Auxiliary particle filter robot localization from high-dimensional sensor observations

By Nikos A. Vlassis, Bas Terwijn, Ben J. A. Kröse. 2002

109 citations recorded by the source corpus.

We apply the auxiliary particle filter algorithm of Pitt and Shephard (1999) to the problem of robot localization. To deal with the high-dimensional sensor observations (images) and an unknown observation model, we propose the use of an inverted nonparametric observation model computed by nearest neighbor conditional density estimation. We show that the proposed model can lead to a fully adapted optimal filter, and is able to successfully handle image occlusion and robot kidnap. The proposed algorithm is very simple to implement and exhibits a high degree of robustness in practice. We report experiments involving robot localization from omnidirectional vision in an indoor environment.

Subfields: Aerospace Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Filtering with State-Observation Examples via Kernel Monte Carlo Filter (2013, methodology): “kNN-PF (Vlassis et al., 2002): This method uses k-NN-based conditional density estimation (Stone, 1977) for learning the observation model.”
Point-Based Value Iteration for Continuous POMDPs (2006, methodology): “The training set can be obtained in a supervised way (Vlassis et al., 2002) or by autonomous interaction with the environment (Porta and Kröse, 2004).”
Sub-meter indoor localization in unmodified environments with inexpensive sensors (2010, methodology): “Several papers have utilized MCL with cameras including [10], [11], [12], [13], [14].”
Monte Carlo Filtering Using Kernel Embedding of Distributions (2014, methodology): “Computational time of the proposed method was competitive to that of KBRF, but slower than that of PF-NN due to the matrix inversion in the correction step.”
Adapting the Sample Size in Particle Filters Through KLD-Sampling (2003, methodology): “Auxiliary particle filters have been applied recently to robot localization [78].”
People Tracking with Mobile Robots Using Sample-Based Joint Probabilistic Data Association Filters (2003, background): “…al. 1999, 2001; Gross, Boehme, and König 2002; Lenser and Veloso 2000; Montemerlo et al. 2002; Montemerlo, Thun, and Whittaker 2002; Murphy and Russell 2001; Vlassis, Terwijn, and Kröse 2002; Wolf, Burgard, and Burkhardt 2002) and dynamic probabilistic networks (Kanazawa, Koller, and Russell 1995).”