1st ACT global trajectory optimisation competition: Results found at DLR

This paper describes the DLR team solution method and results for ESA's 1st ACT global trajectory optimisation competition problem. The other articles in this volume demonstrate that the design and the optimisation of low-thrust trajectories are usually a very difficult task that involves much...

Full description

Saved in:
Bibliographic Details
Published in:Acta astronautica 2007-11, Vol.61 (9), p.742-752
Main Authors: Dachwald, Bernd, Ohndorf, Andreas
Format: Article
Language:English
Subjects:
Algorithms
Asteroid deflection
Competition
Evolutionary
Evolutionary algorithms
Evolutionary neurocontrol
Fuses
Global trajectory optimisation
Kinetic impact
Low-thrust propulsion
Optimization
Tasks
Trajectories
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes the DLR team solution method and results for ESA's 1st ACT global trajectory optimisation competition problem. The other articles in this volume demonstrate that the design and the optimisation of low-thrust trajectories are usually a very difficult task that involves much experience and expert knowledge. We have used evolutionary neurocontrol—a method that fuses artificial neural networks and evolutionary algorithms—to find a solution for the given low-thrust trajectory optimisation problem. This method requires less experience/knowledge in astrodynamics and in optimal control theory than the traditional methods. In this paper, the implementation of evolutionary neurocontrol is outlined and its performance for the given problem is shown.
ISSN:0094-5765
1879-2030
DOI:10.1016/j.actaastro.2007.03.011