WiFi-SLAM Using Gaussian Process Latent Variable Models

[edit]

Brian D. Ferris
Dieter Fox
Neil D. Lawrence, University of Sheffield

in Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007), pp 2480-2485

Related Material

Abstract

WiFi localization, the task of determining the physical location of a mobile device from wireless signal strengths, has been shown to be an accurate method of indoor and outdoor localization and a powerful building block for location-aware applications. However, most localization techniques require a training set of signal strength readings labeled against a ground truth location map, which is prohibitive to collect and maintain as maps grow large. In this paper we propose a novel technique for solving the WiFi SLAM problem using the Gaussian Process Latent Variable Model (GP-LVM) to determine the latent-space locations of unlabeled signal strength data. We show how GP-LVM, in combination with an appropriate motion dynamics model, can be used to reconstruct a topological connectivity graph from a signal strength sequence which, in combination with the learned Gaussian Process signal strength model, can be used to perform efficient localization.


@InProceedings{ferris-wifi07,
  title = 	 {WiFi-SLAM Using Gaussian Process Latent Variable Models},
  author = 	 {Brian D. Ferris and Dieter Fox and Neil D. Lawrence},
  booktitle = 	 {Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007)},
  pages = 	 {2480},
  year = 	 {2007},
  editor = 	 {Manuela M. Veloso},
  month = 	 {00},
  edit = 	 {https://github.com/lawrennd//publications/edit/gh-pages/_posts/2007-01-01-ferris-wifi07.md},
  url =  	 {http://inverseprobability.com/publications/ferris-wifi07.html},
  abstract = 	 {WiFi localization, the task of determining the physical location of a mobile device from wireless signal strengths, has been shown to be an accurate method of indoor and outdoor localization and a powerful building block for location-aware applications. However, most localization techniques require a training set of signal strength readings labeled against a ground truth location map, which is prohibitive to collect and maintain as maps grow large. In this paper we propose a novel technique for solving the WiFi SLAM problem using the Gaussian Process Latent Variable Model (GP-LVM) to determine the latent-space locations of unlabeled signal strength data. We show how GP-LVM, in combination with an appropriate motion dynamics model, can be used to reconstruct a topological connectivity graph from a signal strength sequence which, in combination with the learned Gaussian Process signal strength model, can be used to perform efficient localization.},
  key = 	 {Ferris:wifi07},
  linkpdf = 	 {http://www.ijcai.org/papers07/Papers/IJCAI07-399.pdf},
  group = 	 {gplvm,dimensional reduction}
 

}
%T WiFi-SLAM Using Gaussian Process Latent Variable Models
%A Brian D. Ferris and Dieter Fox and Neil D. Lawrence
%B 
%C Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007)
%D 
%E Manuela M. Veloso
%F ferris-wifi07	
%P 2480--2485
%R 
%U http://inverseprobability.com/publications/ferris-wifi07.html
%X WiFi localization, the task of determining the physical location of a mobile device from wireless signal strengths, has been shown to be an accurate method of indoor and outdoor localization and a powerful building block for location-aware applications. However, most localization techniques require a training set of signal strength readings labeled against a ground truth location map, which is prohibitive to collect and maintain as maps grow large. In this paper we propose a novel technique for solving the WiFi SLAM problem using the Gaussian Process Latent Variable Model (GP-LVM) to determine the latent-space locations of unlabeled signal strength data. We show how GP-LVM, in combination with an appropriate motion dynamics model, can be used to reconstruct a topological connectivity graph from a signal strength sequence which, in combination with the learned Gaussian Process signal strength model, can be used to perform efficient localization.
TY  - CPAPER
TI  - WiFi-SLAM Using Gaussian Process Latent Variable Models
AU  - Brian D. Ferris
AU  - Dieter Fox
AU  - Neil D. Lawrence
BT  - Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007)
PY  - 2007/01/01
DA  - 2007/01/01
ED  - Manuela M. Veloso	
ID  - ferris-wifi07	
SP  - 2480
EP  - 2485
L1  - http://www.ijcai.org/papers07/Papers/IJCAI07-399.pdf
UR  - http://inverseprobability.com/publications/ferris-wifi07.html
AB  - WiFi localization, the task of determining the physical location of a mobile device from wireless signal strengths, has been shown to be an accurate method of indoor and outdoor localization and a powerful building block for location-aware applications. However, most localization techniques require a training set of signal strength readings labeled against a ground truth location map, which is prohibitive to collect and maintain as maps grow large. In this paper we propose a novel technique for solving the WiFi SLAM problem using the Gaussian Process Latent Variable Model (GP-LVM) to determine the latent-space locations of unlabeled signal strength data. We show how GP-LVM, in combination with an appropriate motion dynamics model, can be used to reconstruct a topological connectivity graph from a signal strength sequence which, in combination with the learned Gaussian Process signal strength model, can be used to perform efficient localization.
ER  -

Ferris, B.D., Fox, D. & Lawrence, N.D.. (2007). WiFi-SLAM Using Gaussian Process Latent Variable Models. Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007) :2480-2485