Hand-Eye Calibration Research & Experiments

This repository contains my personal experiments and research focused on improving hand-eye calibration for robotic systems. It combines traditional geometric methods, quadrilateral analysis, and exploratory machine learning approaches.

Project Overview

• Quadrilateral Analysis: Python scripts for detecting and analyzing quadrilaterals in images to aid in calibration.
• Hand-Eye Calibration: Experiments to refine robot-camera alignment and improve precision in manipulation tasks.
• Machine Learning Experiments: Preliminary tests using AI techniques to enhance calibration accuracy and automate feature detection.

Features

• Scripts for detecting geometric features and computing transformations.
• Automated pipelines to process images and calculate calibration parameters.
• Exploration of ML-based approaches for improving hand-eye calibration workflows.
• Modular structure to facilitate further research and experimentation.

Technologies Used

• Python – Core language for scripting and analysis.
• OpenCV – Image processing and feature detection.
• NumPy / SciPy – Mathematical computations and transformations.
• Machine Learning libraries – For exploratory experiments (e.g., scikit-learn, PyTorch, or TensorFlow).

Notes

• This repository is primarily a research and experimental project.
• The focus is on testing and improving hand-eye calibration through a combination of geometry and machine learning.