Large Language Models in Intelligent Robotic Systems for Environment Clean Up

Large Language Models in Intelligent Robotic Systems for Environment Clean Up

If you are interested in robotics and have strong programming and software engineering skills, this could be a project for you.

Supervision will be provided jointly by the Department of Computer Science at the University of York and the UK Atomic Energy Authority’s Centre for Remote Applications in Challenging Environments (UKAEA RACE).

The project is part-funded by RACE. There is an opportunity to be based in RACE’s offices for approximately two weeks per year, and successful completion of this project could lead to exciting career prospects with the UKAEA.

This opportunity is open to applicants paying UK (Home) fees wishing to study on a full-time, on campus basis only. The successful candidate will start in September 2024.

Sorry, this opportunity is not available to international students, or to students wishing to study on a part-time and/or distance learning basis.

About the project

This project is concerned with testing of robots that can autonomously clean up areas where we can find hazardous materials, humans, or both. A challenge is the design and verification of systems that have a vision component to identify particular materials or humans. Use of a Large Language Model (LLM) is a promising prospect, but raises concerns about the reliability of a system that depends on such a component. To allow a robot to operate hazardous materials or interact with humans, we need to trust that robot. Potential consequences if they fail in their operation can range from wasted time and materials, to more serious incidents.

We will apply state-of-the-art technology for modelling, simulation and testing for analysis and verification of robots that can be trusted to work autonomously. First, we will consider existing technology to evaluate the limits of what can be achieved with existing robots and existing software engineering techniques. Second, we will consider advanced testing techniques that support evaluation of designs of systems that use an LLM. Contributions of the work will span from improvements to automation to novel techniques for testing. Our challenge is to enable and promote development approaches that provide evidence that the robot can be trusted to work with sensitive materials and experiments, and potentially around humans.

The successful candidate will benefit from training provided by the Department of Computer Science at the University of York. This will cover topics such as security, research management and leadership, collaborations, employability, public engagement, and communication. As part of a cohort of postgraduate researchers in the Centre for Doctoral Training on Autonomous Robotic Systems for Laboratory Experiments (ALBERT), the successful candidate will regularly meet with students working on similar topics.

Financial benefits

This opportunity is fully funded for up to 3.5 years by RACE and the University of York.

• You’ll receive a tax-free annual stipend of £19,237 for 2024/25, paid in regular instalments. The amount of the stipend usually increases each year in line with inflation.
• Your annual tuition fees will be paid.
• Funding will be available for attendance at relevant events and conferences, and for project-related consumables.

How to apply

• Please submit your application online. Select the option for full-time study, starting in September 2024. 
• Please quote the project title ‘Large Language Models in Intelligent Robotic Systems for Environment Clean Up’.
• As this studentship is for a specific project, you do not need to provide a research proposal.

About the University of York

Become part of our vibrant community and contribute to inspirational and life-changing research:

• We are a prestigious Russell Group university with a global reputation for world-leading research.
• The University is ranked joint 10th in the UK for the quality of our research in the Times Higher Education (THE) Research Excellence Framework (REF 2021)
• The Department of Computer Science is a UK top ten research department. All our research is rated 3* or higher for research impact and research environment in the REF 2021 results
• Our core research strengths reflect our expertise in the field of computer science. Explore our research groups
• You’ll be supported every step of the way to ensure you can make an impact. Find out more about the York Graduate Research School

More reasons to choose York

About RACE

RACE was founded in 2014 as part of the UKAEA’s Fusion Research and Development Programme to design and test robots for operating in challenging environments. UKAEA’s wider mission is to lead the commercial development of fusion power and related technology and position the UK as a leader in sustainable nuclear energy.

Based at its HQ near Oxford and a new technology facility in South Yorkshire, UKAEA operated a Joint European Torus (JET) fusion experiment on behalf of scientists from 28 European countries. It is now leading the decommissioning of the JET machine. UKAEA is keeping the UK at the forefront of fusion as the world comes together to build the first powerplant-scale experiment, ITER – one step away from the realisation of fusion as a low-carbon energy source. UKAEA is also involved in future fusion demonstration powerplant design activities such as DEMO and the UK’s future STEP powerplant.

References

• A. L. C. Cavalcanti, W. Barnett, J. Baxter, G. Carvalho, M. C. Filho, A. Miyazawa, P. Ribeiro, and A. C. A. Sampaio. RoboStar Technology: A Roboticist’s Toolbox for Combined Proof, Simulation, and Testing, pages 249–293. Springer International Publishing, 2021.
• W. Barnett, A. L. C. Cavalcanti, and A. Miyazawa. Architectural Modelling for Robotics: RoboArch and the CorteX example. Frontiers of Robotics and AI, 2022.
• Z. Attala, A. L.C. Cavalcanti, and J. C. P. Woodcock. Modelling and verifying robotic software that uses neural networks. In E. Ábrahám, C. Dubslaff, and S. L. T. Tarifa, editors, Theoretical Aspects of Computing, pages 15–35. Springer, 2023.
• A. L. C. Cavalcanti, J. Baxter, R. M. Hierons, and R. Lefticaru. Testing Robots using CSP. In D. Beyer and C. Keller, editors, Tests and Proofs, pages 21–38. Springer, 2019.
• A comprehensive list of publications is provided on the web pages for RoboStar