arXiv 2604.154752026-04-16cs.ROcs.MA

NeuroMesh：一种用于去中心化多机器人协作的统一神经推理框架

NeuroMesh: A Unified Neural Inference Framework for Decentralized Multi-Robot Collaboration

New York University（纽约大学）；U.S. Army Combat Capabilities Development Command, Army Research Laboratory（美国陆军作战能力发展司令部，陆军研究实验室）；Vanderbilt University（范德比尔特大学）；University of California Berkeley, Department of Electrical Engineering and Computer Sciences（加州大学伯克利分校，电气工程与计算机科学系）

Yang Zhou, Yash Shetye, Long Quang, Devon Super, Jesse Milzman, Manohari Goarin, Aditya Azad, Devang Sunil Dhake, Jeffery Mao, Carlos Nieto-Granda, Giuseppe Loianno

备注：: 8 page, 8 figures, Accepted at the IEEE Robotics Automation Letter (RA-L)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出NeuroMesh框架，通过统一的管道标准化观察编码、消息传递、聚合和任务解码，解决异构机器人部署多机器人模型的挑战，支持混合GPU/CPU推理并在不同任务结构中展示鲁棒性。

摘要：

在异构机器人上部署学习的多机器人模型仍面临挑战，原因包括硬件异质性、通信限制以及缺乏统一的执行栈。本文提出了NeuroMesh，一种多领域、跨平台且模块化的去中心化神经推理框架，它在统一的管道中标准化了观察编码、消息传递、聚合和任务解码。NeuroMesh结合了双聚合范式用于减法和广播基于的信息融合，并采用并行架构，将周期时间与端到端延迟解耦。我们的高性能C++实现利用Zenoh进行机器人间通信，并支持混合GPU/CPU推理。我们验证了NeuroMesh在异构空中和地面机器人团队上，涵盖协同感知、去中心化控制和任务分配，展示了在不同任务结构和负载大小中稳健运行的能力。我们计划将NeuroMesh作为开源框架发布给社区。

英文摘要：

Deploying learned multi-robot models on heterogeneous robots remains challenging due to hardware heterogeneity, communication constraints, and the lack of a unified execution stack. This paper presents NeuroMesh, a multi-domain, cross-platform, and modular decentralized neural inference framework that standardizes observation encoding, message passing, aggregation, and task decoding in a unified pipeline. NeuroMesh combines a dual-aggregation paradigm for reduction- and broadcast-based information fusion with a parallelized architecture that decouples cycle time from end-to-end latency. Our high-performance C++ implementation leverages Zenoh for inter-robot communication and supports hybrid GPU/CPU inference. We validate NeuroMesh on a heterogeneous team of aerial and ground robots across collaborative perception, decentralized control, and task assignment, demonstrating robust operation across diverse task structures and payload sizes. We plan to release NeuroMesh as an open-source framework to the community.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。