From Factory to Desktop.

Building Machines That Can See.

For more than four decades I worked in manufacturing, where I witnessed the introduction of robotics and computer vision systems that transformed quality control. Today, I’m continuing that journey in my workshop, exploring robotics, computer vision, artificial intelligence and embedded systems through small practical projects.

View The Projects

The Projects

My projects explore different aspects of robotics, computer vision, artificial intelligence and automation through hands-on experimentation. Some begin as simple experiments and evolve into increasingly capable machines. Others are inspired directly by the industrial technologies I encountered during my career. Each project is an opportunity to learn, build, test and understand how individual technologies can work together.

Pit Droid

Robotics, Vision & AI

Originally built as a robotics project, the Pit Droid has evolved into a platform for experimenting with computer vision, AI, speech recognition, text-to-speech and Raspberry Pi control.

It provides a practical way to explore individual technologies and see how they can be combined to create a more capable machine.

desktop bottle inspection conveyor concept

Desktop Vision Inspection

Machine Vision & Industrial Automation

This project explores how the principles of automated industrial inspection can be recreated on a desktop scale.

Glass bottles travel along a small conveyor where they are detected and analysed using computer vision and AI. The system demonstrates principles found in modern production lines, including automated inspection, defect detection, object tracking and data-driven decision making.

From Experiment to Application

My projects are connected by a common goal: understanding how machines can see, interpret and respond.

The Pit Droid provides a platform for experimenting with robotics, computer vision, AI and human-machine interaction. The desktop inspection system takes those ideas into a more structured industrial automation problem.

Each project builds on the lessons learned from the previous one, turning individual experiments into a broader exploration of intelligent machines.

Desktop Vision Inspection

Development Roadmap

Modern manufacturing relies on automated inspection systems to identify defects consistently, accurately and at production speeds.

This project explores how those same principles can be recreated on a desktop scale using robotics, computer vision and artificial intelligence.

The aim is to develop the system incrementally, introducing new inspection capabilities as the project evolves.

Each Engineering Log documents the latest improvements, bringing the desktop inspection system a little closer to the type of automated quality control found on industrial production lines.

Computer Vision

Cap/label missing
Fill level
Bottle count
Bottle tracking
Colour verification
Position/orientation

AI Inspection

Defect detection
Damage classification
Learn from new defect examples
Improve accuracy over time

Technologies

Projects bring together several engineering disciplines that are often developed separately. By combining these, I explore how these technologies can work together to create machines that can sense, interpret and respond.

Mechanical Design

The projects are designed using CAD software before being manufactured using 3D printing and standard engineering components. This approach allows ideas to be developed quickly, tested, refined and modified as the projects evolve.

Embedded Systems

A Raspberry Pi acts as the central controller for many of my projects, coordinating cameras, sensors, motors and software. Embedded systems bring together the hardware and software that allow machines to operate as integrated systems.

Robotics

Robotics provides the physical movement and interaction within my projects, from the Pit Droid’s mechanisms to the conveyor used to move bottles through the inspection process.

Computer Vision

Cameras provide machines with the ability to see. Computer vision software analyses images to identify objects, detect features, measure characteristics and extract information that would otherwise require manual inspection.

Artificial Intelligence

Artificial intelligence complements traditional computer vision by recognising more complex patterns and variations. AI is explored where it can provide capabilities that are difficult to achieve using fixed rules alone.

Development Log #5

Identifying bottles using canny edge analysis.

The Engineering Log documents the experiments, discoveries, problems and improvements made throughout the projects.

About Me

Throughout more than four decades in manufacturing I worked in environments where quality, consistency and continuous improvement were central to daily operations.

During that time I witnessed production lines evolve through the introduction of robotics, computer vision and increasingly intelligent automation. These technologies improved repeatability, increased inspection capability and helped manufacturers achieve higher standards of quality.

This website documents my personal exploration of those same ideas through practical engineering projects, combining software, electronics, mechanical design and machine vision to better understand the technologies shaping modern manufacturing.

Why These Projects ?

Glass manufacturing has been a significant part of my professional career, making it a natural choice for demonstrating automated inspection.
Industrial automation has always fascinated me because it brings together engineering disciplines that normally exist separately. A single inspection system combines mechanics, electronics, software, optics, artificial intelligence and data analysis into one integrated solution.
Building desktop-scale systems allows these technologies to be explored, understood and demonstrated without the scale or cost of industrial equipment.