We are searching data for your request:
Upon completion, a link will appear to access the found materials.
NASA wants to create habitats on the Moon and Mars that can support astronauts and remain operational even when they return to earth. To meet that end its funding Habitats Optimized for Missions of Exploration or HOME.
The multi-Unversity Space Technology Research Institute will create these habitats that will be able to process and interpret data and make decisions without the need of an astronaut. HOME is being led by Professor Stephen Robinson, chair of Mechanical and Aerospace Engineering at UC Davis and a former astronaut.
RELATED: IS IT WORTH IT? THE COSTS AND BENEFITS OF SPACE EXPLORATION
AI will be front in center in these autonomous space habitats
Researchers from Carnegie Mellon including Mario Bergés, associated professor of civil and environmental engineering, Burcu Akinci, a CEE professor and expert in information modeling and Stephen Smith and Artur Dubrawski from CMU's Robotics Institute, will lead research on machine learning and robotic systems for the habitats.
NASA is funding HOME for five years, throwing about $15 million toward the effort.
The team is looking at using artificial intelligence to analyze the data gleaned from the space equipment so that they can understand electricity use in the habitat. They can then use that information to monitor the status of the electric-powered systems in the habitat.
Electrical measurements key to self-healing
To lessen the amount of data the scientists will need to detect if there is equipment failure the team plans to collect electrical measurements which will be shared with robotic systems. The systems will process it and act on it, enabling the habitat to be fully autonomous or self-fixing.
"Space is harsh and errors can be catastrophic, so we need autonomous systems that are very good," Bergés said in a press release discussing the new effort. "How do you conduct automated fault detection and diagnosis without a lot of system data? This is where AI comes in. We have machines that learn by themselves if you give them enough data, but we don't have a lot of machines that can reason by using existing engineering knowledge, which can reduce the amount of data they need."