sampling: Adaptive Particle Filters (2001)

Citations: | 62 - 8 self |

### BibTeX

@MISC{Fox01kld-sampling:adaptive,

author = {Dieter Fox},

title = {KLD-Sampling: Adaptive Particle Filters},

year = {2001}

}

### OpenURL

### Abstract

### Citations

657 | On sequential Monte Carlo sampling methods for Bayesian filtering
- Doucet, Godsill, et al.
- 2000
(Show Context)
Citation Context ...lied with great success to a variety of state estimation problems (see [3] for a recent overview). Particle filters estimate the posterior probability density over the state space of a dynamic system =-=[4, 11]-=-. The key idea of this technique is to represent probability densities by sets of samples. It is due to this representation, that particle filters combine efficiency with the ability to represent a wi... |

513 | Filtering via simulation: Auxiliary particle
- Pitt, Shephard
- 1999
(Show Context)
Citation Context ...lied with great success to a variety of state estimation problems (see [3] for a recent overview). Particle filters estimate the posterior probability density over the state space of a dynamic system =-=[4, 11]-=-. The key idea of this technique is to represent probability densities by sets of samples. It is due to this representation, that particle filters combine efficiency with the ability to represent a wi... |

277 | Monte Carlo Localization: Efficient position estimation for mobile robots
- Fox, Burgard, et al.
- 1999
(Show Context)
Citation Context ...mation process. This can be highly inefficient, since the complexity of the probability densities can vary drastically over time. An adaptive approach for particle filters has been applied by [8] and =-=[5]-=-. This approach adjusts the number of samples based on the likelihood of observations, which has some important shortcomings, as we will show. In this paper we introduce a novel approach to adapting t... |

261 |
Mathematical Statistics and Data Analysis
- Rice
- 1995
(Show Context)
Citation Context ...measured by the Kullback-Leibler distance. In what follows, we will first derive the equation for determining the number of samples needed to approximate a discrete probability distribution (see also =-=[12, 7]-=-). Then we will show how to modify the basic particle filter algorithm so that it realizes our adaptation approach. To see, suppose that n samples are drawn from a discrete distribution with k differe... |

94 |
L.: Branching and interacting particle systems approximations of Feynmanâ€“Kac formulae with applications to nonlinear filtering
- Moral, Miclo
(Show Context)
Citation Context ...ters has only rarely been studied: Adapting the number of samples over time. While variable sample sizes have been discussed in the context of genetic algorithms [10] and interacting particle filters =-=[2]-=-, most existing approaches to particle filters use a fixed number of samples during the whole state estimation process. This can be highly inefficient, since the complexity of the probability densitie... |

94 | Particle filters for mobile robot localization
- Fox, Thrun, et al.
- 2000
(Show Context)
Citation Context ...l p(y t j x t ) describes the likelihood of making the observation y t given that the robot is at location x t . In most applications, measurements consist of range measurements or camera images (see =-=[6]-=- for details). Figure 1 illustrates particle filters for mobile robot localization. Shown there is a map of a hallway environment along with a sequence of sample sets during global localization. In th... |

81 | Efficient locally weighted polynomial regression predictions
- Moore, Schneider, et al.
- 1997
(Show Context)
Citation Context ...ther parts a rather crude approximation is sufficient. This problem can be addressed by locally adapting the discretization to the desired approximation quality using multi-resolution tree structures =-=[8, 9] in combin-=-ation with stratified sampling. As a result, more samples are used in "important" parts of the state space, while less samples are used in other parts. Another area of future research is the... |

77 |
Autonomous Robot Vehicles
- Cox, Wilfong
- 1990
(Show Context)
Citation Context ...lters. Robot localization is the problem of estimating a robot's pose relative to a map of its environment. This problem has been recognized as one of the most fundamental problems in mobile robotics =-=[1]-=-. The mobile robot localization problem comes in different flavors. The simplest localization problem is position tracking. Here the initial robot pose is known, and localization seeks to correct smal... |

54 | Using learning for approximation in stochastic processes
- Koller, Fratkina
- 1998
(Show Context)
Citation Context ...ate estimation process. This can be highly inefficient, since the complexity of the probability densities can vary drastically over time. An adaptive approach for particle filters has been applied by =-=[8]-=- and [5]. This approach adjusts the number of samples based on the likelihood of observations, which has some important shortcomings, as we will show. In this paper we introduce a novel approach to ad... |

45 |
Continuous Univariate Distributions, Volume 1
- Johnson, Kotz
- 1970
(Show Context)
Citation Context ...measured by the Kullback-Leibler distance. In what follows, we will first derive the equation for determining the number of samples needed to approximate a discrete probability distribution (see also =-=[12, 7]-=-). Then we will show how to modify the basic particle filter algorithm so that it realizes our adaptation approach. To see, suppose that n samples are drawn from a discrete distribution with k differe... |

39 | E.: Bayesian Optimization Algorithm, Population Sizing, and Time to Convergence
- Pelikan, Goldberg, et al.
(Show Context)
Citation Context ...reasing the efficiency of particle filters has only rarely been studied: Adapting the number of samples over time. While variable sample sizes have been discussed in the context of genetic algorithms =-=[10]-=- and interacting particle filters [2], most existing approaches to particle filters use a fixed number of samples during the whole state estimation process. This can be highly inefficient, since the c... |

1 | On sequential monte carlo sampling methods forBayesian filtering - Doucet, Godsill, et al. - 1999 |

1 | Continuous univariate distributions, volume 1. JohnWiley - Johnson, Kotz, et al. - 1994 |