The big new idea for making self-driving cars that can go anywhere

Cruise control

Either way, should we trust these new waves of companies to chase the front runners? Surprisingly, Moe Elshenvi, executive vice president of engineering at Cruz, is unsure. “The way art exists today is not enough to get us to the cruise stage,” he says.

Cruise is one of the most advanced driverless car companies in the world. It has been operating a live robotaxi service in San Francisco since November. Its vehicles run in a limited area, but now anyone can greet the car with a cruise app and drag it to the curb with someone inside. “We see a real spectrum of our customers’ reactions,” says Elshenvi. “It’s incredibly exciting.”

Cruise has built a huge virtual factory to support its software, with hundreds of engineers working on various parts of the pipeline. ElShenawy argues that the mainstream modular approach is an advantage because it allows the company to swap new technologies as well.

It also rejects the notion that Cruise’s approach will not generalize to other cities. “We could have launched somewhere in the suburbs years ago, and that would have drawn us into a corner,” he says. “The reason we chose a complex urban environment, such as San Francisco — where we see thousands of cyclists and pedestrians and emergency vehicles and cars that cut you off — was very deliberate. It forces us to create something that can easily scale.

But before Cruz can move to a new city, he must first map his streets in centimeter-level details. Most driverless car companies use this type of high-definition 3D map. They provide additional information to the vehicle on top of the raw sensor data obtained on the trip, including whether there are usually signs such as lane boundary and location of traffic lights or restrictions on a specific area of ​​the street.

These so-called HD maps are created by combining the road data collected by the camera and the leader with satellite imagery. Millions of miles of roads have been mapped in this way in the US, Europe and Asia. But the road layout changes every day, which means there is an endless process of mapping.

Many driverless car companies use HD maps created and maintained by specialized companies, but Cruise makes its own. “We can rebuild cities – all driving conditions, street layouts and everything,” says Elshenvi.

This gives Cruise an edge over mainstream competitors, but newcomers like Wave and Autobrains have completely falsified the HD map. Wavey’s cars have GPS, but they learn to read the road using sensor data alone. It may be difficult, but it does mean that they are not connected to a specific location.

Similar Posts

Leave a Reply

Your email address will not be published.