Beyond Amplitude: Channel State Information Phase-Aware Deep Fusion for Robotic Activity Recognition

2026-03-09

AI Summary

This work addresses the limitations of existing Wi-Fi channel state information (CSI)-based robotic activity recognition methods, which predominantly rely on amplitude while neglecting phase information, thereby constraining accuracy and cross-velocity robustness. For the first time, this study systematically investigates the role of CSI phase in this task and proposes GF-BiLSTM, a novel network featuring a dual-stream architecture that separately encodes amplitude and unwrapped/denoised phase information. A gating mechanism is introduced to adaptively fuse these features along the temporal dimension. Evaluated under the Leave-One-Velocity-Out protocol, the proposed method consistently achieves state-of-the-art performance across various input configurations, significantly improving both recognition accuracy and generalization across diverse motion speeds.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Intelligent Robots: State Estimation
• Computer Vision: Biometrics, Face, Gesture & Pose

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

Abstract

Wi-Fi Channel State Information (CSI) has emerged as a promising non-line-of-sight sensing modality for human and robotic activity recognition. However, prior work has predominantly relied on CSI amplitude while underutilizing phase information, particularly in robotic arm activity recognition. In this paper, we present GateFusion-Bidirectional Long Short-Term Memory network (GF-BiLSTM) for WiFi sensing in robotic activity recognition. GF-BiLSTM is a two-stream gated fusion network that encodes amplitude and phase separately and adaptively integrates per-time features through a learned gating mechanism. We systematically evaluate state-of-the-art deep learning models under a Leave-One-Velocity-Out (LOVO) protocol across four input configurations: amplitude only, phase only, amplitude + unwrapped phase, and amplitude + sanitized phase. Experimental results demonstrate that incorporating phase alongside amplitude consistently improves recognition accuracy and cross-speed robustness, with GF-BiLSTM achieving the best performance. To the best of our knowledge, this work provides the first systematic exploration of CSI phase for robotic activity recognition, establishing its critical role in Wi-Fi-based sensing.

Problem

• Channel State Information
• Phase Information
• Robotic Activity Recognition
• Wi-Fi Sensing
• Amplitude

Innovation

• Channel State Information
• Phase-aware Fusion
• Robotic Activity Recognition
• GateFusion-BiLSTM
• WiFi Sensing