WaveMan: mmWave-Based Room-Scale Human Interaction Perception for Humanoid Robots

TL;DR

WaveMan is a novel mmWave-based perception system that enables reliable, privacy-preserving room-scale human interaction sensing for humanoid robots, effectively handling arbitrary user positions with high accuracy.

Contribution

WaveMan introduces a spatially adaptive perception system combining viewpoint alignment, spectrogram enhancement, and dual-channel attention to improve mmWave interaction sensing across unseen positions.

Findings

Achieves same accuracy as baseline with five times fewer training positions.

Increases free-position testing accuracy from 33% to 94.33%.

Demonstrates reliable, privacy-preserving HRI in household environments.

Abstract

Reliable humanoid-robot interaction (HRI) in household environments is constrained by two fundamental requirements, namely robustness to unconstrained user positions and preservation of user privacy. Millimeter-wave (mmWave) sensing inherently supports privacy-preserving interaction, making it a promising modality for room-scale HRI. However, existing mmWave-based interaction-sensing systems exhibit poor spatial generalization at unseen distances or viewpoints. To address this challenge, we introduce WaveMan, a spatially adaptive room-scale perception system that restores reliable human interaction sensing across arbitrary user positions. WaveMan integrates viewpoint alignment and spectrogram enhancement for spatial consistency, with dual-channel attention for robust feature extraction. Experiments across five participants show that, under fixed-position evaluation, WaveMan achieves the same cross-position accuracy as the baseline with five times fewer training positions. In random free-position testing, accuracy increases from 33.00% to 94.33%, enabled by the proposed method. These results demonstrate the feasibility of reliable, privacy-preserving interaction for household humanoid robots across unconstrained user positions.