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.
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.
Stratospheric balloons are a low-cost way to get above 99% of the atmosphere. Payloads lifted that high have wide views of Earth and clear views of the stars. For decades, NASA has launched a handful of stratospheric balloons every year. Although they float for months, they drift at constant altitudes. Now, upstart commercial companies like World View are launching smaller balloons that can remain in place by surfing stratospheric winds.
Efficiently navigating a superpressure balloon in the stratosphere1 requires the integration of a multitude of cues, such as wind speed and solar elevation, and the process is complicated by forecast errors and sparse wind measurements. Coupled with the need to make decisions in real time, these factors rule out the use of conventional control techniques2,3. Here we describe the use of reinforcement learning4,5 to create a high-performing flight controller. Our algorithm uses data augmentation6,7 and a self-correcting design to overcome the key technical challenge of reinforcement learning from imperfect data, which has proved to be a major obstacle to its application to physical systems8. We deployed our controller to station Loon superpressure balloons at multiple locations across the globe, including a 39-day controlled experiment over the Pacific Ocean.
Agents in Texas recently finished a 30-day trial of the camera-toting, helium-filled balloon made by Drone Aviation Holding Corp., a small startup that named former Border Patrol chief David Aguilar to its board of directors in January. The 3-year-old, money-losing company gave Aguilar stock options that may prove lucrative if it gets more orders for its proprietary model. The trial comes as agents test hand-launched drones, which are relatively inexpensive but hampered by short battery life and weight limits. The Border Patrol has also used six large tethered balloons in Texas since 2012, acquired from the Defense Department. President Trump has pledged to add 5,000 Border Patrol agents, but hiring has been slow.