iFANnpp: Nuclear Power Plant Digital Twin for Robots and Autonomous Intelligence

Robotics has gained significant attention in the nuclear industry due its precision and ability to automate tasks. However, the increasing complexity of robots has led to a growing demand for advanced simulation and control methods to predict robot behavior and optimize plant performance, motivating the use of digital twins for robotic applications. Most existing digital twins only address parts of systems and do not offer a total design of a nuclear power plant. Furthermore, they are often designed for specific algorithms or tasks, making them unsuitable for broader research applications or projects. In response, this work proposes a comprehensive nuclear power plant digital twin designed to improve real-time monitoring, operational efficiency, and predictive maintenance. The full nuclear power plant is modeled in Unreal Engine 5 to incorporate the complexities and various phenomena. The high-resolution simulation environment is integrated with a Generic Pressurized Water Reactor Simulator, a high-fidelity physics-driven software, to create a realistic model of a nuclear power plant and a real-time updated virtual environment. The virtual environment provides various features for researchers to easily test custom robot algorithms and frameworks, applicable to research in the nuclear industry as well as industrial systems in general. The digital twin's performance is presented, and critical research problems are addressed, including multi-robot task scheduling and robot navigation in radiation-affected areas, by leveraging implemented features.

@article{do2025_2410.09213,
  title={ iFANnpp: Nuclear Power Plant Digital Twin for Robots and Autonomous Intelligence },
  author={ Youndo Do and Marc Zebrowitz and Jackson Stahl and Fan Zhang },
  journal={arXiv preprint arXiv:2410.09213},
  year={ 2025 }
}