Learning to Automate Surgical Tasks from Demonstration

Summary

Automating repetitive surgical tasks such as surgical suturing, endoscope control or tissue retraction can increase patient safety, efficiency, precision, and reproducibility in operating theatres as well as optimize operating room use times, and better manage resources. While studies on automating surgical tasks are proposed in the literature, most of these solutions require path-planning and defining environment-specific hand-crafted behaviours based on domain knowledge. Therefore, these approaches fail to scale. Reinforcement learning (RL) approaches, on the other hand, have exhibited high scalability in learning diverse control policies, but typically require extensive data collection to solve a task. Reinforcement Learning from expert demonstrations can narrow down exploration and help to achieve efficient training of models.

The topics for this project will focus on:
- Developing a reinforcement learning policy to learn how to automate surgical
tasks from expert demonstrations
- Demonstrating the capabilities of the reinforcement learning model in real-
world research platforms (in simulation and/or real set up (Da Vinci® Surgical
System

The project will allow exploration of different ideas and topics, and a chance to work with collaborators from different disciplines (computer science, robotics, medicine).

A good knowledge of fundamental topics in machine learning and deep learning, along with strong coding skills is expected. Experience with advanced deep learning topics, particularly deep reinforcement learning, and familiarity with simulation environments for robotics is preferred.

Applicants to research degree programmes should normally have at least a first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline. The criteria for entry for some research degrees may be higher, for example, several faculties, also require a Masters degree. Applicants are advised to check with the relevant School prior to making an application. Applicants who are uncertain about the requirements for a particular research degree are advised to contact the School or Graduate School prior to making an application.

The minimum English language entry requirement for research postgraduate research study is an IELTS of 6.5 overall with at least 6.5 in writing and at least 6.0 in reading, listening and speaking or equivalent. The test must be dated within two years of the start date of the course in order to be valid. Some schools and faculties have a higher requirement.