Fast and Robust GPS Fix Using One Millisecond of Data

GPS is used for outdoor localization in a large variety of applications. Current receivers consume too much power for energy-constrained situations like continuous location tracking on small wearable devices. Mainly, this is due to the large amount of GPS signal that has to be decoded to compute the first position fix. While Coarse-Time Navigation (CTN) can reduce the necessary signal to a few milliseconds, it is not robust to noise. Collective Detection (CD) of satellites can mitigate noise to some degree, but the basic method is computationally expensive. We show how CD can be solved optimally and emciently. Furthermore, we improve the accuracy of CD by exploiting the shape of the likelihood function. All our results are based on real-world signal observations and we achieve localization accuracies of less than 25 meters using a single millisecond of signal. When using 10 consecutive millisecond samples the accuracy improves to less than 10 meters.