发表机构
State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology; National Innovation Institute of Digital Design and Manufacturing（华中科技大学机械科学与工程学院智能制造装备与技术国家重点实验室; 国家数字化设计与制造创新中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FasTac是一款集成多光谱光度立体、动态卷积力估计及FPGA加速的曲面多光谱视觉触觉传感器，可实现高精度3D形状与力感知，兼具高速处理能力，经实验验证其性能优于现有方案。
AI 中文摘要
用于灵巧操作的曲面触觉指尖需解析精细接触几何、区分法向与切向载荷并捕捉瞬态信号。现有曲面视觉触觉传感器难以在紧凑形态下同时实现精准3D重建、三轴力估计与高速处理。本文提出FasTac，一种集成多光谱光度立体、动态卷积力估计及现场可编程门阵列（FPGA）硬件加速的曲面视觉触觉传感器。单图像传感器同步多光谱成像提供空间对齐观测，用于鲁棒表面法向估计，随后通过边界先验实现快速泊松深度重建。HyperForce采用位置感知动态卷积建模曲面弹性体的空间非均匀力学响应，估计三轴力。完整的图像-法向-力 pipeline 部署于FPGA。实验表明，近红外（NIR）照明与边界先验使深度平均绝对误差（MAE）从0.2730 mm降至0.0415 mm；HyperForce对法向力与切向力的归一化平均绝对误差（NMAE）分别为2.74%与2.39%；FPGA部署将处理延迟从GPU上的3.26 ms缩短至1.09 ms。多目标重建、反馈抓取及振动测量验证了精细几何感知、稳定力反馈与动态接触传感能力。
英文摘要
Curved tactile fingertips for dexterous manipulation must resolve fine contact geometry, distinguish normal and tangential loads, and capture transient signals. Existing curved vision-based tactile sensors struggle to combine accurate 3D reconstruction, three-axis force estimation, and high-speed processing in a compact form. This article presents FasTac, a curved vision-based tactile sensor integrating multispectral photometric stereo, dynamic-convolution force estimation, and hardware acceleration on a field-programmable gate array (FPGA). Single-image-sensor simultaneous multispectral imaging provides spatially aligned observations for robust surface normal estimation, followed by boundary-prior fast Poisson depth reconstruction. HyperForce uses position-aware dynamic convolution to model the spatially nonuniform mechanical response of curved elastomers and estimate three-axis forces. The complete image-to-normal-force pipeline is deployed on an FPGA. Experiments show that near-infrared (NIR) illumination and the boundary prior decrease depth mean absolute error (MAE) from 0.2730 mm to 0.0415 mm; HyperForce achieves normalized mean absolute error (NMAE) values of 2.74% and 2.39% for normal and shear forces, respectively; and FPGA deployment shortens processing latency from 3.26 ms on the GPU to 1.09 ms. Multi-object reconstruction, feedback grasping, and vibration measurement validate fine geometric perception, stable force feedback, and dynamic contact sensing.
Comments13 pages, 11 figures, including 2 pages of supplementary material. Submitted to IEEE/ASME Transactions on Mechatronics
