Short-Length Code Designs for Integrated Sensing and Communications: A Deep Learning Approach
Authors: Muah Kim, Shuangyang Li, Tayyebeh Jahani-Nezhad, Rafael F. Schaefer, Giuseppe Caire
Organizations: Faculty of Electrical and Computer Engineering, Dresden University of Technology, Dresden 01069, Germany · Faculty of Electrical Engineering and Computer Science, Technical University of Berlin, Berlin 10587, Germany
Integrated sensing and communication (ISAC) enables joint communication and sensing using a shared waveform, but its signal design is challenging due to the inherent trade-off between the two objectives, particularly in the short blocklength regime. This paper proposes an autoencoder (AE)-based framework for ISAC waveform design in noncoherent settings. We derive a modified Cramér-Rao bound for multi-target delay estimation and analyze the maximum-likelihood decoding rule for noncoherent communication under correlated fading. These results reveal structural connections and trade-offs between communication and sensing objectives in waveform design. Based on this analysis, the AE learns waveform representations that jointly optimize both functionalities, with a tunable parameter controlling the trade-off. Simulation results show that the proposed design outperforms conventional schemes in both communication reliability and sensing accuracy, especially under short blocklength and fading conditions.
Figures & tables
Fig. 1: A diagram for the considered ISAC system based on the NN encoder.
Fig. 2: Communication- and sensing-optimal designs are analyzed through BER, MCRB, and constellation visualizations for K=6 , N=9 . The MSE result is additionally reported under a simplified single-target scenario ( P=1 ) to provide empirical validation.
Fig. 3: BER and MCRB of the CNN for N=9 are measured with varying γ .
Fig. 4: BERs and MCRBs of the CNN model for N=90 , measured for varying γ values for joint design.
Fig. 5: Pareto trade-off between BER and MCRB for different values of the joint loss parameter γ , evaluated with the CNN model for K=60,N=90 under a partially correlated channel with fD=0.1 . Each circular marker on the curve corresponds to a specific γ value, whereas a cross and a triangle marker show DBPSK and ZC, respectively.