AI changes the robots in the energy sector

 By Nicholas Newman

Since the oil price crash of the summer 2014, robots dedicated to either welding, drilling or inspection, but that are controlled by humans, have been widely adopted…

Now, advances in artificial intelligence software and robotics research offer the prospect of freeing humans from dangerous and difficult tasks such as decommissioning nuclear plants and offshore oil and gas installations, or inspecting, maintaining and repairing power lines, underwater pipelines and tall wind turbines.
Increasingly, both energy companies and researchers in artificial intelligence (AI) and robotics are recognizing the need for, and value of, employing intelligent robots as a means of increasing efficiency, cutting operational costs, speeding up processes and increasing worker safety. AI software, combined with machine learning, endows robots with decision-making capacity, reducing the need for human monitoring and control. AI robots can now read instruments and detect whether operational conditions are normal, and gather data and detect potential leaks. The most sophisticated robots will be wholly autonomous with the ability to learn and self-improve.

Decommissioning nuclear power

We have reached take-off in decommissioning nuclear plants. In the UK alone, the clean-up and decommissioning of about 5.5 tons (4.9 million tonnes) of nuclear waste is estimated to cost at least $264.2 billion (£200 billion). To meet this important need, a team of computer scientists from the University of Lincoln, are developing a series of mobile AI-enabled robots to deal with nuclear-waste handling, cell decommissioning and site monitoring. One mobile robot under development has a dedicated bimanual arm, operated by `shared autonomy’ – where the machine is able to operate autonomously while still having humans as key decision-makers – or via remote control. Professor Gerhard Neumann, from the School of Computer Science notes, “Recent disaster situations such as Fukushima have shown the crucial importance of robotics technology for monitoring and intervention, which is missing up-to-date, making our work even more vital”.

Nuclear decommissioning and the safe disposal of nuclear waste are massive global challenges and necessitate the use of robots to complete many jobs (

Off-shore Oil and Gas installations

The $47.5 million (£36 million) Orca Programme (Offshore Robotics for Certification of Assets) is developing autonomous and semi-autonomous AI-enabled robots capable of inspecting, repairing, maintaining and certifying offshore-energy installations. These sophisticated robots are equipped with sensors enabling them to understand their environment, while algorithms allow them to plan, act and interact with humans and the environment.
Out in the field, one AI-enabled robot is being tested at Total’s Alwyn platform, approximately 273 miles (440km) northeast of Aberdeen to carry out visual inspections and detect gas leaks. Austrian firm Taurob makes the robot, and its software has been developed by German university, TU Darmstadt. However, Rebecca Allison of the Oil and Gas Technology Center, Aberdeen, believes that it will be at least five years before such robots become common. Will the robots take over? No, says Allison, who maintains that the robot “is not taking jobs. It is giving people the choice to do different jobs. We will still need a human workforce. It’s about allowing people to move into onshore positions”.

Autonomous offshore robot a world-first

Renewable Energy

“Artificial Intelligence boosts efficiency for solar and wind”, a report by energy experts DNV GL, envisions AI robots building and maintaining onshore wind farms and solar parks. This report forecasts the use of self-driving trucks delivering components to a site and AI robots unloading and assembling the components on site, while aerial AI-enabled drones inspect and maintain wind turbines and solar arrays. These technical developments could have a big impact on costs and speed of construction, making renewables the energy of choice.

Impact on jobs

In the oil industry, Scott Desmarais, a partner at McKinsey & Co., envisions that, “work at plants and the wellhead will continue—even if that work is being run from remote operations centers”. In fact, AI will require recruitment in new job classes, such as data scientists, statisticians and machine-learning specialists, which simply don’t exist in oil and gas companies today.
The forthcoming widespread application of AI in the form of autonomous self-learning robots by energy companies will transform decommissioning of nuclear and offshore oil and gas installations, improve the accuracy and speed of inspection and maintenance of energy infrastructure, and improve safety in what is, after all, a complex set of working environments.

READ MORE: The human cost of automation by Michelle Leslie

about the author
Nicholas Newman
Freelance energy journalist and copywriter who regularly writes for AFRELEC, Economist, Energy World, EER, Petroleum Review, PGJ, E&P, Oil Review Africa, Oil Review Middle East. Shale Gas Guide.