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 backward dynamic programming, temporal difference learning and Q-learning are used to solve this problem. Optimal waveform selection algorithm and approximate solutions are proposed respectively. The simulation results demonstrate that the two approximate methods approach the optimal waveform selection scheme and have lower uncertainty of state estimation compared to fixed waveform. The performance of temporal difference learning is better than Q-learning, but Q-learning is more suitable to use in radar scene. Finally, the whole paper is summarized.

Index Terms—waveform selection, backward dynamic programming, temporal difference learning, Q-learning

Cite: Bin Wang, Jinkuan Wang, Xin Song and Yinghua Han, "Research on Adaptive Waveform Selection Algorithm in Cognitive Radar," Journal of Communications, vol. 5, no.6, pp.467-474 , 2010. Doi: 10.4304/jcm.5.6.467-474