Artificial Intelligence(AI) in Space Exploration ‍🚀👨🏿‍🚀

“The stars will never be won by little minds; we must be big as space itself.”

There’s no denying the fact that we live in a time where technology has become less artificial and more intelligent. Whether we talk about AI applications or the applications of its subsets in particular (machine learning and deep learning), the scope is far beyond what humans could have or can imagine.

From asking Alexa to order our pizza to unlock our phone through facial recognition, we all have explored AI applications in our daily life. Given that, would it be strange to know that AI applications have surpassed our regular lives and are now taking over space (Indian moon mission — Chandrayaan-2, for instance)?

For it’s obvious, space exploration is a vast topic. And human intelligence needs something to complement it to be able to comprehend the intricacies of space. There cannot be a better model than AI to do that.

Space is so vast how can we ever explore all of it? We may finally have an answer — Artificial Intelligence.

The world is but a mystery and AI could help in finding answers and explore such mysteries.

AI (Artificial Intelligence) has long been a companion of space research agencies like NASA, European Space Agency, CNSA (China National Space Administration) and Space X. The history of AI and space exploration is older than anyone could possibly think. Let’s travel back in time of World War II when more than 30 countries got involved in the war of the worlds. During World War II, a Rocket Booster technology was developed enabling the first generation of spaceflight, with the Soviet Union and the United States launching artificial satellites and interplanetary probes using AI technologies. The journey had started long back in the mid 20th century.

But the recent breakthroughs and discoveries have resulted in AI gaining momentum in space research. AI has helped astronomers discover two new planets in our solar system, along with exoplanet discoveries. AI has also helped in establishing new theories about how Mars lost some of its water.

AI Applications: Role of AI in Space Exploration ‍🚀

1. Space exploration gives rise to humongous amounts of data that cannot be analyzed through human intelligence. That is where Artificial Intelligence applications, score. Through analyzing and deriving the meaning of the data, AI can change the trajectory of space exploration. The data can help researchers find life on new planets. It can help identify and map patterns that were not possible by humans. Also, planets that have the right conditions to support life, can be known.
2. The rovers (robots) currently roaming the surface of Mars are required to make decisions without specific commands from the mission control. It is AI applications that make it possible. The NASA Curiosity rover, for example, can move on its own while avoiding obstacles on the way and determining the best route to travel.
3. The data that we receive from the space in the form of images. The challenge, however, is to decode those images and extract the needed information. Machine Learning can help here. The NASA Frontier Development Lab and tech-giants such as IBM and Microsoft have come together to leverage machine learning as a solution for solar storm damage detection, atmosphere measurement, and determining the ‘space weather’ of a given planet through the magnetosphere and atmosphere measurement. The same technique can also be used for resource discovery in the space and to identify suitable planet landing sites.
4. Machine Learning, a subset of Artificial Intelligence, had a role to play in the successful landing of SpaceX Falcon 9 at Cape Canaveral Air Force Station in 2015. It identified the best way to land the rocket through real-time data facilitating route prediction.
5. Through AI applications, the geological makeup and historical significance of a planet can be known. Not only this, but AI can also send, analyze, and classify images of the same and decide the next best action.
6. Deep Learning, a subset of Artificial Intelligence can be applied in automatic landing, intelligent decision-making and fully automated systems.
7. The new-generation spacecraft, by the courtesy of Artificial Intelligence applications, will be more independent, self-sufficient, and autonomous. AI will go beyond human limits to identify findings and send information back to Earth.
8. AI applications can optimize planetary tracking systems, enable smart data transmission, and nullify the risk of human error (by using predictive maintenance).

Achievements of AI — Past, Present, and Future👨🏿‍🚀

PAST:

• Earth Observing-1 — The satellite EO-1 (Earth Observing 1) has been successful in the past in gathering images of natural calamities. The AI functioning with it started to take pictures of the calamities even before the ground crew knew that the incident had taken place. It was the first satellite –

1. to map active lava flows from space;
2. to measure a facility’s methane leak from space;
3. to track re-growth in a partially logged Amazon forest from space.

• SKICAT — SKICAT (Sky Image Cataloging and Analysis Tool) identified what was beyond human capabilities. It classified approximately a thousand objects in low resolution during the second Palomar Sky Survey.

PRESENT:

• Kepler data — AI, with NASA and Google, made 2017- the year of discovery of two obscure planets.

1. Kepler-90, now- Kepler-90i.
2. Kepler 80, now- Kepler-80g.

• CIMON — Crew Interactive Mobile Companion, is basically, a head-shaped robot, used in the International Space Station. The device is an AI-based assistant for astronauts. It is capable of hearing and seeing and serves through searching for objects, inventory management, documenting experiments, videography, and photography.

FUTURE:

• GPS in Space — NASA Frontier Development Lab has been working on an AI application that would do the job of a GPS in space and would make it easy to explore Titan, Mars, or even the Moon. The use of GPS and the other GNSS systems in Medium Earth Orbit (MEO), Geostationary Orbit (GEO) and beyond, including cislunar space ( area between the earth and the moon), is “an emergent capability,” according to Miller (the Positioning Navigation and Timing (PNT) policy lead for the NASA Goddard Space Flight Center).

Now that we’ve discussed the past, present, and the future of space exploration, it would be an injustice to miss out on India’s recent achievement — Indian Moon Mission -Chandrayaan-2.

AI in Indian Moon Mission — Chandrayaan2

India’s second moon mission — Chandrayaan-2, has been a defining episode in the history of space exploration. But as we were busy noticing the indelible mark it made, there was something else that was happening. And that was the integration of Artificial Intelligence with Chandryaan-2’s rover — Pragyan.

Indian Space Research Organisation delivered Pragyan — a solar-powered robotic vehicle that was to explore the lunar surface on its six wheels.

Pragyan comprised –

• LIBS (Laser Induced Breakdown Spectroscope) from LEOS (Laboratory for Electro Optic Systems), Bengaluru. It was to identify elements present near the landing site.
• APIXS (Alpha Particle Induced X-ray Spectroscope) from the Physical Research Laboratory (PRL), Ahmedabad. It was to inspect the composition of the elements identified by LIBS near the landing site.

Artificial Intelligence enabled the Chandrayaan-2’s rover in the following manner –

• The AI-powered rover — Pragyan could communicate with the lander. It featured motion technology which was to help the rover move over and land on the lunar surface.
• Not only this, but the artificial intelligence algorithm could also help the rover detect traces of water and other minerals on the lunar surface.
• Through AI the rover could send images that would have been used for research and testing.

The Future of Space flight ‍🚀

AI-powered robots for future Mars exploration -

Scientists see great potential in expanding the role of AI on the Red planet. With Space X intending to colonize Mars and turning humans into space colonizers and NASA’s Mars Science laboratory mission which successfully landed Curiosity rover on Mars in August 2012, the rover is still operational and as of April 23, 2019, Curiosity has been on Mars for 2386 sols (2451 total days).

With the development of a highly capable AI humanoid by DLR, a German Space agency, our future homes on mars is further taking its shape. The humanoid, Rollin Justin, is a platform for research in service robots. It can handle tools, navigate obstacles and catch flying objects. The 200 Kg and 1.9 meters tall humanoid will carry out household tasks in the future and assist astronauts in space. The robot was first presented to the public in 2008.

It’ll be a while before intelligent robots are ready to do any real heavy lifting in the final frontier- say helping astronauts repair damaged spacecraft systems or treating sick crew members. This is a slice of future of human space flight.

“AI is already a game changer that has made scientific research and exploration much more efficient. We are not just thinking about a doubling but about a multiple of ten” -Leoplold Summerer, Head of the Advanced Concepts and studies office at ISA.

Medicine in Space — Exploration Medical Capability (ExMC)

Now that astronauts are moving further and further into space beyond the Earth orbit, what will happen if they need medical help? They will obviously not be able to return to Earth for a check-up with a doctor! For this reason, NASA is working on Exploration Medical Capability that will use Machine Learning to develop healthcare options based on the anticipated future medical needs of the astronauts. These healthcare options will be created by certified doctors and surgeons and they will learn and evolve with time according to the astronaut experiences.

Exploration Medical Capability — This is how the interior of a future medical habitat in space might look
Image Source — NASA

All in all, the main aim of the Exploration Medical Capability is that astronauts stay fit and healthy in space (Especially on long and far-away missions). And unlike what comic books tell you about space, some of the common health risks associated with space travel are radiation hazards, harsh environmental challenges, issues due to gravitational changes, etc. In these situations, the astronauts cannot directly contact doctors on Earth as there is a time-lag and so the ExMC uses machine learning to provide self-reliant autonomous medical care with the help of remote medical technologies.

Finding Other Planets in the Universe — Planetary Spectrum Generator

I am sure I don’t need to tell you that the universe is huge! NASA believes that there are around 100 billion stars in the galaxy and out of them about 40 billion may have life. This is not science fiction, NASA actually believes we may find aliens one day! But for discovering aliens, NASA first needs to discover more and more new planets in different solar systems. Once these exoplanets are discovered, then NASA measures the atmospheric spectrum of these planets to find if there is any possibility of life.

While these steps are complicated enough, the problem is that there is no real data available for experimentation! So NASA scientists just generate the required data and that’s where Machine Learning comes in. The Planetary Spectrum Generator is a tool that NASA uses to create 3-D orbits and atmospheric properties of the exoplanets they find. To create a working model for the solar system, scientists use linear regression as well as convolutional neural networks. Then further fine-tuning is conducted on the model before it is ready for training.

Image Source — NASA

The above image demonstrates the results generated for an exoplanet that demonstrate the amount of water and methane in the atmosphere. As you can see in the CH4 and H2O graph, the black lines denote the predictions that were made using Machine Learning and the red lines indicate the actual findings. As you can see the trained ML model is quite accurate in this situation!

Concluding Notes -“AI has infinite potential in terms of space exploration. It is justified to say that Artificial Intelligence will prove to a defining enabler in space revolution. There’s so much that we have seen, and so much more that we cannot possibly imagine.”