By Tyler Irving
Last night, the aUToronto team — U of T Engineering’s entry into the AutoDrive Challenge™ — placed first in a virtual competition to demonstrate the capabilities of their self-driving electric vehicle, dubbed Zeus. It marks the fourth year in a row that the team has come out on top.
The aUToronto team consists of more than 70 members, most of whom are U of T Engineering undergraduate or graduate students. Its faculty supervisors include Professors Tim Barfoot, Angela Schoellig and Steven Waslander (all UTIAS).
Keenan Burnett (EngSci 1T6+PEY, UTIAS PhD candidate), a former captain of the team, has continued to act as a key advisor in the latest competition.
“We’re elated to see this continued validation of our team’s efforts,” says Burnett. “We try our best to stay competitive and not let our past wins make us complacent. We use ourselves as our benchmark for success, continually trying to outdo ourselves and improve on our previous iterations.”
“Despite all the challenges of keeping the team going throughout COVID, our students have had a great year of learning about self-driving technology, working in a team, and pushing their limits,” says Barfoot. “I couldn’t be more proud of our aUToronto team once again for another great year in the Autodrive competition.”
“A tremendous amount of effort went into succeeding this year,” says Schoellig. “We had to accomplish new and more advanced autonomous driving tasks, complete more sophisticated simulation challenges, and prove the safety of our car. This win reflects our team’s continued technical, collaboration and communication strength. I am extremely proud to work together with such a capable team.”
Zeus is a Chevrolet Bolt that has been retrofitted with a suite of sensors, including visual cameras, radar and lidar. Additional hardware and student-designed software inside the car processes these signals and converts them into commands that enable the car to drive itself safely and efficiently.
The AutoDrive Challenge™ launched in 2017 with eight universities from across Canada and the U.S. In addition to U of T Engineering, competitors included Kettering University, Michigan State University, Michigan Tech University, North Carolina A & T State University, Texas A & M University, University of Waterloo and Virginia Tech.
Zeus has taken the top spot in each of the competition’s yearly meets: the 2018 meet in Yuma, Ariz., the 2019 meet in Ann Arbor, Mich., and a virtual competition held in the fall of 2020. Originally scheduled to be a three-year competition, the challenge was rolled over for a fourth year, and it is this competition that the team has now won as well.
“Both the Year 3 and Year 4 competitions challenged the teams to perform autonomous ride-sharing under controlled environments,” says Jingxing “Joe” Qian (EngSci 1T8 + PEY, UTIAS MASc candidate), the current Team Lead for aUToronto.
Watch the team’s safety video to see Zeus in action.
“The vehicles are tasked with navigating multiple destinations while handling various traffic scenarios. One particular interesting requirement this year is that we need to reach SAE J3016 Level standard for the loss-of-GPS scenario: the vehicle must perform fallback strategies to either continue the task or pull to the road shoulder when GPS signal is lost.”
While the teams based in the U.S. were able to meet in person in Ann Arbor, the Canadian teams competed by means of reports, presentations, simulations and video demos. Qian says that the team is used to this format, as much of the work on the car has been done virtually for the past year.
“We managed to get a small task force to perform real world tests one or two days per week,” says Qian. “After testing, they would share demo videos and results to the team. We also developed an automatic evaluation system that leverages various simulation environments. It runs daily on our deployment server against a set of test scenarios, and it has greatly improved our development efficiency.”
Watch the full demonstration video that earned the aUToronto team first place in the Year 4 competition of the AutoDrive Challenge™.
As for the next steps, aUToronto has already been selected to compete in the SAE AutoDrive Challenge™ II, scheduled to begin in the fall of 2021. They will have a new car and new competition, and they are actively recruiting new team members as well.
“We will be getting a brand new GM Chevy Bolt EUV 2022 to build up our autonomy system from the ground up,” says Frank (Chude) Qian (UTIAS MASc candidate), who will lead the team for the AutoDrive Challenge™ II.
“We hope to develop our vehicle with real-world driving scenarios, apply industry safety standards, and bring awareness and assurance to the general public about autonomous vehicles. We are excited to compete with the new universities and hopefully continuing our winning streak!”