LeLaR: The First In-Orbit Demonstration of an AI-Based Satellite Attitude Controller

TL;DR

This paper reports the first in-orbit demonstration of an AI-based satellite attitude controller trained via Deep Reinforcement Learning in simulation, successfully deployed on a real nanosatellite, showing robust performance.

Contribution

It presents the first successful deployment of an AI controller trained in simulation onto a real satellite, demonstrating its effectiveness in orbit.

Findings

AI controller achieved robust in-orbit performance

Compared favorably with classical PD controller

Demonstrated effective Sim2Real transfer in satellite control

Abstract

Attitude control is essential for many satellite missions. Classical controllers, however, are time-consuming to design and sensitive to model uncertainties and variations in operational boundary conditions. Deep Reinforcement Learning (DRL) offers a promising alternative by learning adaptive control strategies through autonomous interaction with a simulation environment. Overcoming the Sim2Real gap, which involves deploying an agent trained in simulation onto the real physical satellite, remains a significant challenge. In this work, we present the first successful in-orbit demonstration of an AI-based attitude controller for inertial pointing maneuvers. The controller was trained entirely in simulation and deployed to the InnoCube 3U nanosatellite, which was developed by the Julius-Maximilians-Universit\"at W\"urzburg in cooperation with the Technische Universit\"at Berlin, and launched in January 2025. We present the AI agent design, the methodology of the training procedure, the discrepancies between the simulation and the observed behavior of the real satellite, and a comparison of the AI-based attitude controller with the classical PD controller of InnoCube. Steady-state metrics confirm the robust performance of the AI-based controller during repeated in-orbit maneuvers.