Programmable and GPU-Accelerated Edge Inference for Real-Time ISAC on NVIDIA Aerial Testbed

TL;DR

This paper introduces an open-source, GPU-accelerated framework for real-time AI processing at the edge of 5G networks, enabling integrated sensing and communication without hardware modifications.

Contribution

It presents a programmable, open-source framework for GPU-accelerated AI at the edge RAN, supporting real-time ISAC applications on NVIDIA Aerial Testbed.

Findings

The framework achieves 150 microseconds overhead for AI inference.

cuSense localizes indoor targets with 77 cm mean error.

The framework supports multiple GPU platforms with and without hardware isolation.

Abstract

The transition of cellular networks to (i) software-based systems on commodity hardware and (ii) platforms for services beyond connectivity introduces critical system-level challenges. As sensing emerges as a key feature toward 6G standardization, supporting Integrated Sensing and Communication (ISAC) with limited bandwidth and piggybacking on communication signals, while maintaining high reliability and performance, remains a fundamental challenge. In this paper, we provide two key contributions. First, we present a programmable, open-source framework for processing PHY/MAC signals through real-time, GPU-accelerated Artificial Intelligence (AI) applications on the edge Radio Access Network (RAN) infrastructure. Building on the Open RAN dApp architecture, the framework interfaces with a GPU-accelerated gNB based on NVIDIA Aerial Testbed (ATB), feeding PHY/MAC data to custom AI logic with a framework overhead of 150 us, multiple inference engines, and support for several AI backends. We evaluate the framework on multiple GPU platforms with and without hardware-level GPU isolation. Second, we demonstrate the framework capabilities through cuSense, an indoor localization dApp that consumes uplink DMRS channel estimates, removes static multipath components, and runs a neural network to infer the position of a moving person. Evaluated on a 3GPP-compliant 5G NR deployment, cuSense achieves a mean localization error of 77 cm, with 75% of predictions falling within 1 meter, without dedicated sensing hardware or modifications to the RAN stack or signals. The framework is released as open source, providing a reference design for future AI-native RANs and ISAC applications.