NASA Field-Tests AI Fleet Capability for Science, Exploration
In this field test, a fleet of three robots worked together, and researchers assessed the fleet’s ability to act like an independent science team. The post NASA Field-Tests AI Fleet Capability for Science, Exploration appeared first on NASA Science .
NASA scientists and industry partners recently conducted field tests of an artificial intelligence system that could enhance future space exploration missions. The Adaptive Sensing Technology for Responsive Autonomy (ASTRA) team, comprised of researchers from Noblis and NASA's Goddard Space Flight Center in Maryland, tested a fleet of three robots at the Virginia Tech Transportation Institute in Virginia.
The process began with a drone selecting an area of scientific interest based on initial goals provided by human experts. The fleet's programming then evaluated potential risks and scientific rewards, determining which robot was best suited for investigation. Throughout the test, the fleet continuously monitored for environmental hazards, reassessed its strategy, and reported findings to its human managers.
The ultimate goal of this project is to create a reliable extension of the human science team for uncrewed missions in distant solar system locations, such as the outer planets, or hazardous environments like the Moon and Mars. One key question the field test aimed to answer was whether the fleet would autonomously adjust its tasks based on new information once it had started working on a science objective.
The results showed the fleet could maintain focus on its original goals while also promptly adapting to new opportunities.
Written by urgent.news from NASA Science's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
