LATIDIA · Robótica

Aceleración de la optimización sobre gráficos de conjuntos convexos a través de aproximaciones de redes neuronales

arXiv: 2608.15440v2Tipo de anuncio: reemplazar Resumen: Los problemas de planificación de movimiento, como la navegación sin colisiones y la manipulación rica en contactos, se pueden formular naturalmente como problemas de optimización que combinan decisiones discretas

La noticia

arXiv:2608.15440v2 Announce Type: replace Abstract: Motion planning problems such as collision-free navigation and contact-rich manipulation can be naturally formulated as optimization problems that couple discrete decisions with continuous trajectories. The Graphs of Convex Sets (GCS) framework offers a practical solution to these problems. It represents discrete decisions as nodes of a graph and encodes continuous trajectories in the edges connecting them. However, the resulting optimization subproblems can become computationally prohibitive for online replanning. In this work, we propose a learning-based strategy to mitigate this limitation. Specifically, we replace the costly convex relaxation step required by nominal GCS with a single forward pass through a Graph Attention Network that predicts a