Google’s Project Loon will be controlled by AI, instead of algorithms

In order to efficiently handle Google’s giant white Internet-delivering balloons, the Project Loon team has revealed that it's using artificial intelligence technology instead of hard-coded algorithms.

Initially, the Project Loon team used algorithms to change the altitude and stay in position. However, due to unexpected weather patterns, its range was limited in the aerial phase. Hence, it is replacing static algorithms with artificial intelligence technology i.e., machine learning to alter balloons' behavior and keep them in position for much longer.

According to a report in Wired, AI system can keep analyzing new data to improve how to react to conditions in a way that a hard-coded algorithm can’t, comparing the actual flight path to the intended one for a given decision.

Using the same, one test balloon stayed in the Peruvian stratosphere for 98 days, adapting to tricky wind conditions that might have sent it drifting away.

The AI-based upgrade should not only keep balloons in place for longer but help Google trim costs and expand its reach. With fewer balloons and with aerial internet access, it can either scale back the size of the fleet or spread out over a wider area.

Google has also placed, "reinforcement learning" in the balloon which will keep refining its behavior even after making predictions as to what will happen.