Automated Vehicles

The applications surrounding successfully developing self-driving cars and other vehicles are reshaping not only the auto industry, but mobility worldwide. As a U.S. Department of Transportation designated AV Proving Grounds, Wisconsin is at the forefront of these transformative technologies, and the R&D we do contributes to revolutionizing how the world uses transportation. Scroll down or explore additional resources to learn more.

The Wisconsin AV Proving Grounds partners are a natural choice for the AV R&D because of the range of environments and facilities available to accommodate the testing of a wide variety of different technologies and applications. These range from lab-based and simulated environments, the closed track at MGA Research in Burlington, Road America in Elkhart Lake, corporate campuses, the UW-Madison campus, and public roads.

Want to keep up with what's happening at the proving grounds? Sign up for updates.
Sign Up
RSVP
In Person
Online

Got it!

We have received your RSVP. We look forward to seeing you at the forum.

Sign Up for Updates

Your request to be added to our mailing list has been delivered. We will add you to our mailing list shortly.

Automated Vehicle Technology

Avid attention on automated or autonomous vehicle (AV) technology is widespread and burgeoning, and the collaborative groundwork being laid in Wisconsin is a prime example. Wisconsin is leading the development of deeper understanding of this transformative technology and how it can be harnessed for the greater good of society. Researchers with the College of Engineering at the University of Wisconsin-Madison (UW-Madison) assess the benefits, technical aspects, and risks of AV, as well as collaborate on policy issues with government. AVs are rapidly pushing technical, safety, acceptability, legal, regulatory, and liability boundaries.

AVs have significant potential to improve safety and quality of life. More specifically, AV shared mobility can provide ladders of opportunity to all, including previously underserved communities. Furthermore, AVs can bring significant new research and development opportunities to UW-Madison and new businesses to the state of Wisconsin, including startups and tech companies.

Navya Arma

How Automated Vehicles Work

AV Technology - Top View
AV Technology - Cameras

Cameras

Cameras gather visual information from the road and traffic control and send them to the controller for processing.

AV Technology - LiDAR

LiDAR

LiDAR sensors bounce lasers off of detected objects. LiDAR can detect road lines and assets and differentiate objects.

AV Technology - Radar

Radar

Radar sensors bounce radio waves off detected objects. Radar cannot differentiate objects.

GPS Unit

GPS Unit

The GPS unit identifies the precise position of the vehicle and aids in navigation.

About the Proving Grounds

The mission of the Wisconsin AV Proving Grounds (AVPG) is to provide a path to public road evaluation by contributing to the safe and rapid advancement of automated vehicle development and deployment, and providing a full suite of test environments, coupled with research, open data, and stakeholder communication. Our team’s philosophy holds paramount safety, followed by best practice tenets of security and open data. Without these fundamental elements, we recognize it makes little difference what our readiness is or what research and development objectives may be.

AV Working Group

Proving Grounds Objectives

Objective - Data and Sensing

Data and sensing including LIDAR, GPS, cameras, communications, and other sensors. This parallels the Safety Assessment point on Object and Event Detection and Response.

Objective - Testing and Validation

Testing and validation methods for AV systems.

Objective - Standards

Advancing standards, safety protocols, and security.

Objective - Vehicle Operations

Vehicle operations including speed, acceleration and deceleration, performance on grades and curves, and in the case of electric vehicles, range and charging time.

Objective - Interfaces

Human-machine interfaces such as sensors, communications, and responses. For this item, our team has the opportunity to leverage the full-scale driving simulator at UW-Madison’s College of Engineering.

Objective - Interaction

Interaction with pedestrians, bicycles, mopeds, cars, and traffic control devices.

Objective - Weather

Inclement weather operations including snow, ice, fog, and high winds. One of the larger unknowns for AVs is winter operation.

Objective - Passenger

Passenger comfort, public perception, and safety improvement.

AV microtransit developments, enhancements, and testing.

Testing Timeline

Testing timeline

Mandli Communications

MGA Research

Road America

UW – Madison

Corporate Campuses

City of Madison

Testing Facility

Testing Types

Proving Grounds Facilities

The team includes the second largest city in Wisconsin, the region’s largest private employer, a premier private proving grounds in operation for decades, one of the nation’s most reputable race tracks, public agencies, and Wisconsin’s flagship research university. Researchers with the UW-Madison College of Engineering will manage and oversee all aspects of the AV proving grounds work, as well as provide research, development, and data stewardship. A key partner on this team is the automotive proving grounds facility owned and operated by MGA Research Corporation near Burlington, WI. The City of Madison and other agencies are partners for AV policy development, regulation, and operations on their roads.

1

Mandli Communications

Fitchburg, WI

2

MGA Research

Burlington, WI

3

Road America

Elkhart Lake, WI

4

UW – Madison

Madison, WI

5

City of Madison

Madison, WI

6

Chippewa Valley Regional Airport

Eau Claire, WI

Additionally, we work with corporate campuses to test automated vehicles in workplace environments, accounting for such factors as safety, usability, and acceptance.

Automated Vehicle Events

IEEE Madison AVs

Madison, Wisconsin

October 19, 2017

ITS World Congress

Montreal, Quebec

October 29 – November 02, 2017

Our Partners

News from the Proving Grounds

Autonomous Vehicle Safety Reports Leave a Lot to Desire

Madison, Wisconsin – On the heels of the California Department of Motor Vehicle annual autonomous vehicle disengagement report, Beijing’s Innovation Center for Mobility Intelligent (BICMI) published its 2019 survey of self-driving vehicles being tested on local roads.

Both reports, which hinge on tracking disengagements – or the frequency at which human safety drivers were forced to take control of their autonomous vehicles – are a stark reminder of how little we have to measure the safety and performance of autonomous vehicles.

“Comparing disengagement rates between companies is worse than meaningless. It creates perverse incentives,” said Bryant Walker Smith, associate professor at the University of South Carolina’s School of Law and an expert in self-driving cars.

Smith explained to the Verge that if he were to register in California and never test, for instance, he’d look good. “If I wanted to look even better, I’d do a ton of easy freeway miles in California and do my real testing anywhere else,” he continued.

California law requires that every company testing autonomous vehicles on public roads submit data on the number of miles driven and the frequency of disengagements. Beijing is one of the few cities globally to mandate that autonomous car companies disclose their disengagement results too.

According to Verge coverage of the California report, the total number of autonomous miles driven in California last year rose 40%, to more than 2.87 million, thanks largely to a notable increase in public on-road testing by Baidu, Cruise, Pony.ai, Waymo, Zoox, and Lyft.

But the report has generated considerable discussion about whether disengagements communicate anything meaningful. Echoing similar sentiments as Smith, Waymo, which drove 1.45 million miles in California in 2019 and logged a disengagement rate of 0.076 per 1,000 self-driven miles, said that the metric “does not provide relevant insights” into its technology. Cruise, for their part, drove 831,040 miles last year and reported a disengagement rate of 0.082, said the “idea that disengagements give a meaningful signal about whether an [autonomous vehicle] is ready for commercial deployment is a myth.”

Meanwhile, Venture Beat reported that a total of 77 autonomous vehicles from 13 China-based companies covered over 646,000 miles on Beijing roads during 2019, according to the BICMI. That’s up from the 95,000 miles eight firms drove in 2018.

The BICMI report doesn’t break out disengagement numbers by company or vehicle, but it said 86% of disengagements in 2019 resulted from human takeovers. Examples might include drivers tinkering with data-recording equipment, changes in planned routes, or “personal reasons” (like bathroom breaks). The remaining 14% of disengagements were attributable to some form of mechanical or software system failure.

The inherent weakness of using disengagements to measure the success of autonomous vehicles are glaring.

For starters, the very nature of public road testing means that the environments are inconsistent. A mile in Palo Alto is very different than a mile in downtown San Francisco.

Also, in California, the vague DMV definition of disengagement means that car companies aren’t following the same protocols. The DMV defines disengagements as “deactivation of the autonomous mode when a failure of the autonomous technology is detected or when the safe operation of the vehicle requires that the autonomous vehicle test driver disengage the autonomous mode and take immediate manual control of the vehicle.” That leaves a lot of room for interpretation.

For example, a self-driving car owned by GM Cruise ran a red light in San Francisco after the safety driver took control to avoid blocking a crosswalk. But the company didn’t include the incident in its report because, according to Cruise’s interpretation, the human driver didn’t act out of safety concerns or a failure of the autonomous system.

And finally, nowhere in either report is it specified which advanced driver assist system (i.e. adaptive cruise control) failed and precisely what event triggered the disengagement.

The result is that it is impossible to make an apples-to-apples comparison about the performance and safety of these vehicles.

And if you thought you could turn to the federal government for better data, think again. Most major players in the US have also submitted voluntary safety reports to the federal government as part of the Department of Transportation’s voluntary guidance. But these reports read more like marketing documents.

The reality is that if the public wants to understand how safe self-driving vehicles are, one alternative is to consider leveraging methods and techniques currently being used by insurance providers. After all, insurance groups have a lot at stake when it comes to understanding the quality of these systems.

When the Insurance Institute of Highway Safety (IIHS) set out to evaluate the success rates of active lane-keeping systems in 2018, for instance, it tracked the number of times the vehicle had to overcorrect after crossing clearly marked lane lines. Why? Because evaluating the safety of these vehicles requires the collection of relevant and targeted data about specific advance driver assist systems.

An alternative approach, according to Smith, would be for companies to release testing summaries with details and context about each disengagement. While not ideal, the thought is that with more information about precisely which system failed and under what conditions, the public could conceivably start teasing out some meaningful conclusions. But no company to date has done that.

And short of any new regulations set forth by public authorities, the industry may have to forge its own path by developing their own standards. Dmitry Polishchuk, head of Russian tech giant Yandex’s autonomous car project, noted that Yandex hasn’t released any disengagement reports because they are “waiting for some sort of industry standard” to overcome the discrepancies in how companies are defining and recording disengagements. The right industry standard could help overcome this test-and-don’t-report alternative.

The good news is the SAE has created a task force to provide definitions, information and best practices to support verification and validation of self-driving systems. It’s still unclear, however, when we can expect to see the fruits of their labor.

At this point, there is little reason to expect much will change in 2020, which leaves us in a frightful situation: There are currently millions of miles being driven by automated vehicles on public roads, and no one can agree about what data we should use to measure their safety.

If that’s not reckless driving, then what is?

 

Robert Fischer is President of GTiMA, a Technology and Policy Advisor to Mandli Communications, and an Associate Editor of the SAE International Journal of Connected and Autonomous Vehicles. Follow Rob on Twitter (@Robfischeris) and Linkedin.

Eric Nutt is the Chief Technology Officer of Mandli Communications, Inc., and an Associate Editor of the SAE International Journal of Connected and Automated Vehicles. Follow Eric on LinkedIn.

Read More…

Overcoming The High Carbon Debt of Electric Vehicle Production

Editor’s Note: While the WI AVPG is focused on advancing the safe deployment of AV tech, oc…

Read More…

How Cities Can Digitize Their 21st Century Mobility Policies

For the better part of the last century, cities used analog systems like lane markings and curbs …

Read More…

Digital Transportation: The Future of Urban Mobility

The physical scale and unprecedented population growth in some cities have officials grappling wi…

Read More…
View All

Contact the Proving Grounds

College of Engineering

1415 Engineering Drive

Madison WI 53706

United States

Wisconsin

608.890.0509

Washington, D.C.

202.568.2273

One for more of the form fields is incomplete or invalid. Please correct the errors before submitting the form.

Your message has been sent. We will get back to you shortly.

Recent AV Forums

Date
Location
Speakers
Aug 15 2018

TAPCO

5100 W Brown Deer Road

Brown Deer WI 53223

Brian Scharles Jr

Steve Cyra

Rob Fischer

Art Harrington

Ray Mandli

Mar 20 2018

American Family Insurance

6000 American Parkway

Madison WI 53783

Lingqiao Qin

Todd Smith

Sean Kelly

Feb 23 2018

AAA

8401 Excelsior Drive

Madison WI 53717

Ray Mandli

Jamie Retterath

Nicholas Jarmusz

Dec 11 2017

Godfrey & Kahn

833 E. Michigan Street, Suite 1800

Milwaukee WI 53202

Peter Rafferty

Asher Elmquist

Joe Vruwink

Ray Mandli

Nov 7 2017

Fitchburg Public Library

5530 Lacy Road

Fitchburg WI 53711

Art Harrington

Ted Nickel

Steve Cyra

Adam Neylon

Oct 5 2017

Fitchburg Public Library

5530 Lacy Road

Fitchburg WI 53711

Peter Rafferty

Ray Mandli

J.P. Wieske

Back to top of page