Terminal multiple surface sliding guidance for planetary landing: Development, tuning and optimization via reinforcement learning

Roberto Furfaro, Daniel R. Wibben, Brian Gaudet, Jules Simo

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

The problem of achieving pinpoint landing accuracy in future space missions to planetary bodies such as the Moon or Mars presents many challenges, including the requirements of higher accuracy and degree of flexibility. These new challenges may require the development of a new class of guidance algorithms. In this paper, a nonlinear guidance algorithm for planetary landing is proposed and analyzed. Based on Higher-Order Sliding Control (HOSC) theory, the Multiple Sliding Surface Guidance (MSSG) algorithm has been specifically designed to take advantage of the ability of the system to reach multiple sliding surfaces in a finite time. As a result, a guidance law that is both globally stable and robust against unknown, but bounded perturbations is devised. The proposed MSSG does not require any offline trajectory generation, but the acceleration command is instead generated directly as function of the current and final (target) state. However, after initial analysis, it has been noted that the performance of MSSG critically depends on the choice in guidance gains. MSSG-guided trajectories have been compared to an open-loop fuelefficient solution to investigate the relationship between the MSSG fuel performance and the selection of the guidance parameters. A full study has been executed to investigate and tune the parameters of MSSG utilizing reinforcement learning in order to truly optimize the performance of the MSSG algorithm in powered descent scenarios. Results show that the MSSG algorithm can indeed generate closed-loop trajectories that come very close to the optimal solution in terms of fuel usage. A full comparison of the trajectories is included, as well as a further Monte Carlo analysis examining the guidance errors of the MSSG algorithm under perturbed conditions using the optimized set of parameters.

Original languageEnglish (US)
Pages (from-to)73-99
Number of pages27
JournalJournal of the Astronautical Sciences
Volume62
Issue number1
DOIs
StatePublished - Mar 1 2015

Fingerprint

planetary landing
Electronic guidance systems
Reinforcement learning
reinforcement
Landing
learning
sliding
Tuning
tuning
optimization
Trajectories
trajectory
trajectories
Monte Carlo analysis
Moon
Control theory

Keywords

  • Mars
  • Planetary landing
  • Reinforcement learning
  • Sliding guidance

ASJC Scopus subject areas

  • Aerospace Engineering
  • Space and Planetary Science

Cite this

Terminal multiple surface sliding guidance for planetary landing : Development, tuning and optimization via reinforcement learning. / Furfaro, Roberto; Wibben, Daniel R.; Gaudet, Brian; Simo, Jules.

In: Journal of the Astronautical Sciences, Vol. 62, No. 1, 01.03.2015, p. 73-99.

Research output: Contribution to journalArticle

@article{a2ee1741126545a4a5eedc90ebb3c63d,
title = "Terminal multiple surface sliding guidance for planetary landing: Development, tuning and optimization via reinforcement learning",
abstract = "The problem of achieving pinpoint landing accuracy in future space missions to planetary bodies such as the Moon or Mars presents many challenges, including the requirements of higher accuracy and degree of flexibility. These new challenges may require the development of a new class of guidance algorithms. In this paper, a nonlinear guidance algorithm for planetary landing is proposed and analyzed. Based on Higher-Order Sliding Control (HOSC) theory, the Multiple Sliding Surface Guidance (MSSG) algorithm has been specifically designed to take advantage of the ability of the system to reach multiple sliding surfaces in a finite time. As a result, a guidance law that is both globally stable and robust against unknown, but bounded perturbations is devised. The proposed MSSG does not require any offline trajectory generation, but the acceleration command is instead generated directly as function of the current and final (target) state. However, after initial analysis, it has been noted that the performance of MSSG critically depends on the choice in guidance gains. MSSG-guided trajectories have been compared to an open-loop fuelefficient solution to investigate the relationship between the MSSG fuel performance and the selection of the guidance parameters. A full study has been executed to investigate and tune the parameters of MSSG utilizing reinforcement learning in order to truly optimize the performance of the MSSG algorithm in powered descent scenarios. Results show that the MSSG algorithm can indeed generate closed-loop trajectories that come very close to the optimal solution in terms of fuel usage. A full comparison of the trajectories is included, as well as a further Monte Carlo analysis examining the guidance errors of the MSSG algorithm under perturbed conditions using the optimized set of parameters.",
keywords = "Mars, Planetary landing, Reinforcement learning, Sliding guidance",
author = "Roberto Furfaro and Wibben, {Daniel R.} and Brian Gaudet and Jules Simo",
year = "2015",
month = "3",
day = "1",
doi = "10.1007/s40295-015-0045-1",
language = "English (US)",
volume = "62",
pages = "73--99",
journal = "Journal of the Astronautical Sciences",
issn = "0021-9142",
publisher = "American Astronautical Society",
number = "1",

}

TY - JOUR

T1 - Terminal multiple surface sliding guidance for planetary landing

T2 - Development, tuning and optimization via reinforcement learning

AU - Furfaro, Roberto

AU - Wibben, Daniel R.

AU - Gaudet, Brian

AU - Simo, Jules

PY - 2015/3/1

Y1 - 2015/3/1

N2 - The problem of achieving pinpoint landing accuracy in future space missions to planetary bodies such as the Moon or Mars presents many challenges, including the requirements of higher accuracy and degree of flexibility. These new challenges may require the development of a new class of guidance algorithms. In this paper, a nonlinear guidance algorithm for planetary landing is proposed and analyzed. Based on Higher-Order Sliding Control (HOSC) theory, the Multiple Sliding Surface Guidance (MSSG) algorithm has been specifically designed to take advantage of the ability of the system to reach multiple sliding surfaces in a finite time. As a result, a guidance law that is both globally stable and robust against unknown, but bounded perturbations is devised. The proposed MSSG does not require any offline trajectory generation, but the acceleration command is instead generated directly as function of the current and final (target) state. However, after initial analysis, it has been noted that the performance of MSSG critically depends on the choice in guidance gains. MSSG-guided trajectories have been compared to an open-loop fuelefficient solution to investigate the relationship between the MSSG fuel performance and the selection of the guidance parameters. A full study has been executed to investigate and tune the parameters of MSSG utilizing reinforcement learning in order to truly optimize the performance of the MSSG algorithm in powered descent scenarios. Results show that the MSSG algorithm can indeed generate closed-loop trajectories that come very close to the optimal solution in terms of fuel usage. A full comparison of the trajectories is included, as well as a further Monte Carlo analysis examining the guidance errors of the MSSG algorithm under perturbed conditions using the optimized set of parameters.

AB - The problem of achieving pinpoint landing accuracy in future space missions to planetary bodies such as the Moon or Mars presents many challenges, including the requirements of higher accuracy and degree of flexibility. These new challenges may require the development of a new class of guidance algorithms. In this paper, a nonlinear guidance algorithm for planetary landing is proposed and analyzed. Based on Higher-Order Sliding Control (HOSC) theory, the Multiple Sliding Surface Guidance (MSSG) algorithm has been specifically designed to take advantage of the ability of the system to reach multiple sliding surfaces in a finite time. As a result, a guidance law that is both globally stable and robust against unknown, but bounded perturbations is devised. The proposed MSSG does not require any offline trajectory generation, but the acceleration command is instead generated directly as function of the current and final (target) state. However, after initial analysis, it has been noted that the performance of MSSG critically depends on the choice in guidance gains. MSSG-guided trajectories have been compared to an open-loop fuelefficient solution to investigate the relationship between the MSSG fuel performance and the selection of the guidance parameters. A full study has been executed to investigate and tune the parameters of MSSG utilizing reinforcement learning in order to truly optimize the performance of the MSSG algorithm in powered descent scenarios. Results show that the MSSG algorithm can indeed generate closed-loop trajectories that come very close to the optimal solution in terms of fuel usage. A full comparison of the trajectories is included, as well as a further Monte Carlo analysis examining the guidance errors of the MSSG algorithm under perturbed conditions using the optimized set of parameters.

KW - Mars

KW - Planetary landing

KW - Reinforcement learning

KW - Sliding guidance

UR - http://www.scopus.com/inward/record.url?scp=84983027362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983027362&partnerID=8YFLogxK

U2 - 10.1007/s40295-015-0045-1

DO - 10.1007/s40295-015-0045-1

M3 - Article

AN - SCOPUS:84983027362

VL - 62

SP - 73

EP - 99

JO - Journal of the Astronautical Sciences

JF - Journal of the Astronautical Sciences

SN - 0021-9142

IS - 1

ER -