dorsal/arxiv
View SchemaWaveMan: mmWave-Based Room-Scale Human Interaction Perception for Humanoid Robots
| Authors | Yuxuan Hu, Kuangji Zuo, Boyu Ma, Shihao Li, Zhaoyang Xia, Feng Xu, Jianfei Yang |
|---|---|
| Categories | |
| ArXiv ID | 2601.07454vv1 |
| URL | https://arxiv.org/abs/2601.07454 |
| License | http://creativecommons.org/licenses/by/4.0/ |
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.
{
"annotation_id": "d1d6334d-5f25-421a-a18d-8a2a18b65c1c",
"date_created": "2026-02-17T05:53:11.826000Z",
"date_modified": "2026-02-17T05:53:11.826000Z",
"file_hash": "f972c553746a971311c33c653b9f2be22b1aa3f08c903aac527be5afe860e38f",
"private": false,
"record": {
"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.",
"arxiv_id": "2601.07454",
"authors": [
"Yuxuan Hu",
"Kuangji Zuo",
"Boyu Ma",
"Shihao Li",
"Zhaoyang Xia",
"Feng Xu",
"Jianfei Yang"
],
"categories": [
"cs.RO"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "WaveMan: mmWave-Based Room-Scale Human Interaction Perception for Humanoid Robots",
"url": "https://arxiv.org/abs/2601.07454",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "f1483d22-7a30-4db5-975f-fa1a52e1e1bb",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}