AI is coming for our jobs, and now we can add “Mars Rover Driver” to that list. Last month, the Perseverance rover successfully made not one, but two trips across the surface of Mars, planned by AI rather than humans. In fact, the rover lived to tell the tale. By NASA:
NASA’s Perseverance Mars rover has completed the first trips on another world planned by artificial intelligence. The demonstration, conducted Dec. 8 and 10 and led by the agency’s Jet Propulsion Laboratory in Southern California, used generative AI to create waypoints for Perseverance, a complex decision-making task typically performed manually by the mission’s human rover planners.
We are not talking about autonomous driving here. We already know that Perseverance is much better at this than Earth cars. We’re talking about the meticulous route planning that goes into the rover’s movements. Without this, the $2.7 billion rover could crash into a boulder, roll over on uneven terrain, or get stuck in a sand trap, as the Spirit rover did. That’s not a good prospect for NASA’s precarious budget.
It is not possible to remotely control the rover in real time due to the large distance between the planets. Even at the speed of light you can come from anywhere four to 24 minutes before radio signals reach Mars, and that much time before signals return to Earth. Typically, human route planners carefully study all available photographs and terrain data from the surface of Mars to determine the safest route from point A to point B, upload the route to the rover, and then execute it. In this case, the Jet Propulsion Laboratory ran the data through Anthropic’s Claude AI to plan the route.
We don’t need roads where we’re going
On December 8, Perseverance successfully drove a 200-meter AI-generated route. On December 10, it drove another route of 250 meters. The rover’s autonomous driving systems deviated slightly from the planned route based on real-world data it collected along the way, but overall the routes worked successfully. From NASA:
“Imagine intelligent systems not only on the ground on Earth, but also in edge applications in our rovers, helicopters, drones and other surface elements trained with the collective wisdom of our NASA engineers, scientists and astronauts,” said Matt Wallace, manager of JPL’s Exploration Systems Office. “That’s the breakthrough technology we need to build the infrastructure and systems necessary for a permanent human presence on the moon and take the US to Mars and beyond.”
Other worlds have their dangers, but human astronauts drove rovers on the moon long before AI was the buzzword of the week, because they were there and could apply human driving skills to the task. Alien robot drivers also don’t have crime stops to drive through, stopped school buses to breeze past, or kids to run in front of them (unless there are alien kids we haven’t discovered yet). As much as we joke about AI stealing the jobs of route planners, it would make sense if a rover could scan the area and use that, along with existing map data, to plan its own route without waiting for “drivers” on another planet to tell it what to do. It would certainly speed up travel, as JPL says.
#Mars #Rover #escape #separate #planet #Jalopnik