11 Jun AutoDrive team captures 3rd place in first competition
After a journey that involved a crash, a dead battery, and late-night coding sprints, a Virginia Tech engineering team took third place in the first year of an autonomous vehicle competition held by the Society of Automotive Engineers (SAE) and General Motors.
Victor Tango AutoDrive was the only one of eight teams to successfully complete all three portions of the AutoDrive Challenge, held at the GM Desert Proving Ground in Yuma, Arizona.
The challenges were based on complex perception, navigation, and behavior algorithms for a self-driving car, such as stopping at stop signs or staying in lane lines.
The road to Yuma
For the Victor Tango team, the road to Yuma itself was the first challenge.
“It is really an underdog success story,” said Andy Cohen, a mechanical engineering senior (’18) and a member of the controls subteam and the business subteam lead.
Weeks prior to competition, an incident resulted in the vehicle crashing through the garage door at the team facility. No one was hurt, however, and no major damage was done to the $100,000 of hardware mounted to the roof of the vehicle.
Less than a month before the competition, the battery on the Bolt died, and the car had to be sent back to GM for servicing.
With the car in Detroit, the team considered pulling out of the competition if the car didn’t make it back in time to complete the necessary testing to ensure the safety of student vehicle operators.
“…Later that week, we got notice [from GM] that said, ‘We’ve fixed your car, we’re sending it back,” said Cohen.
With 10 days to go before competition, the team had to complete 100 hours of testing. Working around the clock, the team was in coding mode, and had just enough time to complete all the testing they set out to accomplish.
Ironically, Cohen said, the time crunch enabled their success as the team was forced to use a “fusion of old school and new school,” methods integrating traditional environment mapping with complex perception algorithms.
“Everyone else at the competition hadn’t relied on the maps because they figured they could do it entirely with perception,” Cohen said. “But the environment wasn’t as well regulated as they thought it was going to be.”
Because their vehicle could navigate the faded lane lines, Victor Tango AutoDrive was the only team to complete the second, lateral challenge.
Each team was tasked to develop a fully autonomous passenger vehicle using a 2017 Chevy Bolt. In Arizona, teams presented on the social impacts of autonomous vehicles then put their electrical designs and coding to the test by navigating a closed test track in autonomous mode.
In year one of the three-year competition teams focused on concept selection by becoming familiar with sensing and computing software. They had to write a concept design, and complete an on-site evaluation with dynamic tasks such as straight roadway driving and object avoidance and detection.
The team placed in the top three in each category:
3rd – Social Responsibility Report
3rd – Social Responsibility Presentation
3rd – Mapping Challenge
1st – Lateral Challenge
3rd – Object Detection and Avoidance Challenge
Over the next two years the car will carry out more complex tasks, such as moving at higher speeds, making U-turns, and dodging a dynamic object. The goal is that by 2020, the team will produce a level four autonomous vehicle – capable of steering, braking, and responding to traffic without the need for human intervention, according to SAE standards.
About the team
Victor Tango AutoDrive Team is composed of engineering, computer science, and business students and faculty from mechanical engineering, computer science, the Charles E. Via Jr. Department of Civil and Environmental Engineering, the Bradley Department of Electrical and Computer Engineering, and the Pamplin College of Business.
The AutoDrive competition is sponsored by GM and SAE, with support from Continental, Intel, MathWorks, and Velodyne LiDAR.
Victor Tango AutoDrive Team received support from TORC Robotics, Odoo, Edmund Optics, and the Virginia Tech Transportation Institute.