Generative Latent Alignment for Interpretable Radar Based Occupancy Detection in Ambient Assisted Living

TL;DR

This paper introduces a novel interpretable radar occupancy detection method using a generative latent alignment framework that combines autoencoders and CLIP to visualize spatial regions supporting presence decisions in privacy-sensitive ambient assisted living environments.

Contribution

The work presents a new GLA framework that aligns radar heatmap representations with semantic anchors for interpretability, integrating Grad-CAM for spatial visualization in radar-based occupancy detection.

Findings

Grad-CAM blobs align with strong radar returns for 'person present'

Semantic anchors improve interpretability of radar heatmaps

Ablation with unrelated prompts degrades explanation quality

Abstract

In this work, we study how to make mmWave radar presence detection more interpretable for Ambient Assisted Living (AAL) settings, where camera-based sensing raises privacy concerns. We propose a Generative Latent Alignment (GLA) framework that combines a lightweight convolutional variational autoencoder with a frozen CLIP text encoder to learn a low-dimensional latent representation of radar Range-Angle (RA) heatmaps. The latent space is softly aligned with two semantic anchors corresponding to "empty room" and "person present", and Grad-CAM is applied in this aligned latent space to visualize which spatial regions support each presence decision. On our mmWave radar dataset, we qualitatively observe that the "person present" class produces compact Grad-CAM blobs that coincide with strong RA returns, whereas "empty room" samples yield diffuse or no evidence. We also conduct an ablation study using unrelated text prompts, which degrades both reconstruction and localization, suggesting that radar-specific anchors are important for meaningful explanations in this setting.