A Fiducial-Marker-Based Localization Method for Automotive Chassis Bolt Assembly

Area of Science:

• Robotics and Automation
• Computer Vision
• Mechanical Engineering

Background:

• Accurate localization of automotive chassis bolts is critical for automated assembly.
• Challenges include non-uniform illumination, limited space, and occlusions in industrial environments.
• Existing methods struggle with robustness and precision.

Purpose of the Study:

• To propose a fiducial marker-based localization method for automotive chassis bolts.
• To enhance the accuracy and robustness of bolt localization in industrial settings.
• To meet the precision requirements for automatic bolt assembly.

Main Methods:

• A concentric ring-shaped fiducial marker is used on the assembly wrench.
• Region of Interest (ROI) extraction via HSV color space segmentation.
• Improved Retinex-based image enhancement for robustness.
• Optimized ellipse fitting using the Leitz criterion.
• Spatial localization using vanishing lines and ellipse parameter matrix to calculate the projected center.

Main Results:

• The improved image enhancement significantly boosts ROI extraction accuracy.
• Optimized ellipse fitting demonstrates higher accuracy and reliability.
• The method achieves high localization accuracy and strong robustness.
• Validated results align with theoretical bolt hole coordinates.

Conclusions:

• The proposed fiducial marker localization method effectively addresses industrial challenges.
• It offers high precision and robustness for automated automotive bolt assembly.
• The method meets practical requirements for industrial applications.