Nikunj C. Oza's Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

Learning Points of Interest for Observation Flight Planning Optimization: A Preliminary Report

Learning Points of Interest for Observation Flight Planning Optimization: A Preliminary Report. Elif Kurklu, Robert M. Morris, and Nikunj C. Oza. In Workshop on AI Planning and Learning, International Conference on Automated Planning and Scheduling (ICAPS), September 2007.

Download

[PDF]126.1kB  

Abstract

This paper describes the initial stage of an effort the goal ofwhich is to demonstrate the effectiveness of automated datamining, learning and planning for the daily management ofEarth Science missions. Currently, data mining and machinelearning technologies are being used by scientists at researchlabs for validating Earth science models. However, few if anyof these advanced techniques are currently being integratedinto daily mission operations. Consequently, there are significantgaps in the knowledge that can be derived from themodels and data that are used each day for guiding missionactivities. The result can be sub-optimal observation plans,lack of useful data, and wasteful use of resources. Recent advancesin data mining, machine learning, and planning makeit feasible to migrate these technologies into the daily missionplanning cycle. This paper describes the design of a closedloop system for data acquisition, processing, and flight planningthat integrates the results of machine learning into theflight planning process.

BibTeX Entry

@inproceedings{kumo07,
	author = {Elif Kurklu, Robert M. Morris, and Nikunj C. Oza},
	title = {Learning Points of Interest for Observation Flight Planning Optimization: A Preliminary Report},
	booktitle={Workshop on AI Planning and Learning, International Conference on Automated Planning and Scheduling (ICAPS)},
	month={September},
	abstract={This paper describes the initial stage of an effort the goal of
which is to demonstrate the effectiveness of automated data
mining, learning and planning for the daily management of
Earth Science missions. Currently, data mining and machine
learning technologies are being used by scientists at research
labs for validating Earth science models. However, few if any
of these advanced techniques are currently being integrated
into daily mission operations. Consequently, there are significant
gaps in the knowledge that can be derived from the
models and data that are used each day for guiding mission
activities. The result can be sub-optimal observation plans,
lack of useful data, and wasteful use of resources. Recent advances
in data mining, machine learning, and planning make
it feasible to migrate these technologies into the daily mission
planning cycle. This paper describes the design of a closed
loop system for data acquisition, processing, and flight planning
that integrates the results of machine learning into the
flight planning process.},
	bib2html_pubtype = {Refereed Conference},
	bib2html_rescat = {Planning and Data Mining},
	year = {2007}
}

Generated by bib2html.pl (written by Patrick Riley ) on Sun Jan 13, 2008 22:02:08