COLoRIS: Localization-agnostic Smart Surfaces Enabling Opportunistic ISAC in 6G Networks

TL;DR

This work tackles user localization in 6G ISAC networks by exploiting the configuration of Reconfigurable Intelligent Surfaces (RIS) in a non-intrusive, localization-agnostic manner. The proposed COLoRIS framework employs learning-based models to map RIS configurations to user positions, supported by Fisher Information and CRB analyses to quantify feasibility and bound accuracy. It validates the concept through large-scale simulations and a low-power embedded prototype, achieving around 5% area-based localization error in simulations and about 11% in resource-constrained hardware, with energy usage suitable for long-term operation. The practical impact lies in enabling accurate, energy-efficient localization without GPS or extra infrastructure, leveraging existing communication configurations and an opportunistic ISAC workflow compatible with dynamic 6G deployments.

Abstract

The integration of Smart Surfaces in 6G communication networks, also dubbed as Reconfigurable Intelligent Surfaces (RISs), is a promising paradigm change gaining significant attention given its disruptive features. RISs are a key enabler in the realm of 6G Integrated Sensing and Communication (ISAC) systems where novel services can be offered together with the future mobile networks communication capabilities. This paper addresses the critical challenge of precisely localizing users within a communication network by leveraging the controlled-reflective properties of RIS elements without relying on more power-hungry traditional methods, e.g., GPS, adverting the need of deploying additional infrastructure and even avoiding interfering with communication efforts. Moreover, we go one step beyond: we build COLoRIS, an Opportunistic ISAC approach that leverages localization-agnostic RIS configurations to accurately position mobile users via trained learning models. Extensive experimental validation and simulations in large-scale synthetic scenarios show 5% positioning errors (with respect to field size) under different conditions. Further, we show that a low-complexity version running in a limited off-the-shelf (embedded, low-power) system achieves positioning errors in the 11% range at a negligible +2.7% energy expense with respect to the classical RIS.

Figures (15)

• Figure 1: Geometrical representation of the considered scenario, including the position $\mathbf{{b}}$, the position $\mathbf{{r}}$, and a position $\mathbf{{u}}$.
• Figure 2: configurations from coherent paths optimization Eq. \ref{['eq:coherent_solution']}, optimization method from bjornson2019intelligent and alternate optimization algorithm from mursia2020risma.
• Figure 3: Example of communication scenario with in the far-field and in near-field regimes of the , with a representation of the corresponding wavefront spatially sampled at elements, and resulting configuration.
• Figure 4: Schematic representation of COLoRIS: the configuration as input, the internal estimators, and the user position and accuracy as output.
• Figure 5: Cumulative Fisher information across all elements. Computed for a $21\times21$ with $\sigma_{\uptheta}=\frac{\pi}{6}$ rad, $\mathbf{{p}}_{\text{ref}}$ set in the geometric center of the .