Scientists have secured £1.1 million in grant funding to create artificial intelligence (AI) systems to enable self-learning robots to be used as a substitute for humans in risky nuclear sites.
It is projected that up to £200 billion will be spent on the clean-up and decommissioning of nuclear waste spanning the next 100 years. At present, a team of computer scientists from the University of Lincoln will develop machine learning algorithms to boost capabilities in several vital areas of nuclear robotics, including cell decommissioning, waste handling, and site monitoring with mobile robots.
Machine learning is an application of AI which allows systems to gather data and use it to inform automated decision-making and make enhancements based on experience without being overtly programmed.
The Lincoln researchers will develop algorithms for vision-guided robot grasping, mobile robot navigation, manipulation and cutting, and outdoor mapping and navigation. The aim is to design systems which can use machine learning to adjust to the distinctive conditions of nuclear sites, including areas contaminated by radiation.
A dedicated bimanual robot arm which will be mounted on a mobile system is being built. It will be worked using shared autonomy - where the machine can function independently while still having humans as chief decision makers - or via remote control. The team will also examine the potential of augmented reality in the domain of nuclear robotics.
The project, funded with £1.1 million from the UK's Engineering and Physical Sciences Research Council (EPSRC), is being headed by Professor Gerhard Neumann with co-investigator Dr Marc Hanheide, both from the University of Lincoln's School of Computer Science.
Professor Neumann said: "Clean-up and decommissioning of nuclear waste is one of the biggest challenges for our generation and the next, and the predicted costs are enormous: up to £200 billion over the next 100 years.
"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."
The Lincoln project is part of the National Centre for Nuclear Robotics (NCNR), a multi-disciplinary EPSRC RAI (Robotics and Artificial Intelligence) Hub led by the University of Birmingham, and also involves Queen Mary University of London, the University of West England, University of Bristol, University of Edinburgh, and Lancaster University.
Through the NCNR, over 40 postdoctoral researchers and PhD researchers form a team to promote advanced scientific solutions for nuclear robotics, including mobile robotics, sensor and manipulator design, robotic grasping and manipulation, computer vision, intuitive user interfaces and shared autonomy.