This study proposes an augmented reality (AR)-assisted workpiece-localization technique for rod-type flexible fixtures used in automotive and aerospace industries, for machining thin-walled components. The machining accuracy of a component depends considerably on the profile error and envelopment condition of the blank workpiece. An AR virtual reference of the component is created in the image space using a pinhole camera with a lens distortion model that visually assists the rough placement of the workpiece at the desired location. The fine workpiece-localization process is formulated as a nonlinear optimization problem to minimize the profile error. The problem is subjected to a point-in-polygon constraint in the image space to guarantee the envelopment requirement. The proposed method is validated using an aircraft body panel. It uses only the measurement data acquired from the upper surface of the panel and the AR reference and is a more flexible and accurate solution than the locating-pin method.

这项研究提出了一种增强现实（AR）辅助的工件定位技术，用于汽车和航空航天工业中用于加工薄壁部件的杆式柔性夹具。零件的加工精度在很大程度上取决于毛坯工件的轮廓误差和包络状态。使用带有透镜畸变模型的针孔摄像机在图像空间中创建组件的AR虚拟参考，该透镜在视觉上有助于将工件粗略放置在所需位置。将精细的工件定位过程公式化为非线性优化问题，以最大程度地减少轮廓误差。该问题在图像空间中受到多边形中点的约束，以确保包络要求。使用飞机机身面板验证了所提出的方法。