Nvidia has announced the Drive PX2, the “world’s first in-car artificial intelligence supercomputer” for self-driving cars at the Computer Electronics Show (CES) 2016. The device promises to “boost the IQ of autonomous vehicles” thereby paving the way to a safer future on the road. Here is everything we know so far about the Drive PX2.
Peeking under the hood
The Drive PX2 is a powerful piece of hardware to say the least. The device is powered by two next-gen Tegra (System on Chip) SOCs processors and two discrete Pascal GPU’s (The upcoming GPU architecture by Nvidia expected to hit the gaming hardware market later this year.
It features 12 CPU cores and four chips that pack the Pascal GPU, which translates into 8 TFLOPs of performance and 24 Deep Learning (DL) TOPs. That is 24 Trillion Deep Learning Operations per second. “Deep Learning operations are specialized instructions that accelerate the math used in deep learning network inference” which means it is more than 10 times as powerful as last year’s Drive CX.
Now the numbers here might not make sense to most, so in comparison, if you look at the GeForce Titan X, the GPU produces 7 TFLOPs of processing power and 7 DL TOPs. Further, Nvidia explains that the Drive PX2 has the power equivalent to 150 MacBook Pros to put the device’s power into a real world perspective.
Nvidia’s CEO and co-founder Jen-Hsun Huang states that: “It's the first supercomputer made for cars - it's certainly the first we've seen with such insane specs.”
With the processing power of the device comes a lot of heat, which is why Nvidia’s Drive PX2 utilizes a liquid-cooling system to keep the device at low temperatures and running smoothly.
With great power comes great progress
It’s an extremely difficult task to create a fully self-driving vehicle that can handle all the pressures and reactions a driver faces each day. With the immense processing power that the Drive PX2 offers and by utilizing deep learning on Nvidia’s most advanced GPU architecture, the automotive industry has just gotten a big push forward.
The Drive PX2 can handle the calculations needed for artificial intelligence to quickly learn “how to address the challenges of everyday driving, such as unexpected road debris, erratic drivers and construction zones. Deep learning also addresses numerous problem areas where traditional computer vision techniques are insufficient - such as poor weather conditions like rain, snow and fog, and difficult lighting conditions like sunrise, sunset and extreme darkness." - Source
The Drive PX2 delivers 360-degree situational awareness around the vehicle to “determine precisely where the car is and to compute a safe, comfortable trajectory.”
Nvidia’s CEO and co-founder Jen-Hsun Huang comments:
"Drivers deal with an infinitely complex world. Modern artificial intelligence and GPU breakthroughs enable us to finally tackle the daunting challenges of self-driving cars. Nvidia's GPU is central to advances in deep learning and supercomputing. We are leveraging these to create the brain of future autonomous vehicles that will be continuously alert, and eventually achieve superhuman levels of situational awareness. Autonomous cars will bring increased safety, new convenient mobility services and even beautiful urban designs -providing a powerful force for a better future."
For a deeper explanation of how self-driving vehicles work, check out Nvidia’s post entitled: “Eyes on the Road: How Autonomous Cars Understand What They’re Seeing”
Further, Nvidia revealed the "world’s biggest infotainment system" during some demos on stage, stating on their blog that:
“The highlight of the demos was what Huang called the world’s largest car infotainment system - an elegant block the size of a medium-sized bedroom wall mounted with a wide horizontal screen and a tall vertical one.
While a third larger screen showed the scene that a driver would take in, the wide demo screen showed how the car - using deep learning and sensor fusion - 'viewed' the very same scene in real time, stitched together from its array of sensors. On its right, the huge portrait-oriented screen shows a highly precise map that marked the car’s progress. It’s a demo that will leave an impression on an audience that’s going to be hearing a lot about the future of driving in the week ahead.” - Source
Automakers on Nvidia’s technology
Nvidia’s AI platform for deep learning and autonomous driving development was adopted by over 50 automakers, suppliers, research institutions and “tier 1 suppliers” when the first Drive CX was announced last year. Let’s take a look at what some of the individuals working with the technology has to say.
Director of Architecture Driver Assistance Systems at Audi, Matthias Rudolph, states:
"Using NVIDIA's DIGITS deep learning platform, in less than four hours we achieved over 96 percent accuracy using Ruhr University Bochum's traffic sign database. While others invested years of development to achieve similar levels of perception with classical computer vision algorithms, we have been able to do it at the speed of light."
Head of BMW’s Group Technology Office in the US, Uwe Higgen, states:
"BMW is exploring the use of deep learning for a wide range of automotive use cases, from autonomous driving to quality inspection in manufacturing. The ability to rapidly train deep neural networks on vast amounts of data is critical. Using an NVIDIA GPU cluster equipped with NVIDIA DIGITS, we are achieving excellent results."
Director of Vehicle Automation at Daimler, Ralf G. Herrtwich, states:
"Due to deep learning, we brought the vehicle's environment perception a significant step closer to human performance and exceed the performance of classic computer vision."
Technical Director of the Ford Research and Innovation Center, Dragos Maciuca, states:
"Deep learning on NVIDIA DIGITS has allowed for a 30X enhancement in training pedestrian detection algorithms, which are being further tested and developed as we move them onto NVIDIA DRIVE PX." - Source
Volvo leads the way to a crash-free future
The journey to a “crash-free future” will make its public start in 2017. The first automaker to deploy the Drive PX2 in its vehicles is Volvo, a brand “known for safety and reliability”. The Swedish Automaker will lease 100 XC90 luxury SUVs using the Drive PX2 technology in the world’s first public autonomous driving trial.
It is important to note that the vehicles will only drive autonomously around Volvo’s hometown of Gothenburg, while anywhere else the vehicles will be restricted to semi-autonomous driving.
It is clear that Nvidia’s technology is helping automakers increase the efficiency of self-driving vehicles by a large margin. With the immense power of the Drive PX2, we might finally see safe, fully self-driving vehicles become a reality.
Would you use a self-driving car in the future? How powerful do you think Nvidia GPU’s based on the Pascal architecture will be? Let us know in the comment section below.
Sources: Nvidia, Nvidia 2, WCCF Tech
Sillicur Twitter / MWEB GameZone Twitter | Facebook