外观
论文arXiv 2609.335511 个月前
FoLD：用于灵巧关节式物体操作的力信息学习
原文链接：FoLD: Force-Informed Learning for Dexterous Articulated Object Manipulation（arXiv 2609.33551 · 发布日期：2026-09-27）
FoLD: Force-Informed Learning for Dexterous Articulated Object Manipulation
FoLD通过由人类示范和机器人交互状态计算力先验，学习残差策略，并在关节物体操作基准与真实灵巧机器人上验证。
核心要点
- 人类示范迁移到灵巧机器人时，手部形态和接触动力学差异常使重定向动作失效。
- FoLD根据人类示范和当前交互状态计算补偿力场，形成促进示范物体运动的力先验。
- 该力先验指导残差策略，调整重定向手部动作以满足任务接触需求。
- 在公开关节物体操作基准上持续优于先进基线，并在真实灵巧机器人平台验证迁移。
验证范围与局限：验证范围包括公开关节物体操作基准和真实灵巧机器人平台，摘要未说明具体平台数量或任务细节。
英文摘要 (Abstract)
Transferring human demonstrations to dexterous robots remains challenging because differences in hand morphology and contact dynamics often cause retargeted motions to fail at producing the intended object behavior. We present \textbf{FoLD}, a framework for learning dexterous manipulation of articulated objects through explicit force guidance. FoLD compute compensatory force fields from human demonstrations together with the robot's current interaction state, yielding a force prior that promotes the demonstrated object motion. This force prior informs a residual policy that adapts retargeted hand motions to the contact requirements of the task. We evaluate FoLD on a public benchmark for articulated object manipulation, where it consistently outperforms state-of-the-art baselines across tasks and embodiments. We further validate FoLD on real dexterous robot platforms, demonstrating successful transfer of human manipulation skills to robot execution. Here is the link of our project page: https://gghgghgghgg.github.io/FoLD-project-page/.
作者：Haowei Shen, Tingai Li, Yumeng Liu, Wenyuan Guang, Xuanze Yang, Qing Fang, Kai Xu, Ligang Liu, Ruizhen Hu
来源
本页事实对应的公开页面，以原文为准。