发表机构
North Carolina State University; The Ohio State University（北卡罗来纳州立大学; 俄亥俄州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大规模并行机器人学习，提出GPU批处理5G仿真模块Isaac-Net，实现网络在环训练，在单个GPU上支持约百万机器人，并准确复现延迟与信息年龄。
AI 中文摘要
大规模并行GPU仿真器在数千个环境中训练多机器人策略，许多机器人车队使用私有第五代（5G）网络，其中每个机器人的延迟取决于其队友的流量。网络在环训练将模拟的5G网络置于该循环中。然而，GPU机器人仿真器将网络简化为每条消息的独立延迟，而数据包级仿真器每个CPU进程运行一个场景，无法跟上数千个并行环境的步伐。为弥合这一差距，我们提出了Isaac-Net，一个GPU批处理的5G新无线电（NR）模块，它与Isaac Lab物理同步推进数千个环境的上行链路。Isaac-Net同时仿真所有环境的每个时隙（0.5毫秒间隔，在此期间基站决定哪些机器人传输）。大量实验证实，其NR引擎在各种负载下重现了ns-3 5G-LENA的中位延迟，在未见载波上中位延迟低5-10%，在闭环中每环境32个机器人时高9%。该引擎还重现了信息年龄（AoI），即每个机器人最新交付报告的年龄，而每条消息的独立延迟使AoI尾部约轻三倍。在针对5G-LENA验证的配置中，Isaac-Net在随机策略下测量，以83%的Isaac Lab速率（无网络）在单个GPU上保持约一百万个机器人的网络在环。Isaac-Net在此https URL开源。
英文摘要
Massively parallel GPU simulators train multi-robot policies in thousands of environments, and many fleets use private Fifth-Generation (5G) networks, where each robot's delay depends on its teammates' traffic. Network-in-the-loop training places a simulated 5G network inside this loop. However, GPU robot simulators reduce the network to an independent delay per message, while packet-level simulators run one scenario per CPU process and cannot keep pace with thousands of parallel environments. To bridge this gap, we present Isaac-Net, a GPU-batched 5G New Radio (NR) module that advances the uplink of thousands of environments in lockstep with Isaac Lab physics. Isaac-Net simulates every slot, the 0.5~ms interval in which the base station decides which robots transmit, for all environments at once. Extensive experiments confirm that its NR engine reproduces the median delay of ns-3 5G-LENA across loads, with a median delay 5--10\% low on an unseen carrier and 9\% high at 32 robots per environment in closed loop. The engine also reproduces the Age of Information (AoI), the age of each robot's newest delivered report, while an independent delay per message leaves the AoI tail about three times too light. In a configuration validated against 5G-LENA, Isaac-Net keeps the network in the loop for about one million robots on one GPU at 83\% of the Isaac Lab rate without the network, measured under a random policy. Isaac-Net is open source at https://github.com/ZzZTripleZzZ/isaac-net
CommentsIt is open source at https://github.com/ZzZTripleZzZ/isaac-net
