A Model-Based Reinforcement Learning algorithm (MBRL) is proposed to perform nearly-optimal reconfiguration and maintenance in distributed formation flying spacecraft. In addition, two algorithms, namely Inverse Reinforcement Learning (IRL) and Long Short-Term Memory (LSTM) network, are proposed to reconstruct and predict neighbouring future trajectories to perform collision-free maneuvers when simultaneous reconfiguration occurs, i.e. all spacecrafts evolve following non-natural trajectories. The dynamics reconstruction, used for planning exploits a Recurrent Neural Network, whereas the IRL uses a nested short-horizon optimization to approximate the cost function. The paper compares the proposed algorithm with a baseline Model-Predictive Control approach. In particular two mission concepts are studied as application scenarios.

Spacecraft Formation Relative Trajectories Identification for Collision-Free Maneuvers using Neural-Reconstructed Dynamics

Silvestrini, Stefano;Lavagna, Michele
2020-01-01

Abstract

A Model-Based Reinforcement Learning algorithm (MBRL) is proposed to perform nearly-optimal reconfiguration and maintenance in distributed formation flying spacecraft. In addition, two algorithms, namely Inverse Reinforcement Learning (IRL) and Long Short-Term Memory (LSTM) network, are proposed to reconstruct and predict neighbouring future trajectories to perform collision-free maneuvers when simultaneous reconfiguration occurs, i.e. all spacecrafts evolve following non-natural trajectories. The dynamics reconstruction, used for planning exploits a Recurrent Neural Network, whereas the IRL uses a nested short-horizon optimization to approximate the cost function. The paper compares the proposed algorithm with a baseline Model-Predictive Control approach. In particular two mission concepts are studied as application scenarios.
2020
AIAA Scitech 2020 Forum
978-1-62410-595-1
File in questo prodotto:
File Dimensione Formato  
SILVS02-20.pdf

Accesso riservato

Descrizione: Paper
: Publisher’s version
Dimensione 811.52 kB
Formato Adobe PDF
811.52 kB Adobe PDF   Visualizza/Apri

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/11311/1129533
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? ND
social impact