As part of NASA’s Vision for Space Exploration program, future human missions to the moon will require an increased automation level. In particular, it will be essential to perform safe landing autonomously in the presence of hazards. This work deals with an image-based hazard detection for 6DOF (Degrees of Freedom) lunar landing. The proposed approach relies on the new deep learning semantic segmentation for image classification. Images are rendered using a detailed Digital Terrain Model (DTM) from which terrain features are extracted at different illumination conditions. Results show good accuracy for both training and test sets.

IMAGE-BASED LUNAR LANDING HAZARD DETECTION VIA DEEP LEARNING / Ghilardi, L.; D’Ambrosio, Andrea.; Scorsoglio, A.; Furfaro, R.; Curti, Fabio. - (2021). (Intervento presentato al convegno 31st AAS/AIAA Space Flight Mechanics Meeting tenutosi a Virtual).

IMAGE-BASED LUNAR LANDING HAZARD DETECTION VIA DEEP LEARNING

D’Ambrosio Andrea.;Curti Fabio
2021

Abstract

As part of NASA’s Vision for Space Exploration program, future human missions to the moon will require an increased automation level. In particular, it will be essential to perform safe landing autonomously in the presence of hazards. This work deals with an image-based hazard detection for 6DOF (Degrees of Freedom) lunar landing. The proposed approach relies on the new deep learning semantic segmentation for image classification. Images are rendered using a detailed Digital Terrain Model (DTM) from which terrain features are extracted at different illumination conditions. Results show good accuracy for both training and test sets.
2021
31st AAS/AIAA Space Flight Mechanics Meeting
aerospace engineering; space systems; image-based hazard detection; lunar landing; Convolutional Neural Network
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
IMAGE-BASED LUNAR LANDING HAZARD DETECTION VIA DEEP LEARNING / Ghilardi, L.; D’Ambrosio, Andrea.; Scorsoglio, A.; Furfaro, R.; Curti, Fabio. - (2021). (Intervento presentato al convegno 31st AAS/AIAA Space Flight Mechanics Meeting tenutosi a Virtual).
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1559761
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact