https://nighthawkrottweilers.com/

https://www.chance-encounter.org/

Business

Tesla doubles its radical approach to self-driving cars




CEO Elon Musk and other Tesla executives explained to investors Monday that their plans to have more than one million fully self-propelled Teslas on roads next year.

The optimistic rhetoric contrasts with the rest of the autonomous vehicle industry, which warns to a greater extent how long and hard a way it will be to get such cars on the streets a lot. Tesla has already forged ahead with the Autopilot software, which has been distributed in some vehicles since 2015 and handles less driving tasks. Tesla sees Autopilot as an incremental step towards full self-propelled vehicles. The software can be updated with an over-the-air update.

Tesla also stands up for its approach to building a safe self-propelled car.

The company will not rely on high-definition maps to control its vehicles; there will be no geofenced boundaries that limit where the cars can run and it does not use a sensor nearly all other views as essential. The sensor, called LIDAR, is appreciated for its ability to tell a vehicle exactly how far away from nearby objects are, such as a pedestrian, car, or intersection.

Instead, Tesla will rely on cameras, radar and ultrasonic sensors to understand the environment of a car.

"LIDAR is an idiot's origin. Everyone who trusts LIDAR is doomed," said Musk, who described LIDAR as expensive and unnecessary.

LIDAR usually dents from the roof of a self-propelled car, which resembles a spinning bucket of roasted chicken. Early LIDAR sensors cost $ 75,000, but the costs have declined as the industry evolves and the sensors are made in larger quantities.

  Tesla's promise of

Tesla's approach is controversial, and has drawn public criticism from competitors.

"These vehicles that do not have LIDAR and which do not have advanced radar that has not taken a 3D map are not self-propelled vehicles," said Ken Washington, Ford Vice President of Research and Advanced Technology on an event earlier this month. "Let me just emphasize that. They are consumer cars with a very good driver-assisted technology."

Tesla claims that if people can run with two eyes, machines should be able to run with cameras.

Andrei Karpathy, Tesla senior director of artificial intelligence, described LIDAR on Monday as a shortcut that gives self-car companies a false sense of progress.

"Is that person distracted and on their phone? Should they go into your lane?" Karpathy said. "These answers are only found in vision."

He said that Tesla is training an artificial intelligence system to understand what is happening on roads from camera images taken by Tesla's fleet. He described how Tesla had taken a picture of a bicycle mounted on the back of a vehicle, and used it to search for similar images of the Tesla fleet. Then Tesla found a lot of photographs of bikes on the back of cars, and used them to train his AI to distinguish between a bike that was ridden on a street and a bike mounted on the back of a car. Understanding such differences is essential before cars can operate without human drivers.

Experts say the technology is state of the art.

"It's remarkable. It's incredibly technological," said Bryan Reimer, researcher at MIT AgeLab and assistant director of the New England University Transportation Center at MIT. "I don't think anyone else in the industry can do it in near real time."

Reimer also warns that there may be threatening restrictions that reduce Tesla's success.

"Everyone else is betting on the other way," Reimer said. "At some point we know if Musk is right or wrong, but it can be decades."



Source link

Back to top button

mahjong slot

https://covecasualrestaurant.com/

sbobet

https://mascotasipasa.com/

https://americanturfgrass.com/

https://www.revivalpedia.com/

https://clubarribamidland.com/

https://fishkinggrill.com/