The video shows cars are now basing decisions on things we can’t even see.
We’ve no doubt heard a lot about the future and imminence of self-driving cars over the past decade. Slowly, we’re facets of “autopilot” come online in the form of features like assisted braking and “smart” cruise control that maintains distance from cars as well as keeps the vehicle in its lane.
But the video below, recorded by a Tesla owner’s dashcam, gives a real-world example of just how far we’ve come. In it, you’ll hear the car issue a series of urgent beeps just a moment before two cars collide ahead of the driver. The car then slams on its brakes to avoid the collision unfolding in front of it.
The driver of the Tesla, Netherlands resident Hans Noordisj, says that he’s sure the car saved him. He said about the incident, “[The Autopilot] was essential,” Hans stated. “No one could predict the accident but the radar did and acted by emergency braking.”
Where this technology differs from others we’ve seen is that the beeping and braking aren’t based on the car directly in front of the Tesla, but rather the car in front of that one. The technology saw that a distant car (the black SUV) was braking whereas the car following it, the red hatchback, was not. The difference in speed signified that a collision was imminent, which triggered a Tesla feature in Autopilot called Forward Collision Warning.
Tesla confirmed this with a statement and offered a September blog post discussing the science behind the feature. It discusses using radar to analyze beyond line-of-sight using something the company calls “bounce.” It reads, “ a Tesla will also be able to bounce the radar signal under a vehicle in front —using the radar pulse signature and photon time of flight to distinguish the signal — and still brake even when trailing a car that is opaque to both vision and radar.”
In short, Tesla’s using this technology to make decisions on factors we can’t even see to ensure safety.
It’s likely a long time before the public gets comfortable with fully automated driving systems, but videos like this show their competence might far exceed our expectations, even after a decade of discussion.