Learning to combine multi-sensor information for context dependent state estimation

Alexandre Ravet 1 Simon Lacroix 1 Gautier Hattenberger 2 Bertrand Vandeportaele 1
1 LAAS-RIS - Équipe Robotique et InteractionS
LAAS - Laboratoire d'analyse et d'architecture des systèmes
2 DRONES - ENAC - Programme transverse Drones
ENAC - Ecole Nationale de l'Aviation Civile
Abstract : The fusion of multi-sensor information for state estimation is a well studied problem in robotics. However, the classical methods may fail to take into account the measurements validity, therefore ruining the benefits of sensor redundancy. This work addresses this problem by learning context-dependent knowledge about sensor reliability. This knowledge is later used as a decision rule in the fusion task in order to dynamically select the most appropriate subset of sensors. For this purpose we use the Mixture of Experts framework. In our application, each expert is a Kalman filter fed by a subset of sensors, and a gating network serves as a mediator between individual filters, basing its decision on sensor inputs and contextual information to reason about the operation context. The performance of this model is evaluated for altitude estimation of a UAV.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00921516
Contributor : Bertrand Vandeportaele <>
Submitted on : Friday, December 20, 2013 - 3:58:21 PM
Last modification on : Friday, January 10, 2020 - 9:10:15 PM
Long-term archiving on: Friday, March 21, 2014 - 12:20:39 PM

File

iros2013.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00921516, version 1

Citation

Alexandre Ravet, Simon Lacroix, Gautier Hattenberger, Bertrand Vandeportaele. Learning to combine multi-sensor information for context dependent state estimation. IROS 2013, IEEE/RSJ International Conference on Intelligent Robots and Systems, Nov 2013, Tokyo, Japan. pp.WeCT2.6. ⟨hal-00921516⟩

Share

Metrics

Record views

553

Files downloads

284