With a Better Brain, Curiosity Mars Rover Picks Its Own Targets
The Curiosity Mars Rover is now smart enough to choose its own exploration targets, according to a new study.
The secret of Curiosity’s best brain was a software update sent to the ground in October 2015, called Stand-Alone Exploration to Collect Enhanced Science (AEGIS).
This was the first time that artificial intelligence had been tested on a remote probe, and the results showed that similar AI techniques could be applied to future missions, according to NASA scientists working on the project.
AEGIS allows the rover to be “trained” to identify rocks with certain characteristics that field scientists want to investigate. This is valuable because human Curiosity controllers can not be in direct contact with the mobile all the time.
Instead of waiting for instructions to “go there and sample this piece of rock”, Curiosity can now search for goals, even if it is not in contact with its human controllers, according to a new study that describes Curiosity use of the software.
“We can not be in constant contact with the rover – Mars turns and when [Curiosity is] on the opposite side, we can not get in touch with him,” said Raymond Francis, senior system engineer for the deployment of AEGIS . .com.
According to the study, once the AEGIS system was deployed, it was used 54 times between May 13, 2016 and April 7, 2017. Without intelligent targeting, curiosity could be expected to reach a goal Scientists are interested in about 24% time; With AEGIS, the rover managed 93 percent, according to the study.
Even when the rover is in contact, signals from Earth to Mars take the time to get there and come back. In May 2016, Mars was the closest it came from Earth in 11 years – 46.8 million miles.
A radio signal would take a little more than 4 minutes to get there and four more to come back. So if there are planetary scientists who want to take a closer look, it may take some time to send the orders.
Inactive time is often lost for mission rover time, and because sending a robot to Mars is expensive and difficult, it’s not ideal. A few hours hanging around each day may not seem like much, but it adds up during an entire mission.
With AEGIS, the rover could lead to a location, select investigative targets and collect data while waiting for radio contact with the Earth again. This means that terrestrial scientists are free to choose a new target once they re-establish contact with the rover.
For the study, the NASA team formed Curiosity, with the AEGIS software, to analyze the pedestal in a function called the Murray Formation after each training. The Murray Formation is a rocky outcrop with characteristic bands of stones, possibly laid by lakes of liquid water.
One question scientists wanted to answer was whether the chemical composition of the Murray Formation changed over time, as this might reveal changes in water chemistry, disclosing more about the history of water on Mars.