We “train” our autonomous system to recognize traffic signs and obey the rules of right-of-way on the road. Although deep learning is used to classify everything the self-driving car sees, stationary road features such as stop signs are pulled from pre-created High Definition (HD) maps. HD maps are high-precision maps specifically built for autonomous vehicles. Because features like stop signs are built into the maps, they are immune to obscuration, defacement, poor lighting, and inclement weather.

Here, the Torc self-driving car obeys a stop sign and correctly gives the right-of-way to the vehicle on the other side of the road. It then detects and waits for an approaching car to pass before continuing to drive.

We’re showcasing the capabilities of our autonomous car system on real public roads with real scenarios the car has encountered. To get updates on the latest videos, check back on our blog or subscribe to our YouTube channel.