Skip to main content
Move the World.
Driverless Cars Go Off-roading
A self-driving car heads into the woods.Credit: Matthew Doude, CC BY-ND

Autonomous vehicles can follow the general rules of American roads, recognizing traffic signals and lane markings, noticing crosswalks and other regular features of the streets. But they work only on well-marked roads that are carefully scanned and mapped in advance.

Many paved roads, though, have faded paint, signs obscured behind trees and unusual intersections. In addition, 1.4 million miles of U.S. roads – one-third of the country’s public roadways – are unpaved, with no on-road signals like lane markings or stop-here lines. That doesn’t include miles of private roads, unpaved driveways or off-road trails.

What’s a rule-following autonomous car to do when the rules are unclear or nonexistent? And what are its passengers to do when they discover their vehicle can’t get them where they’re going?

Accounting for the obscure

Most challenges in developing advanced technologies involve handling infrequent or uncommon situations, or events that require performance beyond a system’s normal capabilities. That’s definitely true for autonomous vehicles. Some on-road examples might be navigating construction zones, encountering a horse and buggy, or seeing graffiti that looks like a stop sign. Off-road, the possibilities include the full variety of the natural world, such as trees down over the road, flooding and large puddles – or even animals blocking the way.

At Mississippi State University’s Center for Advanced Vehicular Systems, we have taken up the challenge of training algorithms to respond to circumstances that almost never happen, are difficult to predict and are complex to create. We seek to put autonomous cars in the hardest possible scenario: driving in an area the car has no prior knowledge of, with no reliable infrastructure like road paint and traffic signs, and in an unknown environment where it’s just as likely to see a cactus as a polar bear.

Our work combines virtual technology and the real world. We create advanced simulations of lifelike outdoor scenes, which we use to train artificial intelligence algorithms to take a camera feed and classify what it sees, labeling trees, sky, open paths and potential obstacles. Then we transfer those algorithms to a purpose-built all-wheel-drive test vehicle and send it out on our dedicated off-road test track, where we can see how our algorithms work and collect more data to feed into our simulations.

Starting virtual

We have developed a simulator that can create a wide range of realistic outdoor scenes for vehicles to navigate through. The system generates a range of landscapes of different climates, like forests and deserts, and can show how plants, shrubs and trees grow over time. It can also simulate weather changes, sunlight and moonlight, and the accurate locations of 9,000 stars.

The system also simulates the readings of sensors commonly used in autonomous vehicles, such as lidar and cameras. Those virtual sensors collect data that feeds into neural networks as valuable training data.

Simulated desert, meadow and forest
environments generated by the
Mississippi State University Autonomous
Vehicle Simulator.
Simulated desert, meadow and forest environments generated by the Mississippi State University Autonomous Vehicle Simulator. Credit: Chris Goodin, MSU

Building a test track

Simulations are only as good as their portrayals of the real world. Mississippi State University has purchased 50 acres of land on which we are developing a test track for off-road autonomous vehicles. The property is excellent for off-road testing, with unusually steep grades for our area of Mississippi – up to 60 percent inclines – and a very diverse population of plants.

We have selected certain natural features of this land that we expect will be particularly challenging for self-driving vehicles, and replicated them exactly in our simulator. That allows us to directly compare results from the simulation and real-life attempts to navigate the actual land. Eventually, we’ll create similar real and virtual pairings of other types of landscapes to improve our vehicle’s capabilities.

A road washout, as seen in real life,
left, and in simulation.
A road washout, as seen in real life, left, and in simulation. Credit: Chris Goodin / MSU

Collecting more data

We have also built a test vehicle, called the Halo Project, which has an electric motor and sensors and computers that can navigate various off-road environments. The Halo Project car has additional sensors to collect detailed data about its actual surroundings, which can help us build virtual environments to run new tests in.

The Halo Project car can collect data
about driving and navigating in rugged
terrain.
The Halo Project car can collect data about driving and navigating in rugged terrain. Credit: Beth Newman Wynn / MSU

Two of its lidar sensors, for example, are mounted at intersecting angles on the front of the car so their beams sweep across the approaching ground. Together, they can provide information on how rough or smooth the surface is, as well as capturing readings from grass and other plants and items on the ground.

Lidar beams intersect, scanning the
ground in front of the vehicle.
Lidar beams intersect, scanning the ground in front of the vehicle. Credit: Chris Goodin / MSU

We’ve seen some exciting early results from our research. For example, we have shown promising preliminary results that machine learning algorithms trained on simulated environments can be useful in the real world. As with most autonomous vehicle research, there is still a long way to go, but our hope is that the technologies we’re developing for extreme cases will also help make autonomous vehicles more functional on today’s roads.The Conversation

Matthew Doude is the Associate Director of the Center for Advanced Vehicular Systems at MSU. Christopher Goodin is an Assistant Research Professor at the Center for Advanced Vehicular Systems. Daniel Carruth is an Assistant Research Professor and Associate Director for Human Factors and Advanced Vehicle System at the Center for Advanced Vehicular Systems. This article was first published on The Conversation.

More About

Health
The Future of Healthcare Could Look a Lot Like the 1900s
The Future of Healthcare Could Look a Lot Like the 1900s
Health
The Future of Healthcare Could Look a Lot Like the 1900s
For many cancer patients, being treated at home is just as safe, more affordable, and more convenient than being treated…

For many cancer patients, being treated at home is just as safe, more affordable, and more convenient than being treated in a clinical setting.

Innovation
A Quiet Revolution in Trucking
A Quiet Revolution in Trucking
Watch Now
Innovation
A Quiet Revolution in Trucking
She’s a veteran, a single mom, and a trucker, who used to have to wait around for hours for her cargo. Now, a revolutionary solution from SAP and Uber Freight is getting her back on the road and home to her son sooner.
Watch Now

She’s a veteran, a single mom, and a trucker, who used to have to wait around for hours for her cargo. Now, a revolutionary solution from SAP and Uber Freight is getting her back on the road and home to her son sooner. Almost every good we use was at some point transported by truck drivers. Trucking is a $700 billion dollar industry in America, employing millions of people. However,…

Science
Fighting Superbugs with Viruses
Fighting Superbugs with Viruses
Watch Now
Science
Fighting Superbugs with Viruses
This Yale scientist's experimental treatment is a Texas woman's last resort.
Watch Now

Ben Chan searches sewers, lakes, and pig farms all around the world for bacteriophages (bacteria-destroying viruses) that could help fight antibiotic-resistant bacteria, also known as “superbugs.” Paige is a young woman in Texas with cystic fibrosis who is suffering from a drug-resistant infection; Ben’s experimental phage therapy is her last resort. We follow Ben as he travels from his laboratory at Yale to Lubbock, Texas, to deliver the treatment —…

3 Ways To Think About the Future
3 Ways To Think About the Future
Watch Now
3 Ways To Think About the Future
Why don’t we have a moon base? A cartoonist and a scientist explain.
Watch Now

Zach Weinersmith, creator of the Saturday Morning Breakfast Cereal webcomic and Kelly Weinersmith, professor and scientist, explain how to think about the future - a focus of their new illustrated book “Soonish: Ten Emerging Technologies That'll Improve and/or Ruin Everything.” The New York Times best-selling book has been praised for its exciting and nuanced looks at ten technologies that could change the world dramatically. In this interview, they explain their…

Sponsored
Saving Lives with AI
Saving Lives with AI
Watch Now
Sponsored
Saving Lives with AI
Artificial intelligence can find hidden patterns in patient’s vital signs - and stop emergencies before they happen.
Watch Now

As hospitals collect more and more data, analyzing it is a challenge and an opportunity. Montefiore Medical Center of the Albert Einstein College of Medicine is a case study in how using artificial intelligence in hospitals can help improve outcomes. They’re working with Intel’s Healthcare AI team to develop machine learning algorithms that can see patterns within it. The result, which they call the Patient Centered Analytic Learning Machine or…

Teaching Engineering with Dirt Bikes
Teaching Engineering with Dirt Bikes
Watch Now
Teaching Engineering with Dirt Bikes
This teacher is using dirt bikes to help Baltimore's kids learn STEM.
Watch Now

Baltimore’s kids are obsessed with dirt bikes. Some people think that's a problem, but teacher Brittany Young is using dirt bikes to get kids into engineering and STEM education. Her organization, B-360 Baltimore, aims to use dirt bike culture to help end the cycle of poverty, disrupt the prison pipeline, and bring together communities — while giving dirt bikes a better reputation. Dirt bikes are a controversial issue in…

Dispatches
To Eradicate TB, We Need Old-Fashioned Ambition
To Eradicate TB, We Need Old-Fashioned Ambition
Dispatches
To Eradicate TB, We Need Old-Fashioned Ambition
The Ebola outbreak sparked more medical innovation in two years than TB has in decades, even though TB is killing…
By Madhukar Pai

The Ebola outbreak sparked more medical innovation in two years than TB has in decades, even though TB is killing millions of people a year.

Challengers
Building a Better School System
Building a Better School System
Watch Now
Challengers
Building a Better School System
A highly-personalized experience could be the foundation for the future of education.
Watch Now

Everyone wants America’s education system to do better. Ex-Googler Max Ventilla has a radical idea for how to make it happen. Ventilla’s AltSchool is building a highly-personalized education experience that gets better and cheaper as more students use it.

Challengers
Meet the Startup Developing Human-Level Artificial Intelligence
Meet the Startup Developing Human-Level Artificial Intelligence
Challengers
Meet the Startup Developing Human-Level Artificial Intelligence
The story of Vicarious' mission to build the world's first human-level artificial intelligence and use it to help humanity thrive.
By Mike Riggs

The story of Vicarious' mission to build the world's first human-level artificial intelligence and use it to help humanity thrive.

Challengers
Meet the Entrepreneurs Disrupting Industries and Changing the World
Meet the Entrepreneurs Disrupting Industries and Changing the World
Challengers
Meet the Entrepreneurs Disrupting Industries and Changing the World
Fast Company and Freethink bring you powerful stories of a new generation of entrepreneurs.
By Mike Riggs

Fast Company and Freethink bring you powerful stories of a new generation of entrepreneurs.