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

2026-01-12

AI Summary

Existing millimeter-wave (mmWave)-based human-computer interaction systems struggle to simultaneously ensure robust sensing performance across arbitrary user positions and preserve user privacy in home environments, while also exhibiting limited spatial generalization. To address these challenges, this work proposes a spatially adaptive mmWave perception framework that achieves room-level spatial consistency through viewpoint alignment and spectrogram enhancement. A dual-channel attention mechanism is introduced to extract robust interaction features invariant to position and viewpoint variations. The proposed method significantly improves cross-position and cross-view recognition generalization, matching baseline accuracy with only one-fifth of the training locations. In tests conducted at random, unconstrained positions, the system boosts recognition accuracy from 33.00% to 94.33%, all while maintaining strong privacy guarantees.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Multi-modal Vision
• Humans and AI: Interaction Techniques and Devices

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• humanoid-robot interaction
• mmWave sensing
• spatial generalization
• privacy-preserving interaction
• room-scale perception

Innovation

• mmWave sensing
• spatial generalization
• viewpoint alignment
• dual-channel attention
• privacy-preserving interaction