Learning to Decommission: Robots in the Nuclear World

Robotic assistance has the potential to enable breakthroughs in healthcare, scientific exploration on Earth and beyond, and nuclear decommissioning. Although at first glance these applications might be seemingly disjoint, all these fields can benefit from cleverly designed model-based robotic control strategies that can be customized to provide accurate motion with guaranteed safety. In this talk, I briefly describe these robot control strategies, their applications, case studies, and their ongoing combination with data-driven strategies and empower them to perform completely automated – and complex – tasks in challenging scenarios.

It is difficult to overstate the importance of robotics to nuclear decommissioning. It is impossible to decommission nuclear reactors without robotics or remote handling systems. In delivering the most complex decommissioning challenges, we are asking engineers to redefine the possible to make improvements that can save billions of pounds and decades of time.
This talk will provide a view from industry on the use of robotics for decommissioning; highlighting key challenges, presenting examples that are currently in use, and speculating on the future of the industry.

This talk explores how artificial intelligence enables robots to learn from data and experience, moving beyond traditional rule-based programming. Focusing on key AI-driven approaches such as supervised learning, reinforcement learning, and imitation learning, the talk explains how robots use sensory data to perceive their environment, make decisions, and adapt their behaviour over time. Through real-world examples and a live demonstration, the audience will see how learning allows robots to improve at tasks like recognising objects or interacting with people, bringing us closer to a future where robots are more helpful, flexible, and intelligent collaborators in everyday life.