跳到正文
返回论文列表
cs.RO提交于 已译

深度强化学习控制铁磁流体形状

Ferrofluid Shape Control with Deep Reinforcement Learning

Anthony Czubarow · Antonio Terpin · Raffaello D'Andrea

中文摘要

铁磁流体是含磁性纳米颗粒的液体,可通过外部磁场控制形状。这种可变形性使其能作为软体机器人,在受限空间中导航并操作物体。然而,其非线性连续动力学使可靠控制变得困难。已有工作表明,电磁铁阵列产生的空间磁场可建立并维持所需的铁磁流体构型。一个互补目标是利用流体在有限驱动下的动力学,达到可能无法在平衡态下维持的指定形状。这里使用基于深度模型的强化学习来控制这些瞬态形状。策略通过物理交互直接学习,基于视觉观察为单个固定电磁铁选择电流指令,引导移动中的铁磁流体趋向指定几何形状。学习到的策略反复实现了多种形状,包括多边形、星号和五格骨牌。这些结果表明,直接从物理交互中学习可实现可靠的流体形状控制,为控制基于铁磁流体的软体机器人开辟了新可能。

关键要点

  1. 01铁磁流体非线性连续动力学使可靠形状控制困难,现有方法依赖电磁铁阵列维持平衡构型。
  2. 02采用基于深度模型的强化学习,通过物理交互直接学习,仅用单个固定电磁铁和视觉观察选择电流指令。
  3. 03策略成功实现多边形、星号和五格骨牌等多种瞬态形状,证明学习控制可行。
  4. 04局限在于仅使用单个固定电磁铁,且目标为瞬态形状而非平衡态可持续形状。

解读

尚无解读。

原始英文摘要

arXiv:2611.25232v1 Announce Type: new Abstract: Ferrofluids are liquids containing magnetic nanoparticles, enabling shape control through external magnetic fields. This deformability supports their use as soft robotic bodies that can navigate confined spaces and manipulate objects. Their nonlinear continuum dynamics, however, make reliable control challenging. Existing work shows how spatial magnetic fields from electromagnet arrays can establish and maintain desired ferrofluid configurations. A complementary objective is to exploit the fluid's dynamics under limited actuation to reach prescribed shapes that may not be sustainable at equilibrium. Here, we use deep model-based reinforcement learning to control these transient shapes. Learning directly through physical interaction, our policies select current commands for a single fixed electromagnet based on visual observations, guiding the moving ferrofluid toward prescribed geometries. The learned policies repeatedly attain a variety of shapes spanning polygons, asterisks and pentominoes. These results demonstrate that learning directly from physical interaction enables reliable fluid shaping, opening new possibilities for controlling ferrofluid-based soft robots.

同方向论文 · cs.RO

查看全部 →