Automated & Connected

Driverless Stanford test car Shelley nears speeds of 120 mph as it tears around Thunderhill Raceway in Willows, California. Photo: Kurt Hickman

Stanford neural network teaches AVs how to handle tough conditions—and go fast

Researchers at Stanford University have developed a new way of controlling autonomous cars that integrates prior driving experiences. Tested on a racetrack using Niki, Stanford’s autonomous Volkswagen GTI, and Shelley, Stanford’s autonomous Audi TTS, the system performed about as well as an existing autonomous control system and an experienced racecar driver.

According to a report from Stanford, current autonomous cars might rely on in-the-moment evaluations of their environment, the control system these researchers designed incorporates data from recent maneuvers and past driving experiences—including trips Niki took around an icy test track near the Arctic Circle. 

Control systems for autonomous cars need access to information about the available road-tire friction, says the Stanford report. This information dictates the limits of how hard the car can brake, accelerate, and steer in order to stay on the road in critical emergency scenarios. If engineers want to safely push an autonomous car to its limits, such as having it plan an emergency maneuver on ice, they have to provide it with details, like the road-tire friction, in advance. This is difficult in the real world where friction is variable and often is difficult to predict, according to Stanford.

To develop a more flexible, responsive control system, the researchers built a neural network—a type of artificially intelligent computing system—that integrates data from past driving experiences at Thunderhill Raceway in Willows, California, and a winter test facility with foundational knowledge provided by 200,000 physics-based trajectories.

The group ran comparison tests for their new system at Thunderhill. First, Shelley sped around controlled by the physics-based autonomous system, pre-loaded with set information about the course and conditions. When compared on the same course during 10 consecutive trials, Shelley and a skilled amateur driver generated comparable lap times. Then, the researchers loaded Niki with their new neural network system. The car performed similarly running both the learned and physics-based systems, even though the neural network lacked explicit information about road friction.


Subscribe to SAE’s growing collections of standards, papers, journals, books, and more:


“Our work is motivated by safety, and we want autonomous vehicles to work in many scenarios, from normal driving on high-friction asphalt to fast, low-friction driving in ice and snow,” said Nathan Spielberg, a graduate student in mechanical engineering at Stanford and lead author of the paper about the research, published in Science Robotics. “We want our algorithms to be as good as the best skilled drivers—and, hopefully, better.”

The results were encouraging, but the Stanford report says researchers stress that their neural network system does not perform well in conditions outside the ones it has experienced. They say as autonomous cars generate additional data to train their network, the cars should be able to handle a wider range of conditions.

This story was developed based on a report from Stanford University by Taylor Kubota

Read the paper: Neural network vehicle models for high-performance automated driving