LATIDIA · Robótica

Fleet-To-Lab: un marco de aprendizaje de transferencia para la estimación del deslizamiento del rover lunar a través de Model Fusion

arXiv: 2609.17187v1Tipo de anuncio: nuevo Resumen: La estimación precisa del deslizamiento de la rueda es esencial para la movilidad y navegación autónomas del vehículo lunar. Los modelos de aprendizaje automático entrenados en datos terrestres se generalizan mal a lun

La noticia

arXiv:2609.17187v1 Announce Type: new Abstract: Accurate wheel slip estimation is essential for autonomous lunar rover mobility and navigation. Machine Learning models trained on terrestrial data generalize poorly to lunar terrain, and real lunar datasets are scarce due to the limited number of missions and costly data acquisition. We present Fleet-to-Lab, a transfer learning framework that leverages proprioceptive data collected by previously deployed heterogeneous lunar rovers to mitigate the Earth-Moon domain gap in slip estimation for a future deployable unit. We fuse several heterogeneous expert models into a single architecture, using a modest dataset collected after the rover deployment. We propose AcoMerge, a new hybrid swarm-intelligence algorithm that performs model fusion