Both robot and hand-eye calibration have been object of research for decades. While current approaches manage to precisely and robustly identify the parameters of a robot's kinematic model, they still rely on external devices such as calibration objects, markers and/or external sensors. Instead of trying to fit recorded measurements to a model of a known object, this paper treats robot calibration as an offline SLAM problem, where scanning poses are linked to a fixed point in space via a moving kinematic chain. As such, we enable robot calibration by using nothing but an arbitrary eye-in-hand depth sensor. To the authors' best knowledge the presented framework is the first solution to three-dimensional (3D) sensor-based robot calibration that does not require external sensors nor reference objects. Our novel approach utilizes a modified version of the Iterative Corresponding Point algorithm to run bundle adjustment on multiple 3D recordings estimating the optimal parameters of the kinematic model. A detailed evaluation of the system is shown on a real robot with various attached 3D sensors. The presented results show that the system reaches precision comparable to a dedicated external tracking system at a fraction of its cost.

中文翻译：

---

使用驱动 3D 传感器的机器人自校准

几十年来，机器人和手眼校准一直是研究的对象。虽然当前的方法能够精确、稳健地识别机器人运动模型的参数，但它们仍然依赖于外部设备，例如校准物体、标记和/或外部传感器。本文没有尝试将记录的测量数据拟合到已知物体的模型中，而是将机器人校准视为离线 SLAM 问题，其中扫描姿势通过移动运动链链接到空间中的固定点。因此，我们只使用任意的手眼深度传感器即可实现机器人校准。据作者所知，所提出的框架是第一个基于三维（3D）传感器的机器人校准解决方案，不需要外部传感器或参考物体。我们的新颖方法利用迭代对应点算法的修改版本对多个 3D 记录运行束调整，估计运动学模型的最佳参数。在带有各种附加 3D 传感器的真实机器人上显示了系统的详细评估。所呈现的结果表明，该系统的精度可与专用外部跟踪系统相媲美，而成本仅为专用外部跟踪系统的一小部分。