Our research focuses primarily on four themes which relate to the implementation of SLAM across multiple environments.
- Marine robotics: we address the challenges of localization and mapping in the underwater environment.
- Theoretical foundations: we tackle fundamental problems in SLAM that are applicable across domains such as robustness, scalability, consistency, map representation and others.
- Dense mapping: our work in this area focuses on object-based representations and how these can be used to aid localization.
- Visual SLAM: We also have ongoing work based on using only a camera (and sometimes an IMU) to perform Visual SLAM both in indoor environments and also outdoors for applications such as driverless cars.