Artificial Intelligence Aiding Search for Life on Mars

Over the past several years we have heard a lot from the European Space Agency in their search for signs of past or present life on Mars. Since January 2005, the Express search has been using its sophisticated instruments to study all aspects of Mars; from its atmosphere, all the way down to its subsurface.

As a result, we’ve seen evidence of glaciers, water, and more that has lent support to the idea that there could be, or could have been, life on Mars.

Not surprisingly however, the small pieces of evidence that have been found are just a tiny part of the large amount of scientific data that has been sent back to Earth. With multiple instruments recording their findings, and a limited amount of built-in storage, a whole lot of information has to be sent back home.

On top of that, data has to be sent back at the correct time, in the right sequence.

For a long time this data downloading was a human-operated process; built around scheduling software to generate command sequences sent to Express. "This is tedious, time-consuming and never really eliminated the occasional loss - forever - of valuable science data," says Alessandro Donati, Head of the Advanced Mission Concepts and Technologies Office at ESA's Space Operations Centre (ESOC), Darmstadt, Germany.

So that is why, along with researchers at Italy's Institute for Cognitive Science and Technology (ISTC-CNR), as well as mission planners and computer scientists at ESOC, Donati is heading up the development of an artificial intelligence answer to this dilemma.

The result of this work is the creation of a new smart tool that they’ve dubbed MEXAR2 ('Express AI Tool').

Having successfully passed initial testing and validation, MEXAR2 is now an integral part of the Express mission planning system, and has managed to reduce the team’s workload by at least 50%. "And because it optimises bandwidth used to receive data on Earth, we have been able to free expensive ground station time for other missions," says Michel Denis, Express Spacecraft Operations Manager at ESOC.

MEXAR2 works by considering the variables that affect data downloading - including the overall science observation schedule for all Mars Express instruments - and then intelligently projecting which on-board data packets might be later lost due to memory conflicts. It then optimises the data download schedule and generates the commands needed to implement the download.

The MEXAR2 system has also been recognized as one of three outstanding AI applications for mission operations. "It should be noted, that - like the very few other AI tools in spacecraft operations - MEXAR2 is a trailblazer in bringing AI technology to spacecraft operations. The effectiveness of the tool and the benefits it has provided are therefore significant accomplishments in themselves," says Dr Ari Kristinn Jónsson, who is Dean of the School of Computer Science at Reykjavik University, Iceland.

Posted by Josh Hill.

http://www.eurekalert.org/pub_releases/2008-04/esa-aib042908.php

Comments

[saudi]

Why not to land space crafts on Mars polar white caps to explore for water and where it is more likely? Rather than landing elsewhere!

The look of the polar white caps seems to be CO2 only in ice form and as the atmosphere data suggests already.

An old mars as the earth is would have evolved to a primitively living planet of some sort, and would have exhibits some land marks of some more rapidly changing patterns other than sand storms.

I strongly think Mars is dry bone of any water or of any quantity that would support life.

Or might have had a little water and early life consumed it all, there was not enough of water to have sustainable dynamic lasting cycle.