Title:
Small Body Reconnaissance by Multiple Spacecraft via Deep Reinforcement Learning

Thumbnail Image
Author(s)
Tomita, Kento
Shimane, Yuri
Ho, Koki
Authors
Person
Advisor(s)
Advisor(s)
Editor(s)
Associated Organization(s)
Organizational Unit
Daniel Guggenheim School of Aerospace Engineering
The Daniel Guggenheim School of Aeronautics was established in 1931, with a name change in 1962 to the School of Aerospace Engineering
Series
Supplementary to
Abstract
Small-body investigations by spacecraft are one of the most scientifically important space exploration missions. Due to the strong uncertainty of the dynamics around the body, geological surface features, and scientific values of candidate target sites, these missions require dedicated planning and execution from the ground. As a study of automated operations for asteroid investigation, this paper investigates how small-body reconnaissance operations could be performed by multiple spacecraft. By comparing baseline policies with different model parameters and a policy trained via deep reinforcement learning, we discuss the optimal balance of exploration and exploitation for our science model.
Sponsor
Date Issued
2022-08
Extent
Resource Type
Text
Resource Subtype
Paper
Rights Statement
Unless otherwise noted, all materials are protected under U.S. Copyright Law and all rights are reserved