On Flange-based 3D Hand-Eye Calibration for Soft Robotic Tactile Welding

TL;DR

This work introduces flange-based hand-eye calibration that directly measures ISO-standardized tool-flange features with high-fidelity 3D scanners, enabling a transformation calibration with iterative refinement that can reach the camera's accuracy limits (translational $<$ $0.28$ mm, rotational $<$ $0.25^{\circ}$). It formalizes a four-configuration framework and solvability conditions for hand-eye calibration, and demonstrates a practical, marker-free approach validated across multiple collaborative robots and scanners. A concurrent soft-tactile welding system combines flange-based calibration with a soft robotic metamaterial to track weld seams via deformation, allowing real-time trajectory adjustments and improved weld quality. The integrated vision-tactile system is demonstrated on autonomous seam tracking tasks, highlighting the potential for more robust, adaptable manufacturing processes and guiding future work toward depth-based calibration and ML-driven trajectory optimization.

Abstract

This paper investigates the direct application of standardized designs on the robot for conducting robot hand-eye calibration by employing 3D scanners with collaborative robots. The well-established geometric features of the robot flange are exploited by directly capturing its point cloud data. In particular, an iterative method is proposed to facilitate point cloud processing toward a refined calibration outcome. Several extensive experiments are conducted over a range of collaborative robots, including Universal Robots UR5 & UR10 e-series, Franka Emika, and AUBO i5 using an industrial-grade 3D scanner Photoneo Phoxi S & M and a commercial-grade 3D scanner Microsoft Azure Kinect DK. Experimental results show that translational and rotational errors converge efficiently to less than 0.28 mm and 0.25 degrees, respectively, achieving a hand-eye calibration accuracy as high as the camera's resolution, probing the hardware limit. A welding seam tracking system is presented, combining the flange-based calibration method with soft tactile sensing. The experiment results show that the system enables the robot to adjust its motion in real-time, ensuring consistent weld quality and paving the way for more efficient and adaptable manufacturing processes.

Figures (14)

• Figure 1: A direct hand-eye calibration based on a three-dimensional measurement of the standardized geometrical features on the robot's tool flange.
• Figure 2: Common configurations of robot hand-eye calibration.
• Figure 3: Eye-on-Arm configuration for robot hand-eye calibration.
• Figure 4: The standardized geometric features on the flange of an industrial robot following ISO 9409-1: 2004 ISO9409-1.
• Figure 5: The flanges of a few collaborative robots following ISO 9409-1-50-4-M6 standard: (a) Universal Robots' UR10e UR10e, (b) Universal Robots' UR5 UR5, (c) Franka's Emika FrankaEmika, and (d) AUBO's i5 AUBOi5.