Nvidia Video of Self-Driving Car in Rain, Unmarked Lanes

A new video from Nvidia researchers offers an extended view of an autonomous car driving on public roads in

Nearly all of the 14-minute video presents the point of view of a car observing the autonomous vehicle. There are a few minutes showing the autonomous car’s view as it travels a curving country road.

The researchers used an Nvidia DevBox and Torch 7 for training and an Nvidia Drive PX self-driving car using a Torch 7. The system operates at 30 frames per second.

The video shows the vehicle on a multilane highway, a curving country road, moving through a tight curve, driving in the rain, and on an unmarked dirt road.

The video was shot around Matawan and the Cheesequake State Park in N.J.

Much of the video shows the autonomous vehicle in a business park, and in what appears to be a parking lot that may have blocked off standard-driving vehicles.

The new video is linked to a paper “End to End Learning for Self-Driving Cars” from 13 Nvidia researchers based in the firm’s regional office in Holmdel, N.J., an old Bell Labs site.

The paper abstract reports the researchers “trained a convolutional Neural Network (CNN) to map raw pixels from a single-front-facing camera directly to steering commands.”

This system soon learned to drive on local roads “with and without lane markings,” on highways, and on unpaved roads, the researchers report.

The researchers says their system automatically learns how to detect road features with minimal human intervention.

They conclude that their system will bring better performance and smaller systems because “the internal components self-optimize to maximize overall system performance, instead of optimizing human-selected intermediate criteria, e.g., lane detection. Such criteria understandably are selected for ease of human interpretation which doesn’t automatically guarantee maximum system performance.

“Smaller networks are possible because the system learns to solve the problem with the minimal number of processing steps.”