Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration

Huajie Tan, Cheng Chi, Xiansheng Chen, Yuheng Ji, Zhongxia Zhao, Xiaoshuai Hao, Yaoxu Lyu, Mingyu Cao, Junkai Zhao, Huaihai Lyu, Enshen Zhou, Ning Chen, Yankai Fu, Cheng Peng, Wei Guo, Dong Liang, Zhuo Chen, Mengsi Lyu, Chenrui He, Yulong Ao, Yonghua Lin, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang

TL;DR

RoboOS-NeXT tackles lifelong adaptability, scalable collaboration, and robust scheduling in open-world multi-robot systems by introducing STEM, a unified memory that fuses spatial geometry, temporal history, and embodiment profiles. The framework couples STEM with a Brain–Cerebellum–Memory loop, enabling global planning to retrieve and update memory while local controllers execute actions with low latency and corrections. Empirical results across restaurants, supermarkets, and households show that memory-guided planning delivers stronger lifelong performance, improved scalability with larger heterogeneous teams, and greater fault tolerance, with real-world demonstrations validating the approach. This work offers a principled mechanism for memory-centric coordination in open-world multi-robot systems and points to avenues for more general embodied intelligence.

Abstract

The proliferation of collaborative robots across diverse tasks and embodiments presents a central challenge: achieving lifelong adaptability, scalable coordination, and robust scheduling in multi-agent systems. Existing approaches, from vision-language-action (VLA) models to hierarchical frameworks, fall short due to their reliance on limited or dividual-agent memory. This fundamentally constrains their ability to learn over long horizons, scale to heterogeneous teams, or recover from failures, highlighting the need for a unified memory representation. To address these limitations, we introduce RoboOS-NeXT, a unified memory-based framework for lifelong, scalable, and robust multi-robot collaboration. At the core of RoboOS-NeXT is the novel Spatio-Temporal-Embodiment Memory (STEM), which integrates spatial scene geometry, temporal event history, and embodiment profiles into a shared representation. This memory-centric design is integrated into a brain-cerebellum framework, where a high-level brain model performs global planning by retrieving and updating STEM, while low-level controllers execute actions locally. This closed loop between cognition, memory, and execution enables dynamic task allocation, fault-tolerant collaboration, and consistent state synchronization. We conduct extensive experiments spanning complex coordination tasks in restaurants, supermarkets, and households. Our results demonstrate that RoboOS-NeXT achieves superior performance across heterogeneous embodiments, validating its effectiveness in enabling lifelong, scalable, and robust multi-robot collaboration. Project website: https://flagopen.github.io/RoboOS/

RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration

TL;DR

RoboOS-NeXT tackles lifelong adaptability, scalable collaboration, and robust scheduling in open-world multi-robot systems by introducing STEM, a unified memory that fuses spatial geometry, temporal history, and embodiment profiles. The framework couples STEM with a Brain–Cerebellum–Memory loop, enabling global planning to retrieve and update memory while local controllers execute actions with low latency and corrections. Empirical results across restaurants, supermarkets, and households show that memory-guided planning delivers stronger lifelong performance, improved scalability with larger heterogeneous teams, and greater fault tolerance, with real-world demonstrations validating the approach. This work offers a principled mechanism for memory-centric coordination in open-world multi-robot systems and points to avenues for more general embodied intelligence.

Abstract

The proliferation of collaborative robots across diverse tasks and embodiments presents a central challenge: achieving lifelong adaptability, scalable coordination, and robust scheduling in multi-agent systems. Existing approaches, from vision-language-action (VLA) models to hierarchical frameworks, fall short due to their reliance on limited or dividual-agent memory. This fundamentally constrains their ability to learn over long horizons, scale to heterogeneous teams, or recover from failures, highlighting the need for a unified memory representation. To address these limitations, we introduce RoboOS-NeXT, a unified memory-based framework for lifelong, scalable, and robust multi-robot collaboration. At the core of RoboOS-NeXT is the novel Spatio-Temporal-Embodiment Memory (STEM), which integrates spatial scene geometry, temporal event history, and embodiment profiles into a shared representation. This memory-centric design is integrated into a brain-cerebellum framework, where a high-level brain model performs global planning by retrieving and updating STEM, while low-level controllers execute actions locally. This closed loop between cognition, memory, and execution enables dynamic task allocation, fault-tolerant collaboration, and consistent state synchronization. We conduct extensive experiments spanning complex coordination tasks in restaurants, supermarkets, and households. Our results demonstrate that RoboOS-NeXT achieves superior performance across heterogeneous embodiments, validating its effectiveness in enabling lifelong, scalable, and robust multi-robot collaboration. Project website: https://flagopen.github.io/RoboOS/

Paper Structure

This paper contains 18 sections, 15 equations, 4 figures, 4 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. Embodied Vision–Language Models
  4. Architectural Paradigms for Embodied Control
  5. Multi-Robot Collaboration
  6. METHOD
  7. Spatio-Temporal--Embodiment Memory (STEM)
  8. STEM Generation and Lifelong Update
  9. Brain–Cerebellum–Memory Framework
  10. Experiments
  11. Experimental Details
  12. Lifelong Adaptability (RQ1)
  13. Collaborative Scalability (RQ2)
  14. Scheduling Robustness (RQ3)
  15. Ablation Study (RQ4)
  16. ...and 3 more sections

Figures (4)

  • Figure 1: Overview of RoboOS-NeXT. RoboOS-NeXT is a unified memory-based framework for multi-robot collaboration, built around a shared Spatio-Temporal–Embodiment Memory (STEM). STEM provides a unified representation by integrating spatial scene geometry, temporal event history, and embodiment profiles, making it accessible to all robots. Based on the STEM, a brain–cerebellum framework closes the loop between cognition, planning and control, supporting lifelong adaptation, scalable collaboration and robust scheduling.
  • Figure 2: Pipeline of RoboOS-NeXT. The RoboOS-NeXT framework implements a workflow pipeline for multi-robot collaboration, consisting of four key phases: (1) global task decomposition, (2) topological subtask allocation, (3) distributed subtask agent, and (4) dynamic memory updating. Together, these phases establish a memory-centric workflow that enables lifelong, scalable, and robust multi-robot collaboration.
  • Figure 3: Failure distribution in the restaurant scenario. Most errors arise from tool invocation and memory operations, with additional sensitivity in subtask generation.
  • Figure 4: Real-world RoboOS-NeXT Demonstrations. We showcase multi-robot collaboration in three types of scenarios: (a) Restaurant, (b) Household and (c) Supermarket.