arXiv 2604.185572026-08-04cs.CVcs.GRcs.RO

SynAgent：通过独狼到协作代理协同实现通用化的人形机器人操作

SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy

School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；Department of Automation, Tsinghua University（清华大学自动化系）；College of Artificial Intelligence, Nanjing Forestry University（南京林业大学人工智能学院）

Wei Yao, Haohan Ma, Hongwen Zhang, Liangjun Xing, Zhile Yang, Yuanjun Guo, Yunlian Sun, Yebin Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出SynAgent框架，通过独狼到协作代理协同转移单agent人-物体交互技能，实现可扩展且物理合理的协作操作，实验显示其在协作模仿和轨迹条件控制方面优于现有基线。

摘要：

可控的协作人形操作是具身智能中的基本但具有挑战性的问题，由于严重的数据稀缺、多智能体协调的复杂性和在不同物体上的有限泛化能力。本文提出SynAgent，一个统一框架，通过利用独狼到协作代理协同来转移单agent人-物体交互技能到多agent人-物体-人场景。为了在运动转移过程中保持语义完整性，我们引入了一种基于通过Delaunay四面体化构建的Interact Mesh的交互保持重定向方法，忠实保持人类和物体之间的空间关系。在此基础上，我们提出了一种单agent预训练和适应范式，通过去中心化训练和多智能体PPO从丰富的单人数据中引导协同协作行为。最后，我们开发了一种轨迹条件生成策略，使用条件VAE训练，通过多教师蒸馏从运动模仿先验训练以实现稳定且可控的物体级轨迹执行。大量实验表明，SynAgent在协作模仿和轨迹条件控制方面显著优于现有基线，同时在多样化的物体几何上实现了泛化。代码和数据将在发表后提供。项目页面：http://yw0208.github.io/synagent

英文摘要：

Controllable cooperative humanoid manipulation is a fundamental yet challenging problem for embodied intelligence, due to severe data scarcity, complexities in multi-agent coordination, and limited generalization across objects. In this paper, we present SynAgent, a unified framework that enables scalable and physically plausible cooperative manipulation by leveraging Solo-to-Cooperative Agent Synergy to transfer skills from single-agent human-object interaction to multi-agent human-object-human scenarios. To maintain semantic integrity during motion transfer, we introduce an interaction-preserving retargeting method based on an Interact Mesh constructed via Delaunay tetrahedralization, which faithfully maintains spatial relationships among humans and objects. Building upon this refined data, we propose a single-agent pretraining and adaptation paradigm that distills synergistic collaborative behaviors from abundant single-human data through decentralized training and multi-agent PPO. Finally, we develop a trajectory-conditioned generative policy using a conditional VAE, trained via multi-teacher distillation from motion imitation priors to achieve stable and controllable object-level trajectory execution. Extensive experiments demonstrate that SynAgent significantly outperforms existing baselines in both cooperative imitation and trajectory-conditioned control, while generalizing across diverse object geometries. Codes and data will be available after publication. Project Page: https://yw0208.github.io/synagent/

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。