Search papers, labs, and topics across Lattice.
This paper introduces GateFusion-Bidirectional Long Short-Term Memory network (GF-BiLSTM), a two-stream gated fusion network, to improve robotic activity recognition using WiFi Channel State Information (CSI). The network separately encodes and adaptively integrates CSI amplitude and phase information. Experiments under a Leave-One-Velocity-Out protocol demonstrate that incorporating phase information alongside amplitude consistently improves recognition accuracy and cross-speed robustness.
Ignoring CSI phase information in robotic activity recognition is a mistake: fusing it with amplitude data in a novel gated BiLSTM architecture significantly boosts accuracy and robustness.
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.
