A Maximum Likelihood Time Delay Estimator Using Importance Sampling

In this paper, we present a new time delay estimator for multipath environments using the importance sampling (IS) method. The new technique allows finding the maximum of the compressed likelihood function in an efficient manner. The main idea consists in generating realizations of a random variable distributed according to a function that approximates the actual compressed likelihood function and then computing the mean of the plausible realizations. We avoid eigen-decomposition operation that is widely used in the conventional high-resolution methods. We show through computer simulations that the new algorithm provides accurate estimates for closely spaced unknown time delays. Moreover, the method does not suffer from lack of convergence and initialization problems that arise with other iterative implementations of the maximum likelihood estimator.