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

• URL: http://arxiv.org/abs/2604.15475v1
• Date: Thu, 16 Apr 2026 18:54:34 GMT
• Title: NeuroMesh: A Unified Neural Inference Framework for Decentralized Multi-Robot Collaboration
• Abstract summary: NeuroMesh is a multi-domain, cross-platform, and modular decentralized neural inference framework.<n>It standardizes observation encoding, message passing, aggregation, and task decoding in a unified pipeline.<n>We validate NeuroMesh on a heterogeneous team of aerial and ground robots, demonstrating robust operation across diverse task structures and payload sizes.
• Score: 7.824386969078225
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion [20.46826223980239]
  Mind- Omni is a versatile framework that unifies seven distinct encoding and decoding tasks.<n>At its core is a novel Brain Tokenizer that transforms heterogeneous, continuous brain signals into standardized, discrete tokens.<n>Our work offers a powerful new paradigm for neural modeling and paves the way for foundation models of neural activity.
  arXiv  Detail & Related papers  (2026-05-28T08:33:43Z)
• NeuroClaw Technical Report [54.14941057366186]
  NeuroClaw is a domain-specialized multi-agent research assistant for neuroimaging research.<n>NeuroClaw operates directly on raw neuroimaging data across formats and modalities.<n>A three-tier skill/agent hierarchy separates user-facing interaction, high-level orchestration, and low-level tool skills.
  arXiv  Detail & Related papers  (2026-04-27T16:57:14Z)
• OmniClone: Engineering a Robust, All-Rounder Whole-Body Humanoid Teleoperation System [39.72804196709836]
  Whole-body humanoid teleoperation enables humans to remotely control humanoid robots, serving as both a real-time operational tool and a scalable engine for collecting demonstrations for autonomous learning.<n>Here we present OmniClone, a whole-body humanoid teleoperation system that achieves high-fidelity, multi-skill control on a single consumer with modest data requirements.
  arXiv  Detail & Related papers  (2026-03-15T11:13:04Z)
• The More the Merrier: Running Multiple Neuromorphic Components On-Chip for Robotic Control [0.9503420085198421]
  We show a first example of a pipeline for vision-based robot control in which numerous networks can be run entirely on hardware.<n>We show that all components can run concurrently on-chip in the milli Watt regime at latencies competitive with the state-of-the-art.<n>An equivalent network on simulated hardware is shown to accomplish robotic arm plug insertion in simulation, and the core elements of the pipeline are additionally tested on a real robotic arm.
  arXiv  Detail & Related papers  (2026-02-14T12:39:15Z)
• Multi Part Deployment of Neural Network [0.17205106391379024]
  This paper proposes a distributed system architecture that partitions a neural network across multiple servers.<n>A Multi-Part Neural Network Execution Engine facilitates seamless execution and training across distributed partitions.<n>A Neuron Distributor module enables flexible partitioning strategies based on neuron count, percentage, identifiers, or network layers.
  arXiv  Detail & Related papers  (2025-06-02T07:24:29Z)
• NNTile: a machine learning framework capable of training extremely large GPT language models on a single node [83.9328245724548]
  NNTile is based on a StarPU library, which implements task-based parallelism and schedules all provided tasks onto all available processing units.<n>It means that a particular operation, necessary to train a large neural network, can be performed on any of the CPU cores or GPU devices.
  arXiv  Detail & Related papers  (2025-04-17T16:22:32Z)
• Neuromorphic Wireless Split Computing with Multi-Level Spikes [69.73249913506042]
  Neuromorphic computing uses spiking neural networks (SNNs) to perform inference tasks.<n> embedding a small payload within each spike exchanged between spiking neurons can enhance inference accuracy without increasing energy consumption.<n> split computing - where an SNN is partitioned across two devices - is a promising solution.<n>This paper presents the first comprehensive study of a neuromorphic wireless split computing architecture that employs multi-level SNNs.
  arXiv  Detail & Related papers  (2024-11-07T14:08:35Z)
• LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control [72.81786007015471]
  We propose a learnable Perception-Action-Communication (LPAC) architecture for the problem.<n>CNN processes localized perception; a graph neural network (GNN) facilitates robot communications.<n> Evaluations show that the LPAC models outperform standard decentralized and centralized coverage control algorithms.
  arXiv  Detail & Related papers  (2024-01-10T00:08:00Z)
• Neuromorphic Intermediate Representation: A Unified Instruction Set for Interoperable Brain-Inspired Computing [4.066607775161713]
  Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention. Here, we establish a common reference frame for computations in digital neuromorphic systems. We demonstrate by reproducing three spiking neural network models of different complexity across 7 neuromorphic simulators and 4 digital hardware platforms.
  arXiv  Detail & Related papers  (2023-11-24T18:15:59Z)
• Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection [101.38634057635373]
  We focus on applications where robots are required to jointly select actions to maximize team submodular objectives. We propose a general-purpose learning architecture towards submodular at scale, with decentralized communications. We demonstrate the performance of our GNN-based learning approach in a scenario of active target coverage with large networks of robots.
  arXiv  Detail & Related papers  (2021-05-18T15:32:07Z)
• VGAI: End-to-End Learning of Vision-Based Decentralized Controllers for Robot Swarms [237.25930757584047]
  We propose to learn decentralized controllers based on solely raw visual inputs. For the first time, that integrates the learning of two key components: communication and visual perception. Our proposed learning framework combines a convolutional neural network (CNN) for each robot to extract messages from the visual inputs, and a graph neural network (GNN) over the entire swarm to transmit, receive and process these messages.
  arXiv  Detail & Related papers  (2020-02-06T15:25:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.