Virginia Tech partners are designing a blueprint to improve autonomous vehicles with a $7.5 million grant

Virginia Tech partners are designing a blueprint to improve autonomous vehicles with a $7.5 million grant

Researchers at Virginia Tech’s Transportation Institute will soon hand over the keys to lawmakers and developers, after creating a blueprint for how self-driving vehicles can safely interact with other cars on the state’s roads.

In 2019, Virginia Tech received a $7.5 million grant from the U.S. Federal Highway Administration to collect data on improving autonomous driving (ADS) vehicles in road scenarios — including safely navigating around first responders, construction workers, and work zones — amid increases in… In self-reliance. Car driving malfunction.

“Our goal is just to improve transportation,” Zach Dorzaf, executive director of VTTI, said after an Oct. 11 presentation in Northern Virginia on the closed express lanes of Interstate 395.

The project was completed in partnership with the Virginia Department of Transportation, Crash Prevention Metrics Partners LLC, a consortium of vehicle manufacturers and global toll operator Transurban North America, which oversees Interstates 495, 95 and 395 in Washington, D.C. region.

Problems with ads

While autonomous vehicles, or autonomous vehicles, rely on artificial intelligence and can operate without a driver, the vehicles and their developers have faced criticism due to an increase in crashes nationwide. Data from the National Highway Traffic Safety Administration, an entity of the U.S. Department of Transportation, shows Virginia recorded 13 crashes with SAE Level 2 advanced driver assistance systems, which increased to 31 as of August. SAE International, a global association of engineers and technical experts, developed the levels based on the capabilities of the self-driving car.

In June 2021, the National Highway Traffic Safety Administration, an entity of the U.S. Department of Transportation, announced, I started to require Manufacturers and operators to report accidents with their self-driving cars.

“The U.S. Department of Transportation’s top priority is safety,” the Highway Administration said in a 2019 statement. “Automation offers the potential to improve safety for vehicle operators, passengers and other travelers who share the road.”

Not every automated driving system is the same and varies depending on its offerings.

According to the Safety Administration, the basic ADS system can operate without driver intervention, but it is still being tested on public roads and is not available for consumer purchase. A Level 2 Advanced Driver Assistance System provides speed and steering inputs, but requires the human driver to remain engaged in driving at all times.

Another problem with self-driving vehicles is that they do not respond to commands because they rely on wireless communication.

On October 24, the self-driving car company Cruise It was wanted To remove all of its vehicles from San Francisco roads, after the California Department of Motor Vehicles and the state Public Utilities Commission determined that the vehicles created an “unreasonable risk” to public safety.

The suspension was issued after the GM-owned tech startup failed to disclose full details of the Oct. 2 collision that besieged A pedestrian Under a self-driving car.

A visual image of the six SAE levels of driving automation adopted by the National Highway Traffic Safety Administration. (Photo courtesy of the National Highway Traffic Safety Administration)


For four years, the project team worked to create a blueprint for autonomous vehicle developers. The group consists of equipment manufacturers, service and public safety partners to help address the challenges of safe operation of autonomous vehicles in real-world scenarios, according to the Technology Transportation Institute.

One of the challenges facing self-driving vehicles is the need for more real-time and distance information that vehicles need to function optimally, the researchers said.

The group then developed a software platform that can provide information such as traffic conditions, work zones and potential vehicle accidents.

Transurban supported the project by allowing researchers to use the I-395 express lanes in Northern Virginia to identify solutions for autonomous vehicles in several scenarios. The lanes are also equipped with roadside sensors to assist the institute’s Level 4 Ford F-150 autonomous vehicle, which is equipped with sensors and cameras.

“The future of how we get from Point A to Point B is changing every day. Transurban and our partners recognize that we must continually innovate to keep travelers safe as technology enables the next generation of transportation,” said Mike Discenza, acting president, Transurban North America. “Transurban’s integrated and proprietary technologies and the enclosed environment on the 395 Express Lanes provide an ideal testing ground for infrastructure that talks to vehicles and vice versa – making roads safer as travel transitions to autonomous driving.”

Crash Prevention Metrics Partners LLC helped develop a list of 18 situations to research. Some included detecting upcoming hazards and navigating through construction workers and work zones.

“A lot of the scenarios we’ve developed are impactful,” said Joe McLean, GM’s director of public safety and president of CAMP LLC. “We believe that solving these problems, demonstrating technological innovation and moving towards its implementation is a great step and the reason why we are part of this project.”

One noteworthy situation was when an F-150 responded to law enforcement by pulling into the far right lane on the closed highway lane. As the Virginia State Trooper approached the ADS and turned on its lights, the vehicle activated its right flasher and, when appropriate, moved from the center lane to the emergency lane.

The trooper exited his vehicle, approached the ADS on the right passenger side and used the touchscreen on the window to communicate with the fleet manager or a contact person to resolve any issue. After collecting the necessary information, the soldier returned to his car. ADS then turned on the left blinker and safely merged back into the previous lane.

The researchers said that the early stages of the project required a lot of trust because a self-driving car can stop more suddenly compared to a human driver.

On October 11, researchers from the Virginia Tech Transportation Institute and their partners subjected a self-driving Ford F-150 to a series of public safety driving scenarios on the 395 freeway lanes in Arlington. (Photo courtesy of Transurban North America)

What then?

Last year, the Virginia Department of Transportation Mercury said Virginia does not have a written law for self-driving vehicles. The agency published Strategic plan to operate autonomous vehicles in 2020. VDOT expects the deployment of the vehicles to impact safety and mobility for drivers, and create opportunities for economic development.

Virginia has already begun creating space for self-driving vehicles. according to Diving into smart citiesInterstate 66 in northern Virginia reopened with lanes to support self-driving cars last year.

Dorzaf said the study is expected to help lawmakers make future policy decisions, one of which could be creating an interoperable connected transportation ecosystem.

The Uniform Traffic Control Devices Guide, created by the Federal Highway Administration, provides best practices for the way roads are designed, Dorzaf said. The guide also assisted during the study by identifying work areas that were easier for ADS to handle than others.

Mike Mollenhauer, director of technology implementation at VTTI, said the sensors provided by Transurban helped the self-driving car understand road conditions, but he was unsure whether vehicles would need them in the future. Sensors “can really make the experience better,” he said.

“I think, at some level, you have to have some ability for infrastructure to play a role in that deployment, but I don’t know that you have to have a system as qualified as Transurban’s operating here.” Mollenhauer said.

“Early deployment is certainly a benefit, but because you want that extra information, you can probably do it more safely than you could otherwise,” he added.

Virginia Tech will publish its results online in early 2024, including videos and photos, according to Mollenhauer.

Get the morning headlines delivered to your inbox

You may also like...

Leave a Reply

Your email address will not be published. Required fields are marked *