外观
论文arXiv 2609.234321 个月前
RopeFormer：用于动态绳索操控的基于交互历史的跨试次适应
RopeFormer用跨试次交互历史作为控制上下文，在仿真绳索任务和Unitree H1-2真机未知绳索上验证动态绳索操控。
宇树 H1原文链接：RopeFormer: Cross-Trial Adaptation from Interaction History for Dynamic Rope Manipulation（arXiv 2609.23432 · 发布日期：2026-09-20）
RopeFormer: Cross-Trial Adaptation from Interaction History for Dynamic Rope Manipulation
RopeFormer用跨试次交互历史作为控制上下文，在仿真绳索任务和Unitree H1-2真机未知绳索上验证动态绳索操控。
核心要点
- 动态绳索操控对未知物体动力学敏感，显式识别相关物理属性困难。
- 框架保留跨试次动作-响应历史作为上下文，策略权重固定且无需在线估计绳索参数。
- 仿真中在单臂持续旋转、双臂旋转和瞬态鞭打任务上，保留上下文优于重置同一检查点。
- 真机从T1到T3缩短Rope Swing和Rope Twirl目标获取时间，并提升Rope Whip命中数；代码数据已开放。
验证范围与局限：验证范围包括匹配仿真的三类任务，以及Unitree H1-2上此前未见实体绳索的Rope Swing、Rope Twirl和Rope Whip。
英文摘要 (Abstract)
Dynamic rope manipulation is highly sensitive to unknown object dynamics: the same robot motion can produce substantially different responses across ropes, while explicitly identifying the relevant physical properties is difficult. We present RopeFormer, a history-conditioned framework that uses prior task interaction as context for subsequent control. The policy retains cross-trial action-response history while keeping its weights fixed and requires no explicit online rope-parameter estimation. In matched simulation evaluations across sustained single-arm rotation, bimanual rotation, and transient whipping, retaining context improves subsequent control relative to resetting the same checkpoint, with the benefit varying across rope dynamics and observation settings. We further deploy the frozen policies on a Unitree H1-2 with previously unseen physical ropes. From T1 to T3, target-acquisition time decreases by 30.9% for Rope Swing and 33.9% for Rope Twirl, while mean Rope Whip target hits increase from 0.2 to 2.3 out of three. These results show that prior interaction can provide effective control context for dynamic deformable-object manipulation. Robot videos, code, and data are available at https://ropeformer.github.io/.
作者：Menglin Wu, Kaixiang Yao, Shangbo Luan, Masayoshi Tomizuka, Yuxin Chen
来源
本页事实对应的公开页面，以原文为准。