Artificial intelligence has managed to solve problems faster and more efficiently than all traditional computer science. Progress has made it possible to achieve results unthinkable for scientists in many fields. Also includes space missions. These are advances that can clearly be transposed to optimize life on Earth. A recent article identifies five ways in which artificial intelligence can help humans take interesting and forward-looking steps in space exploration.
An anti stress assistant
More and more science and less fiction. The “collaborating” robots, like those in the most famous films in the history of cinema, are becoming more and more real. In this case, they also have a name. CIMONs are artificial intelligence-based assistants, which could be incredibly useful for space exploration. This is a study still in the testing phase, but it is already bearing fruit.
An AI assistant named Cimon was flown to the International Space Station (ISS) in December 2019, where it was tested for three years. Cimon will be used to reduce the stress of astronauts by performing the tasks of controlling the spacecraft’s atmosphere and any malfunctions. NASA is also developing a companion for astronauts aboard the ISS, called the Robonaut, who will either work alongside the astronauts or take on tasks that are too risky for them.
A multi-tasking planner
Planning a mission to Mars is no easy task. It requires an unlimited flow of technical information that is difficult for a design engineer to manage. Therefore, a system with artificial intelligence is being considered, capable of answering complex questions with reliable and relevant information to help with the design and advance planning of new space missions. With far fewer hours of human work. “Daphne” is an example of an intelligent assistant for the design of Earth observation satellite systems. Daphne is used by systems engineers on satellite design teams. Simplify their work by providing access to relevant information, including feedback and answers to specific questions.
Interactive satellite data
Earth observation satellites generate huge amounts of data. This is received by the ground stations in blocks over a long period of time and must be put together before it can be analyzed. Artificial intelligence can come to the rescue with detailed satellite data analysis. Due to the huge volume of data received, the AI was very effective in processing it intelligently. It was used to estimate heat build-up in urban areas and to combine meteorological data with satellite images for wind speed estimation. Artificial intelligence also helped with solar radiation estimation using satellite data. In this sense, AI has also proved very useful for remote health monitoring of satellite performance.
The control of space “junk”.
According to ESA, there are nearly 34,000 objects larger than 10cm which is a serious threat to space infrastructure. There are some innovative approaches to controlling them. In a recent study, researchers developed a method for designing collision avoidance manoeuvres using machine learning (ML) techniques.
Another innovative approach is to use the enormous computing power available on Earth to train ML models, transmit those models to the spacecraft already in orbit or travelling, and use them on board for various decisions. A way to ensure the safety of space flights has recently been proposed using networks already trained on board the spacecraft. This allows for greater flexibility in satellite design while keeping the danger of collision in orbit to a minimum.
A GPS on the Moon.
At the moment there is still no system like the most famous digital maps, for extraterrestrial bodies. However, millions of images from observation satellites such as the Lunar Reconnaissance Orbiter (LRO) could be used. In 2018, a team of NASA researchers in collaboration with Intel developed an intelligent navigation system that uses AI to explore planets. They trained the model on the millions of photographs available from various missions and created a virtual moon map.
Read also:
