James Garforth (cohort rep)
The aim of our work is to improve robotic navigation techniques for use in natural environments, such as forests. It is undertaken in collaboration with Geoscientists performing large scale forest monitoring, as well as Neuroscientists and Ecologists tracking animals for behavioural studies.
The common environments for the deployment of visual Simultaneous Localisation and Mapping (SLAM) systems are well-organised and structured by humans, so the solutions produced do not necessarily perform well with complex, dynamic natural scenes. We are investigating the limitations of the state of the art in this difficult setting and developing improvements to address them.
Research interests: Vision, Navigation, Localisation, Mapping, Reconstruction, Bio-inspired Robotics