LATIDIA · Robótica

Comienza el aprendizaje profundo para la optimización de la trayectoria en la Estación Espacial Internacional

arXiv: 2505.05588v4Tipo de anuncio: reemplazar Resumen: La optimización de la trayectoria es una piedra angular de la autonomía moderna del robot, que permite a los sistemas calcular trayectorias y controles en tiempo real respetando la seguridad y la física

La noticia

arXiv:2505.05588v4 Announce Type: replace Abstract: Trajectory optimization is a cornerstone of modern robot autonomy, enabling systems to compute trajectories and controls in real-time while respecting safety and physical constraints. However, it has seen limited usage in spaceflight applications due to its heavy computational demands that exceed the capability of most flight computers. In this work, we provide results on the first in-space demonstration of using machine learning-based warm starts for accelerating trajectory optimization for the Astrobee free-flying robot onboard the International Space Station (ISS). We formulate a data-driven optimal control approach that trains a neural network to learn the structure of the trajectory generation problem being solved using sequential convex