StarWhisper Telescope: an AI framework for automating end-to-end astronomical observations

Area of Science:

• Astronomy
• Artificial Intelligence
• Computer Science

Background:

• Large-scale telescope arrays have accelerated time-domain astronomy.
• Operational bottlenecks exist in observation planning, data processing, and real-time decision-making.

Purpose of the Study:

• To present the StarWhisper Telescope system, an AI agent framework for automating astronomical observations.
• To reduce human intervention in observation planning, telescope control, and data processing.

Main Methods:

• Integration of large language models with specialized function calls and modular workflows.
• Autonomous generation of site-specific observation lists.
• Real-time image analysis and dynamic triggering of follow-up proposals.

Main Results:

• Successful deployment across 10 amateur telescopes for the Nearby Galaxy Supernovae Survey.
• Detection of astronomical transients with competitive response times.
• Demonstration of reduced human intervention and enhanced collaboration.

Conclusions:

• The StarWhisper Telescope system effectively automates end-to-end astronomical observations.
• The scalable agent architecture serves as a blueprint for future large-scale telescope facilities.
• AI-driven autonomy is crucial for managing complex, multi-telescope observational networks.