Safe spacecraft swarm deployment and acquisition in perturbed near-circular orbits subject to operational constraints

Koenig, Adam W.; D’Amico, Simone

doi:10.1016/j.actaastro.2018.01.037

Cited by 11 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural network training aims to minimize the error function E, which is the mean squared error (MSE) that quantifies the difference between the computed output trajectory (feedforward neural network) and the actual trajectory (mathematical model). The number of layers and parameters were determined empirically by examining the performance of several different layers (3)(4)(5)(6)(7)(8)(9)(10)(11)(12) and parameters . We found that 100 parameters per layer and 4 total layers gave the least mean squared error (M SE < 0.001).…”

Section: Supervised Learning Approachmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Based Relative Orbit Transfer for Swarm Spacecraft Motion Planning

Sabol¹,

Yun²,

Adil³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper we describe a machine learning based framework for spacecraft swarm trajectory planning. In particular, we focus on coordinating motions of multi-spacecraft in formation flying through passive relative orbit(PRO) transfers. Accounting for spacecraft dynamics while avoiding collisions between the agents makes spacecraft swarm trajectory planning difficult. Centralized approaches can be used to solve this problem, but are computationally demanding and scale poorly with the number of agents in the swarm. As a result, centralized algorithms are ill-suited for real time trajectory planning on board small spacecraft (e.g. CubeSats) comprising the swarm. In our approach a neural network is used to approximate solutions of a centralized method. The necessary training data is generated using a centralized convex optimization framework through which several instances of the n=10 spacecraft swarm trajectory planning problem are solved. We are interested in answering the following questions which will give insight on the potential utility of deep learning-based approaches to the multispacecraft motion planning problem: 1) Can neural networks produce feasible trajectories that satisfy safety constraints (e.g. collision avoidance) and low in fuel cost? 2) Can a neural network trained using n spacecraft data be used to solve problems for spacecraft swarms of differing size?

show abstract

Section: Supervised Learning Approachmentioning

confidence: 99%

“…For such missions, autonomy is crucial in its operation, and how to plan coordinated motions of multi-spacecraft plays a key role. Spacecraft swarms have been well studied in the literature, see [6], [7], [8], [9] for examples of recent work in spacecraft swarms. For a survey on formation flying see [10].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Relative Orbit Transfer for Swarm Spacecraft Motion Planning

Sabol¹,

Yun²,

Adil³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…is shifting towards the nanosatellites. The solution to these problems involves the creation of low-orbit nanosatellite`s constellations [8][9][10][11]. A nanosatellite-follower of the constellation should have increased manoeuvrability, power supply and autonomy.…”

Section: Introductionmentioning

confidence: 99%

Formation of an Additional Motion Control Loop for the Nanosatellite to Adapt its Onboard Model to the Current Operating Conditions

Ломака

2022

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

The paper presents the formation of additional feedback in the loop of the attitude control system of a nanosatellite. Feedback is based on the assessment of the inertial characteristics of the nanosatellite. The influence of the accuracy of knowledge of the inertial characteristics of a nanosatellite on the formation of an optimal control law in the problem of reorientation was estimated. Statistical modelling has been carried out to assess the effectiveness of nanosatellite on-board sensors in the problem of identifying the inertial characteristics of a nanosatellite. Recommendations for the selection of sensor’s characteristics and time interval of data collection have been formulated.

show abstract

“…For formation flying, one of the main factors that influence the design is the collision-free flight during the overall mission profile. A suitable collision avoidance strategy should be defined among the satellites in the formation (Wermuth et al, 2015;Koenig & D'Amico, 2018). For Earth observation missions, the close formation is introduced to achieve the concept of a distributed scientific payload.…”

Section: Introductionmentioning

confidence: 99%

“…The concept of formation flying reconfiguration has been extensively analysed in the literature (Tillerson et al, 2002;Armellin et al, 2004;Acikmese et al, 2006;Morgan et al, 2014;Koenig & D'Amico, 2018;Sarno et al, 2020). Acikmese et al (2006) proposed a guidance algorithm for formation reconfiguration with heuristic collision avoidance constraints when the satellite distances are in the order of tens of metres.…”

Section: Introductionmentioning

confidence: 99%

Design of optimal low-thrust manoeuvres for remote sensing multi-satellite formation flying in low Earth orbit

Scala,

Gaias,

Colombo

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper presents a strategy for optimal manoeuvre design of multi-satellite formation flying in low Earth orbit environment, with the aim of providing a tool for mission operation design. The proposed methodology for formation flying manoeuvres foresees a continuous low-thrust control profile, to enable the operational phases. The design is performed starting from the dynamic representation described in the relative orbital elements, including the main orbital perturbations effects. It also exploits an interface with the classical radial-transversal-normal description to include the maximum delta-v limitation and the safety condition requirements. The methodology is applied to a remote sensing mission study, Formation Flying L-band Aperture Synthesis, for land and ocean application, such as a potential high-resolution Soil Moisture and Ocean Salinity (SMOS) follow-on mission, as part of a European Space Agency mission concept study. Moreover, the results are applicable to a wide range of low Earth orbit missions, exploiting a distributed system, and in particular to Formation Flying L-band Aperture Synthesis (FFLAS) as a follow-on concept to SMOS.

show abstract

Safe spacecraft swarm deployment and acquisition in perturbed near-circular orbits subject to operational constraints

Cited by 11 publications

References 16 publications

Machine Learning Based Relative Orbit Transfer for Swarm Spacecraft Motion Planning

Machine Learning Based Relative Orbit Transfer for Swarm Spacecraft Motion Planning

Formation of an Additional Motion Control Loop for the Nanosatellite to Adapt its Onboard Model to the Current Operating Conditions

Design of optimal low-thrust manoeuvres for remote sensing multi-satellite formation flying in low Earth orbit

Contact Info

Product

Resources

About