Using Autonomy Flight Software to Improve Science Return on Earth Observing One

Chien, Steve; Sherwood, Rob; Tran, Daniel; Cichy, B.; Rabideau, Gregg; Castaño, Rebecca; Davis, Ashley E.; Mandl, Daniel; Trout, Bruce; Shulman, Seth; Boyer, Darrell

doi:10.2514/1.12923

Cited by 182 publications

(102 citation statements)

References 5 publications

(3 reference statements)

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…For instance, the spacecraft associated with the Earth Observing-1 (EO-1) mission already makes use of classification schemes to automatically analyze hyperspectral image data such that follow-up observations of interesting regions or events can be made (without any human interaction) [28,37]. As pointed out by Wagstaff and Bornstein [144,145], on board autonomy will be an important issue for future missions in general and in particular for those involving large one-way communication times like missions to Jupiter or Saturn.…”

Section: Motivationmentioning

confidence: 99%

From Supervised to Unsupervised Support Vector Machines and Applications in Astronomy

Gieseke

2013

Künstl Intell

View full text Add to dashboard Cite

A common task in the field of machine learning is the classification of objects. The basis for such a task is usually a training set consisting of patterns and associated class labels. A typical example is, for instance, the automatic classification of stars and galaxies in the field of astronomy. Here, the training set could consist of images and associated labels, which indicate whether a particular image shows a star or a galaxy. For such a learning scenario, one aims at generating models that can automatically classify new, unseen images. In the field of machine learning, various classification schemes have been proposed. One of the most popular ones is the concept of support vector machines, which often yields excellent classification results given sufficient labeled data.However, for a variety of real-world tasks, the acquisition of sufficient labeled data can be quite time-consuming. In contrast to labeled training data, unlabeled one can often be obtained easily in huge quantities. Semi-and unsupervised techniques aim at taking these unlabeled patterns into account to generate appropriate models. In the literature, various ways of extending support vector machines to these scenarios have been proposed. One of these ways leads to combinatorial optimization tasks that are difficult to address.In this thesis, several optimization strategies will be developed for these tasks that (1) aim at solving them exactly or (2) aim at obtaining (possibly suboptimal) candidate solutions in an efficient kind of way. More specifically, we will derive a polynomial-time approach that can compute exact solutions for special cases of both tasks. This approach is among the first ones that provide upper runtime bounds for the tasks at hand and, thus, yield theoretical insights into their computational complexity. In addition to this exact scheme, two heuristics tackling both problems will be provided. The first one is based on least-squares variants of the original tasks whereas the second one relies on differentiable surrogates for the corresponding objective functions. While direct implementations of both heuristics are still computationally expensive, we will show how to make use of matrix operations to speed up their execution. This will result in two optimization schemes that exhibit an excellent classification and runtime performance.Despite these theoretical derivations, we will also depict possible application domains of machine learning methods in astronomy. Here, the massive amount of data given for today's and future projects renders a manual analysis impossible and necessitates the use of sophisticated techniques. In this context, we will derive an efficient way to preprocess spectroscopic data, which is based on an adaptation of support vector machines, and the benefits of semi-supervised learning schemes for appropriate learning tasks will be sketched. As a further contribution to this field, we will propose the use of so-called resilient algorithms for the automatic data analysis taking place aboard toda...

show abstract

Section: Motivationmentioning

confidence: 99%

From Supervised to Unsupervised Support Vector Machines and Applications in Astronomy

Gieseke

2013

Künstl Intell

View full text Add to dashboard Cite

show abstract

“…The nature of search for MAPGEN does not allow it to search the infeasible space for plan solutions; that is, when a constraint violation arises, the planner backtracks. ASPEN admits search in the infeasible space (in fact, threats and constraint violations are rolled up into a single generic entity called a conflict) allowing for faster response to off-nominal execution (Chien et al 2000;Chien et al 2005). In fact, ASPEN has been demonstrated for in situ rover technology (Castano et al 2007;Estlin et al 1999;Gaines et al 2008) P. Maldague, A. Ko, D. Page, and T. Starbird (Maldague et al 1997) have developed a schedule generation framework (APGEN) that automatically generates and validates plans used for commanding spacecraft but does not perform general planning and scheduling.…”

Section: Related Workmentioning

confidence: 99%

Leveraging Multiple Artificial Intelligence Techniques to Improve the Responsiveness in Operations Planning: ASPEN for Orbital Express

et al. 2014

Self Cite

View full text Add to dashboard Cite

“…The most recent and comprehensive space-based application of goal-based operations is the ASE 1,2 . ASE is an autonomous software agent currently flying onboard the EO-1 spacecraft, which has demonstrated several integrated autonomy technologies that together enable science-directed autonomous operations.…”

Section: A Brief History Of Goal-based Operationsmentioning

confidence: 99%

“…The Autonomous Sciencecraft Experiment (ASE 1,2 ) on the Earth Observing 1 (EO-1) spacecraft is such an example. As a result of on-board image processing, ASE re-targets EO-1 on subsequent orbits based upon changes such as flooding, ice melt, and lava flows.…”

Section: Introductionmentioning

confidence: 99%

Goal-Based Operations: An Overview

Dvorak

Ingham

Morris

et al. 2007

AIAA Infotech@Aerospace 2007 Conference and Exhibit

View full text Add to dashboard Cite

Operating robotic space missions via time-based command sequences has become a limiting factor in the exploration, defense, and commercial sectors. Command sequencing was originally designed for comparatively simple and predictable missions, with safe-mode responses for most faults. This approach has been increasingly strained to accommodate today's more complex missions, which require advanced capabilities like autonomous fault diagnosis and response, vehicle mobility with hazard avoidance, opportunistic science observations, etc. Goal-based operation changes the fundamental basis of operations from imperative command sequences to declarative specifications of operational intent, termed goals. Execution based on explicit intent simplifies operator workload by focusing on what to do rather than how to do it. The move toward goal-based operations, which has already begun in some space missions, involves changes and opportunities in several places: operational processes and tools, human interface design, planning and scheduling, control architecture, fault protection, and verification and validation. Further, the need for future interoperation among multiple goal-based systems suggests that attention be given to areas for standardization. This overview paper defines the concept of goal-based operations, reviews a history of steps in this direction, and discusses the areas of change and opportunity through comparison with the prevalent operational paradigm of command sequencing.

show abstract

Using Autonomy Flight Software to Improve Science Return on Earth Observing One

Cited by 182 publications

References 5 publications

From Supervised to Unsupervised Support Vector Machines and Applications in Astronomy

From Supervised to Unsupervised Support Vector Machines and Applications in Astronomy

Leveraging Multiple Artificial Intelligence Techniques to Improve the Responsiveness in Operations Planning: ASPEN for Orbital Express

Goal-Based Operations: An Overview

Contact Info

Product

Resources

About