Failure and recovery of robotic chemists for computationally-guided materials discovery

Description

A fully funded PhD studentship is available in the area of robotics/automation in a chemical laboratory, as part of a prestigious international Synergy Grant, funded by the European Research Council. The project 'Autonomous Discovery of Advanced Materials' (ADAM), aims to revolutionise the way that new materials are discovered by combining computational simulation, robotics, and materials synthesis.

To achieve the ADAM project goals, a multidisciplinary team that comprises researchers with expertise in chemistry, robotics, machine learning, and computational chemistry is required. We would like to appoint a PhD student who can develop autonomous robotic methods deployed in chemical laboratories, with a particular focus on intelligent methods on failure detection and recovery. The project will be based in the materials discovery research group led by Prof. Andy Cooper (https://www.liverpool.ac.uk/cooper-group/). You will be part of a multi-disciplinary team that includes collaborators at the University of Southampton and Rostock University. Through these collaborations, you will interact with computational chemists, synthetic chemists, and also engineers and computer scientists developing the use of robots in materials chemistry laboratory.

The key objectives for this project are:

  • to develop novel methods for robotic (mobile) manipulation in chemistry laboratory environments to increase overall safety in the presence of human collaborators;
  • to study how multimodal sensory fusion and probabilistic learning-based methods can be used to detect and recover from failures stemming from laboratory environmental disturbances;
  • to find optimal ways to adopt robot learning in safety-critical environments such as real-world material discovery labs.

We are looking for candidates with:

  • skills in programming (C/C++/Python/Java), using middleware (ROS), ML frameworks (PyTorch/Tensorflow/Jax), knowledge of git;
  • research interests in reinforcement learning, self-supervised learning, and/or skill learning with failure recovery;
  • an enthusiasm for research, multidisciplinary collaboration and tackling challenging problems through teamwork;
  • an interest in deploying algorithms on real robotic platforms;
  • MSc in CS/Robotics/AI, but we would also consider exceptional Physical Science students with solid programming skills.

You do not need to have a strong background in chemistry, but willingness to learn basic concepts, ontologies and definitions is a requirement.

The position is available immediately.

Entry requirements

Applicants should hold, or expect to obtain, a good degree (equivalent to a UK First or Upper Second Class degree) in CS/Robotics/AI or other relevant discipline.

If you wish to discuss any details of the project informally, please contact Dr Gabriella Pizzuto, Senior Research Fellow in robotics (email: Gabriella.Pizzuto@liverpool.ac.uk) or Dr Zuzana Oriou, Cooper Group Research Manager (email: z.oriou@liverpool.ac.uk).

https://www.liverpool.ac.uk/study/postgraduate-research/how-to-apply/

Please include Curriculum Vitae, Two reference letters, Degree Transcripts to date

Please ensure you quote the following reference on your application: Reference CCPR059 - Failure and recovery of robotic chemists for computationally-guided materials discovery

Availability

Open to students worldwide

Funding information

Funded studentship

The award will pay full tuition fees and a maintenance grant for 3.5 years. The maintenance grant will be at the UKRI rate, currently £17,668  per annum for 2022-23, subject to possible increase. The award will pay full home tuition fees and a maintenance grant for 3.5 years. Non-UK applicants may have to contribute to the higher non-UK tuition fees.

Supervisors