About the project
During this project you will undertake research into vision based localisation algorithms and systems that would allow resource constrained robots and mobile devices to understand their position in an environment over long periods.
Visual place recognition is a critical component of many autonomous navigation systems, including autonomous vehicles, drones and computer vision systems. Improving camera hardware offers potential for deep learning based techniques to improve these systems.
Your focus will be to help robots become more autonomous in building and maintaining their map of the environment, so that they can collaborate and become more useful for humans. The PhD we will focus on investigating approaches that are suitable for small unmanned aerial vehicles with restricted payload onboard and as a result, limited computational capabilities.
Inspired by the need for lightweight and effective techniques for VPR onboard small aircraft, this project will investigate novel methods capable of coping with the variability of places when experienced from such small aircraft, while bounding the onboard computation effort for real-time operation.
