acm-header
Sign In

Communications of the ACM

ACM TechNews

Nvidia Developing an 'Autonomous Car Driver's License' Based on Its Tech


View as: Print Mobile App Share:
The company is developing"driver's license" testing for self-driving cars, based on an open-source algorithm.

The Nvidia Drive AP2X release 9.0 can make decisions at complex intersections, work through congested traffic, and automatically move into a faster-moving lane without endangering the vehicle's occupants.

Credit: iStockPhoto

Nvidia recently announced that it will be releasing to developers version 9.0 of its Nvidia Drive platform for autonomous vehicles, and that it is working with German standards body TÜV SÜD to develop a kind of driver's license for self-driving cars.

The Nvidia Drive AP2X release 9.0 includes a few new features with which autonomous vehicle developers can experiment.

In addition, the software will be able to make decisions at complex intersections, work through congested traffic, and automatically move into a faster-moving lane without endangering the vehicle's occupants.

Drive 9.0 can also generate its own map data, piecing together information from cameras, LiDAR, and radar sensors to create a Local HD map that can be used for self-driving navigation after just a few human-piloted trips.

Nvidia has also developed Safety Force Field, an open-source collision avoidance algorithm for autonomous vehicles that uses computational predictions to estimate where nearby cars, pedestrians, and other obstructions will be in the immediate future.

From CNet
View Full Article

 

Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account