Formation control in low-Earth orbits by means of machine learning methods

Shirobokov, Maksim; Trofimov, Sergey

doi:10.20948/prepr-2020-19

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [46] synthesizes an adaptive neurocontroller for the formation flying of two SCs in low near-Earth orbit. One of the SCs is considered to be controllable, the second one is uncontrollable with an unknown ballistic coefficient.…”

Section: Relative Controlmentioning

confidence: 99%

Deep learning for spacecraft guidance, navigation, and control

Khoroshylov¹,

Redka²

2021

Kosm. nauka tehnol.

View full text Add to dashboard Cite

The advances in deep learning have revolutionized the field of artificial intelligence, demonstrating the ability to create autonomous systems with a high level of understanding of the environments where they operate. These advances, as well as new tasks and requirements in space exploration, have led to an increased interest in these deep learning methods among space scientists and practitioners. The goal of this review article is to analyze the latest advances in deep learning for navigation, guidance, and control problems in space. The problems of controlling the attitude and relative motion of spacecraft are considered for both traditional and new missions, such as orbital service. The results obtained using these methods for landing and hovering operations considering missions to the Moon, Mars, and asteroids are also analyzed. Both supervised and reinforcement learning are used to solve such problems based on various architectures of artificial neural networks, including convolutional and recurrent ones. The possibility of using deep learning together with methods of control theory is analyzed to solve the considered problems more efficiently. The difficulties that limit the application of the reviewed methods for space applications are highlighted. The necessary research directions for solving these problems are indicated.

show abstract

Section: Relative Controlmentioning

confidence: 99%

Deep learning for spacecraft guidance, navigation, and control

Khoroshylov¹,

Redka²

2021

Kosm. nauka tehnol.

View full text Add to dashboard Cite

show abstract

“…In [21,22], the control of a formation of two satellites in a near-earth circular orbit is discussed. It is proposed to use adaptive neurocontrol.…”

Section: Introductionmentioning

confidence: 99%

Development and Simulation of Motion Control System for Small Satellites Formation

et al. 2021

View full text Add to dashboard Cite

In the paper, the problem of forming and maintaining the small satellites formation in the near-earth projected circular orbits is considered. The satellite formation reconfiguration and formation-keeping control laws are proposed by employing the passivity-based output feedback control. For the complete nonlinear and time-dependent dynamics of the relative motion of a pair of satellites in elliptical orbits, new combined control algorithms, including a consensus protocol, are proposed and analyzed. A comparison of the control modes using the passivity-based output feedback control and the proportional-differential controller with and without the consensus algorithm is given. On the basis of the passification method, the algorithm is obtained ensuring the stable motion of the slave satellite relative to the orbit of the master satellite. To improve the accuracy of the satellites’ positioning, a consensus protocol based on measurements of the relative positions of the satellites is proposed and studied. Computer simulations of the proposed algorithms for options to construct formations are provided for two projected circular orbits of 8 satellites, demonstrating the efficiency of the proposed control schemes. It is shown that the resulting passivity-based output feedback control provides better accuracy than the PD controller. It is also shown that the use of the consensus protocol further increases the positioning accuracy of the satellite constellation.

show abstract

Formation control in low-Earth orbits by means of machine learning methods

Abstract: Работа поддержана грантом Российского фонда фундаментальных исследований (РФФИ) 18-31-00403.

Cited by 2 publications

References 23 publications

Deep learning for spacecraft guidance, navigation, and control

Deep learning for spacecraft guidance, navigation, and control

Development and Simulation of Motion Control System for Small Satellites Formation

Contact Info

Product

Resources

About