Posts Tagged: autonomous vehicles

AutoDrive Challenge™: U of T Engineering places first for the fourth straight year

Zeus, a self-driving electric car created by a team of students from U of T Engineering, parked outside the MarsDome at the University of Toronto Institute for Aerospace Studies. The team has placed first in the intercollegiate Autodrive Challenge the last four years in a row. (Photo: Chude Qian)

 

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 BarfootAngela 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!”

This article originally appeared in the U of T Engineering News.


U of T Engineering to compete in SAE AutoDrive Challenge™ II

U of T's Zeus self-driving electric car

Zeus, a self-driving electric car created by a team of students from U of T Engineering, dominated the first series of the intercollegiate Autodrive Challenge. Now, the team is preparing to compete in the SAE Autodrive Challenge II. (Photo: Chude Qian)

 

By Tyler Irving

For the last three years, U of T Engineering has been leading the pack in the Autodrive Challenge, an intercollegiate competition to create a self-driving electric car. Now, they’re gearing up for the next round.

“We’ll have a new car, we’ll face new teams, and we’ll need to meet new challenges, probably more sophisticated ones,” says Jingxing “Joe” Qian (EngSci 1T8 + PEY, UTIAS MASc candidate), Team Lead for aUToronto, U of T’s self-driving car team. “But I think we’re well prepared.”

The general concept for SAE AutoDrive Challenge™ II, which is sponsored by SAE International and General Motors, will be similar to the original. Teams will receive an electric vehicle – the team’s award-winning entry in the first round was a Chevrolet Bolt that they named “Zeus” – along with sensors and certain software packages.

Their task is to integrate these components and enable the car to meet certain standards, such as recognizing and obeying stop signs or arriving at a sequence of pre-determined address points.

The aUToronto team — which has more than 60 members, including Professors Tim Barfoot, Angela Schoellig and Steven Waslander (all UTIAS) as faculty supervisors and Keenan Burnett (EngSci 1T6+PEY, UTIAS PhD candidate) as a graduate advisor  — has a track record of success. Zeus has placed first in all of the yearly meets held so far: the 2018 meet in Yuma, Ariz., the 2019 meet in Ann Arbour, Mich., and a virtual competition held last fall.

There is a fourth meet currently scheduled for June 2021. The SAE AutoDrive Challenge™ II will begin in fall 2021.

For more than a year now, most of the work on Zeus has been done remotely. Sub-teams such as perception, control and simulation coordinate their work using a variety of tools, meeting all together weekly to update each other on progress.

A small task force takes turns physically visiting the vehicle, which is housed at the University of Toronto Institute of Aerospace Studies, near Downsview Airport.

“It’s been a challenging time to work on this project,” says Qian. “Deliverables such as demonstration videos have become really important. They help our teams see that the changes they make have an impact on how the car behaves in a real-world environment.”

The other institutions competing in SAE AutoDrive Challenge II include Kettering University, Michigan Tech, North Carolina Agricultural & Technical State, Penn State, Queen’s University, Texas A & M, Ohio State, the University of Wisconsin and Virginia Tech. Qian is optimistic about aUToronto’s chances.

“I’m very proud of all the effort the team, and the university, have put into this project over the past few years,” says Qian. “I think we deserve to enter the second round, and I’m really excited to get started.”

 

This story originally appeared in the U of T Engineering News.


Three-peat victory: U of T Engineering team wins AutoDrive Challenge, Year Three

Zeus, shown here outside the Myhal Centre in October 2019, is a self-driving car designed and built by aUToronto, a student-led team from U of T Engineering. This week, aUToronto placed first overall in the three-year AutoDrive Challenge, an intercollegiate competition between eight top engineering schools across North America. (Photo: Liz Do)

 

By Tyler Irving

aUToronto has placed first in an intercollegiate challenge to transform an electric car into a self-driving one — their third consecutive win.

“All of us take pride in the work that we have done at aUToronto,” says Jingxing “Joe” Qian (EngSci 1T8 + PEY, UTIAS MASc candidate), Team Lead for aUToronto. “The competition results clearly reflect the high calibre and dedication of the team.”

The team also took the top overall prize for the most cumulative points over the three years of the AutoDrive Challenge. Second place went to Texas A & M, with Virginia Tech scoring third. The other schools in the competition were: University of Waterloo, Michigan State, Michigan Tech, North Carolina A&T State, and Kettering University.

The AutoDrive Challenge began in 2017, when each of the student-led teams was provided with a brand-new electric vehicle, a Chevrolet Bolt. Their task was to convert it into an autonomous vehicle, meeting yearly milestones along the way.

Sponsors of the AutoDrive include General Motors, the Society of Automotive Engineers (SAE) and a number of other companies that produce hardware and software for self-driving cars.

The U of T team took the top spot at the first meet of the competition, held in the spring of 2018 at the General Motors Proving Grounds in Yuma, Ariz. In the second year, they again placed first at the competition, which took place in MCity, a simulated town for self-driving vehicle testing, built at the University of Michigan in Ann Arbor.

The third yearly meet was originally scheduled to take place last spring at the Transportation Research Center in East Liberty, Ohio. However, it was postponed and reorganized due to the global COVID-19 pandemic.

“The goal of this year’s challenge was to simulate an autonomous ride-sharing scenario,” says Qian. “That means the car needed to arrive at a sequence of pre-determined address points and perform pseudo pick-up and drop-off behaviours. The routes would have been much longer and more complex compared with Year 2.”

In the absence of a live event, the organizers used what are known as “static event” scores, which are based on reports and presentations that the teams could submit remotely. These included an analysis of the social responsibility aspects of the project, the overall conceptual design and the results of a number of sophisticated computer simulations.

Qian says that the latest iteration of Zeus includes a number of enhancements, including improvements in perception, path planning and GPS-free localization. To make them, the aUToronto team overcame numerous challenges, not the least of which was coordinating more than 50 team members who were working remotely on the project.

“We are located in many different places around the world, so team building and organization becomes extremely important,” says Qian. “We have weekly meetings online where sub-team leads present their updates to the rest of the team, and we have also been planning virtual paper talks and knowledge sharing sessions.”

“aUToronto has been focused on putting together a top-notch self driving car for three years now,” says Keenan Burnett (EngSci 1T6+PEY, UTIAS MASc candidate), who served as aUToronto’s Team Lead through the first two years of the AutoDrive Challenge. “This win is the result of hundreds of hours of work by our team.”

“As a faculty advisor, I have watched with awe as the 100%-student-run team really seized this unique opportunity,” says Professor Tim Barfoot (UTIAS). Barfoot, along with Professor Angela Schoellig (UTIAS) is one of the two co-Faculty Leads of the team. He also serves as Associate Director of the University of Toronto Robotics Institute and the Chair of the Robotics Option offered by the Division of Engineering Science.

“Robotics is a very hands-on discipline, so experiences such as the AutoDrive Challenge are needed to complement classroom learning,” says Barfoot “I am deeply grateful to SAE and GM for organizing this activity and the Faculty of Applied Science and Engineering for their ongoing support through the Dean’s Strategic Fund.   I feel our graduates are better prepared to head into the exciting field of autonomous vehicles than perhaps anywhere in the world at this moment in time.  The fact that we won the competition is a bonus.”

The competition has been rolled into a fourth year, with a live meet set to take place sometime in 2021, again at MCity in Ann Arbour, Mich.

“We’re very proud the results of this third-year competition and looking forward to raising the bar yet again at the fourth-year competition,” says Burnett. “Although we’re disappointed we didn’t get to show off our autonomous functions this year, we’re looking forward to going back to MCity and demonstrating our Level 4 self-driving car.”

But aUToronto is also thinking beyond the end of the AutoDrive Challenge.

“We’ve always said we do not want to design a system that is specific towards this competition,” says Qian. “Our goal is to achieve full autonomy under many different scenarios.”

This story was originally posted in the U of T Engineering News.


© 2020 Faculty of Applied Science & Engineering