Virtual Reality Helping Expedite Driverless Cars

The New York Times recently had an article discussing virtual realities increasing role in helping driverless vehicles get on the road sooner. The article goes into specifics:

Waymo and many of its rivals have already embraced deep neural networks, complex algorithms that can learn tasks by analyzing data. By analyzing photos of pedestrians, for example, a neural network can learn to identify a pedestrian. These kinds of algorithms are also helping to identify street signs and lane markers, predict what will happen next on the road, and plan routes forward. The trouble is that this requires enormous amounts of data collected by cameras, radar and other sensors that document real-world objects and situations. And humans must label this data, identifying pedestrians, street signs and the like. Gathering and labeling data describing every conceivable situation is an impossibility. Data on accidents, for instance, is hard to come by. This is where simulations can help. Recently, Waymo unveiled a roadway simulator it calls Carcraft. Today, the company said, this simulator provides a way of testing its cars at a scale that is not possible in the real world. Its cars can spend far more time on virtual roads than the real thing. Presumably, like other companies, Waymo is also exploring ways that its algorithms can actually learn new behavior from this kind of simulator.

What is interesting here is how much quicker virtual reality and simulated scenarios are able to speed up the process of ensuring safety. I'm sure each of these companies will start to publicize how many 'virtual' miles their vehicles have gone. The question is, will 'virtual' miles comfort an already uncomfortable public in regards to driverless vehicles? Only time will tell.