Beyond Amplitude: Channel State Information Phase-Aware Deep Fusion for Robotic Activity Recognition
This work addresses the problem of enhancing robotic activity recognition accuracy and robustness for researchers and practitioners in Wi-Fi sensing, though it is incremental by building on existing CSI amplitude methods.
The paper tackled the underutilization of phase information in Wi-Fi Channel State Information for robotic activity recognition by proposing a two-stream gated fusion network (GF-BiLSTM) that encodes amplitude and phase separately, resulting in improved recognition accuracy and cross-speed robustness, with GF-BiLSTM achieving the best performance.
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.