Learning Beamforming Codebooks for Active Sensing with Reconfigurable Intelligent Surface
Zhongze Zhang, Wei Yu
TL;DR
The paper tackles active sensing for uplink localization in RIS-aided networks by tackling the discrete, combinatorial problem of designing beamforming codebooks and a sequential codeword-selection policy. It introduces a data-driven architecture that fuses vector-quantized variational autoencoders (VQ-VAE) with long short-term memory (LSTM) networks to jointly learn robust BS and RIS codebooks and to map temporal measurements to discrete codeword indices, using gradient-approximation to enable training across the non-differentiable components. The proposed VQ-C framework demonstrates that learned codebooks can yield interpretable beampatterns and achieve localization performance close to codebook-free baselines while significantly reducing the control signaling overhead, across both single-RIS SISO and multi-RIS MISO scenarios. The results highlight the practicality of codebook-based active sensing with RIS, offering substantial reductions in pilot overhead and showing potential for extension to MIMO and multi-user localization. Overall, the work provides a scalable pathway to enable RIS-enabled active sensing in real-world localization tasks by learning the sensing codebooks and adaptive selection policies directly from data.
Abstract
This paper explores the design of beamforming codebooks for the base station (BS) and for the reconfigurable intelligent surfaces (RISs) in an active sensing scheme for uplink localization, in which the mobile user transmits a sequence of pilots to the BS through reflection at the RISs, and the BS and the RISs are adaptively configured by carefully choosing BS beamforming codeword and RIS codewords from their respective codebooks in a sequential manner to progressively focus onto the user. Most existing codebook designs for RIS are not tailored for active sensing, by which we mean the choice of the next codeword should depend on the measurements made so far, and the sequence of codewords should dynamically focus reflection toward the user. Moreover, most existing codeword selection methods rely on exhaustive search in beam training to identify the codeword with the highest signal-to-noise ratio (SNR), thus incurring substantial pilot overhead as the size of the codebook scales. This paper proposes a learning-based approach for codebook construction and for codeword selection for active sensing. The proposed learning approach aims to locate a target in the service area by recursively selecting a sequence of BS beamforming codewords and RIS codewords from the respective codebooks as more measurements become available without exhaustive beam training. The codebook design and the codeword selection fuse key ideas from the vector quantized variational autoencoder (VQ-VAE) and the long short-term memory (LSTM) network to learn respectively the discrete function space of the codebook and the temporal dependencies between measurements.