Autoencoder-Based Enhanced Orthogonal Time Frequency Space Modulation

Orthogonal time frequency space (OTFS) is a novel waveform that provides a superior performance in doubly-dispersive channels. Since it spreads information symbols across the entire delay-Doppler plane, OTFS can achieve full diversity. However, reliability still needs to be improved in OTFS systems to meet the stringent demands of future communication systems. To address this issue, we propose an autoencoder (AE)-based enhanced OTFS (AEE-OTFS) modulation scheme. By training an AE under an additive white Gaussian noise (AWGN) channel, a feasible mapper and demapper are learned to improve the error performance and decrease the detection complexity of the OTFS system. The learned mapper is used to map incoming bits into high-dimensional symbols while the learned demapper recovers the information bits in the delay-Doppler domain. Additionally, we derive a theoretical upper bound for the frame error rate (FER). Simulation results confirm that AEE-OTFS outperforms conventional OTFS in terms of FER under perfect and imperfect channel conditions. AEE-OTFS also enjoys low decoding complexity in addition to its superior error performance.