Channel Coding meets Sequence Design via Machine Learning for Integrated Sensing and Communications

2025-03-29

AI Summary

In integrated sensing and communication (ISAC), a core challenge lies in reusing channel coding waveforms for joint communication and ranging sensing—specifically, how to simultaneously preserve strong error-correction capability and achieve excellent autocorrelation properties (e.g., low sidelobes) in binary codewords. Method: We propose the first machine learning-driven, end-to-end framework for joint optimization of binary codewords, targeting both bit-error rate (BER) performance and autocorrelation sidelobe level under short blocklength (N = 32) and code rate 1/2 constraints. Contribution/Results: The optimized codewords match Polar-code-level BER performance while achieving an ultra-low autocorrelation peak sidelobe level of −24 dB—surpassing the fundamental limitations of Zadoff–Chu sequences, which cannot support rate-1/2 codes. Moreover, our framework enables scalable generation of high-rate, large-size codebooks, significantly expanding the design space for ISAC waveforms.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

For integrated sensing and communications, an intriguing question is whether information-bearing channel-coded signals can be reused for sensing - specifically ranging. This question forces the hitherto non-overlapping fields of channel coding (communications) and sequence design (sensing) to intersect by motivating the design of error-correcting codes that have good autocorrelation properties. In this letter, we demonstrate how machine learning (ML) is well-suited for designing such codes, especially for short block lengths. As an example, for rate 1/2 and block length 32, we show that even an unsophisticated ML code has a bit-error rate performance similar to a Polar code with the same parameters, but with autocorrelation sidelobes 24dB lower. While a length-32 Zadoff-Chu (ZC) sequence has zero autocorrelation sidelobes, there are only 16 such sequences and hence, a 1/2 code rate cannot be realized by using ZC sequences as codewords. Hence, ML bridges channel coding and sequence design by trading off an ideal autocorrelation function for a large (i.e., rate-dependent) codebook size.

Problem

• Design error-correcting codes with good autocorrelation for sensing
• Use machine learning to bridge channel coding and sequence design
• Achieve low autocorrelation sidelobes while maintaining code rate

Innovation

• Machine learning designs channel-coded sensing signals
• ML balances autocorrelation and codebook size
• Short block codes with low autocorrelation sidelobes