发表机构
ETH Zurich; NVIDIA; Microsoft; University of Bonn（苏黎世联邦理工学院; 英伟达; 微软; 波恩大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ForceTwin通过手持力传感夹爪从人类交互中识别铰接物体的物理信息数字孪生，估计惯性、摩擦和状态相关机构力，在阻抗控制中达到87%目标完成率，优于现有基线。
AI 中文摘要
操作物体不仅需要理解其运动，还需要理解决定运动的物理属性。对于铰接物体，这些属性包括惯性、摩擦力以及弹簧或闭门器等机构，其效果可能随构型和速度而变化。这些属性无法从外观直接观察：视觉上相同的门可能需要非常不同的操作力度。现有的数字孪生流程主要恢复运动学，或从视觉和语言先验中分配静态物理参数，这可能产生物理上不合理的估计。因此，状态相关的机构动力学仍未识别，且未在标准资产格式中表示。我们提出ForceTwin，一个从仪器化人类交互中识别铰接物体物理信息数字孪生的系统。一个人使用手持力传感夹爪探测物体，提供同步的位姿和交互力，我们从中估计铰接、包括惯性、库仑摩擦、粘性阻尼的参数化动力学，以及捕获状态相关机构力的结构化神经残差。ForceTwin将VLM先验的惯性参数误差几乎减半。作为Spot和Franka FR3上阻抗控制的前馈动力学模型，ForceTwin在九个物体-实体对中实现了87%的目标完成率，而使用VLM先验和仅运动学孪生的完成率分别为60%和57%，在强机构导致两个基线停滞的物体上收益最大。我们进一步使用识别出的孪生训练全身穿门策略，并在现实世界中部署。项目页面：此https URL
英文摘要
Manipulating objects requires understanding not only their motion, but also the physical properties that determine it. For articulated objects, these include inertia, friction, and mechanisms such as springs or door closers, whose effects can vary with configuration and velocity. Such properties are not directly observable from appearance: visually identical doors may require very different effort to manipulate. Existing digital-twin pipelines recover primarily kinematics or assign static physical parameters from visual and language priors, which can yield physically implausible estimates. As a result, state-dependent mechanism dynamics remain unidentified and are not represented in standard asset formats. We present ForceTwin, a system for identifying physics-informed digital twins of articulated objects from instrumented human interaction. A person probes an object using a handheld force-sensing gripper, providing synchronized poses and interaction forces from which we estimate the articulation, parametric dynamics including inertia, Coulomb friction, viscous damping, and a structured neural residual capturing state-dependent mechanism forces. ForceTwin nearly halves the inertial-parameter error of a VLM prior. As a feedforward dynamics model for impedance control on a Spot and a Franka FR3, ForceTwin achieves 87% goal completion across nine object-embodiment pairs, compared with 60% using VLM-prior and 57% using kinematics-only twins, with the largest gains on objects whose strong mechanisms cause both baselines to stall. We further use the identified twins to train whole-body door-traversal policies and deploy them in the real world. Project Page: https://timengelbracht.github.io/forcetwin-website/
