🤖 AI Summary
This work addresses the challenge of persistent signal dead zones in wireless networks, which remain difficult to cover using conventional approaches. Existing reconfigurable intelligent surface (RIS) deployment methods relying on channel state information (CSI) incur high overhead and limited practicality. To overcome these limitations, the authors propose RFZero—a plug-and-play RIS deployment scheme that operates without CSI or base station coordination. RFZero first leverages visual imagery to extract macroscopic environmental features for initial surface placement and then dynamically optimizes the RIS phase shifts using terminal-reported reference signal received power (RSRP) measurements. This approach achieves, for the first time, complete elimination of dead zones: merely a pair of 1.5 m × 0.9 m RIS panels fully covers all blind spots in a 100 m² indoor environment, substantially reducing deployment complexity while enhancing real-world applicability.
📝 Abstract
Deploying metasurfaces (MTSs) to eliminate wireless blind spots requires jointly determining the physical placement of MTSs and the meta-atom phase shifts. Existing methods typically rely on explicit channel estimation, which incurs prohibitive overhead and is often intractable in real-world networks. To sidestep this bottleneck, we propose RFZero, a channel-state-information (CSI)-free deployment paradigm. Instead of estimating channels, RFZero extracts macro-environmental features from visual photos to guide MTS placement, and leverages reference signal received power (RSRP) feedback for dynamic phase-shift optimization. Most importantly, RFZero operates independently of base stations, thereby enabling seamless plug-and-play implementation. Real-world field tests confirm that RFZero completely eliminates all blind spots in a $100\text{ m}^2$ indoor area using just a pair of $1.5\text{ m}\times 0.9\text{ m}$ MTSs.