AI in Space Research
Remember the robots CASE & TARS from Interstellar , the master piece made by Mr. Christopher Nolan, Yes that was fantasy but not going to remain so, as within few years from now we will be having our AI based robots helping astronauts in multiple space stations around Earth and other planets. It may sound like a distant dream with too much optimism but its going to be true with advanced computing capabilities and with the rise of Machine Learning and AI.
Here Comes CIMON!
CIMON was developed by the European aerospace company Airbus on behalf of the German space agency, which is known by its German acronym, DLR. The robot’s AI is IBM’s famous Watson system.
CIMON is roughly spherical and weighs 11 lbs. (5 kilograms). The robot can converse with people, and it knows whom it’s talking to thanks to facial-recognition software. (CIMON has a face of its own — a simple cartoon one.) The astronaut assistant is also mobile; once aboard the ISS, CIMON will be able to fly around, by sucking air in and expelling it through special tubes.
Though CIMON is flexible enough to interact with anyone, it’s “tailored to” European Space Agency astronaut Alexander Gerst, who arrived at the ISS aboard a Russian Soyuz spacecraft earlier this month. CIMON’s mission calls for the robot to work with Gerst on three separate investigations.
What Machine Learning And AI can achieve in Space Exploration & Research?
These are some of the fields of study which ML and AI has started helping.
Data transmission, Space Station Maintenance , Visual Data Analytics, Navigation , Rocket landing , Material Analysis, Structural Analysis , Biological research , Distance calculation and Risk management, Automation and Space Robotics.
Spacecrafts, satellites hovering around the earth or any other host planet are exposed to huge amount of data which they collect through several complex procedures. As these huge amount data is being collected, scientists need a specific and fault tolerant mechanism to transmit the data back to earth or to the parent spaceship. There lays the challenge of orbital spin , space obstacle , EM wave disruptions, magnetic anomalies. To overcome these challenges Scientist find specific window of opportunity when they can send these bulky data packets transmitted to required locations for further analysis.
Machine learning enables a “smart” method to manage the distant planet to Earth data transmission problem. The outer space machine learning application MEXAR2 (‘Mars Express AI Tool) was introduced in 2005 at Italy’s Institute for Cognitive Science and Technology (ISTC-CNR). The onboard learning algorithm can leverage historical data to remove superfluous data and pinpoint the download schedule to optimize data packet transmission. This outer data transmission technique is already being used by NASA and others in their space research programs.
The same kind of technology that speeds up your legal research with accuracy via ROSS Intelligence, can also speed up saving Earth with accuracy. Katherine Bourzac writes, “machine learning algorithms can more quickly identify and cluster the debris that comets leave in their wake. By speeding up analysis of meteor showers, researchers hope to pinpoint the orbits of distant, but potentially dangerous, comets. This project is one of five being explored as part of an artificial intelligence pilot research program sponsored by NASA.”
The Futurism site reports that “Any AI that we use in the future of space exploration will allow us to retrieve data from the places we send probes to, as well as allow us to explore them further, and collect better data. Since humans aren’t yet able to traverse these locales ourselves, unless we’re willing to hand at least some of that responsibility over to AI, it’s unlikely any of these missions could happen.”
Deep Learning also has its set of utilities in space, no matter however nascent in scope. Deep Learning can be applied in automatic landing, intelligent decision making and fully automated systems. ESA’s Advanced Concepts Team (ACT) is researching these possibilities. In particular, the ACT researched evolutionary computation, which includes writing computer code in such a manner so that all evolution possibilities are considered. The better results are kept, and the worse are simply rejected — just like in Darwinian ‘Survival of the Fittest’ evolution. This can be used to calculate the trajectories of the planets. ACT is also working on a community science mobile app that would enhance and improve the autonomous capability of space probes and optimize planetary and celestial tracking system.
The SpaceX Falcon 9’s successful landing at Cape Canaveral Air Force Station in 2015 demonstrated machine learning and computer vision’s power to transform space exploration. SpaceX used a convex optimization algorithm to determine the best way to land the rocket, with real-time computer vision data aiding route prediction. These advanced machine learning applications enabled the first reusable rocket in space exploration history — a feat scientists regard as essential in developing deep space exploration.
Boston Dynamics is improving theirs robots/ humanoids with latest AI and most promising ones are Atlas and spotmini. These class of robots will be very helpful in space research , bot deployment in space and data collection. As their intelligence increases through ML and AI , they can perform some of the critical and complex activities which only requires astronauts in space to do.
We are at the dawn of 4th Industrial revolution dominated by intelligence. Humans are poised to take the next step in the space. Researches in ML , AI and Robotics for space has enormous potential.
