NIO Will Use NVIDIA Drive Orin Chips for AI Driving

NIO will use NVIDIA DRIVE for advanced automated driving technology in its future fleets, marking the genesis of truly intelligent and personalized NIO vehicles.

The NIO ET7 sedan will ship in China starting in 2022. ET7 will use an NVIDIA-powered supercomputer, called Adam, that uses NVIDIA DRIVE Orin to deploy advanced automated driving technology.

“The cooperation between NIO and NVIDIA will accelerate the development of autonomous driving on smart vehicles,” said NIO CEO William Li. “NIO’s in-house developed autonomous driving algorithms will be running on four industry-leading NVIDIA Orin processors, delivering an unprecedented 1,000+ trillion operations per second in production cars.”

The Orin chip is capable of delivering up to 254 TOPS to handle the large number of applications and deep neural networks that run simultaneously in autonomous vehicles and robots, while achieving systematic safety standards such as ISO 26262 ASIL-D.

By using multiple SoCs, Adam integrates the redundancy and diversity necessary for safe autonomous operation. The first two SoCs process the 8 gigabytes of data produced by the vehicle’s sensor set every second. The third Orin serves as a backup to ensure the system can still operate safely in any situation, while the fourth enables local training, improving the vehicle with fleet learning as well as personalizing the driving experience based on individual user preferences.


NIO ET7 sedan was revealed. The ET7 has 600 miles range and advanced autonomous driving. ET7 can perform point-to-point autonomy, leveraging 33 sensors and high-performance compute to continuously expand the domains in which it operates — from urban to highway driving to battery swap stations.

Written By Brian Wang,

7 thoughts on “NIO Will Use NVIDIA Drive Orin Chips for AI Driving”

  1. 1000 TOPS is not a supercomputer nowadays.
    1000 TFLOPS would not even make it as #500 in the top supercomputer list and we are not even talking about Floating point here


  2. But what sort of ops(operations)? I think this sort of work is done with tensor, rather than floating point, or integer operations. How many tensor ops per second is 1000 TOPS.

  3. Interesting. This is the first competitor to Tesla who is starting their journey towards full self driving. And its a chinese automaker, not an European or american one.

  4. Being able to match Chinese driving standards should be feasible. Gives them the ability to gather years of data while trying to make it safe.

  5. Obvious question: How does the ORIN compare to the Tesla in house solution for autonomous driving?
    Hopefully competition in self driving will force Tesla's self driving price down from it's current $10,000. I understand that the not yet self driving option goes for much less than that on used Tesla's already.

Comments are closed.