Scientists have proposed that nuclear power plants could be decommissioned in the future using teams of autonomous robots called SMuRF.
The development of the SMuRF system, acronym for Symbiotic Multi-Robot Fleet, is being carried out by engineers from the University of Glasgow, the University of Manchester, Bristol Robotics Laboratory and Heriot-Watt University.
This system offers an approach to allowing wheeled, four-legged, and aerial robots to collaborate and execute tasks that would be difficult or disruptive for humans if they attempted to perform them individually.
Instead, a single human supervisor can remotely observe the actions of the robots, who share sensor data with each other, combining their skills to achieve results that far exceed the capabilities of a single machine.
SMuRFs could provide authorities, regulators and industry with a safer and more efficient method of monitoring nuclear facilities, while opening up new opportunities for the maintenance of engineering infrastructure in challenging environments such as offshore wind platforms.
In a recent paper titled “Lessons Learned: Symbiotic Autonomous Robot Ecosystem for Nuclear Environments,” published in the journal IET Cyber-Systems and Robotics, researchers detail the successful implementation of the SMuRF in a practical demonstration conducted at the Robotics Collaboration. and Artificial Intelligence (RAICo) in Cumbria.
RAICo is a collaboration between the United Kingdom Atomic Energy Authority (UKAEA), the Nuclear Decommissioning Authority (NDA), Sellafield Ltd and the University of Manchester.
During the demonstration, the SMuRF successfully completed an inspection mission at a simulated radioactive storage facility, facing challenges similar to those encountered in real nuclear power decommissioning environments.
The robots’ ability to collaborate is the result of a sophisticated computing system developed by the researchers, called a “cyber-physical system, or CPS.”
The CPS has the ability to communicate with up to 1,600 sensors, robots and other physical and digital assets in near real time. In addition, it enables collaboration between robots with very diverse capabilities and operating systems, effectively updating the human operator.
Likewise, the collection and processing of data by the CPS makes it possible to create a 3D digital twin of a real physical space. This allows the SMuRF to navigate and carry out tasks with minimal supervision, while providing human operators with a wealth of data via a digital dashboard specifically designed to help the SMuRF make informed decisions when necessary. Human operators also have the ability to take direct control of robots as needed.
The robots’ combination of skills allowed them to complete a series of tasks commonly associated with radiation monitoring around nuclear sites, known as post-operational cleanup.
The robots worked together to map the environment, generating a 3D digital twin of the space through the use of their built-in sensors. This mapping was complemented with additional data from an aerial drone controlled by a human operator.
Daniel Mitchell, from the James Watt School of Engineering at the University of Glasgow and lead author of the paper, commented: ” The robots we programmed and designed in this SMuRF prototype each have their own unique abilities and limitations, as well as different operating systems. “.
” Humans will still be needed to supervise and direct the robot fleet, but their high level of autonomy could help keep people safe by allowing them to interact with the robots from their desks rather than visiting workplaces .”
David Flynn, Professor of Cyber-Physical Systems at the University of Glasgow, is a co-author of the paper. Professor Flynn added: ” These types of autonomous robotic fleets have great potential to perform a wide range of dangerous, dirty, boring, distant and expensive jobs .”
Don’t miss any of our posts and follow us on social media!