Point It, Strike It: Direction-Conditioned Dynamic Manipulation of Deformable Linear Objects

📄 arXiv: 2610.09573v1 📥 PDF

作者: Yi Yang, Xiang Fei, Lehong Wang, Zilin Dai, Ruogu Li, Jiting Cai, Liyao Chang, Xinyi Yang, Henry Kou, Ruijie Fu, Lu Li, Howie Choset

分类: cs.RO

发布日期: 2026-10-07

备注: 9 pages, 5 figures, 4 tables. Project Page: https://deformx.github.io/DeformY


💡 一句话要点

提出TRACE与RECAP以解决可变形线性物体的动态操控问题

🎯 匹配领域: 支柱一:机器人控制 (Robot Control) 支柱二:RL算法与架构 (RL & Architecture)

关键词: 动态操控 可变形物体 机器人技术 轨迹优化 参数校准

📋 核心要点

  1. 现有方法主要将目标定义为绳索尖端的到达位置,忽视了到达方式对任务成功的影响,导致实际应用中的可靠性不足。
  2. 论文提出TRACE方法,通过温启动生成击打数据,并设计RECAP策略以适应仿真器参数,从而提高动态操控的精确性和可靠性。
  3. 在真实机器人实验中,RECAP方法使得位置目标的成功率从72%提升至87%,同时在方向目标的成功率也有显著提升。

📝 摘要(中文)

可变形线性物体的动态操控通常将目标定义为绳索尖端的到达位置,但实际任务往往依赖于尖端的到达方式。本文研究了单摆绳索击打,目标不仅包括尖端的三维位置,还包括到达方向。为应对绳索动力学建模困难、缺乏示例、不同摆动的可靠性差异以及仿真与现实之间的差距,本文扩展了现有的DLO仿真器DeformX,提出了TRACE和RECAP方法。TRACE通过温启动生成击打数据,RECAP则通过少量标定摆动调整仿真器参数,最终在真实机器人上实现了显著的成功率提升。

🔬 方法详解

问题定义:本文旨在解决可变形线性物体(如绳索)的动态操控问题,现有方法在目标定义上仅关注位置,忽略了到达方式的影响,导致操控效果不佳。

核心思路:论文提出TRACE(基于轨迹的自适应交叉熵)和RECAP(残差校准策略)两种方法,TRACE通过温启动生成击打数据,RECAP则通过少量标定摆动来调整仿真器参数,以提高操控的准确性和可靠性。

技术框架:整体流程包括三个主要模块:首先是扩展的DLO仿真器DeformX2.0,其次是TRACE生成的击打数据,最后是RECAP策略用于适应和校准。

关键创新:最重要的创新在于TRACE和RECAP的结合,TRACE通过优化击打数据生成过程,RECAP则通过少量的校准摆动来提高仿真器的适用性,这在现有方法中尚未实现。

关键设计:TRACE的损失函数设计考虑了绳索弯曲和尖端运动的平滑性,以促进可重复的摆动;RECAP通过校准策略调整仿真器的绳索和设备参数,以适应真实环境。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,RECAP方法在真实机器人上实现了位置目标成功率从72%提升至87%,而在同时考虑到达方向的目标上,成功率从50%提升至79%。这些结果表明,所提出的方法在动态操控任务中具有显著的性能提升。

🎯 应用场景

该研究的潜在应用领域包括机器人抓取、自动化装配和物料搬运等场景,尤其是在处理可变形物体时,能够显著提高操作的精确性和效率。未来,该方法有望在更复杂的动态环境中得到应用,推动智能机器人技术的发展。

📄 摘要(原文)

Goal-conditioned dynamic manipulation of deformable linear objects has mainly specified goals as positions for a rope tip to reach. Many tasks, however, depend on how the tip arrives. We therefore study single-swing rope striking with goals that specify the tip's 3D position and arrival direction, across the workspace and on different ropes. This is challenging because rope dynamics are hard to model, no demonstrations exist, distinct swings reach the same goal with different reliability, and the sim-to-real gap extends beyond the rope. To address these challenges, we extend the state-of-the-art DLO simulator DeformX with GPU acceleration, a stable Cosserat rod solver, and a cross-flow aerodynamic model, yielding DeformX2.0, which is more than $20{,}000\times$ faster. We then propose TRACE (Trace-rooted Adaptive Cross-Entropy), which generates striking data by warm-starting each new target from the stored swing whose tip path passes closest to it. Its cost penalizes rope bending and abrupt tip motion to favor repeatable swings. A conditional flow-matching policy trained on this data reaches 92.1% accuracy in simulation. Finally, we propose RECAP (Residual Calibration Policy), which fits the simulator's rope and rig parameters to a few calibration swings and adapts actions with a correction policy trained in simulation. On a real robot, across three ropes, RECAP raises success within 5cm from 72% to 87% for position goals, and within 10cm and 10° from 50% to 79% for goals that also specify the arrival direction.