This project aims to use machine vision (computer vision) to detect objects and improve underwater localisation for an underwater robot.

You'll develop machine vision algorithms to help our new underwater robot (ROV - remotely operated vehicle) to detect objects underwater and to understand where it is in relation to those objects (localisation). This will involve some simulations in Matlab/Simulink, some coding in ROS, and the opportunity to apply your code to the BlueROV owned by the School. This is a unique opportunity to do applied machine vision for an underwater application.

School

Mechanical and Manufacturing Engineering

Research Area

Robotics | Underwater robotics | Machine vision | Computer vision | Object detection | Localisation and mapping

I have weekly 30-minute meetings with my thesis and ToR students, as well as a bi-weekly group meeting where we share progress and help each other with debugging or other thorny problems.

  • Poster showing the aims and outcomes of the project
  • A visual localisation software stack that improves the ROV's underwater localisation
  • An object-detection program that has been deployed to the ROV
Senior Lecturer in Robotics and Mechatronics Will Midgley
Senior Lecturer in Robotics and Mechatronics