Adding artificial intelligence to the machines we send out to explore space makes a lot of sense, as it means they can make decisions without waiting for instructions from Earth, and now NASA scientists are trying to figure out how it could be done.
As we send out more and more probes into space, some of them may have to operate completely autonomously, reacting to unknown and unexplained scenarios when they get to their destination – and that's where AI comes in.
Steve Chien and Kiri Wagstaff from NASA's Jet Propulsion Laboratory think that these machines will also have to learn as they go, adapting to what they find beyond the reaches of our most powerful telescopes.
"By making their own exploration decisions, robotic spacecraft can conduct traditional science investigations more efficiently and even achieve otherwise impossible observations, such as responding to a short-lived plume at a comet millions of miles from Earth," write the researchers.
One example they give is AI that can tell the difference between a storm and normal weather conditions on a distant planet, making the readings that are being taken much more useful to scientists back home.
Just like Google uses AI to recognise dogs and cats in photos, an explorer buggy could learn to tell the difference between snow and ice, or between running water and still water, adding extra value and meaning to the data it gathers.
The researchers suggest AI-enabled probes could reach as far as Alpha Centauri, some 4.24 light-years away from Earth. Communications across that distance would be received by the generation after the scientists who launched the mission in the first place, so giving the probe a mind of its own would certainly speed up the decision-making process.
The next generation of AI robots will have to be able to detect "features of interest", detect unforeseen features, process and analyse data, and adapt their original plans where necessary, say the researchers.
And when smart probes get the chance to work together, the effects of AI will be even more powerful, as these artificial minds will be able to put their heads together to overcome challenges.
We are already seeing some of this artificial intelligence and autonomy out in space today. The Mars Curiosity rover has software on board that helps it to pick promising targets for its ChemCam – a device that studies rocks and other geological features on the Red Planet.
By making its own decisions rather than always waiting for instructions from Earth, Curiosity is now much better at finding significant targets and is able to gather a larger haul of data, according to researchers.
Meanwhile the next rover to be sent to Mars in 2020 will be able to adjust its data collection processes based on the resources available, report Chien and Wagstaff.
In time, AI is going to become more and more important to space travel, the researchers say, and as artificial intelligence makes big strides forward here on Earth it's also set to have a big role in how we explore the rest of the Universe.
The research has been published in Science Robotics.