SIMULATORS HELP ROBOTS

Simulators help robot cars prepare for the road. This technique offer a way to correct flaws without endangering real people.

As the computers that operate driverless cars digest the rule of the road, some engineers think it might be nice of they could learn from mistakes made in virtual reality rather than on real streets.

Companies like Toyota, Uber and Waymo have discussed at length how they are testing autonomous vehicles on the streets of Mountain View, Calif., Phoenix and other cities.

What is not as well known is that they are also testing vehicles inside computer simulations of these same cities.

Virtual cars, equipped with the same software as the real thing, spend thousands of hours during their digital worlds.

Think of it as a way of identifying flaws in the way the cars operate with out endangering real people.

If a car makes a mistake on a simulated drive, engineers can tweak its software accordingly, laying down new rules of behavior.

Researchers are also developing methods that would allow cars to learn new behavior from these simulations, gathering skills more quickly than human engineers could ever lay them down with explicit software code.

''Simulation is a tremendous thing,'' said Gill Pratt, chief executive of the Toyota Research Institute one of the Artificial Intelligence Labs exploring kind of virtual training for autonomous vehicles and their robotics.