Towards Distributed and Intelligent Integrated Sensing and Communications for 6G Networks

TL;DR

DISAC addresses ISAC's limitations by enabling large‑scale distributed sensing, a semantic, goal‑oriented information framework, and high‑resolution multi‑sensor processing for 6G. It introduces a distributed DISAC architecture, a native semantic layer, optimized PHY design, intelligent resource allocation, and an evolved network architecture to support sensing and communications co‑design. The paper surveys use cases, standardization progress, and enabling technologies, including AI/ML considerations and multi‑modal sensor fusion, to chart a path toward semantic, data‑driven 6G networks. Collectively, these contributions provide a roadmap for energy‑efficient, semantically aware, and scalable wireless systems with new business models for operators and verticals.

Abstract

This paper introduces the distributed and intelligent integrated sensing and communications (DISAC) concept, a transformative approach for 6G wireless networks that extends the emerging concept of integrated sensing and communications (ISAC). DISAC addresses the limitations of the existing ISAC models and, to overcome them, it introduces two novel foundational functionalities for both sensing and communications: a distributed architecture (enabling large-scale and energy-efficient tracking of connected users and objects, leveraging the fusion of heterogeneous sensors) and a semantic and goal-oriented framework (enabling the transition from classical data fusion to the composition of semantically selected information).

Figures (5)

• Figure 1: The vision evolution from ISAC to DISAC, the latter being implemented by a new architecture that supports an AI-based semantic approach and super-resolution multi-sensor processing.
• Figure 2: The standardization roadmap covering different SDO.
• Figure 3: The radio domain (bottom) and the DISAC semantic domain (top), which provides improved robustness and resource allocation efficiency, for an example multi-static sensing scenario.
• Figure 4: Examples of quantifiable performance gains of DISAC. Left: Experimental evaluation of a time-coherent D-MIMO system at 2.35 GHz in terms of positioning and communication KPI Loc_DMIMO_2022. Right: The ambiguity function computed from the near-field steering vector of 4 and 20 phase-coherent receivers (randomly placed in a 1D environment $[-50~\text{m},+50~\text{m}]$) for a single-tone signal at 3 GHz. More receivers yield benefits in terms of inherent resolution and low sidelobes lehmann2006high.
• Figure 5: The core components of the DISAC network architecture.