Active Engineering Physics & Astronomy

EPSRC Centre for Doctoral Training in Robotics and AI for Net Zero

In plain English

AI plain-English summary

The UK is training a new generation of robotic systems engineers to inspect, maintain, and decommission wind turbines, nuclear reactors, and other clean energy infrastructure. This Centre for Doctoral Training addresses a critical skills gap: advanced robotics in the energy sector currently contributes only £0.6 billion to the UK economy, but could deliver £23 billion by 2035 if technological and cultural barriers are overcome. The problem is that robots deployed in hazardous, high-value environments require highly skilled workers who currently do not exist in sufficient numbers. If successful, the programme will produce engineers who can automate dangerous maintenance tasks—reducing human exposure to radiation or working at height—and lower the costs of keeping renewable and nuclear assets running. The research focuses initially on operations, maintenance, and decommissioning, then expands to design, logistics, construction, and recycling. Each cohort of PhD students tackles an industry-defined challenge, with the first focused on autonomous environmental interactions in constrained spaces. The centre aims for 50–75% of graduates to enter robotics industries, and expects to spin out at least five companies and submit five fellowship proposals.

View original technical description
The EPSRC Centre for Doctoral Training in Robotics and AI for Net Zero (RAINZ CDT) is a new CDT in Robotics and AI (RAI) which will train and develop the next generation of multi-disciplinary robotic systems engineers. These engineers will be trained in both research and commercialization of RAI, and will help revolutionise lifecycle asset management of critical infrastructure in support of the UK's Net Zero Strategy. The research focus of the CDT will be on how RAI can provide step-changes at each stage of the lifecycle of Net Zero energy generation assets through the adoption of new innovative technologies, workflows, etc., which will increase safety, reduce costs, and enhance the overall viability of such systems. Initially there will be a focus on the use of RAI in operations & maintenance, through inspection, maintenance, and repair activities, and the decommissioning of infrastructure in renewables (wind, solar, geothermal, tidal, hydrogen) and nuclear (fission and fusion). The research in the CDT will also support the decarbonization of these phases for assets across a diverse range of sectors. The scope of research will expand through the lifetime of the CDT to address the other lifecycle phases: Design, Logistics, Construction and Recycling. The RAINZ CDT is a partnership between three of the UKs leading Universities and represents an unparalleled critical mass of complimentary end-to-end robotic systems research capabilities, facilities and sustainability expertise. It has been co-created with leading industrial partners in the Net Zero sector to address the national challenge that "advanced robotics requires highly skilled workers such as engineers, leading to a need to train new workers". RAI used in the energy sector are often deployed into complex, hazardous and high-value environments, but significant barriers, both technological and cultural, are limiting its estimated economic yield to £0.6B gross value added (GVA) by 2035 instead of a potential £23B GVA. Overcoming these barriers is a key focus of this CDT. In addition to addressing a vital national need, it will support local initiatives, such as the Blenheim Palace Solar Farm in Oxford. It will also support the levelling-up agenda across the three host cities, as well as in West Cumbria through the Robotics and AI Collaboration (RAICo) facility, which has been established to build an innovation pipeline for new RAI solutions in both the nuclear and other sectors. The RAINZ CDT will adopt an innovative cohort training and research model to ensure graduates are not only subject matter experts, but have highly valuable skills in teamworking, multi-disciplinary systems integration, industrial engagement, and commercialisation. Each cohort will be recruited to conduct research directed towards an industry co-created cross-sector challenge which will evolve for each new cohort. Cohort 1's challenge will be Autonomous Environmental Interactions in Constrained Environments. PhD projects for each cohort will be co-created with industry to address gaps in enabling science and technologies through both fundamental and applied research. Robots are highly complex systems drawing on a diverse range of research areas. Whilst RAINZ students will undertake their own individual research, it will be significantly enhanced through collaborations with others. There will be annual research sprints where the cohort will come together to demonstrate elements of their research on industry defined demonstrator scenarios. The CDT will create an innovation pipeline that will produce high-quality, highly skilled and employable Robotic Systems Engineers with an aim that at least 50% - 75% of the graduates are employed in robotics industries. It has an ambition to have supported the creation of 5 spin-out companies and the submission of at least 5 Fellowship proposals.

View the original record at the funder ↗

Researchers

David Flynn (Co-Investigator)Guido Herrmann (Co-Investigator)Guodong Zhao (Co-Investigator)Lina Mohjazi (Co-Investigator)Louise Dennis (Co-Investigator)Maria Sharmina (Co-Investigator)Maurice Fallon (Co-Investigator)Nick Hawes (Co-Investigator)Olaoluwa Popoola (Co-Investigator)Perla Maiolino (Co-Investigator)

Related Research

Grants with similar aims, by meaning.

EPSRC Centre for Doctoral Training in Process Industries: Net Zero (PINZ CDT)
EPSRC Centre for Doctoral Training in Robotics and Autonomous Systems (CDT-RAS)
EPSRC Centre for Doctoral Training in Robotics and Autonomous Systems (RAS) in Edinburgh
EPSRC Centre for Doctoral Training in Engineering Hydrogen Net Zero
EPSRC Centre for Doctoral Training in Green Industrial Futures

Original classification

Training Grant

Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.