Lucy Fothergill

Research Topic: Coverage measure and navigation strategies for robotic colonoscopy: Fusing machine learning and robotics to enhance diagnosis and treatment.

Supervisors: Prof Pietro Valdastri, Dr Duygu Sarikaya, Dr Dominic Jones.

About Lucy: I graduated from Lancaster University in 2022 after completing an integrated masters degree in Mathematics and Statistics. In my dissertation project I investigated the use of the Exp3 algorithm and adversarial bandits as a way of solving the multi armed bandit problem.

Project Description: This project is focused on vision-based 6 degree-of-freedom surgical tool pose estimation. Currently, the 6D pose (position and orientation) of the end effector of a surgical robotic arm is estimated using kinematic equations, which can lead to compounded joint angle errors. Without highly precise pose estimation, certain repetitive surgical tasks cannot be automated as risk is too high and consequences can be fatal. We aim to estimate 6D pose using vision-based methods such as CNNs, solely from RGB images and 3D CAD models of the tools. Ultimately, the goal is to combine our work with others’ from the STORMLab and make steps towards automated surgical procedures.