Generative AI and flexible cognitive robots for discrete manufacturing

Background:

Current Human-Robot collaborations are driven by kinaesthetic teaching which requires humans to guide the robot end effectors to do a task. The above technique often works well in environments that are rigid and well structured. However, in situations where the task is often varying and the environment can change, these strategies fail. Furthermore, one of the paradigms that have been created by the machine learning community is the Reinforcement Learning paradigm. Though state of the art reinforcement learning algorithms have given impressive results, they often have shortcomings when the variation in the environment or task increases. On the other hand, natural cognition in humans provide us with a lot of food for thought in creating flexible, resilient and robust artificial intelligent systems.

Aim:

The aim of this PhD is to develop new human cognition inspired algorithms (such as Generative AI) that can learn how humans complete manufacturing tasks while dealing with variations in the environment as well as how they transfer learnt skills between tasks to solve problems. This would involve collaborating with our partners in Psychology, Computer Science, the Advanced Manufacturing Research Centre at Sheffield as well as the Institute of High Performance Computing in Singapore (https://www.a-star.edu.sg/).

Research Environment:

Our academic and research staff are world leaders in the study of robotics, signal processing and intelligent systems. This project is based in the autonomous Systems and Robotics Research Group which carries out world leading research in autonomous processes and autonomous robotic systems by investigating key research problems of sensing, control, decision making and system integration. The collective competence of the group is unparalleled in the UK and covers most essential topics of this area: design of autonomous industrial robots, condition monitoring for fault tolerant autonomous systems, biologically inspired principles of sensing and control, international standards for autonomous robots, self-assembling robotic systems and swarms, advanced software architectures for decision making, autonomous hybrid systems modelling, formal verification, and distributed and parallel control systems.

Period of Study:

This is a 4 years A*STAR ARAP programme (https://www.a-star.edu.sg/Scholarships/for-graduate-studies/a-star-graduate-scholarship-singapore). Submission of thesis is expected by the end of month 48 at the very latest. It is expected that students will spend approximately half of the programme in Sheffield and half in Singapore, with the distribution of time and research activity to be determined by the supervisory team at the outset as part of the proposal.

Funding Notes

Award details:

For each student admitted to the 4-year programme, A*Star will provide the following financial support, whilst the student is in Singapore:

 Monthly stipend of S$2,700

 Monthly housing allowance of S$600

 One-time airfare grant of S$1,500

 One-time settling-in allowance of S$1,000

 One-time IT allowance of S$800 

 Medical insurance 

 Conference allowance

Whilst in Sheffield, students receive fees and stipend at the UKRI rate. Currently these are £4,712 fees and £18,622 stipend per annum, but will be slightly higher for 2024/25.

Eligibility of students:

 Applicants should have, or expect to achieve, a first or upper second class UK honours degree (or equivalent qualifications gained outside the UK) in an appropriate STEM area of study.

 Applicants should be registering on their first year of study with the University for 2024/25 on an eligible programme of doctoral study.

 Candidates must qualify for Home fee status.