Related Experiment Video
Updated: Jul 2, 2025
09:41
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
Published on: April 21, 2023
1.6K
Submillimeter-Accurate Markerless Hand-Eye Calibration Based on a Robot's Flange Features
Velibor Đalić1, Vedran Jovanović1, Petar Marić1
1Faculty of Electrical Engineering, University of Banja Luka, Patre 5, 78000 Banja Luka, Bosnia and Herzegovina.
Sensors (Basel, Switzerland)
|February 24, 2024
Summary
This study introduces a novel markerless hand-eye calibration method for robots, achieving submillimeter accuracy with fewer calibration points. The new approach significantly enhances precision and efficiency in vision-guided robotic applications.
Area of Science:
- Robotics
- Computer Vision
- Calibration Techniques
Background:
- Accurate hand-eye calibration is crucial for vision-guided robotics.
- Existing methods often require markers and complex error compensation.
Purpose of the Study:
- To develop a novel markerless hand-eye calibration approach.
- To improve accuracy, flexibility, and efficiency in robot-sensor transformation estimation.
Main Methods:
- Utilizing the robot's tool center point (TCP) as a reference.
- Estimating TCP coordinates from the robot's flange point cloud using geometric features.
- Developing a new algorithm for automatic flange feature estimation (3D circle fitting, least squares, nearest neighbor).
Main Results:
- Achieved submillimeter accuracy in robot-3D scanner transformation estimation.
- Improved calibration accuracy by approximately four times compared to state-of-the-art methods.
- Reduced the number of required robot flange positions by approximately 40%.
Conclusions:
- The proposed markerless hand-eye calibration method offers superior simplicity and precision.
- It enables highly accurate calibration without error compensation, even with minimal data.
- This advancement streamlines calibration for diverse robotic applications.
