Radiation-Resilient AI: Next-Generation Robotic Systems with Adaptive Machine Learning for Nuclear Facility Management

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume : 15 | Issue : 02 | Page : –
    By

    K.V.V. Subba Rao,

  • Manas Kumar Yogi,

  1. Assistant Professor, Department of Computer Science and Engineering, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India
  2. Assistant Professor, Department of Computer Science and Engineering, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India

Abstract

document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_abs_193304’);});Edit Abstract & Keyword

The increasing complexity of nuclear facility operations, decommissioning activities, and emergency response scenarios necessitates the development of advanced autonomous systems capable of functioning in highly radioactive environments. This paper presents a comprehensive review of radiation-resilient artificial intelligence systems integrated with next-generation robotic platforms, specifically designed for nuclear facility management applications. We examine the convergence of adaptive machine learning algorithms, radiation-hardened hardware architectures, and intelligent robotic systems that can operate autonomously in contaminated environments where human presence is either impossible or extremely hazardous. The review encompasses current technological capabilities, emerging trends in AI-robotics integration, hardware resilience strategies, and the transformative potential of these systems for nuclear industry applications. Key focus areas include real-time environmental assessment, autonomous navigation in dynamic contaminated spaces, predictive maintenance of nuclear infrastructure, and emergency response coordination. The analysis reveals significant progress in developing robust AI systems that can adapt to radiation-induced hardware degradation while maintaining operational effectiveness, though challenges remain in achieving full autonomous operation in the most extreme nuclear environments.

Keywords: Radiation, nuclear, fusion, fission, machine learning, predictive

[This article belongs to Journal of Nuclear Engineering & Technology ]

How to cite this article:
K.V.V. Subba Rao, Manas Kumar Yogi. Radiation-Resilient AI: Next-Generation Robotic Systems with Adaptive Machine Learning for Nuclear Facility Management. Journal of Nuclear Engineering & Technology. 2025; 15(02):-.
How to cite this URL:
K.V.V. Subba Rao, Manas Kumar Yogi. Radiation-Resilient AI: Next-Generation Robotic Systems with Adaptive Machine Learning for Nuclear Facility Management. Journal of Nuclear Engineering & Technology. 2025; 15(02):-. Available from: https://journals.stmjournals.com/jonet/article=2025/view=0


document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_ref_193304’);});Edit

References

1. Ahmed S, Khan M, Lee J, Park J. Machine learning applications in nuclear power plant operations: A comprehensive review. Nucl Eng Technol. 2023;55(8):2847–65.
2. Bonin H, Martin P, Clark A. Artificial intelligence and machine learning for nuclear facility management: Current status and future perspectives. Prog Nucl Energy. 2021;142:103–18.
3. Chen W, Rodriguez M. Radiation-hardened AI processors for autonomous nuclear operations. IEEE Trans Nucl Sci. 2023;70(4):445–58.
4. Dobrev D, Ivanov T, Mihaylova M, Petrov P. Application of artificial intelligence technologies and big data computing for nuclear power plants control: A review. Front Nucl Eng. 2024;3:1355630.
5. Fernandez C, Yamamoto T, Singh R. Next-generation robotics for nuclear decommissioning:Integrating AI and radiation tolerance. Robot Auton Syst. 2022;158:104–19.
6. Gupta R, Thompson S. Adaptive machine learning algorithms for nuclear facility monitoring under radiation exposure. Ann Nucl Energy. 2022;175:109–24.
7. International Atomic Energy Agency. Artificial intelligence for accelerating nuclear applications, science and technology. Vienna: IAEA; 2021.
8. International Atomic Energy Agency. Seven ways AI will change nuclear science and technology[Internet]. Vienna: IAEA; 2022 Sep 23 [cited 2025 May 30]. Available from:https://www.iaea.org/newscenter/news/seven-ways-ai-will-change-nuclear-science-and-technology

9. Johnson M, Patel K, Zhang Y. Robust neural networks for radiation-harsh environments: Design and implementation. J Nucl Sci Technol. 2022;59(12):1534–48.
10. Kim JH, Walker E. Multi-agent reinforcement learning for coordinated nuclear robotics operations. Nucl Eng Des. 2022;392:111–26.
11. Lopez Pulgarin E, Nakamoto K, Tellez H, Yamazaki T. From traditional robotic deployments towards assisted robotic deployments in nuclear decommissioning. Front Robot AI.2025;12:1344892.
12. Martinez A, Liu J. Radiation effects on deep learning hardware: Mitigation strategies for nuclear applications. IEEE Trans Device Mater Reliab. 2023;23(2):287–301.
13. Nakamura H, Suzuki T, Chang Y, Lee S. A survey of artificial intelligence applications in nuclear power plants. Appl Sci. 2023;13(15):8847.
14. Patel A, Brown R. Edge computing architectures for radiation-resilient nuclear monitoring systems. Comput Netw. 2022;218:109–24.
15. Rahman A, Chen L, Gomez F. Intelligent robotic systems for nuclear emergency response: Challenges and solutions. Saf Sci. 2022;154:105–19.
16. Smith D, Lin K, O’Brien M. Robotic development for the nuclear environment: Challenges and strategy. Robotics. 2020;9(4):94.
17. Taylor R, Wilson J. Transfer learning approaches for nuclear facility AI systems: From simulation to reality. Expert Syst Appl. 2022;201:117–32.
18. Zhang L, Zhao Q, Kumar A, Li M. Predictive maintenance in nuclear facilities using machine learning: A state-of-the-art review. Reliab Eng Syst Saf. 2023;230:108–25.

Regular Issue Subscription Review Article
Volume 15
Issue 02
Received 29/05/2025
Accepted 30/05/2025
Published 19/06/2025
Publication Time 21 Days
77

[last_name]

My IP

PlumX Metrics