Stanford autonomous car learns to handle unknown conditions

March 27, 2019

Researchers at Stanford University have developed a new way of controlling autonomous cars that integrates prior driving experiences - a system that will help the cars perform more safely in extreme and unknown circumstances. Tested at the limits of friction 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.

"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 this research, published March 27 in Science Robotics. "We want our algorithms to be as good as the best skilled drivers - and, hopefully, better."

While 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. Its ability to learn from the past could prove particularly powerful, given the abundance of autonomous car data researchers are producing in the process of developing these vehicles.

Physics and learning

Control systems for autonomous cars need access to information about the available road-tire friction. 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.

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.

"With the techniques available today, you often have to choose between data-driven methods and approaches grounded in fundamental physics," said J. Christian Gerdes, professor of mechanical engineering and senior author of the paper. "We think the path forward is to blend these approaches in order to harness their individual strengths. Physics can provide insight into structuring and validating neural network models that, in turn, can leverage massive amounts of data."

The group ran comparison tests for their new system at Thunderhill Raceway. 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.

In simulated tests, the neural network system outperformed the physics-based system in both high-friction and low-friction scenarios. It did particularly well in scenarios that mixed those two conditions.

An abundance of data

The results were encouraging, but the 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.

"With so many self-driving cars on the roads and in development, there is an abundance of data being generated from all kinds of driving scenarios," Spielberg said. "We wanted to build a neural network because there should be some way to make use of that data. If we can develop vehicles that have seen thousands of times more interactions than we have, we can hopefully make them safer."
To read all stories about Stanford science, subscribe to the biweekly Stanford Science Digest.

Co-authors of the paper are graduate students Matthew Brown and John C. Kegelman and postdoctoral scholar Nitin R. Kapania, all of Stanford. Gerdes is also senior fellow in the Precourt Institute for Energy.

This research was funded by the National Science Foundation, a William R. and Sara Hart Kimball Stanford Graduate Fellowship and Volkswagen Group of America, with additional support from Volkswagen Group Research.

Stanford University

Related Physics Articles from Brightsurf:

Helium, a little atom for big physics
Helium is the simplest multi-body atom. Its energy levels can be calculated with extremely high precision only relying on a few fundamental physical constants and the quantum electrodynamics (QED) theory.

Hyperbolic metamaterials exhibit 2T physics
According to Igor Smolyaninov of the University of Maryland, ''One of the more unusual applications of metamaterials was a theoretical proposal to construct a physical system that would exhibit two-time physics behavior on small scales.''

Challenges and opportunities for women in physics
Women in the United States hold fewer than 25% of bachelor's degrees, 20% of doctoral degrees and 19% of faculty positions in physics.

Indeterminist physics for an open world
Classical physics is characterized by the equations describing the world.

Leptons help in tracking new physics
Electrons with 'colleagues' -- other leptons - are one of many products of collisions observed in the LHCb experiment at the Large Hadron Collider.

Has physics ever been deterministic?
Researchers from the Austrian Academy of Sciences, the University of Vienna and the University of Geneva, have proposed a new interpretation of classical physics without real numbers.

Twisted physics
A new study in the journal Nature shows that superconductivity in bilayer graphene can be turned on or off with a small voltage change, increasing its usefulness for electronic devices.

Physics vs. asthma
A research team from the MIPT Center for Molecular Mechanisms of Aging and Age-Related Diseases has collaborated with colleagues from the U.S., Canada, France, and Germany to determine the spatial structure of the CysLT1 receptor.

2D topological physics from shaking a 1D wire
Published in Physical Review X, this new study propose a realistic scheme to observe a 'cold-atomic quantum Hall effect.'

Helping physics teachers who don't know physics
A shortage of high school physics teachers has led to teachers with little-to-no training taking over physics classrooms, reports show.

Read More: Physics News and Physics Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to