Toward Native ISAC Support in O-RAN Architectures for 6G

2026-03-03

AI Summary

This work addresses the lack of native support for Integrated Sensing and Communication (ISAC) in current O-RAN architectures, which cannot expose physical-layer sensing data, execute sub-millisecond tasks, or associate transmitted waveforms with their echoes. To bridge this gap, the paper proposes three native extensions: deploying a sensing dApp at the O-DU to process IQ samples and extract features, defining an E2SM-SENS service model to enable xApps to subscribe to configurable sensing telemetry, and standardizing metadata in the fronthaul interface to correlate waveforms with echoes. This approach provides the first systematic ISAC architecture within O-RAN, supporting monostatic, bistatic, and cooperative sensing scenarios. Prototype validation demonstrates near-real-time end-to-end latency and closed-loop control, establishing a foundation for 6G ISAC deployment in O-RAN ecosystems.

Technology Category

• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Data transparency and provenance
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

ISAC is an emerging paradigm in 6G networks that enables environmental sensing using wireless communication infrastructure. Current O-RAN specifications lack the architectural primitives for sensing integration: no service models expose physical-layer observables, no execution frameworks support sub-millisecond sensing tasks, and fronthaul interfaces cannot correlate transmitted waveforms with their reflections. This article proposes three extensions to O-RAN for monostatic sensing, where transmission and reception are co-located at the base station. First, we specify sensing dApps at the O-DU that process IQ samples to extract delay, Doppler, and angular features. Second, we define E2SM-SENS, a service model enabling xApps to subscribe to sensing telemetry with configurable periodicity. Third, we identify required Open Fronthaul metadata for waveform-echo association. We validate the architecture through a prototype implementation using beamforming and Full-Duplex operation, demonstrating closed-loop control with median end-to-end latency suitable for near-real-time sensing applications. While focused on monostatic configurations, the proposed interfaces extend to bistatic and cooperative sensing scenarios.

Problem

• ISAC
• O-RAN
• 6G
• sensing integration
• fronthaul

Innovation

• ISAC
• O-RAN
• E2SM-SENS
• Open Fronthaul
• monostatic sensing