PinFT：可嵌入镊子式工具的微型五轴力/力矩传感器

Jul 16, 2026

Upload by Quinn

PinFT introduces a miniature five-axis capacitive force/torque sensor for direct tip-level integration into tweezer-like tools. A compact three-PCB stack with segmented plated through-hole electrodes and a silicone elastomer dielectric measures five degrees of freedom (Fx, Fy, Fz, Tx, Ty) via displacement of a central 2 mm stainless-steel pin. Calibration with higher-order polynomial mapping yields mean absolute errors around 0.23 N for forces and 2.5 mN·m for torques, with R² above 0.97 on all axes. A 3D-printed dual-tip tweezer enables per-tip force signatures across grasping, hair pulling, and compliant tearing tasks, distinguishing success from failure through gradient-based features.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

Introduction

Related Work: Tool-Mounted Force and Tactile Sensors

PinFT: Miniature 5-Axis Force/Torque Sensor Embeddable to Tweezer-like Tool Leo King, Jenny Chen, Tae Myung Huh arXiv :2607 . 10000v1 [ cs .RO] 10 Jul 2026 Abstract—We present PinFT, a miniature five-axis capacitive force/torque sensor designed for direct tip-level integration into tweezer-like tools. The sensor employs a compact three-PCB stack with segmented plated through-hole electrodes and a silicone elastomer dielectric, enabling five-degree-of-freedom force and torque sensing (Fx, Fy , Fz , Tx, Ty ) through displacement of a central 2 mm-diameter stainless steel pin. The fabricated prototype was calibrated using a higher-order polynomial mapping, yielding mean absolute errors of approximately 0.23 N for forces and 2.5 mN·m for torques, with coefficients of determination (R2) exceeding 0.97 across all axes. To demonstrate practical utility, a 3D-printed tweezer integrating PinFT sensors at both tips was mounted on a parallel-jaw gripper and evaluated across three representative manipulation tasks: grasping a submillimeter SMD capacitor, pulling a simulated hair from a silicone substrate, and tearing a compliant silicone specimen. In all cases, per-tip force sensing reliably captured characteristic force signatures that distinguish successful manipulation from failure events—including slip and object ejection—using gradient-based features derived from internal grasp force and net interaction force. These results demonstrate that direct, per-tip force sensing enables standard parallel-jaw grippersto monitor and interpret fine manipulation tasks performed through a handheld tweezer. I. INTRODUCTION Humans routinely use tools to extend their manipulation capabilities, achieving levels of precision and delicacy that are difficult to attain with bare hands alone. Instruments like tweezers enable reliable interaction with small fragile objects essential in domains ranging from microsurgery to electronics assembly. The effectiveness arises from complementary factors: mechanical leverage attenuates finger forces to enable controlled, low-force interaction at the tool tips, while slender contact geometries provide access and precision at size scales where fingertips are too large. Moreover, during tool use, humans perceive the tool as an extension of the body, with tool-mediated haptic signals conveying contact, force, and slip information. Localizing sensation at the tooltip, effectively acting as an extended fingertip [1] . Robotic manipulation could benefit from similar principles by leveraging handheld tools, such as tweezers, to achieve fine and delicate interactions beyond the capabilities of conventional parallel-jaw grippers. Prior work has explored specialized end-effectors that emulate forceps- or tweezerlike kinematics [2]; however, broader usability would be achieved if standard robotic grippers could flexibly manipulate a variety of task-specific tools. A key challenge in enabling such tool-mediated manipulation is providing the All authors are with Dept. of Electrical and Computer Engineering, University of California Santa Cruz, Santa Cruz, CA, USA. [thuh@ucsc.edu](thuh@ucsc.edu) Fig. 1: The PinFT-integrated robotic tweezer system. Left: Close-up of the dual-tip configuration, where each tweezer tip is instrumented with a miniature PinFT five-axis capacitive force/torque sensor. The inset shows a sub-millimeter SMD capacitor used in precision grasping experiments. Top right: Integration of the 3D-printed tweezer tool mounted on a parallel-jaw gripper. Bottom right: Definition of the local force and torque coordinate frame (Fx , Fy , Fz , Tx , Ty) measured at each tip through the central 2 mm stainless steel sensing pin. robot with tactile or force feedback that accurately reflects interactions occurring at the tool–object interface. One approach is to infer tool–object interaction forces using tactile or force sensors mounted at the gripper [3] . Such methods require explicit modeling of tool g

FAQs

PinFT的传感方式如何实现五轴力/力矩测量？

PinFT采用紧凑的三层PCB堆叠，通过分段电镀通孔电极与硅橡胶弹性体介质实现测量；中心2 mm不锈钢针的位移被用来获取五个自由度（Fx、Fy、Fz、Tx、Ty）。

PinFT的标定精度表现如何？

原型使用高阶多项式映射进行标定，力的平均绝对误差约为0.23 N，力矩约为2.5 mN·m；各轴的决定系数R²在0.97以上。

该传感器如何用于在抓取任务中区分成功与失败事件？

在3D打印镊子工具的每个尖端集成传感器后，系统基于来自内部夹持力与净相互作用力的梯度特征提取每端的力响应，从而捕捉可表征成功操控与失败（如打滑与物体弹出）的典型力学特征。

Jul 16, 2026

Upload by Quinn