Skip to content

论文HF Daily Papers · arXiv 2611.222755 天前

Heave-Ho框架实现十机异构人形机器人去中心化长程协作 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration(HF Daily Papers · arXiv 2611.22275)

核心内容 ​

针对人形机器人多机协作中全身交互、长程规划及精确同步难题,研究团队发布Heave-Ho去中心化框架。该系统底层采用多智能体后训练适配物理耦合交互,高层结合视觉语言规划器与语音领导者-跟随者机制,仅依赖本地观测即可在无网络通信下完成协同。实验表明系统从双机扩展至十机规模,且支持异构编队零样本泛化,真机测试验证了其在复杂任务中的鲁棒性。

技术架构上,底层将人形基础跟踪模型微调为适应物理耦合的去中心化控制器;高层利用VLM进行任务分解,并通过语音指令替代传统网络通信实现执行同步。为量化评估,团队构建HH-Bench基准,涵盖2至10台同构或异构人形机器人的12类协作任务。评测结果显示Heave-Ho在各项指标上均超越现有基线,解决了多机长程协作中的通信依赖与异构适配瓶颈。

关键看点 ​

  • 去中心化控制:基于多智能体后训练框架适配物理耦合交互,仅凭本地观测实现协同,摆脱对中心化网络通信的依赖
  • 语音协调机制:设计基于语音的领导者-跟随者协议同步执行逻辑,配合视觉语言规划器解决无网环境下的长程任务对齐
  • 异构零样本泛化:在同构双机数据上训练,可直接扩展至10机规模并适配异构团队,无需针对新构型重新训练模型
  • HH-Bench基准:发布包含12项任务的评测集,覆盖2至10台人形机器人协作场景,系统性验证算法在真实物理交互中的优势

工程与产业观察 ​

该工作突破了多机协作对高带宽通信和同质化本体的强依赖,验证了“基础模型后训练+自然语言协调”在具身集群中的有效性。其去中心化范式降低了工程部署复杂度,异构泛化能力则为混合编队作业提供了低成本技术路径,对人形机器人从单机演示走向群体实战具有重要参考价值。

英文摘要 (Abstract) ​

Collaboration promises to extend humanoid capabilities beyond what individual robots can achieve. However, realizing this potential requires coordinated whole-body interactions, coherent long-horizon planning, and precise synchronization across robots. We introduce Heave-Ho, a decentralized framework for long-horizon collaborative multi-humanoid loco-manipulation. At the low level, we develop a multi-agent post-training framework that adapts a humanoid foundation tracking model to physically coupled interactions between humanoids, enabling coordinated decentralized control from local observations alone. At the high level, we train a vision-language planner and design a speech-based leader-follower coordination mechanism to synchronize decentralized execution without network communication. Trained with two identical humanoids, our system scales to teams of up to ten robots and generalizes to heterogeneous teams without retraining. To benchmark these capabilities, we introduce HH-Bench, comprising 12 tasks involving teams of 2 to 10 humanoids, including heterogeneous teams. Systematic evaluations show that Heave-Ho consistently outperforms baseline methods, while real-world experiments demonstrate robust decentralized collaboration across challenging tasks.

Hugging Face Daily Papers 热度:21 upvotes 作者:Ting-Hsuan Chen, Siheng Zhao, Han Jiang, Qi Pan, Louison Lu, Jiaheng Luo, Henghui Bao, Yiyu Chen, Quan Nguyen, Yue Wang

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. HF Daily Papers · arXiv 2611.22275:Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration ↗访问 2026-11-19