Teaching offshore robots to speak our language
A team of researchers led from Edinburgh has unveiled a new system that allows humans and robots to speak the same language.
The system is called MIRIAM – Multimodal Intelligent inteRactIon for Autonomous systeMs.
It allows users to ask robots questions and understand their actions in real time.
The researchers worked at the Offshore Robotics for the Certification of Assets (ORCA) Hub, a consortium led by the universities of Heriot-Watt and Edinburgh.
MIRIAM uses natural language. This allows users to speak or send text queries and receive clear explanations from the robot about what it is doing.
Robotics consortium for the financing of offshore technology
- Can computer translators ever beat speaking a foreign language?
- Robotic inspectors developed to repair wind farms
The first applications will be in the energy, underwater and onshore industries.
“Believe me – I’m a journalist” is a phrase that for some reason struggles for credibility among the wider public.
Robots, it seems, have similar trust issues.
MIRAM will promote the “adoption” of robots by us hot-blooded types by improving the way robots communicate and building the trust of the people who use them.
It’s the latest in a multimillion-dollar investment in research by energy giant Total, which will see the technology used first at Total’s Shetland Gas Plant.
“It’s a bit like Amazon Alexa”
A tracked maintenance robot will be controlled as part of a human-robot team using MIRIAM.
Total say robots offer greater safety, efficiency and new ways of working.
Helen Hastie, a computer science professor at Heriot-Watt University, says: “It’s a bit like controlling your home with an Amazon Alexa: you use your voice: ‘where are you, what are you doing?’
“The robot might be doing something strange, like avoiding an obstacle. Now he can explain why.”
He says autonomous robots can sense their environment and can make some decisions on their own.
But there is currently a communication barrier between them and their human supervisors when it comes to explaining why they take certain courses of action.
“This is particularly problematic in remote, highly demanding and dangerous environments such as offshore, which can involve multiple vehicles and platforms.”
Professor Hastie says that greater trust between man and machine will mean greater safety.
“There is a need for transparency, for robots to explain how they work so you can trust them.”
From this, he says, will come the machines “adopted” as trusted partners of human beings.
“A lot of the work we’ve done on robots has been to enable them to plan and make their own decisions. But if we can’t get them adopted, it’ll all be wasted.”
MIRIAM will be used by a new collaborative team in which Heriot-Watt will integrate his research with engineering software company Phusion and data science company Merkle Aquila.
Funding and support came from the UK Engineering and Physical Science Research Council, Dstl and SeeByte Ltd.
The ORCA Hub is led by the Edinburgh Center for Robotics, a partnership between Heriot-Watt University and the University of Edinburgh. The consortium also includes the universities of Imperial College London, Oxford and Liverpool.
MIRIAM’s first task in the field will be to build a human team with a crawler robot called OGRIP.
Which stands for Offshore Ground Robotics Industrial Pilot, a machine developed by Total, the Austrian technology company Taurob and the Oil and Gas Technology Center in Aberdeen.
OGRIP was designed to support exploration and energy production operations under increasingly harsh and demanding conditions. These include extreme cold, arid climates, and isolated locations.
MIRIAM was also used with Husky, a large wheeled robot that exists in the relative calm of Heriot-Watt’s robotics lab.
‘Change of attitude’
Professor Hastie thinks future applications will be limited only by our imagination, sharpened by the current global crisis.
“There has been a change in attitudes towards robots since Covid-19 hit,” he says.
“It’s a devastating situation, but an opportunity for robots to do good.
“Ours are big ugly robots, a little different from the health robots you see with friendly faces.
“But they get the job done.”
- Heriot-Watt University
- University of Edinburgh