Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

3D Hand-Eye Calibration for Collaborative Robot Arm: Look at Robot Base Once

Leihui Li, Lixuepiao Wan, Volker Krueger, Xuping Zhang

TL;DR

The paper addresses the bottleneck of hand-eye calibration in collaborative robotics by proposing a target-free 3D-vision approach that uses the robot base as the calibration target. It introduces a generic dataset generation method for point-cloud registration and validates the approach through large-scale simulations across 14 arms and real-world experiments with UR10e, demonstrating calibration in seconds with accuracy comparable to commercial solutions. The key contributions include (i) a dataset generation pipeline around the robot base, (ii) validation across diverse robot arms, and (iii) a real-world demonstration showing significant time savings without external calibration objects. The practical impact is a faster, more convenient calibration workflow suitable for dynamic industrial environments, with open-source code available for adoption.

Abstract

Hand-eye calibration is a common problem in the field of collaborative robotics, involving the determination of the transformation matrix between the visual sensor and the robot flange to enable vision-based robotic tasks. However, this process typically requires multiple movements of the robot arm and an external calibration object, making it both time-consuming and inconvenient, especially in scenarios where frequent recalibration is necessary. In this work, we extend our previous method which eliminates the need for external calibration objects such as a chessboard. We propose a generic dataset generation approach for point cloud registration, focusing on aligning the robot base point cloud with the scanned data. Furthermore, a more detailed simulation study is conducted involving several different collaborative robot arms, followed by real-world experiments in an industrial setting. Our improved method is simulated and evaluated using a total of 14 robotic arms from 9 different brands, including KUKA, Universal Robots, UFACTORY, and Franka Emika, all of which are widely used in the field of collaborative robotics. Physical experiments demonstrate that our extended approach achieves performance comparable to existing commercial hand-eye calibration solutions, while completing the entire calibration procedure in just a few seconds. In addition, we provide a user-friendly hand-eye calibration solution, with the code publicly available at github.com/leihui6/LRBO.

3D Hand-Eye Calibration for Collaborative Robot Arm: Look at Robot Base Once

TL;DR

The paper addresses the bottleneck of hand-eye calibration in collaborative robotics by proposing a target-free 3D-vision approach that uses the robot base as the calibration target. It introduces a generic dataset generation method for point-cloud registration and validates the approach through large-scale simulations across 14 arms and real-world experiments with UR10e, demonstrating calibration in seconds with accuracy comparable to commercial solutions. The key contributions include (i) a dataset generation pipeline around the robot base, (ii) validation across diverse robot arms, and (iii) a real-world demonstration showing significant time savings without external calibration objects. The practical impact is a faster, more convenient calibration workflow suitable for dynamic industrial environments, with open-source code available for adoption.

Abstract

Hand-eye calibration is a common problem in the field of collaborative robotics, involving the determination of the transformation matrix between the visual sensor and the robot flange to enable vision-based robotic tasks. However, this process typically requires multiple movements of the robot arm and an external calibration object, making it both time-consuming and inconvenient, especially in scenarios where frequent recalibration is necessary. In this work, we extend our previous method which eliminates the need for external calibration objects such as a chessboard. We propose a generic dataset generation approach for point cloud registration, focusing on aligning the robot base point cloud with the scanned data. Furthermore, a more detailed simulation study is conducted involving several different collaborative robot arms, followed by real-world experiments in an industrial setting. Our improved method is simulated and evaluated using a total of 14 robotic arms from 9 different brands, including KUKA, Universal Robots, UFACTORY, and Franka Emika, all of which are widely used in the field of collaborative robotics. Physical experiments demonstrate that our extended approach achieves performance comparable to existing commercial hand-eye calibration solutions, while completing the entire calibration procedure in just a few seconds. In addition, we provide a user-friendly hand-eye calibration solution, with the code publicly available at github.com/leihui6/LRBO.
Paper Structure (12 sections, 7 equations, 11 figures, 3 tables)

This paper contains 12 sections, 7 equations, 11 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Definition and Methods
  4. Problem Definition
  5. Eye-in-Hand Calibration
  6. Eye-to-hand Calibration
  7. Look at Robot Base Once
  8. Experiments
  9. Preparation and Experiment Setup
  10. Experimental Results
  11. Real-world experiments
  12. Conclusion and future work

Figures (11)

  • Figure 1: Our proposed hand-eye and the traditional calibration that needs the external calibration objects.
  • Figure 2: Flowchart of the our developed hand-eye calibration.
  • Figure 3: Visualization of randomly selected robot base-looking poses for various robotic manipulators, with one representative joint configuration shown.
  • Figure 4: The hand-eye calibration results calculated from all poses for each robot arm are shown, with the mean value represented by a black dot. In the box plot, the horizontal line indicates the median value, while the top and bottom edges represent the standard deviation.
  • Figure 5: The differences between poses are illustrated by data points connected with red and blue lines, representing positional and rotational deviations, respectively.
  • ...and 6 more figures