Task-Oriented Candidate-Latent Feedback for Coarse-to-Fine Sensing in Distributed OFDM-ISAC Networks

2026-08-04

AI Summary

This work addresses the challenge of excessive feedback overhead in distributed OFDM-ISAC networks, where full channel or DDAE tensor reporting incurs prohibitive data rates, while peak-only feedback discards discriminative target structure. To overcome this, the authors propose a task-oriented coarse-to-fine sensing mechanism that employs a lightweight convolutional scorer to generate delay–Doppler proposal maps and encodes elevation–azimuth blocks, normalized positions, and confidence scores into compact latent candidates for quantized feedback. This approach introduces, for the first time, task-aware latent-variable feedback, preserving discriminative information at extreme compression ratios (1.2–9.2×10⁴) and reducing the SE–SF interface rate from multi-Gbit/s to sub-Mbit/s without requiring retraining for cross-scenario generalization. Experiments demonstrate detection rates of 96.33–99.50% in urban and campus environments, with angular accuracy maintained or even improved.

Abstract

Future integrated sensing and communication (ISAC) architectures separate the sensing entity (SE) that acquires measurements from the sensing function (SF) that performs inference, creating a need for compact, task-oriented feedback on the SE-SF interface. Forwarding the raw channel frequency response or full per-link delay-Doppler-azimuth-elevation (DDAE) tensor is prohibitively expensive, while peak-only reporting discards target-discriminative structure under clutter. We propose a learning-based coarse-to-fine sensing pipeline with candidate-latent feedback for single-target estimation. At the SE, a lightweight convolutional scorer produces a dense delay-Doppler proposal map from pilot-based OFDM channel estimates, and a learned encoder constructs K compact C-dimensional candidate tokens by fusing per-candidate azimuth-elevation patches, normalized position, and confidence cues. The latents are uniformly quantized post-training to b bits and transmitted under a finite budget B_fb = bKC + 18K + 16 bits to the SF, which performs cross-candidate refinement, reranking, and joint four-parameter estimation. On a ray-traced urban scene with static and dynamic clutter, three operating points in the (K, C, b) design space achieve 96.33-98.88% detection at 107-806 bytes per coherent processing interval, compression ratios of 1.2-9.2 x 10^4 over the 8-bit DDAE magnitude tensor, reducing the SE-SF interface from multi-Gbit/s to sub-Mbit/s rates. Cross-scene evaluation on an independent campus-scale environment achieves 98.79-99.50% detection and at-or-better angular accuracy without retraining, indicating that the learned representation captures target-relevant structure that transports across scenes of comparable or lower clutter density.

Problem

• ISAC
• task-oriented feedback
• candidate-latent representation
• distributed sensing
• data compression

Innovation

• candidate-latent feedback
• coarse-to-fine sensing
• task-oriented compression
• OFDM-ISAC
• learned representation