Five ways artificial intelligence might help space exploration

Artificial intelligence has been making waves lately, enabling us to unravel problems faster than traditional computing could ever allow. Recently, for instance, Google’s artificial intelligence subsidiary DeepMind developed AlphaFold2, a program which solved the protein-folding problem. This is an issue which has had baffled scientists for 50 years.

Advances in AI have allowed us to make progress in every kind of disciplines – and these are usually not limited to applications on this planet. From designing missions to clearing Earth’s orbit of junk, listed below are a number of ways artificial intelligence might help us enterprise further in space.

Astronaut assistants

Do you remember Tars and Case, the assistant robots from the film Interstellar? While these robots don’t exist yet for real space missions, researchers are working towards something similar, creating intelligent assistants to assist astronauts. These AI-based assistants, despite the fact that they might not look as fancy as those in the flicks, could possibly be incredibly useful to space exploration.

A recently developed virtual assistant can potentially detect any dangers in lengthy space missions equivalent to changes within the spacecraft atmosphere – for instance increased carbon dioxide – or a sensor malfunction that could possibly be potentially harmful. It would then alert the crew with suggestions for inspection.

An AI assistant called Cimon was flown to the international space station (ISS) in December 2019, where it’s being tested for 3 years. Eventually, Cimon shall be used to cut back astronauts’ stress by performing tasks they ask it to do. NASA can also be developing a companion for astronauts aboard the ISS, called Robonaut, which is able to work alongside the astronauts or tackle tasks which are too dangerous for them.

Mission design and planning

Planning a mission to Mars is just not a simple task, but artificial intelligence could make it easier. New space missions traditionally depend on knowledge gathered by previous studies. However, this information can often be limited or not fully accessible.

This means the technical information flow is constrained by who can access and share it amongst other mission design engineers. But what if all the data from practically all previous space missions were available to anyone with authority in only a number of clicks. One day there could also be a better system – much like Wikipedia, but with artificial intelligence that may answer complex queries with reliable and relevant information – to assist with early design and planning of recent space missions.

Researchers are working on the concept of a design engineering assistant to cut back the time required for initial mission design which otherwise takes many human work hours. “Daphne” is one other example of an intelligent assistant for designing Earth remark satellite systems. Daphne is utilized by systems engineers in satellite design teams. It makes their job easier by providing access to relevant information including feedback in addition to answers to specific queries.

Satellite data processing

Earth remark satellites generate tremendous amounts of knowledge. This is received by ground stations in chunks over a big time frame, and needs to be pieced together before it will probably be analysed. While there have been some crowdsourcing projects to do basic satellite imagery evaluation on a really small scale, artificial intelligence can come to our rescue for detailed satellite data evaluation.

For the sheer volume of knowledge received, AI has been very effective in processing it smartly. It’s been used to estimate heat storage in urban areas and to mix meteorological data with satellite imagery for wind speed estimation. AI has also helped with solar radiation estimation using geostationary satellite data, amongst many other applications.

AI for data processing may also be used for the satellites themselves. In recent research, scientists tested various AI techniques for a distant satellite health monitoring system. This is able to analysing data received from satellites to detect any problems, predict satellite health performance and present a visualisation for informed decision making.

Space debris

One of the most important space challenges of the twenty first century is the right way to tackle space debris. According to ESA, there are nearly 34,000 objects greater than 10cm which pose serious threats to existing space infrastructure. There are some progressive approaches to take care of the menace, equivalent to designing satellites to re-enter Earth’s atmosphere in the event that they are deployed inside the low Earth orbit region making them disintegrate completely in a controlled way.

Another approach is to avoid any possible collisions in space, stopping the creation of any debris. In a recent study, researchers developed a technique to design collision avoidance manoeuvres using machine-learning (ML) techniques.

Another novel approach is to make use of the big computing power available on Earth to coach ML models, transmit those models to the spacecraft already in orbit or on their way, and use them on board for various decisions. One solution to ensure safety of space flights has recently been proposed using already trained networks on board the spacecraft. This allows more flexibility in satellite design while keeping the danger of in orbit collision at a minimum.

Navigation systems

On Earth, we’re used to tools equivalent to Google Maps which use GPS or other navigation systems. But there isn’t a such a system for other extraterrestrial bodies, for now.

We should not have any navigation satellites across the Moon or Mars but we could use the thousands and thousands of images we have now from remark satellites equivalent to the Lunar Reconnaissance Orbiter (LRO). In 2018, a team of researchers from NASA in collaboration with Intel developed an intelligent navigation system using AI to explore the planets. They trained the model on the thousands and thousands of photographs available from various missions and created a virtual Moon map.

As we feature on to explore the universe, we’ll proceed to plan ambitious missions to satisfy our inherent curiosity in addition to to enhance the human lives on Earth. In our endeavours, artificial intelligence will help us each on Earth and in space make this exploration possible.