This project aims to show that evolved ANNs can be used to control one or more spacecraft in an environment simulating zero friction and tidal gravity. The first application we consider is the autonomous docking of a spacecraft with another spacecraft. It is part of the research activity on AI at the European Space Agency, within the Advanced Concepts Team.
Autonomous docking is defined as one spacecraft approaching another one from close proximity, with hard constraints on the final position, the final speed (usually very close to zero) and the final attitude of the spacecraft. We are using an ANN representation and we evolve its weights with artificial evolution using PaGMO, an open source software platform for global optimization of unconstrained problems developed at the Advanced Concepts Team (ACT) at the European Space Agency (ESA).
|2011-06-26 22:13:56 (cache-nb)||1309126362||0||-0.053572|
|2011-06-26 21:13:46 (neo.lan)||1309122757||16||-0.503303|
|2011-06-26 21:13:42 (neo.lan)||1309122757||0||-0.378735|
|2011-03-20 05:30:15 (dev.juxi.net)||1294760035||42457||-0.978604|
|2011-03-16 22:00:09 (dev.juxi.net)||1294760035||39623||-0.939719|
|2011-03-13 19:10:06 (dev.juxi.net)||1294760035||37352||-0.922611|
|2011-03-03 21:04:27 (dev.juxi.net)||1294760035||30867||-0.922323|