|
BEACON eSpace at Jet Propulsion Laboratory >
JPL Technical Report Server >
JPL TRS 1992+ >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/2014/39046
|
| Title: | Robust local search for spacecraft operations using adaptive noise |
| Authors: | Fukunaga, Alex S.
Rabideau, Gregg
Chien, Steve |
| Keywords: | planning
scheduling
autonomy
machine learning |
| Issue Date: | 23-Jun-2004 |
| Publisher: | Pasadena, CA : Jet Propulsion Laboratory, National Aeronautics and Space Administration, 2004. |
| Citation: | International Workshop on Planning and Schedule for Space, Darmstadt, Germany, June 23-25, 2004 |
| Abstract: | Randomization is a standard technique for improving the performance of local search algorithms for constraint satisfaction. However, it is well-known that local search algorithms are constraints satisfaction. However, it is well-known that local search algorithms are to the noise values selected. We investigate the use of an adaptive noise mechanism in an iterative repair-based planner/scheduler for spacecraft operations. Preliminary results indicate that adaptive noise makes the use of randomized repair moves safe and robust; that is, using adaptive noise makes it possible to consistently achieve, performance comparable with the best tuned noise setting without the need for manually tuning the noise parameter. |
| URI: | http://hdl.handle.net/2014/39046 |
| Appears in Collections: | JPL TRS 1992+
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|
