Just under a year after it was installed on the International Space Station, HPE’s Spaceborne Computer-2 (SB-2) has already successfully completed 24 research experiments, HPE said Monday. Using the powerful SB-2, HPE’s partners used AI to inspect astronaut gloves for dangerous flaws, enabled 3D priting in space, and used AI to analyze satellite images of Earth.
The experiments show how advanced computer systems in space can help astronauts analyze data without having to send it back to Earth. By building AI systems powerful enough for large real-time data processing — and robust enough to withstand the conditions of space — astronauts can become self-sufficient as they travel to the Moon, Mars and beyond.
The experiments demonstrate “new possibilities for space exploration and milestones for humanity,” said Dr. Mark Fernandez, principal investigator of HPE Spaceborne Computer-2, in a statement.
The SB-2 was launched into space in February 2021, after its predecessor, the HPE Spaceborne Computer, completed a successful proof-of-concept mission aboard the ISS. The HPE systems are designed to withstand the harsh physical conditions of space — variables such as radiation, solar flares, micrometeoroids, unstable electrical current and erratic cooling. The SB-2 offers twice the computational speed of its predecessor and is equipped with GPUs to efficiently process image-intensive data, such as images of Earth’s polar ice caps or medical X-rays. The GPUs also support specific projects using AI and machine learning.
In one of the SB-2 experiments, NASA and Microsoft developed an AI model of a glove analyzer to detect damage to astronaut gloves. These gloves are used during spacewalks, when astronauts repair equipment or install new instruments on the ISS. The AI model was used to quickly analyze photos and recorded videos captured in the space of recently worn gloves. If damage was detected, an AI-annotated photo was generated in space and immediately sent to Earth, marking areas for further investigation by NASA engineers.
Another experiment focused on 3D printing, which could help astronauts repair or build new equipment on long journeys. Cornell University researchers have developed modeling software that can simulate 3D printing of metal parts and even predict defects or deformations that can result from printing in the harsh conditions of space. The software has been successfully tested on SB-2, confirming that it can be used in space to digitally simulate a part and understand how it will perform in reality.
Meanwhile, NASA Jet Propulsion Laboratory (JPL) used SB-2 to test deep learning inference networks designed to analyze images of Earth after a disaster. JPL observes Earth from space to study science and climate, and to support response to disasters such as floods and hurricanes. Studying satellite images aboard future spacecraft could help with quick help.