Nvidia Unveils Single-Chip Version of Drive PX 2 for Self-Driving Cars
The new offering will expand the GPU maker's portfolio of products aimed at the rapidly growing autonomous vehicle market.Nvidia officials are looking to accelerate the development of self-driving cars with the release this week of a smaller version of the Drive PX 2 platform that was introduced earlier this year. At the company's GPU Technology Conference (GTC) in Beijing Sept. 12, Nvidia executives introduced the new single-processor Drive PX 2 that is designed for what they called "auto cruise" functions, including automated driving and high-definition mapping. Like its larger brethren, the new version uses artificial intelligence (AI) capabilities and machine learning to enable the computer system in the car to collect, storage and process data from multiple cameras and sensors in real time. Through the capabilities of Drive PX 2, self-driving cars will be able to instantly understand the environment around them and react accordingly to avoid accidents and enable point-to-point autonomous driving, according to Nvidia officials. The new version of the platform will make it easier for car makers to incorporate the Nvidia technology into their designs, according to Rob Csonger, vice president and general manager of Nvidia's automotive business unit. "Bringing an AI computer into the car in a small, efficient form factor is the goal of many automakers," Csonger said in a statement. "Nvidia Drive PX 2in the car solves this challenge for our OEM and tier-one partners and complements our data center solution for mapping and training."
The palm-sized computer will be used by Chinese tech vendor Baidu as the in-vehicle car computer for the company's map-based self-driving offer to car makers. Nvidia and Baidu announced a partnership in August in which the company's will unite Baidu's cloud and deep-learning capabilities with Nvidia's self-driving car platform.