ForceGT.com

Tesla updates Autopilot: Seeing the World in Radar

Tesla has revamped its Autopilot semi-autonomous driving technology with an incremental update designed to improve collision prevention.

The version 8.0 update will, for the first time, use the car’s onboard radar as a primary control sensor without requiring the camera to confirm visual image recognition. Previously, the radar was only used as a supplementary sensor to the primary forward-facing camera and image processing system. With the new update and thanks to more advanced signal processing, the radar will now be used as one of the main image sensor inputs to ‘stitch’ together a better picture of the world around it.

According to Tesla, version 8.0 unlocks access to six times as many radar objects with the same hardware with a lot more information per object. The radar snapshots are then assembled, which take place every tenth of a second, into a 3D “picture” of the world.

As it is hard to tell from a single frame whether an object is moving or stationary or to distinguish spurious reflections, the system compares several contiguous frames against vehicle speed and expected path to determine if something is real and assess the probability of collision.

The new software also introduces ‘fleet learning’, where Tesla’s vehicle fleet will take no action in confusing situation – such as approaching an overhead highway road sign positioned on a rise in the road or a bridge where the road dips underneath – except to note the position of road signs, bridges and other stationary objects, mapping the world according to radar.

The car computer will then silently compare when it would have braked to the driver action and upload that to the Tesla database. If several cars drive safely past a given radar object, whether Autopilot is turned on or off, then that object is added to the geocoded whitelist.

The update also adds other improvement to the Autopilot system, amongst them are:

Read ForceGT’s Tesla Autopilot Review