Future fusion maintenance with autonomous robot

The collaboration between the United Kingdom Atomic Energy Authority (UKAEA) and the Oxford Robotics Institute (ORI), University of Oxford, resulted in the first autonomous robot to conduct maintenance tasks within a fusion energy site. The trial, which spanned 35 days, took place at UKAEA’s Joint European Torus (JET) facility. Until its recent operational shutdown, JET had been one of the largest and most powerful fusion research machines globally.

This successful deployment is a significant step towards commercialising fusion energy. By demonstrating that an autonomous robot can carry out part of the facility’s maintenance, the project has highlighted the potential to improve safety and reduce operational costs. Such advancements are crucial for the future of fusion powerplants, which will require frequent maintenance. Traditional robotic inspections have typically relied on human operators to make decisions and guide the process.

Dr Robert Skilton, Head of Research at UKAEA’s Remote Applications in Challenging Environments division, said: “The project aimed to validate the reliability of autonomous robotic technology and instil trust and confidence in their use for safe and efficient inspections in fusion facilities over extended periods.”

The development is particularly important for future fusion facilities, where human access may be restricted due to extreme conditions, including high levels of radiation, vacuum pressures, and intense temperatures.

JET presented an ideal testing ground for ORI’s ‘AutoInspect’ autonomy platform, which was used to control a Boston Dynamics Spot quadruped robot. Despite the hazardous conditions left after two high-powered deuterium-tritium experiments in the last three years, the robot navigated the environment and completed its tasks.

Dr Skilton added: “This deployment demonstrates that autonomous robots can enhance safety and cut costs. These ‘next generation’ solutions are becoming ready to be used in other industrial facilities such as nuclear decommissioning, environmental clean-up, and disaster relief.”

During the trial, the robot was tasked with mapping the facility, taking sensor readings, and avoiding obstacles, all while navigating through the decommissioning activities within JET. To handle these challenges, UKAEA’s inspection payload was integrated with ORI’s autonomy solutions, developed by teams led by Professors Hawes and Fallon. Boston Dynamics’ collision avoidance technology further augmented the robot’s performance.

The robotic system collected essential environmental and facility data twice daily, enabling the team to assess the viability of replacing human inspections with fully autonomous operations.

Professor Nick Hawes, Professor of AI & Robotics at the University of Oxford, commented on ORI’s goals for the project: “Projects like this demonstrate the value of autonomous robots – robots that can do things themselves without direct control of humans. They also ground our science in real use cases, and provide requirements and constraints that drive us to invent new AI and robotics algorithms.”

ORI’s work on the project was supported by the Engineering and Physical Sciences Research Council through the Embodied Intelligence: From Sensing to Collaboration programme. This initiative aims to develop autonomous systems that extend human capabilities.