Artificial intelligence has made waves in recent years, enabling us to solve problems faster than conventional computers could ever allow. For example, Google’s artificial intelligence subsidiary DeepMind recently developed AlphaFold2, a program that solves the problem of protein folding. This is a problem that has baffled scientists for 50 years.
Advances in AI have allowed us to make advances in all kinds of disciplines – and these are not limited to applications on this planet. Here are a few ways artificial intelligence can help us move further into space.
CIMON will support astronauts on the International Space Station. NASA / Kim Shiflett, CC BY
Do you remember Tars and Case, the assistant robots from the movie Interstellar? While these robots for real space missions don’t yet exist, researchers are working toward something similar, creating intelligent assistants to help astronauts. These AI-based assistants could be incredibly useful for exploring space, even if they don’t look as fancy as the ones in the movies.
A recently developed virtual assistant can detect potential dangers during lengthy space missions, e.g. B. Changes in the spacecraft’s atmosphere – such as increased carbon dioxide – or a sensor malfunction that could potentially be harmful. It would then alert the crew with suggestions for inspection.
An AI assistant named Cimon was flown to the International Space Station (ISS) in December 2019, where it will be tested for three years. After all, cimon is used to help reduce astronauts’ stress by performing tasks that they ask of them. NASA is also developing a companion for astronauts aboard the ISS called the Robonaut who will work with the astronauts or take on tasks that are too risky for them.
Mission design and planning
Planning a mission to Mars is not an easy task, but artificial intelligence can make it easier. New space missions traditionally rely on knowledge from previous studies. However, often this information can be limited or not fully accessible.[Read: How this company leveraged AI to become the Netflix of Finland]
This means that the flow of technical information is restricted by who can access it and share it with other mission design engineers. But what if all information from practically every previous space mission was available to every member of authority with just a few clicks? One day there could be a smarter system – similar to Wikipedia, but with artificial intelligence that can answer complex questions with reliable and relevant information – to help with the early planning and planning of new space missions.
Researchers are working on the idea of a design assistant to cut down on the time it takes to initial mission design, which would otherwise take many human hours. “Daphne” is another example of an intelligent assistant for the design of earth observation satellite systems. Daphne is used by systems engineers on satellite design teams. It makes their jobs easier by providing access to relevant information including feedback and answers to specific questions.
Satellite data processing
Earth observation satellites generate enormous amounts of data. This is received in pieces over a long period of time by ground stations and must be put together before it can be analyzed. While there have been some crowdsourcing projects to do basic satellite image analysis on a very small scale, artificial intelligence can help us with detailed analysis of satellite data.
Because of the enormous volume of data, AI was very effective at intelligent processing. It was used to estimate heat storage in urban areas and combine meteorological data with satellite imagery for wind speed estimation. Among other things, AI has helped estimate solar radiation using geostationary satellite data.
AI for computing can also be used on the satellites themselves. Recently, scientists have tested various AI techniques for a remote satellite health monitoring system. This allows data received from satellites to be analyzed to identify problems, predict satellite condition performance, and present a visualization for making informed decisions.
AI has also been used to address the problem of space debris. NASA Orbital Debris Program Office, CC BY
One of the greatest space challenges of the 21st century is the fight against space debris. According to ESA, there are almost 34,000 objects larger than 10 cm that pose a serious threat to the existing space infrastructure. There are some innovative approaches to dealing with the threat such as: B. the development of satellites that re-enter the earth’s atmosphere when deployed in orbit and completely disintegrate in a controlled manner.
Another approach is to avoid possible collisions in space and prevent debris from building up. In a recent study, researchers developed a method for designing collision avoidance maneuvers using machine learning (ML) techniques.
Another novel approach is to use Earth’s vast computing power to train ML models, transfer those models to the spaceship that is already in orbit or on its way, and use them for various on-board decisions . One way of ensuring the safety of space flights has recently been proposed using pre-established networks on board the spacecraft. This allows more flexibility in satellite design and at the same time minimizes the risk of a collision in orbit.
On earth, we are used to tools like Google Maps that use GPS or other navigation systems. There is currently no such system for other extraterrestrial bodies.
We don’t have navigation satellites around the Moon or Mars, but we could use the millions of images we have from observation satellites like the Lunar Reconnaissance Orbiter (LRO). In 2018, a team of NASA researchers worked with Intel to develop an intelligent navigation system that uses AI to explore the planets. They trained the model on the millions of photos available from various missions and created a virtual moon map.
As we continue to explore the universe, we will continue to plan ambitious missions to satisfy our inherent curiosity and improve human life on earth. In our endeavors, artificial intelligence, both on earth and in space, will help us make this exploration possible.
This article by Deep Bandivadekar, PhD student at the Aerospace Center of Excellence at the University of Strathclyde, and Audrey Berquand, PhD student in Mechanical and Aerospace Engineering at the University of Strathclyde, is republished by The Conversation under a Creative Commons license. Read the original article.
Published on January 27, 2021 – 11:00 UTC