The Role of AI in Space Exploration
Sun, April 18, 2021

The Role of AI in Space Exploration

All of us might have looked at the sky and dreamed about space. Human curiosity has driven us to discover new worlds, explore the unknown, and push the boundaries of our scientific and technical limits / Photo by: Aphelleon via Shutterstock

 

All of us might have looked at the sky and dreamed about space. Human curiosity has driven us to discover new worlds, explore the unknown, and push the boundaries of our scientific and technical limits. Over the years, we have seen how countries have become so invested in human space exploration, aiming not only to satisfy our curiosity but also answer fundamental questions about our history and the history of our solar system.

Fortunately, it became possible for us to venture into outer space with the development of rockets and other machines. The emergence of new technologies has greatly helped the space industry, and this includes artificial intelligence. However, the history of AI and space exploration is older than many people think.

AI has played a huge role in research into our planet, the solar system, and the universe. A good example of this is the Earth Observer 1 (EO-1) satellite, which has been helpful in gathering images of hurricanes and volcanic eruptions. Other satellite and astronomy machines such as the Sky Image Cataloging and Analysis Tool (SKICAT) have assisted in classifying objects discovered during the second Palomar Sky Survey. It helped to determine thousands more objects than a human would have been able to as the objects were caught in low resolution.

AI had helped NASA and Google last 2017 in discovering two obscure planets. According to Eduonix, an online site that provides the latest news, updates, tips, and tricks on programming, AI, IoT, and other technology, these planets are Kepler-90, now called Kepler-90i, and Kepler 80, now called Kepler-80g. AI is a great tool in differentiating real planets between false indications by using huge amounts of data from space exploration. 

Indeed, AI has a lot of potential in the space industry. It can find patterns that humans may not be able to spot themselves, decide the behavior of things that we send to space instead of human prompts from Earth, help astronauts respond to unexpected events, and much more. 

Giving Directions in Space

Last year, the NASA Frontier Development Lab (FDL) conducted an eight-week summer program to discuss the core problems for space travel and extraterrestrial colonization. The event aimed to use AI in solving these issues. One of the issues raised was the problem with extraterrestrial navigation for both robots and humans. While it’s easy for us to know where we are on Earth, it’s extremely difficult in space, especially on the moon because everything looks gray. 

Thus, researchers Andrew Chung, Philippe Ludivig, Ross Potter, and Benjamin Wu developed a system for simulating the Moon’s surface and comparing the simulation to a local environment to give directions in space. According to The Next Web, a website and annual series of conferences focused on new technology and start-up companies in Europe, the AI system could find out where the humans and robots were after humans fed it millions of images. It would then use a neural network to create a virtual moon. The AI would then compare the real images of the moon with the simulation.

Last year, the NASA Frontier Development Lab (FDL) conducted an eight-week summer program to discuss the core problems for space travel and extraterrestrial colonization / Photo by: Ingus Kruklitis via Shutterstock

 

Assisting Humans in Space Exploration

Going to the Moon or outer space is both challenging and scary. Story Musgrave, an American physician and a retired NASA astronaut, stated that humans are not designed to be in outer space in terms of the biological system. According to him, 70% of astronauts become ill going into space, while 50% become ill to the point of vomiting due to the inability of their system to cope with the free-fall and zero-G conditions. AI can help in conditioning humans on their long-duration space flights.

AI can also help astronauts complete long, tedious, multi-step tasks. Astronauts can ask the AI systems or machines what their next step is, to track how far they have gotten into the procedure, and to deal with a problem. This particularly important when they need to communicate with mission control and complete missions in deep space. According to Intel Software, an online site that features exciting innovations that are built with products from Intel, retired astronaut Nicole Stott emphasized the importance of smart interfaces. 

“The day-to-day operation of the station, or a habitat on the moon or Mars, or a spacecraft on an extended-duration journey between destinations, will require an intelligent computer system to keep it going. Even on the ISS, we are primarily relying on the computers and MCC interface to support daily operation — [the] crew really only interfaces when a physical task is required,” Stott said. 

AI can also help astronauts complete long, tedious, multi-step tasks. Astronauts can ask the AI systems or machines what their next step is, to track how far they have gotten into the procedure, and to deal with a problem / Photo by: Vadim Sadovski via Shutterstock

 

Solving Space Problems

In this year’s FDL, NASA gathered science and computer engineering early-career doctoral students, the world’s biggest technology companies, and experts from the space agency and academia in an effort to apply advanced computer algorithms to problems in space science. Giada Arney, an astrobiologist at NASA's Goddard Space Flight Center in Greenbelt, Maryland, stated that technologies such as AI and machine learning are significant, particularly for big data sets and in the exoplanet field. 

"Because the data we're going to get from future observations are going to be sparse and noisy. It's going to be really hard to understand. So using these kinds of tools has so much potential to help us,” Arney said. 

According to Phys.org, an internet portal provides the latest news on science, the team had developed a machine learning technique for scientists who would venture the atmospheres of exoplanets or planets beyond our solar system. The hope that they can use advanced machine learning techniques in quickly interpreting data that would reveal the chemistry of exoplanets based on the wavelengths of light emitted or absorbed by molecules in their atmospheres.

AI continues to help and address the problems in the space industry. It is a great tool in learning and understanding what has long captured our interest and curiosity.