Echo-Conditioned Denoising Diffusion Probabilistic Models for Multi-Target Tracking in RF Sensing

TL;DR

This paper introduces a novel echo-conditioned denoising diffusion probabilistic model framework for multi-target tracking in RF sensing, leveraging deep generative models to improve accuracy over traditional methods.

Contribution

It develops a conditional diffusion model with VAE-based echo compression and classifier-free guidance for enhanced multi-target tracking in RF systems.

Findings

Outperforms classical signal processing and deep learning benchmarks.

Achieves lower estimation errors in angle and distance tracking.

Demonstrates the effectiveness of generative models for integrated sensing and communications.

Abstract

In this paper, we consider a dynamic radio frequency sensing system aiming to spatially track multiple targets over time. We develop a conditional denoising diffusion probabilistic model (C-DDPM)-assisted framework that learns the temporal evolution of target parameters by leveraging the noisy echo observations as conditioning features. The proposed framework integrates a variational autoencoder (VAE) for echo compression and utilizes classifier-free guidance to enhance conditional denoising. In each transmission block, VAE encodes the received echo into a latent representation that conditions DDPM to predict future target states, which are then used for codebook beam selection. Simulation results show that the proposed approach outperforms classical signal processing, filtering, and deep learning benchmarks. The C-DDPM-assisted framework achieves significantly lower estimation errors in both angle and distance tracking, demonstrating the potential of generative models for integrated sensing and communications.