Google's Horn Honking Algorithm Instills Robo Road Rage In Its Self-Driving Cars

Part of being a safe driver is knowing when to use a car horn and to what degree. It's a skill that's lost on many drivers, who instead use the horn as an outlet for their frustration at other motorists rather than a warning signal that something bad is about to happen. Google's determined to teach its fleet of autonomous vehicles the correct way to use the horn.

Like so many other aspects of Google's self-driving cars, horn use relies on an algorithm. This is something Google developed slowly over time—at first, the horn would only be played inside the vehicle so that test drivers could offer feedback. This allowed Google to fine tune its horn honking algorithm without confusing other drivers.

Google Self Driving Car

"Each time our cars sound the horn, our test drivers take note whether the beep was appropriate, and this feedback helps our engineering team refine our software further," Google stated in its May 2016 monthly report for self driving cars. "As our honking algorithms improved, we've begun broadcasting our car horn to the world."

Google's even taught its autonomous vehicles to use different kinds of beeps. For example, if another car is reversing towards Google's self-driving car, it might sound two short, quieter pips to politely alert the inattentive driver. But if there's a driving situation that requires more urgency, Google's algorithm will respond in kind with a louder sustained beep.

"Our goal is to teach our cars to honk like a patient, seasoned driver. As we become more experienced honkers, we hope our cars will also be able to predict how other drivers respond to a beep in different situations," Google said.

No small thing, horn usage is particularly important in Google's prototype electric vehicles because they're relatively quiet to begin with and can sneak up on motorists, bicyclists, and pedestrians.

Via:  Google
Show comments blog comments powered by Disqus