Q-Learning-Based Adaptive Waveform Selection in Cognitive Radar

HTML  Download Download as PDF (Size: 224KB)  PP. 669-674  
DOI: 10.4236/ijcns.2009.27077    5,345 Downloads   9,575 Views  Citations

Affiliation(s)

.

ABSTRACT

Cognitive radar is a new framework of radar system proposed by Simon Haykin recently. Adaptive waveform selection is an important problem of intelligent transmitter in cognitive radar. In this paper, the problem of adaptive waveform selection is modeled as stochastic dynamic programming model. Then Q-learning is used to solve it. Q-learning can solve the problems that we do not know the explicit knowledge of state-transition probabilities. The simulation results demonstrate that this method approaches the optimal wave-form selection scheme and has lower uncertainty of state estimation compared to fixed waveform. Finally, the whole paper is summarized.

Share and Cite:

B. WANG, J. WANG, X. SONG and F. LIU, "Q-Learning-Based Adaptive Waveform Selection in Cognitive Radar," International Journal of Communications, Network and System Sciences, Vol. 2 No. 7, 2009, pp. 669-674. doi: 10.4236/ijcns.2009.27077.

Copyright © 2024 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.