Computers
NVIDIA's latest computer designed to help develop self driving cars might have a lot of other applications apart from our future roadways. Computer technology built for handling artificial intelligence and deep neural network processing like the new DRIVE PX system are pointing the way to a future of smart devices and system that are straight out of science fiction.
The soon-to-be-available NVIDIA DRIVE PX is the world's most advanced autonomous car platform according to the chip maker. Unveiled recently at the Consumer Electronics Show, in Las Vegas, Drive PX 2 provides supercomputer-like performance in an enclosure the size of a lunchbox.
NVIDIA claims the Drive PX is capable of processing up to 24 trillion operations per second for artificial intelligence applications.
"Drivers deal with an infinitely complex world," said Jen-Hsun Huang, NVIDIA co-founder and CEO. "Modern artificial intelligence and GPU breakthroughs enable us to finally tackle the daunting challenges of self-driving cars."
"The brain of future autonomous vehicles will be continuously alert, and eventually achieve superhuman levels of situational awareness."
Huang says, "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."Combining deep learning, sensor fusion, and surround vision to change the driving experience, the drive PX delivers several new computational and sensor capabilities, including the ability to fuse data from 12 cameras, as well as lidar, radar, and ultrasonic sensors.
Related articles
These capabilities allow algorithms to accurately understand the full 360 degree environment around the car to produce a robust representation, including static and dynamic objects.Using Deep Neural Networks (DNN) for the detection and classification of objects, the new system can accurately interpret the sensor data into meaningful code for driving. Drive PX also includes an advanced computer vision library and primitives. These technologies deliver an impressive combination of detection and tracking (see video below).
The Drive PX is intended to be used by auto makers in research and development projects abut if it works as promoted, it could help advance much more than self driving cars.
Enderle points out the computer might also find its way into applications for cities, the military and robotics.
With computational abilities and image recognition systems like the DRIVE PX could help manage traffic lights, emergency responders and security systems in urban areas. Integration of a deep neural network enabled system would also mean that a highly customized approach would not be required.
For military applications, such a system could be used in naval and aircraft implementations and might dramatically drive down the cost of automating many military vehicles. "Since DRIVE PX 2 is designed to network with other vehicles, it‘s already set up to coordinate with a battle group of ships, coordinating a response between a carrier and its destroyer escort far better and far more cheaply than deployed systems," writes Enderle.
Self driving cars are essentially robotic vehicles, and the DRIVE PX and systems like it could be applied to a wider range of robotic applications.
Enderle writes, "DRIVE PX 2 is only focused on cars, which is why I think NVIDIA hasn’t yet realized just how powerful a digital brain tied to deep learning could actually be."
0 comments:
Post a Comment