ASTREA: Introducing Agentic Intelligence for Orbital Thermal Autonomy
This addresses autonomous spacecraft operations for space agencies and satellite operators, representing a novel application of agentic AI in space-qualified systems.
The paper tackles autonomous spacecraft thermal control by introducing ASTREA, an agentic system combining a resource-constrained LLM with reinforcement learning, validated on flight-heritage hardware aboard the ISS. Ground experiments showed improved thermal stability and reduced violations, and on-orbit synchronization with orbit length surpassed baselines with reduced violations, extended episode durations, and improved CPU utilization.
This paper presents ASTREA, the first agentic system executed on flight-heritage hardware (TRL 9) for autonomous spacecraft operations, with on-orbit operation aboard the International Space Station (ISS). Using thermal control as a representative use case, we integrate a resource-constrained Large Language Model (LLM) agent with a reinforcement learning controller in an asynchronous architecture tailored for space-qualified platforms. Ground experiments show that LLM-guided supervision improves thermal stability and reduces violations, confirming the feasibility of combining semantic reasoning with adaptive control under hardware constraints. On-orbit validation aboard the ISS initially faced challenges due to inference latency misaligned with the rapid thermal cycles of Low Earth Orbit (LEO) satellites. Synchronization with the orbit length successfully surpassed the baseline with reduced violations, extended episode durations, and improved CPU utilization. These findings demonstrate the potential for scalable agentic supervision architectures in future autonomous spacecraft.