
This issue includes 121 articles, continuing the growing number of outstanding contributions to PACM IMWUT. As in previous issues, the published articles span several key areas of interest to the IMWUT community.
Device-free human tracking using commodity Wi-Fi has garnered significant interest due to its potential for ubiquitous indoor sensing without the need for user instrumentation. However, achieving precise tracking in non-line-of-sight (NLoS) scenarios, particularly in through-wall environments, remains a challenging issue. This is primarily due to the significant impact of wall refraction on Doppler Frequency Shift (DFS)-based tracking models, leading to accumulation of DFS offsets and subsequent trajectory drift. In this paper, we conduct a systematic theoretical analysis of the impact of wall refraction on tracking performance, aiming to uncover the quantitative relationships between DFS offsets and target motion parameters. To compensate the DFS offsets caused by walls, we propose a compensation mapping method (CompMap) that adaptively corrects DFS offsets based on system deployment and environmental parameters, eliminating the need for real-time wall refraction estimation. Furthermore, we develop WiTrack+, a robust Wi-Fi tracking system for through-wall scenarios. Extensive experiments with commodity hardware demonstrate that WiTrack+ substantially improves the tracking accuracy and stability, which validates the efficacy of the proposed compensation mechanism in suppressing the cumulative impact of DFS offset, thereby reducing path drifts and mitigating error propagation.
For Deaf and Hard-of-Hearing (DHH) users, effective sound awareness goes beyond detecting what sound occurs; it requires understanding what it means, how urgent it is , and what to do. However, existing mobile assistants largely reduce acoustic scenes to isolated labels or generic alerts, failing to provide contextual guidance when the same sound implies different risks across scenarios. We present UbiHearo, a mobile hearing assistant agent that closes the sensing-reasoning-action loop for scenario-aware and personalized DHH assistance. UbiHearo adopts a neuro-symbolic design that transforms continuous acoustic and physical context streams into structured intermediate representations (IRs) for controllable reasoning and guidance. It introduces three key mechanisms. First , a perception-thresholded sensing mechanism enables energy-efficient always-on awareness by activating processing only for perceptually meaningful events while preserving safety-critical cues through deterministic overrides. Second , a staged neuro-symbolic reasoning framework performs promptless scenario understanding by conditioning an on-device audio-language model on structured IRs instead of user-authored context descriptions. Third , a bounded human-in-the-loop personalization mechanism adapts user-specific guidance through lightweight on-device decision-boundary updates while preserving population-aligned reasoning. We evaluate UbiHearo on smartphones and in-vehicle systems across diverse scenarios. It achieves favorable accuracy-latency-energy tradeoffs and personalized guidance.
RFID has become an attractive platform for battery-free sensing and human-centered systems. However, its practical deployment is often constrained by limited communication range or orientation dependency in real-world conditions, due to weak, omnidirectional backscatter communication. In this paper, we present VanTag, a novel UHF RFID tag architecture that integrates a Van Atta-style retrodirective array with a commodity RFID chip to enhance backscatter communication and improve measurement robustness for sensing. VanTag develops a novel coupler-based differential feed network co-designed with a symmetry-preserving matching circuit to overcome key challenges, including differential-port compatibility, differential impedance matching, and physical size constraints. We prototype VanTag designs and evaluate them on a commercial UHF RFID platform. Measurements show a 4.2 dB increase in radar cross-section, a 40.9% extension in read range, and good robustness to angle and orientation variations, all while preserving full compatibility with commodity readers and standard RFID protocols. These results demonstrate that modulated retrodirective backscatter can provide both communication enhancement and more stable backscatter measurements, offering a practical building block for robust battery-free sensing and IoT systems.
Neural network-based device-free Wi-Fi tracking achieves superior accuracy over theory-driven approaches, yet its practical utility is severely limited by poor generalization across different device layouts. Existing models implicitly learn site-specific correlations, necessitating labor-intensive data recollection and retraining whenever the device configuration changes. To overcome this dependency, we propose UbiTrack , a generalized framework capable of robust tracking across diverse device layouts. Our core innovation lies in explicitly modeling the geometric constraints between device positions and signal propagation within the learning process. Instead of treating the layout as a black box, we formulate the tracking problem as a layout-aware mapping. We design a novel neural network architecture that incorporates geometric graph constraints into the analysis of temporal signal features, enabling the model to learn the intrinsic physical interactions between device topology and user trajectories. To facilitate the training of this data-hungry framework, we employ a progressive training strategy leveraging synthetic data derived from theory-driven principles. Extensive real-world experiments using commercial off-the-shelf (COTS) Wi-Fi devices validate that UbiTrack effectively decouples tracking performance from environmental setups. The system achieves median tracking errors of 0.56m in fixed layouts and 0.39m in variable layouts, paving the way for scalable and robust wireless sensing.