Temporal Difference Learning Waveform Selection.

JCP 09/2010; 5:1394-1401. DOI: 10.1109/CCCM.2009.5267516
Source: DBLP

ABSTRACT The largest difference between cognitive radar and other adaptive radar is the adaptivity of transmitter in cognitive radar. How to optimally decide or select the radar waveform for next transmission based on the observation of past radar returns is one of the important issues. In this paper, with the stochastic dynamic programming model of waveform selection, we use the method of temporal difference learning to solve this problem and realize the adaptivity of waveform selection. The simulation results show that the uncertainty of state estimation using temporal difference learning is less than that using fixed waveform.

  • [Show abstract] [Hide abstract]
    ABSTRACT: This article discusses a new idea called cognitive radar. Three ingredients are basic to the constitution of cognitive radar: 1) intelligent signal processing, which builds on learning through interactions of the radar with the surrounding environment; 2) feedback from the receiver to the transmitter, which is a facilitator of intelligence; and 3) preservation of the information content of radar returns, which is realized by the Bayesian approach to target detection through tracking. All three of these ingredients feature in the echo-location system of a bat, which may be viewed as a physical realization (albeit in neurobiological terms) of cognitive radar. Radar is a remote-sensing system that is widely used for surveillance, tracking, and imaging applications, for both civilian and military needs. In this article, we focus on future possibilities of radar with particular emphasis on the issue of cognition. As an illustrative case study along the way, we consider the problem of radar surveillance applied to an ocean environment.
    IEEE Signal Processing Magazine 02/2006; · 3.37 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cognitive radar is a recently proposed approach in which a radar system may adaptively and intelligently interrogate a propagation channel using all available knowledge including previous measurements, task priorities, and external databases. A distinguishing characteristic of cognitive radar is that it operates in a closed loop, which enables constant optimization in response to its changing understanding of the channel. In this paper, we compare two different waveform design techniques for use with active sensors operating in a target recognition application. We also propose the integration of waveform design with a sequential-hypothesis-testing framework that controls when hard decisions may be made with adequate confidence. The result is a system that updates multiple target hypotheses/classes based on measured data, customizes waveforms as the class probabilities change, and draws conclusions when sufficient understanding of the propagation channel is achieved
    IEEE Journal of Selected Topics in Signal Processing 07/2007; · 3.30 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a new nonlinear filter for high-dimensional state estimation, which we have named the cubature Kalman filter (CKF). The heart of the CKF is a spherical-radial cubature rule, which makes it possible to numerically compute multivariate moment integrals encountered in the nonlinear Bayesian filter. Specifically, we derive a third-degree spherical-radial cubature rule that provides a set of cubature points scaling linearly with the state-vector dimension. The CKF may therefore provide a systematic solution for high-dimensional nonlinear filtering problems. The paper also includes the derivation of a square-root version of the CKF for improved numerical stability. The CKF is tested experimentally in two nonlinear state estimation problems. In the first problem, the proposed cubature rule is used to compute the second-order statistics of a nonlinearly transformed Gaussian random variable. The second problem addresses the use of the CKF for tracking a maneuvering aircraft. The results of both experiments demonstrate the improved performance of the CKF over conventional nonlinear filters.
    IEEE Transactions on Automatic Control 07/2009; · 2.72 Impact Factor


Available from