New rugged robots will aim to think and act for themselves in the most dangerous places on earth

June 27, 2022

(News from Nanowerk) A new generation of smart robots is being developed at the University of Manchester as part of an ambitious R&D program to help the UK maintain its leadership in automation technologies,

These new artificial intelligence (AI) powered machines will be designed to think and act for themselves in some of the most dangerous and challenging places on the planet – and beyond. These robots will be challenged to perform work too dangerous for humans,

“Hot robotic” systems were originally designed to operate in radioactive environments found in decommissioned nuclear reactors. But future missions for this type of supermachine will include deployment in nuclear fusion power, the offshore energy sector, agriculture, and even outer space.

As part of an ambitious R&D program aimed at maintaining the UK’s leadership in robotic technologies, experts in Manchester are applying AI technologies to ‘hot robotics’ as they will increasingly need act independently of human operators when entering a range of hazardous areas to perform highly complex operations. Tasks.

Hot Robotics: Investigating the effects of circumventing an armored drone in the University of Manchester’s High Voltage Laboratory. (Image: The University of Manchester)

A significant challenge in the nuclear industry is to improve the autonomy of robots so that the technology can be used to ensure safer, faster and cheaper dismantling of old power stations and other radioactive installations at sites such as Sellafield and Dounrey.

To address this challenge, the Robotics and AI Collaboration (RAICo) was established in Cumbria as a joint research program between the University of Manchester, UK Atomic Energy Agency (UKAEA), Sellafield Ltd, Nuclear Decommissioning Authority and the National Nuclear Laboratory. . The aim is to develop advanced robotics and artificial intelligence solutions and transfer them to sites in the domain of the Nuclear Decommissioning Authority in the United Kingdom.

In addition to supporting the nuclear decommissioning industry, RAICo will also provide a pilot project for the development and application of sophisticated robotic systems in other sectors – a recent report estimates that the total UK market size for autonomous robotic systems will reach nearly £3.5 billion by 2030.

Academic engagement for RAICo is led by Professor Barry Lennox and his team from the University of Manchester. This group leads the RAIN Cluster (Robotics and Artificial Intelligence for Nuclear) and are also part of the Manchester Robotics and AI Center.

“The inclusion of AI is because the goal is to develop automated systems that can operate much more efficiently than if operated by people,” explained Barry Lennox.

“At RAICo, we seek to improve the operation of remote handling and inspection systems. We help Sellafield and other nuclear end users develop the next generation of remote surveying and handling equipment so they can improve their operations.

Professor Lennox explained that Manchester is a world leader in the design and development of autonomous systems through the application of artificial intelligence technologies such as machine learning to dramatically improve robotic systems.

The Manchester-led RAIN group has developed its expertise after pioneering a series of resilient robotic systems to carry out work at many of the UK’s decommissioned nuclear power stations – performing work too dangerous for humans .

Professor Lennox explained: “The ‘hot’ prefix was introduced because we were interested in deploying robots in active environments – but we are now looking to extend hot so that it can refer to more general applications. , including space, agriculture and offshore”. sectors. Many of the challenges are similar, although the bots may end up looking a bit different.

Improving the AI ​​capability of these machines is the next big challenge for his team, Professor Lennox added. “AI introduces many additional issues related to ensuring that AI will do what we expect it to and will not cause harm or endanger human safety.”

Beyond nuclear dismantling, the Manchester-led RAIN team is also establishing joint work programs with the UK Atomic Energy Authority to support them in the development of robotic systems for nuclear fusion reactors.

Rob Buckingham, Director of the UK Atomic Energy Authority and Head of their RACE (Remote Applications in Challenging Environments) centre, said: “The next generation of robotics will be essential for the delivery of fusion energy and, recognizing that, we intend to collaborate extensively with the best, such as the Manchester Robotics Research Group.

“Working with Manchester on the RAIN program has reaped huge benefits for both parties, so let’s do more.”

Finally, the Manchester researchers advise UK policy makers and energy sector leaders on the safe development of robotic and autonomous systems for working in harsh environments.

Professor Michael Fisher, Dr Louise Dennis and Dr Matt Luckcuck recently presented recommendations in their white paper (“Principles for the development and assurance of autonomous systems for safe use in hazardous environments“; PDF), calling for greater transparency and easier verification in autonomous decision-making processes, especially for systems used in situations where there is a risk to human well-being.

Comments are closed.