Deep learning improves short code design for joint sensing and communication
Short-Length Code Designs for Integrated Sensing and Communications: A Deep Learning Approach
Machine LearningInformation Theory
Summary
Communications and sensing often share the same signal, which can cause conflicts in design especially when using short signals. The paper’s authors use deep learning to create code waveforms that work well for both sending messages and sensing multiple targets. They also develop mathematical tools to better understand the limits and trade-offs in this joint design. Their method tunes how much emphasis is put on communication versus sensing to get the best overall performance. Tests show their approach beats traditional methods, especially when signals are short and the wireless channel is unreliable.
What this means in practice
- •For wireless communication engineers: Design short signal codes that reliably combine device communication with sensing functions under challenging fading conditions.
- •For autonomous vehicle developers: Improve joint sensing and communication modules in self-driving cars to better detect multiple targets while maintaining data transmission quality.
Authors
Muah Kim, Shuangyang Li, Tayyebeh Jahani-Nezhad, Rafael F. Schaefer, Giuseppe Caire
Abstract
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.