Maximum Likelihood Channel Path Detection and MMSE Channel Estimation in OTFS Systems

In orthogonal time frequency space (OTFS) systems, channel estimation (CE) is often performed using a pilot based approach. This is usually done in two steps: first, valid channel paths are detected by comparing the magnitude of received symbols against a threshold, and then the associated channel coefficient is estimated. In an attempt to avoid channel path misdetection, existing approaches often deploy large guard bands surrounding a relatively high-power pilot symbol. Furthermore, it is generally assumed that this guard region is sufficiently large to ensure that the time/frequency spreading of the channel does not result in any interference between the pilot and data symbols, thus facilitating simple channel estimation schemes. In this paper, we propose a channel estimation scheme which works even when this assumption is no longer true, i.e., when the channel results in pilot-data interference as may occur in scenarios involving high mobility and/or large delay-spread. The ability of a receiver to operate in such scenarios allows system designers the freedom to use smaller guard bands based on typical (not worst-case) channel spread parameters, thereby yielding higher spectral efficiency. In this work, we derive a maximum likelihood channel path detection scheme followed by a minimum mean-square error channel estimator. The performance advantage of the proposed receiver is verified using extensive bit error rate simulations.