Learning of scanning strategies for electronic support using predictive state representations

Abstract : In Electronic Support, a receiver must monitor a wide frequency spectrum in which threatening emitters operate. A common approach is to use sensors with high sensitivity but a narrow band-width. To maintain surveillance over the whole spectrum, the sensor has to sweep between frequency bands but requires a scanning strategy. Search strategies are usually designed prior to the mission using an approximate knowledge of illumination patterns. This often results in open-loop policies that cannot take advantage of previous observations. As pointed out in past researches, these strategies lack of robustness to the prior. We propose a new closed loop search strategy that learns a stochastic model of each radar using predic-tive state representations. The learning algorithm benefits from the recent advances in spectral learning and rank minimization using nuclear norm penalization.
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/hal-01225807
Contributor : Olivier Pietquin <>
Submitted on : Tuesday, November 10, 2015 - 10:40:24 PM
Last modification on : Thursday, April 4, 2019 - 10:18:05 AM
Long-term archiving on : Friday, February 12, 2016 - 5:08:54 PM

File

MLSP_2015_HGCEJFGOP.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01225807, version 1

Citation

Hadrien Glaude, Cyrille Enderli, Jean-François Grandin, Olivier Pietquin. Learning of scanning strategies for electronic support using predictive state representations. International Workshop on Machine Learning for Signal Processing (MLSP 2015), Sep 2015, Boston, United States. ⟨hal-01225807⟩

Share

Metrics

Record views

267

Files downloads

453