Constant Modulus Waveform Design for Wideband Multicarrier Joint Communications and Sensing via Deep Unfolding

Joint communications and sensing (JCAS) have recently emerged as a promising technology to utilize the scarce spectrum in wireless networks and to reuse the same hardware to save infrastructure costs. In practical JCAS systems, dual functional constant-modulus waveforms can avoid signal distortion in nonlinear power amplifiers. However, the designs of such wave-forms are highly complex due to the nonconvex constant-modulus constraint and high-dimensional variables, especially in wideband multicarrier systems. In this paper, we propose an efficient deep unfolding-based waveform design in a wideband large multiple-input multiple-output (MIMO) JCAS system. The deep unfolding model has a sparsely-connected structure and is trained in an unsupervised fashion. Simulation results show that the proposed deep unfolding design achieves better communications-sensing performance tradeoff while performing 98.5% faster than the conventional branch-and-bound method.