Project Loon is using balloons such as this to set up an aerial wireless network for telecommunications.Credit: Loon The goal of an autonomous machine is to achieve an objective by making decisions while negotiating a dynamic environment. Given complete knowledge of a system's current state, artificial intelligence and machine learning can excel at this, and even outperform humans at certain tasks -- for example, when playing arcade and turn-based board games1. But beyond the idealized world of games, real-world deployment of automated machines is hampered by environments that can be noisy and chaotic, and which are not adequately observed. The difficulty of devising long-term strategies from incomplete data can also hinder the operation of independent AI agents in real-world challenges. Writing in Nature, Bellemare et al.2 describe a way forward by demonstrating that stratospheric balloons, guided by AI, can pursue a long-term strategy for positioning themselves about a location on the Equator, even when precise knowledge of buffeting winds is not known.
Alphabet's Loon, the team responsible for beaming internet down to Earth from stratospheric helium balloons, has achieved a new milestone: its navigation system is no longer run by human-designed software. Instead, the company's internet balloons are steered around the globe by an artificial intelligence -- in particular, a set of algorithms both written and executed by a deep reinforcement learning-based flight control system that is more efficient and adept than the older, human-made one. The system is now managing Loon's fleet of balloons over Kenya, where Loon launched its first commercial internet service in July after testing its fleet in a series of disaster relief initiatives and other test environments for much of the last decade. Similar to how researchers have achieved breakthrough AI advances in teaching computers to play sophisticated video games and helping software learn how to manipulate robotic hands in lifelike ways, reinforcement learning is a technique that allows software to teach itself skills through trial and error. Obviously, such repetition is not possible in the real world when dealing with high-altitude balloons that are costly to operate and even more costly to repair in the event they crash.
High-flying balloons are bringing broadband connectivity to remote nations and post-disaster zones where cell towers have been knocked out. These "super-pressure" helium-filled polyethylene bags float 65,000 feet up in the stratosphere, above commercial planes, hurricanes, and pretty much anything else. But keeping a fleet of tennis-court-sized, internet-blasting balloons hovering over one spot has been a tricky engineering problem, just like keeping a boat floating in one place on a fast-moving river. Now researchers at Google spinoff Loon have figured out how to use a form of artificial intelligence to allow the balloon's onboard controller to predict wind speed and direction at various heights, then use that information to raise and lower the balloon accordingly. The new AI-powered navigation system opens the possibility of using stationary balloons to monitor animal migrations, the effects of climate change, or illegal cross-border wildlife or human trafficking from a relatively inexpensive platform for months at a time.
The largest pressurized balloon to be launched by NASA has set a record for endurance: the longest midlatitude flight by a large scientific balloon. For decades, conventional "zero-pressure" balloons have given researchers a high-altitude platform for studying atmospheric chemistry, the cosmic microwave background, and many other phenomena. But at temperate latitudes, the endurance of conventional balloons is limited. So-called superpressure balloons promise to bring that endurance to temperate latitudes, opening new phenomena to observation. Packing 532,000 cubic meters of helium and measuring 114 meters in diameter, NASA's latest superpressure balloon circled the Southern Hemisphere for 46 days, lofting a gamma ray telescope to the edges of space.
It's a brisk December morning at Spaceport Tucson, America's premiere (only?) dedicated launch pad for stratospheric balloons, and a small army of technicians in reflective vests is milling around on the concrete and dethawing after a long, cold night. Nearby, a white metal tripod the size of a smart car is tethered to two dozen solar panels and hundreds of feet of clear plastic that stretches across the pad. This alien-looking contraption is referred to as a "stratollite," a portmanteau of "stratospheric satellite," operated by a company called World View Enterprises. It's a finely honed surveillance device outfitted with a suite of sensors and a camera sensitive enough to detect people standing on the ground from the edge of space. The stratollite travels by virtue of two balloons, one filled with helium to provide lift, and the other with pressurized air, which functions as a steering system.