Artificial intelligence helps explore Mars

Mars Express has been using sophisticated instruments to study the atmosphere, surface and subsurface of Mars since January 2005, confirming the presence of water and looking for other signatures of life on, and below, the rocky terrain.

The spacecraft generates huge volumes of scientific data, however, which must be downloaded to Earth at the right time and in the correct sequence. This has traditionally been managed with human-operated scheduling software.

"This is tedious, time-consuming and never really eliminated the occasional loss of valuable data," said Alessandro Donati, head of the Advanced Mission Concepts and Technologies Office at ESA's Space Operations Centre in Darmstadt, Germany.

Donati explained that the downloading problem involves several constantly changing variables.

These include spacecraft orientation, ground station availability, space-ground communication bandwidth, onboard storage availability and the varying amounts of data generated by each of the seven onboard instruments.

Researchers at Italy's Institute for Cognitive Science and Technology have been addressing the complex Mars Express scheduling problem by applying artificial intelligence techniques.

The result of this work is a new Mars Express AI Tool which considers the variables that affect data downloading, and intelligently projects which onboard data packets might be lost due to memory conflicts.

It then optimises the data download schedule and generates the commands needed to implement the download.

"With the Mars Express AI Tool any loss of stored data packets has been largely eliminated," said Fred Jansen, ESA's Mars Express mission manager.

Copyright ©v3.co.uk

artificialexplorehelpsintelligencemarssoftware