SAFE LUNAR LANDING VIA IMAGES: A REINFORCEMENT META-LEARNING APPLICATION TO AUTONOMOUS HAZARD AVOIDANCE AND LANDING

Andrea Scorsoglio, Andrea D’ambrosio, Luca Ghilardi, Roberto Furfaro, Brian Gaudet, Richard Linares, Fabio Curti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Future missions to the Moon and Mars will require advanced Guidance, Navigation, and Control (GNC) algorithms for the powered descent phase. GNC tasks are generally performed by independent modules. In this paper, reinforcement meta-learning and hazard detection and avoidance are embedded into a single system to derive the optimal thrust command for a safe lunar pinpoint landing using sequences of images and radar altimeter data as inputs. In particular, we incorporate an image-based autonomous hazard detection and avoidance algorithm with real-time GNC for a successful landing. The former is achieved using a machine learning model trained in a supervised fashion to recognize hazardous areas in the camera field of view and selecting a safe point accordingly. Then, within the reinforcement meta-learning framework, this information is used by the agent to learn how to behave in this simulated environment and land safely.

Original languageEnglish (US)
Title of host publicationASTRODYNAMICS 2020
EditorsRoby S. Wilson, Jinjun Shan, Kathleen C. Howell, Felix R. Hoots
PublisherUnivelt Inc.
Pages91-110
Number of pages20
ISBN (Print)9780877036753
StatePublished - 2021
EventAAS/AIAA Astrodynamics Specialist Conference, 2020 - Virtual, Online
Duration: Aug 9 2020Aug 12 2020

Publication series

NameAdvances in the Astronautical Sciences
Volume175
ISSN (Print)0065-3438

Conference

ConferenceAAS/AIAA Astrodynamics Specialist Conference, 2020
CityVirtual, Online
Period8/9/208/12/20

ASJC Scopus subject areas

  • Aerospace Engineering
  • Space and Planetary Science

Fingerprint

Dive into the research topics of 'SAFE LUNAR LANDING VIA IMAGES: A REINFORCEMENT META-LEARNING APPLICATION TO AUTONOMOUS HAZARD AVOIDANCE AND LANDING'. Together they form a unique fingerprint.

Cite this