Researchers were specially invited to publish a review on the intelligentization of telescope control systems.----Nanjing institute of Astronomical optics & Technology National Astronomical O bservatories .CAS

Modern astronomy is undergoing a profound transformation driven by the rapid advancement of survey observation techniques and the urgent demands of time-domain astrophysics.

With the rapid development of time-domain astronomy, multi-messenger astronomy, and large-scale survey programs, astronomical observations face numerous formidable challenges, characterised by exponentially growing data volumes, the transient nature of observed targets, and extremely stringent requirements on real-time decision-making.

Conventional telescope control systems (TCS) that rely on human expertise and static rules are no longer capable of effectively meeting the demand for efficient responses to complex observing strategies.

In recent years, artificial intelligence (AI) technologies exemplified by machine learning, deep learning, and reinforcement learning have been deeply integrated into astronomical telescope control systems.

They are driving the evolution of telescope operating modes toward greater autonomy, intelligence, and closed-loop optimisation across multiple domains, including observing scheduling, real-time data processing, and instrument health management.

A research team at the Nanjing Institute of Astronomical Optics, Technology and Astrophysics (NIAOTA), Chinese Academy of Sciences, was recently specially invited to publish a review article titled "Artificial Intelligence Empowering Astronomical Observations: A Review of the Intelligentisation of Telescope Control Systems" in Laser & Optoelectronics Progress, which systematically reviews the applications, architectures, and development trends of AI in TCS.

The review systematically examines the overall architecture and key applications of AI in TCS, with emphasis on the research progress and representative cases in three key areas—autonomous observing scheduling, intelligent processing of real-time data streams with closed-loop feedback, and predictive maintenance—and provides an in-depth discussion of critical issues such as interpretability, robustness, and system integration, as well as an outlook on the future development trends of AI-driven astronomical observation systems.

The review points out that AI has evolved from an auxiliary tool into a core driving force for the autonomy upgrade of telescopes, providing a comprehensive theoretical and technical reference for the development of next-generation intelligent astronomical observing instruments.

Future TCS will continue to progress toward higher levels of autonomy, with significantly enhanced autonomous decision-making capabilities; the real-time performance of such systems will also be further strengthened, enabling faster responses to diverse observational requirements and environmental changes; moreover, the level of intelligence will reach new heights, with stronger capabilities in learning, reasoning, and adaptation.

These advances will undoubtedly yield more significant and far-reaching breakthroughs in the field of astronomical research.