具身开发者社区

外观

论文arXiv 2609.214671 个月前

从单个运动片段学习用于人形机器人移动操作的距离条件化物体运输 ​

针对单一参考难控制运输终止距离，提出DCRR重组监督，并在四类交互、仿真迁移和硬件上验证。

AI 整理
  • 硬件零部件
  • 本体 SDK 与控制

原文链接：Learning Distance-Conditioned Object Transport for Humanoid Loco-Manipulation from a Single Motion Clip（arXiv 2609.21467 · 发布日期：2026-09-18）

Learning Distance-Conditioned Object Transport for Humanoid Loco-Manipulation from a Single Motion Clip

针对单一参考难控制运输终止距离，提出DCRR重组监督，并在四类交互、仿真迁移和硬件上验证。

核心要点 ​

  • 固定参考训练的策略主要复现示范终点，存在终止与途经状态错配。
  • DCRR将示范终止段迁移到中间状态，用冻结跟踪教师闭环回放并重标注。
  • DCRR-BC在四项任务上将归一化距离MAE由0.28降至0.15。
  • RL微调提升仿真和sim-to-sim下的命令响应与执行鲁棒性，硬件也展示调距。

验证范围与局限：验证限于Carry、Kick-Push、Crouch-Push、Drag四种交互模式，含训练仿真、sim-to-sim迁移和硬件实验。

英文摘要 (Abstract) ​

Motion tracking can reproduce humanoid loco-manipulation from a single retargeted motion clip, but a policy trained on a fixed reference primarily reproduces its demonstrated transport outcome. Although the source trajectory visits intermediate object displacements, transport termination is demonstrated only at its endpoint. We identify this mismatch as the termination-versus-passage gap: intermediate displacements are observed as passage states rather than termination-complete outcomes. We introduce Distance-Conditioned Reference Recomposition (DCRR), which relocates the demonstrated termination segment to intermediate transport states. A frozen tracking teacher replays the recomposed references under closed-loop dynamics, and the retained trajectories are relabeled by their achieved object placements and distilled into a reference-free policy. This procedure constructs distance-conditioned supervision from the interaction behavior encoded in the source motion. Across Carry, Kick-Push, Crouch-Push, and Drag, DCRR-BC produces command-dependent transport with an overall normalized distance mean absolute error (MAE) of 0.15, compared with 0.28 for source-only behavior cloning. RL fine-tuning further improves the command response and execution robustness in the training simulator and under sim-to-sim transfer. Finally, hardware experiments demonstrate transport-distance modulation across all four interaction modes.

作者：Yuhyeon Hwang, Daniel Sungho Jung, Yonghyeok Seo, Mingi Jung, Chang Nho Cho, Jung-Hoon Hwang, Dongin Shin

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2609.21467：Learning Distance-Conditioned Object Transport for Humanoid Loco-Manipulation from a Single Motion Clip访问 2026-10-21