HeteroHub: An Applicable Data Management Framework for Heterogeneous Multi-Embodied Agent System

TL;DR

HeteroHub is a comprehensive data management framework designed to coordinate heterogeneous multi-embodied AI agents by integrating static, training, and real-time data for scalable system deployment.

Contribution

The paper introduces HeteroHub, a unified data-centric framework that supports real-world deployment of multi-agent systems with diverse data types and dynamic task coordination.

Findings

HeteroHub enables coordination of multiple embodied agents in complex tasks.

The framework supports task-aware training and real-time control.

Demonstration shows effective multi-agent task execution.

Abstract

Heterogeneous Multi-Embodied Agent Systems involve coordinating multiple embodied agents with diverse capabilities to accomplish tasks in dynamic environments. This process requires the collection, generation, and consumption of massive, heterogeneous data, which primarily falls into three categories: static knowledge regarding the agents, tasks, and environments; multimodal training datasets tailored for various AI models; and high-frequency sensor streams. However, existing frameworks lack a unified data management infrastructure to support the real-world deployment of such systems. To address this gap, we present \textbf{HeteroHub}, a data-centric framework that integrates static metadata, task-aligned training corpora, and real-time data streams. The framework supports task-aware model training, context-sensitive execution, and closed-loop control driven by real-world feedback. In our demonstration, HeteroHub successfully coordinates multiple embodied AI agents to execute complex tasks, illustrating how a robust data management framework can enable scalable, maintainable, and evolvable embodied AI systems.