发表机构
University of Illinois Urbana-Champaign; NVIDIA（伊利诺伊大学厄巴纳-尚佩恩分校; 英伟达）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
InterMimicGen提出自进化运动模仿框架，通过数据飞轮将稀疏人-物交互演示扩展为多样化机器人参考，训练通用跟踪器并提升移动操作能力，实现向真实机器人的迁移。
AI 中文摘要
捕获的人-物交互为人类形机器人移动操作提供了丰富的监督信号，但这些数据稀疏、异构，且不能直接被机器人执行。我们提出了InterMimicGen，一个自进化的运动模仿框架，其中机器人运动数据与跟踪策略相互改进。首先，我们整合了动捕的人-物交互数据集，并将其重定向为类人机器人参考，同时保持全身协调和灵巧的手-物关系。这产生了一个大规模且多样化的类人机器人参考集合，用于灵巧的全身移动操作。其次，我们训练了一个基于物理的通用跟踪器，在仿真中于具有灵巧手的类人机器人上执行这些参考，覆盖了先前用于移动操作的类人跟踪系统所无法达到的规模和多样性。第三，我们闭合了一个数据飞轮：每一轮对交互发生的位置和身体执行方式做出小的、保持任务语义的更改，在这些更改上微调跟踪器，并仅保留那些模拟执行完成任务变体，这些变体为下一轮提供种子。随着迭代次数增加，这些小的编辑在稀疏的原始演示周围累积成更广泛的覆盖，同时保持任务语义和运动质量。实验表明，跨机器人配置的接触保持重定向、单一通用策略的广泛跟踪、随增强轮次持续增长的可执行运动，以及向真实机器人的迁移。InterMimicGen提供了一条从异构人类演示到持续扩展的机器人学习运动资源的统一路径。
英文摘要
Captured human-object interactions provide rich supervision for humanoid loco-manipulation, but they are sparse, heterogeneous, and not directly executable by robots. We introduce InterMimicGen, a self-evolving motion-imitation framework in which robot motion data and a tracking policy improve each other. First, we consolidate motion-captured human-object interaction datasets and retarget them into humanoid robot references while preserving whole-body coordination and dexterous hand-object relationships. This produces a large and diverse humanoid robot reference collection for dexterous whole-body loco-manipulation. Second, we train a physics-based generalist tracker that executes these references in simulation on a humanoid with dexterous hands, covering a scale and diversity beyond prior humanoid tracking systems for loco-manipulation. Third, we close a data flywheel: each round makes small, task-preserving changes to where an interaction takes place and how the body performs it, fine-tunes the tracker on them, and keeps only the variants whose simulated execution completes the task, which seed the next round. With more iterations, these small edits compound into broader coverage around the sparse original demonstrations while preserving task semantics and motion quality. Experiments show contact-preserving retargeting across robot configurations, broad tracking with a single generalist policy, executable motions that keep growing over augmentation rounds, and transfer to real robots. InterMimicGen provides a unified path from heterogeneous human demonstrations to a continually expanding motion resource for humanoid robot learning.
CommentsProject Page: https://sirui-xu.github.io/InterMimicGen
