



























Researchers from the German Research Center for Artificial Intelligence (DFKI) and the University of Duisburg-Essen (UDE) participated in the 46th DLR parabolic flight campaign in Bordeaux (May 11–22, 2026) as part of the “MikroBeM” project.
The study investigates whether training with a custom, AI-adapted robotic exoskeleton on Earth could prepare astronauts for the fine-motor challenges caused by microgravity.
The robotic exoskeleton counteracts the arm’s natural weight. Using targeted force to counter gravity, the suit fools the body into feeling weightless in space.
Imagine trying to tighten a loose screw or operate on a circuit board while your own hand weighs absolutely nothing.
On Earth, the human brain knows exactly how much force to apply to lift a finger. In space, that internal math breaks completely. Starved of the familiar pull of gravity, an astronaut‘s hand movements often become shaky, unstable, and frustratingly imprecise. It is dangerous when you are tasked with fixing a space station.
To solve this, researchers took a wild approach using AI-powered robotic suits to simulate the weightlessness of deep space right here on Earth.
And to prove it works, some of the researchers just spent two weeks chasing zero gravity in the skies over France.
They boarded the Airbus A310 “Zero G,” a specialized aircraft that flies in steep, rollercoaster-like arcs. At the apex of each curve, the plane plummets into a controlled dive. For exactly 22 seconds, everyone and everything inside floats.
It is a dizzying work. But it is the only way to get real microgravity on Earth.
This precious time was used to test the project MikroBeM. Inside the floating fuselage, test subjects had a simple but maddening task. They had to use their right index finger to repeatedly poke the exact center of a target on a screen.
Here was a twist. A heavy cape completely blocked their view. Unable to see their hand, participants had to fly blind, relying strictly on muscle memory to guide their touch.
Meanwhile, a suite of sensors tracked every single twitch, measuring brain waves, muscle contractions, and heart rates. The team successfully gathered data from 180 total parabolas without a single equipment failure.
The real magic of the experiment, however, happened weeks before the plane ever took off.
Half of the flight participants had spent a month training in a laboratory on Earth. They practiced the target-poking routine while strapped into a robotic exoskeleton.
Developed by DFKI and UDE, this robotic suit uses artificial intelligence to precisely measure a user’s arm weight. It then applies highly targeted, motorized counter-forces to push up against gravity. The machine completely neutralizes the arm’s weight.
It tricks the brain into thinking it is already floating in deep space.
By comparing the pre-trained group against a completely untrained control group during the actual flights, the researchers can see if the exoskeleton training actually sticks. Early findings look highly promising.
“The long-term goal is to establish the foundation for cost-effective, personalized training approaches that can better prepare astronauts for future long-duration missions to the Moon and Mars,” the researchers noted.
Moreover, the exact same method that helps an astronaut steady their hand in zero gravity could support medical care on Earth. The researchers note that understanding how the brain adapts to altered physical conditions is important for neurotechnology and stroke rehabilitation.
This means a suit designed for the space might just help a paralyzed patient relearn how to hold things.
Get the latest in engineering, tech, space & science - delivered daily to your inbox.
Mrigakshi is a science journalist who enjoys writing about space exploration, biology, and technological innovations. Her work has been featured in well-known publications including Nature India, Supercluster, The Weather Channel and Astronomy magazine. If you have pitches in mind, please do not hesitate to email her.
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。