Space travel is becoming more and more dangerous because of the increasing amount of junk orbiting the Earth. According to studies, there are at least 34,000 pieces of trash bigger than 10cm in diameter which are orbiting the Earth at around 10 times the speed of a bullet. To further illustrate this damage potential, imagine an object as big as a gluestick can impact like 25 sticks of dynamite!  

While the International Space State just avoided a possible colliision and a catastrophe with unknown pieces of debris in Septermber, as space trash rapidly grows, scientists worry that such occurances will only increase in the near-future. And therefore, the scietific community is looking for a solution. 

The European Space Agency (ESA) is already working on a solution with the help of Artificial Intelligence (AI). Together with the Swiss startup ClearSpcae, a spin-off from the Ecole Polytechnique Fédérale de Lausanne (EPFL), the ESA plans to launch the world's first debris-clearing space mission, aptly named, ClearSpace - 1, in 2025. 

The clearing mission, ClearSpace - 1 will be able to find debris thanks to the AI-enabled cameras embedded into the system. Once identified as an artificial debri, its robotic arms will collect objects, bring it back to atmospher and burn it. 

“A central focus is to develop deep learning algorithms to reliably estimate the 6D pose (three rotations and three translations) of the target from video-sequences even though images taken in space are difficult,” said Mathieu Salzmann, an EPFL scientist spearheading the project. “They can be over- or under-exposed with many mirror-like surfaces.” 

Their first mission is the removal of Vespa Upper part, an obsolete, 100-kg payload adaptor that is orbiting the Earth from a distance of 660 km. Since the Vespa hasn't been seen for nearly seven years, the EPFL train the ClearSpace - 1 algorithms with the help of a database of synthetic images of the Vespa. 

Once the mission launches, EPFL will finetune the AI system based on real-life images from the Earth's orbit and beyond. “Since motion in space is well behaved, the pose estimation algorithms can fill the gaps between recognitions spaced one second apart, alleviating the computational pressure,” said Professor David Atienza, head of ESL.

“However, to ensure that they can autonomously cope with all the uncertainties in the mission, the algorithms are so complex that their implementation requires squeezing out all the performance from the platform resources.”

If the mission is successful in clearing the space of human-created trash, it could pave the way for further missions that can make space commute, a safer endevour.