← 研踪 PaperTrailarXiv:2512.06493 · v3
Programmable GPU-Accelerated dApps for Real-Time Edge Inference and ISAC on NVIDIA Aerial Testbed
首次提交 2025-12-07 00:46
版本更新 2026-11-10 15:27
雷达观测 2026-11-11 13:08
摘要
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 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 data to custom AI logic with about 84 s of framework latency per slot and control loops with inference in about 123 s for lightweight TensorRT models, multiple inference engines, and support for several AI backends. We evaluate the framework on two GPU platforms, with different GPU sharing modes and an increasing number of cells and dApps. 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 73 cm on runs unseen during training, with 79% of predictions falling within 1 meter, and runs live in 241 s, without dedicated sensing hardware or modifications to the 5G signals. The framework is released as open source, together with the cuSense dataset, providing a reference design for future AI-native RANs and ISAC applications.
作者备注：18 pages, 20 figures, 3 tables
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-10 15:27 · 最新观测版本
Programmable GPU-Accelerated dApps for Real-Time Edge Inference and ISAC on NVIDIA Aerial Testbed
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 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 data to custom AI logic with about 84 s of framework latency per slot and control loops with inference in about 123 s for lightweight TensorRT models, multiple inference engines, and support for several AI backends. We evaluate the framework on two GPU platforms, with different GPU sharing modes and an increasing number of cells and dApps. 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 73 cm on runs unseen during training, with 79% of predictions falling within 1 meter, and runs live in 241 s, without dedicated sensing hardware or modifications to the 5G signals. The framework is released as open source, together with the cuSense dataset, providing a reference design for future AI-native RANs and ISAC applications.
查看此版本解读 →查看此版本原文 ↗