Testing Early and Often: End-to-End Testing on the Double Asteroid Redirection Test (DART)

Smith, Evan J.; Zhan, Steven; Adams, Elena; Chen, Michelle; Bekker, Dmitriy; Carrelli, David J.; Johnson, Andrew; Heistand, Christopher; Thomas, Justin; Badger, Andrew; Rodríguez, Luis M.; Tran, Minh

doi:10.1109/aero47225.2020.9172455

Cited by 7 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 The space domain is one such high-risk environment, due to the great expense in placing and servicing satellites in orbit or beyond. Even so, space-based intelligent systems will likely be increasingly deployed, with a recent example being the autonomous final asteroid approach of DART mission, 2 where extensive data fusion and navigation algorithm development, verification, and validation was required to ensure mission success in the face of an unknown environment.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement learning application to satellite constellation sensor tasking

Saeed¹,

Holguín²,

Gabriel

et al. 2023

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V

View full text Add to dashboard Cite

Machine learning and artificial intelligence algorithms have expanded dramatically in use across diverse fields of research and practice. Despite the extensive benefits that these algorithms can bring to researchers, system designers, and operators alike, the adoption of these algorithms in space-related scenarios has lagged behind other fields. In order to encourage the increased adoption of artificial intelligence and machine learning techniques to space-domain-related problems, flexible modeling and simulation capabilities are needed to build stakeholder trust in these techniques. This research presents the development of a flexible Python-based modeling and simulation environment for applying Reinforcement Learning to Low Earth Orbit satellite Hyper Spectral Imaging sensor tasking. With the transition away from small numbers of highly exquisite on-orbit systems to proliferated architectures characterized by constellations of lower cost and complexity spacecraft, the methods by which payload sensors are tasked have become dynamic and complex, making the problem of determining effective sensor tasking methods an important area of research. Such a problem lends itself well to the application of Reinforcement Learning. The focus of this work is on developing the role of intelligent systems in improving the data acquisition process in a space-based hyperspectral imaging system, and showing how the developed modeling and simulation framework can be successfully employed to improve the acquisition of targets of interest. A key strength of the presented reinforcement learning application framework is its non-commercial, extensible nature, suitable for both research and educational purposes.

show abstract

Section: Introductionmentioning

confidence: 99%

Reinforcement learning application to satellite constellation sensor tasking

Saeed¹,

Holguín²,

Gabriel

et al. 2023

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V

View full text Add to dashboard Cite

show abstract

“…Additionally, NASA's Lucy spacecraft [7], which will be the first one to study Jupiter's Trojan asteroids is scheduled to launch in October, 2021. Another upcoming asteroid mission, the double asteroid redirection test (DART) mission [8] will perform a kinetic impactor demonstration for the purpose of planetary defense.…”

Section: Introductionmentioning

confidence: 99%

Orbit–attitude dynamics and control of spacecraft hovering over a captured asteroid in the earth–moon system

Chen²,

Zhang

et al. 2022

View full text Add to dashboard Cite

This paper presents a robust orbit-attitude control method for spacecraft body-fixed hovering over a captured asteroid in the earth-moon system. First, relative orbit-attitude motion dynamics model of spacecraft with respect to an asteroid is derived in the context of circular restricted three-body problem. As opposed to previous works focusing on point-mass translational models, this paper proposes a new feature point-based model which is established in a local frame originated in a selected spot attached to the asteroid surface. In such a case, the kinematic coupling effect is explicitly included, and the desired relative motion trajectories are thus to be time-invariant. Next, an adaptive sliding mode controller is devised for spacecraft robust hovering as well as sensor pointing in the presence of external disturbances and parameter uncertainties. Finally, a simulation scenario of spacecraft hovering over an asteroid which is assumed to be captured in a stable lunar distant retrograde orbit is illustrated. Results demonstrate that both orbital and attitude relative motion track the reference trajectories well under the proposed control law. KeywordsOrbit-attitude dynamics • Adaptive sliding mode control • Asteroid • Body-fixed hovering • Circular restricted three-body problem B Xiaowei Shao

show abstract