According to various scientists, there are many projects on board that show that artificial intelligence can get used in astronautics. If an AI is used to detect unknown Anomalies, then it is paramount for AI to get trained. It needs to be fed with what is known to evade the opposite. That sounds weird in context to AI.
There are millions of satellites that are being run with AI. Their AI is trained on the Earth and then sent to orbit. The scientists are looking to innovate a better plan where they want to train AI onboard a small satellite under space conditions. The project gets challenging as it goes on, but is feasible enough to succeed. Miniaturised IT systems are becoming more and more powerful. And we take our time for AI training. So a learning process in orbit can take several days.
Why are the scientists opting for training the AI on space, when computers can get easily manifested and accessible on the Earth? Hakan Kayal has a different vision for the future and is surely in confidence that it will succeed. The increasing distance between Earth and space makes the data transfer, a lengthy procedure.
We can’t be long-headed and keep sending the data back and forth. And that’s why the astronautics looks to be completely independent in training the AI instilled in the satellites. One such plan is the SONATE-2, which would be sent into orbit by 2024. The small satellite from Würzburg will be about the size of a shoebox (30x20x10 centimetres). Its cameras will take pictures in different spectral ranges and will have the Earth in view.