Pioneering autonomous underwater survey robots could revolutionise operations across all manner of hazardous environments.

AN ‘intelligent’ underwater autonomous survey robot fitted with sonar technology to detect and avoid obstacles so it can be used near critical infrastructure has been successfully showcased in a live demonstration.

Developed in a collaboration of firms from across the UK, the Autonomous Aquatic Inspection and Intervention (A2I2) robot successfully completed its nuclear-use case drop two trials at Forth’s Deep Recovery Facility in Cumbria.

Led by Rovco and supported by Innovate UK (under the Industrial Strategy Research Fund), alongside Forth, D-RisQ, the National Oceanography Centre (NOC), Thales UK and The University of Manchester, the pioneering R&D project’s goal is to develop underwater autonomous vehicles that can improve safety and reduce the challenges of operating in hazardous environments, such as in storage ponds on nuclear sites.

Representatives from nuclear power producer Sellafield Ltd and other end-users attended the successful demo at Forth’s test site in Maryport. Holding 1.2million litres of water, Forth’s wet test facility is one of the largest of its kind in the UK and enables businesses from a range of industries – including nuclear, oil & gas, marine and renewables – to carry out R&D, testing and demonstrations.

During a two-hour presentation and demo, attendees saw A2I2 successfully move autonomously through the pond, avoid collisions, locate items on the pond floor, and relay images that could be viewed, analysed and interpreted in real-time on screens nearby on dry land.

Ground-breaking artificial perception tech 

Rovco has been supporting each workstream with its ground-breaking, artificial perception tech, including 3D Computer Vision, Simultaneous Location and Mapping (SLAM), autonomous path planning and scene understanding using Machine Learning (ML). This Intelligent Data Collection System can be integrated onto any subsea vehicle to enhance its capability.

“The whole challenge of this particular project was removing people from hazardous and dangerous environments,” noted Gary Cross, Senior Robotics Engineer at Rovco. “One of the key things is increasing the distance between the operators and the environment they’re working in. And the easiest way to do that is to make the vehicle remote – remotely controlled and remotely operated,” he advised.

 

“Some of the challenges you have, of course, is that as you increase the distance between the operator and the tools which they’re using; you have increased latency and other challenges, which generally make it very difficult to operate,” he continued. “So, technology such as the advanced perception system and mapping capabilities enables us to use the autonomy to provide the appropriate systems to the pilots who can still be controlled in a safe and meaningful way within the pond.”

Joe Tidball, Innovations Manager at Rovco, said the most significant technology he had seen in the trials was the autonomous ability to recreate a scene that hadn’t been seen by the robot before. “The robots are able to go in with a sensor package – it’s got no prior knowledge of where it’s been before – and begin reconstructing that environment for future uses. It means that you don’t have to have a prior knowledge of the environment,” he told us. “This is fantastic in a decommissioning sense when you don’t necessarily know what is down there in the water. It means that you can start looking at removing people from what is a hazardous environment, putting them onshore, and making it safer and more efficient.”

Forth’s enabling Lilypad technology

Forth has incorporated sonar technology with the robot’s system to detect and avoid obstacles underwater to enable the robots to be used near critical infrastructure. Alongside this, the firm has developed an enabling Lilypad technology, which provides launch and recovery, recharging and high bandwidth communications for the ROV.

Forth’s Programme Manager Peter Routledge said afterwards that seeing things in a live demo is sometimes better than seeing a 3D image portrayed. “People were able to see and ask various questions about how the SLAM technology and the Lilypad technology are brought together to pick out assets on the bottom of the pond – so people can see the actual images on a live feed with no delay, and can make judgments in real time. That, in itself, portrays excellence through the technologies,” he remarked.

“You could then survey the same area in two months’ time and overlay the original image to see if you’ve removed the asset or if the asset is still there. That, to me, is one of the greatest developments of this demo,” Mr Routledge continued.

“We’ve demonstrated looking at the pond floor, but you could also use it on the pond wall, possibly for determining the length of radiation that’s in the pond wall. So, there’s various uses from the technology,” he advised, adding that with further development, this could become a single modular approach. “If somebody needed solely the LRE (last response engine) capability to stop things colliding in ponds, for example, then that’s one aspect that could be used if you were looking for wireless technology,” he added.

“The Lilypad and SLAM tech could also be used in their own ways,” he continued. “So, the actual estates that it could be used on are huge and that is just within the NDA (Nuclear Decommissioning Authority) estate. Then you could use it across Europe and then globally. The deliverables from this project, and the escalation, could be fantastic.”

Safety-critical software

Meanwhile, D-RisQ’s high-integrity, autonomous, decision-making, safety-critical software for this demonstrator enables the autonomous operation in accordance with regulatory requirements.

Nick Tudor, CEO of D-RisQ, said there were numerous different aspects of the tech that his firm had demonstrated from its perspective. “We’ve demonstrated that we can alter the capability of the last response engine and soon-to-be-trademarked as safety-critical decision-making software. And we’ve shown that we can be flexible in changing the way in which that behaves very quickly, and be able to take in new sensors and new information – and make a proper, sound decision on that,” he informed. 

Mr Tudor continued that D-RisQ has also developed a safety summary for the safety case for use of the software, and that complies with all the nuclear regs. It has been presented to Sellafield and, crucially, to the UK’s Office for Nuclear Regulation.

Having demonstrated all the various technologies with the vast majority of it integrated, and shown how it all works, what happens next? “We want to be able to develop something to go into one of the ponds at Sellafield with all those technologies fully integrated onto a specific tasking vehicle,” Mr Tudor responds. “We see that happening within the next couple of months.”

Meanwhile, the University of Manchester has been developing wireless underwater communications to eliminate the need for a tether, allowing the A2I2 robot to operate more freely in hazardous environments.  

Autonomous processes to map live environments

Chris Ballard, Robotics and AI Manager at Sellafield Ltd, attended the A2I2 drop two trials demo at Forth, and said that what he’d seen so far in the way the tech has advanced was “absolutely fantastic”. “The benefit for us within Sellafield is that we need to look at removing operators from these harsh environments. Typically, things are done through tele-operational controls. What we’re seeing demonstrated here is the potential for autonomous processes where we can map live environments. It enables us to see what’s going on in our harsh environments,” he told us. “It has also got the collision avoidance systems built in and the communications that we so desperately need from down within the pond. So it’s tackling a lot of different discrete areas for us to utilise within the business,” Mr Ballard advised.

“We have bespoke challenges that we’re trying to help satisfy across the whole organisation at Sellafield. From my perspective, to give that crosscutting value, I’d like to start to extract each of these challenges and the tools that we’ve seen in this demonstration, and the elements of the tools that will help fit those challenges,” he revealed. “What I’d like to do then is to drive each of these differently into different directions, but to give a wholehearted deployment for each of these within our facilities.”

Towards a new era of aquatic inspection and intervention

Steven Martin, Business Change Manager at Sellafield Ltd, who also attended the demo, described what he’d seen as “exciting”. “I’ve been involved in this programme for two years now, and one of the things I wanted to see from this demonstration, which we did see, was that this capability can define a point of interest. For instance, in our legacy ponds we have to decommission and remove inventory. So it’ll be really useful for us to be able to define a data set and then for us to actually survey and prove accountability that we’ve got those items retrieved from the pond.

“I’ve worked on all the programmes with the companies, and this is the furthest we’ve got towards achieving the requirements we need for not only inspection intervention of items that we have within our facilities at Sellafield, but also taking that technology across the NDA estate and across the UK nuclear programmes as we move into decommissioning.”

Forth is keen to hear from businesses and organisations – operating across a range of industries – that would benefit from using its Deep Recovery Facility for research and development, testing, trials or demonstrations. Contact Peter Routledge for further information: peter@forth.uk.com