Wednesday, July 28, 2021

Tesla backs vision-only autonomy approach using powerful supercomputer – TechCrunch

- Advertisement -

Must read

Tesla CEO Elon Musk has been testing a neural network training computer called the ‘Dojo’ since at least 2019. Musk says the Dojo will be able to process large amounts of video data to achieve vision-only autonomous driving. While Dojo is still in development, Tesla today revealed a new supercomputer that will serve as a prototype development version of what Dojo will eventually offer.

At the 2021 Conference on Computer Vision and Pattern Recognition on Monday, Tesla’s head of artificial intelligence Andrej Karpathy revealed the company’s new supercomputer that allows the automaker to ditch radar sensors and lidar in cars. autonomous in favor of high-quality optical cameras. During his workshop on autonomous driving, Karpathy explained that for a computer to respond to a new environment in a way that a human can, it requires an immense data set and an enormously powerful supercomputer to train the neural network-based autonomous driving technology. of the company using that data. place. Hence the development of these Dojo predecessors.

Tesla’s next-generation supercomputer has 10 petabytes of “hot tier” NVME storage and runs at 1.6 terbytes per second, according to Karpathy. At 1.8 EFLOPS, he said it could be the world’s fifth most powerful supercomputer, but later admitted that his team has yet to run the specific benchmark needed to enter the TOP500 supercomputer ranking.

“With that said, if you take the total number of FLOPS, it would actually rank somewhere around fifth place,” Karpathy told TechCrunch. “Fifth is currently held by NVIDIA with its Selene cluster, which has a very comparable architecture and a similar number of GPUs (4,480 vs. our 5,760, slightly less).”

Musk has been advocating a vision-only approach to autonomy for some time, largely because cameras are faster than radar or lidar. As of May, Tesla Model Y and Model 3 vehicles in North America are being built without radar, relying on cameras and machine learning to support their advanced driver assistance and autopilot system.

Many autonomous driving companies use LIDAR and high-definition maps, which means they require incredibly detailed maps of where they operate, including all lanes of the road and how they connect, traffic lights, and more.

“The approach we take is based on vision, using mainly neural networks that, in principle, can work anywhere on earth,” Karpathy said in his workshop.

Replacing a “meat computer”, or rather a human, with a silicon computer results in lower latencies (better reaction time), 360-degree situational awareness, and a fully attentive driver who never checks. her Instagram, Karpathy said.

Karpathy shared some scenarios of how Tesla’s supercomputer uses computer vision to correct driver misbehavior, including an emergency braking scenario in which the computer’s object detection kicks in to prevent a pedestrian from being struck, and a traffic control warning that can identify a yellow light in the distance and send an alert to a driver who has not yet begun to slow down.

Tesla vehicles have also tested a feature called pedal misapplication mitigation, in which the car identifies pedestrians in its path, or even the lack of a driving path, and responds when the driver accidentally steps on the accelerator in instead of braking, potentially saving pedestrians in your path. in front of the vehicle or prevent the driver from accelerating into a river.

Tesla’s supercomputer collects video from eight cameras surrounding the vehicle at 36 frames per second, providing incredible amounts of information about the environment around the car, Karpathy explained.

While the vision-only approach is more scalable than collecting, building, and maintaining high-definition maps around the world, it is also a much greater challenge, because neural networks that detect objects and drive driving have to be able to collect and process large amounts of data at speeds that match a human’s speed and depth recognition capabilities.

Karpathy says that after years of research, he believes it can be achieved by treating the challenge as a supervised learning problem. Engineers testing the technology found they could drive through sparsely populated areas without intervention, Karpathy said, but “they definitely struggle a lot more in very harsh environments like San Francisco.” In order for the system to really work well and mitigate the need for things like high-definition maps and additional sensors, you will have to improve a lot in handling densely populated areas.

One of the Tesla AI team’s game changes has been automatic tagging, through which it can automatically tag things like road hazards and other objects from millions of videos captured by vehicles on the Tesla camera. Large AI data sets have often required a lot of manual labeling, which is time consuming, especially when it comes to coming up with the kind of clearly labeled data set necessary for a supervised learning system in a neural network to work well.

With this latest supercomputer, Tesla has amassed 1 million videos of around 10 seconds each and tagged 6 billion objects with depth, velocity, and acceleration. All of this takes up a whopping 1.5 petabytes of storage. That sounds like a huge amount, but it will take much longer before the company can achieve the kind of reliability it requires from an automated driving system that relies only on vision systems, hence the need to continue to develop increasingly powerful supercomputers. in Tesla’s quest for more advanced AI.

Do Not Miss

More articles

LEAVE A REPLY

Please enter your comment!
Please enter your name here

B. Simone announces that she is no longer in a relationship...

0
"Single again, on the prowl again!" After a few months of happiness, love and happiness on the 'gram with the love of...

Shipping prices will keep rising, but it’s not a supercycle yet:...

0
A ship unloader unloads iron ore at a pier in Suzhou, Jiangsu province, China, April 6, 2021.Costfoto | Barcroft Media | fake...

Reaction of the WWE locker room to Big E’s victory at...

0
Big E has revealed that the overall reaction from his teammates to his Money in the Bank win was very overwhelming.The SmackDown star is...

AEW fighter sends a message to Triple H on his birthday

0
WWE Chief Operating Officer Triple H celebrated his 52nd birthday on Tuesday this week, with many wrestling fans, celebrities and personalities taking to social...

Concerns as India builds rail network in remote state near China...

0
Calcutta, India India's ambitious railway project to connect a small northeastern Indian state along its border with China with the rest of the country...

US tells people vaccinated in high-risk areas for Covid to re-mask

0
WASHINGTON: People vaccinated against Covid-19 in high-risk parts of the United States should go back to wearing masks indoors, the top health authority said...

“Now we will try different combinations”

0
The eve before the four-match T20I series against the West Indies begins, Pakistan captain Babar Azam has suggested that his team will seek to...

Tropical storm makes landfall in northern Japan

0
TOKYO: A tropical storm hit northern Japan on Wednesday, but there were no immediate reports of damage and Olympic soccer games in the region...

49ers plan to start Jimmy Garoppolo on Trey Lance

0
It was no secret that San Francisco 49ers coach Kyle Shanahan planned to open training camp with veteran Jimmy Garoppolo...

Tunisia tries to reassure as Ennahdha pushes for snap elections |...

0
Tunisia's foreign minister telephoned his counterparts in the European Union, as well as Turkey and the High Commissioner for Human Rights to reassure them...

South Korea sets another new record for daily Covid-19 cases

0
SEOUL: South Korea reports a new daily record for coronavirus cases a day after authorities enforced strict restrictions in areas outside the Seoul capital...

Greywing launches Crew Change to help shipping companies navigate COVID-19 regulations...

0
For fleet managers, managing shipping crew changes in different countries is an elaborate process even in the best of times, and now is definitely...

Microsoft’s overall gaming revenue increased to $ 3.7 billion in the...

0
US smartphone market sales grew 27% year-on-year in the first half of 2021 despite component shortages; OnePlus was up 428% YoY, Motorola 83%,...

Republican Party Jake Ellzey wins US House seat over Trump-backed rival

0
AUSTIN, Texas (AP) - Republican Jake Ellzey of Texas won a seat in the U.S. House of Representatives Tuesday night over a rival backed...

China tech selloff stalls as investors await Beijing’s next move

0
Chinese Stock UpdatesSign up for myFT Daily Digest to be the first to know about the news on Chinese stocks. Chinese stocks leveled off on...
- Advertisement -

Don't Miss