Skip to content

论文arXiv 2605.277245 个月前

HumanoidMimicGen:全身规划生成人形操作数据,策略性能提升20% ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning(arXiv 2605.27724)

核心内容 ​

针对人形机器人移动操作模仿学习中遥操作数据采集耗时且高维动作空间难以自动合成的痛点,研究团队提出HumanoidMimicGen数据生成框架。该方法能从少量源演示中自适应生成新状态下的全身技能,解决物体位姿变化泛化难题。配套发布的仿真基准包含9项多样化移动操作任务,验证了自动生成大数据集对策略学习的有效性,混合数据训练策略较纯真实数据性能提升20%。

技术上,HumanoidMimicGen将接触丰富的全身技能与单/双臂操作及全身运动规划交错执行,确保在复杂场景布局下生成稳定、无碰撞的轨迹数据。系统支持从少量源示范向新环境状态迁移,有效覆盖人形机器人手臂、腿部与躯干的高维复合动作空间。该方案不仅解决了数据获取瓶颈,还为量化分析数据生成质量与策略学习决策对模型性能的影响提供了标准化评测工具。

关键看点 ​

  • 数据生成机制:交错执行全身运动规划与单双臂技能,从少量源演示泛化生成稳定无碰撞的移动操作轨迹
  • 性能提升指标:结合生成数据训练的全身视觉运动策略,在仿真基准中比仅用真实数据训练的策略性能提升20%
  • 仿真评测基准:发布包含9项多样化任务的Loco-Manipulation Benchmark,支持数据生成与策略学习决策的系统性研究
  • 高维空间适配:专门解决人形机器人臂腿躯干复合动作空间的数据合成难题,克服传统机械臂算法失效问题

工程与产业观察 ​

该工作为人形机器人移动操作提供了可规模化的合成数据管线,验证了“少量真值+大量生成”范式在高维具身任务中的有效性。其提出的全身规划交错生成机制与标准化Benchmark,为算法工程师解决Sim-to-Real数据缺口、优化模仿学习样本效率提供了关键工程参考与评测基线。

英文摘要 (Abstract) ​

Imitation learning is a promising approach for training humanoid robots to both walk and manipulate, but it requires a large number of demonstrations, which are time-intensive and difficult to collect via teleoperation. Existing data-generation algorithms can automatically synthesize demonstrations for manipulators, but they are ineffective on humanoids because their high-dimensional composite action spaces involve arms, legs, and torsos. We present HumanoidMimicGen, a method for generating humanoid legged loco-manipulation data. Our method adapts contact-rich whole-body skills from a handful of source demonstrations to new states, generalizing across changes in object pose. By interleaving these single- and dual-arm skills with whole-body locomotion and manipulation planning, the method generates stable, collision-free data across diverse scenes and layouts. To evaluate our approach, we introduce a new simulated loco-manipulation benchmark containing nine diverse tasks that test humanoid loco-manipulation capabilities. There, we demonstrate that HumanoidMimicGen automatically generates large datasets for imitation learning and enables a systematic study of how data generation and policy learning decisions impact model performance. We show that whole-body visuomotor policies co-trained with data generated by HumanoidMimicGen outperform those trained only on real-world data by 20%.

作者:Kevin Lin, Ajay Mandlekar, Caelan Reed Garrett, Nikita Chernyadev, Yu Fang, Runyu Ding, Yuqi Xie, Justin Tran, Linxi Fan, Yuke Zhu

来源

本页事实对应的公开页面,以原文为准。

  1. arXiv 2605.27724:HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning访问 2026-10-23