Facilitating laboratory automation using a robot with a simple and inexpensive camera detection system.

Area of Science:

• Bioanalytical Research
• Laboratory Automation
• Robotics

Background:

• Smaller labs face barriers to adopting advanced laboratory automation due to resource and expertise limitations.
• Complex bioanalytical methods further challenge efficient laboratory operations.

Purpose of the Study:

• To develop an accessible and cost-effective robotic-arm-based camera detection system for bioanalytical research.
• To simplify laboratory automation for smaller research facilities with limited resources.

Main Methods:

• Utilized a robotic arm equipped with a camera detection system and two software applications.
• Implemented fiducial markers (Augmented Reality University of Cordoba - ArUco) for object detection.
• Developed a 3D digital environment model for robot navigation and a deep learning model for digital display recognition.

Main Results:

• Achieved automated computer-aided design (CAD) for robot arm navigation using ArUco markers and OpenCV.
• The deep learning model for digital display recognition demonstrated an in-house error rate of 1.69%.
• The system leverages low-cost hardware and open-source software, making it accessible to smaller research labs.

Conclusions:

• The developed system provides an affordable and effective solution for integrating robotic arms into bioanalytical workflows.
• This approach enhances reproducibility and efficiency in scientific research by reducing programming complexity.
• Facilitates broader adoption of laboratory automation in smaller research settings.