PLAIN: Scalable Estimation Architecture for Integrated Sensing and Communication

TL;DR

The paper addresses high-dimensional ISAC parameter estimation under single-snapshot constraints by introducing $PLAIN$, a tensor-based architecture with three stages: compression, decoupled estimation, and input-based fusion. It leverages tensor structure to perform dimension-wise estimation in parallel and fuses the results to form a joint multidimensional estimate, enabling super-resolution with reduced complexity. Key contributions include flexible compression techniques (decimation, averaging, virtual snapshots, smoothing), per-dimension subspace or CS-based estimation, and fusion strategies (Tensor-LS and Tensor-OMP) with performance evaluated against sequential baselines and Tensor-ESPRIT, alongside CRB benchmarks. The approach demonstrates scalable, high-resolution sensing for 6G-like scenarios while maintaining practical processing times and adaptability to deployment constraints.

Abstract

Integrated sensing and communication (ISAC) is envisioned be to one of the paradigms upon which next-generation mobile networks will be built, extending localization and tracking capabilities, as well as giving birth to environment-aware wireless access. A key aspect of sensing integration is parameter estimation, which involves extracting information about the surrounding environment, such as the direction, distance, and velocity of various objects within. This is typically of a high-dimensional nature, which leads to significant computational complexity, if performed jointly across multiple sensing dimensions, such as space, frequency, and time. Additionally, due to the incorporation of sensing on top of the data transmission, the time window available for sensing is likely to be short, resulting in an estimation problem where only a single snapshot is accessible. In this work, we propose PLAIN, a tensor-based estimation architecture that flexibly scales with multiple sensing dimensions and can handle high dimensionality, limited measurement time, and super-resolution requirements. It consists of three stages: a compression stage, where the high dimensional input is converted into lower dimensionality, without sacrificing resolution; a decoupled estimation stage, where the parameters across the different dimensions are estimated in parallel with low complexity; an input-based fusion stage, where the decoupled parameters are fused together to form a paired multidimensional estimate. We investigate the performance of the architecture for different configurations and compare it against practical sequential and joint estimation baselines, as well as theoretical bounds. Our results show that PLAIN, using tools from tensor algebra, subspace-based processing, and compressed sensing, can scale flexibly with dimensionality, while operating with low complexity and maintaining super-resolution.

Figures (7)

• Figure 1: Illustration of the proposed PLAIN architecture with its main building blocks.
• Figure 2: Illustration of the different compression methods for a 1D tensor.
• Figure 3: RMSE results for different compression methods for $N_P = 6$. Root-MUSIC is used with tensor-OMP fusion. True $N_P$ is applied in the final selection.
• Figure 4: RMSE results for LS- and OMP-based fusion for $N_P = 6$. Averaging with root-MUSIC is used. True $N_P$ is applied in the final selection.
• Figure 5: RMSE results for different estimation schemes for $N_P = 6$. Averaging with root-MUSIC is used for PLAIN. True $N_P$ is applied in the final selection.