Self-Driving Cars

Alumni

Graduate Students

Undergraduate Students

Subheadline

"Each time we saw an obstacle – a stop sign, a red light, the railroad bar coming down – and the car reacted by stopping and then continuing, we let out a big cheer or a sigh of relief"

A team from the University of Toronto has placed first for sixth time in seven years in a North American self-driving car competition.

After finishing in second place last year, the aUToronto team returned to the top spot at the 2024 SAE AutoDrive Challenge II, which was held in June at the Mcity Test Facility in Ann Arbor, Mich.

The aUToronto team competed against nine other teams from across Canada and the United States.

“Through the AutoDrive Challenge, we are preparing the next generation of engineers to head into the industry, to keep pushing towards the challenging goal of reaching Level 4 autonomous driving,” says Tim Barfoot, a professor at the ��TV Institute for Aerospace Studies (UTIAS) in the Faculty of Applied Science & Engineering and one of the team’s academic advisers.

“The team did another excellent job this year.”

The team approached the competition by going back to first principles to ensure they had a reliable and robust system, says Kelvin Cui, a ��TV Engineering alumnus and the team’s principal.

He joined aUToronto last fall after five years with the University of Toronto Formula Racing team, where he founded the “driverless” division.

“We looked at what was going to get us the most points at competition and made sure that we were not overbuilding our system and adding too much complexity,” he says.

This meant pushing for additional testing time at UTIAS and achieving more than 900 kilometres of system testing prior to the competition.

The team placed first out of 10 teams from institutions across the United States and Canada (photo courtesy of aUToronto)

A partnership with the AutoDrive team from Queen’s University was instrumental to aUToronto’s preparation. The aUToronto team drove Artemis, their autonomous vehicle, to Kingston, Ont. to assess the system at Queen’s testing facility, which features intersections and electronic streetlights.

“We added radar to our vehicle as a new sensor, so we needed to be aware of all the sensor failure modes,” says third-year Engineering Science student Robert Ren.

“A lot of our testing time went into making sure that including radar didn’t break anything else in our system, and that it could handle any sensor failure cases.”

Including radar sensors in the vehicle’s perception system allowed it to measure the motion of objects directly, which is not possible with light detection and ranging (LiDAR) sensors. 

“Radar can help with adverse weather object detections,” adds Ren. “So, if the vehicle is operating under heavy rain or fog, the LiDAR is going to be limited, but the radio waves from radar can help the vehicle see what objects are in front and what objects are moving. This enables it to make good decisions when driving in uncertain scenarios.” 

View this post on Instagram

A post shared by aUToronto (@autoronto_uoft)

In an event where both LiDAR and radar sensors fail, the aUToronto system can still rely on visual cameras to perform object tracking. This made the team’s object tracker much more robust compared to last year when the team experienced sensor failure during a dynamic event.

Brian Cheong, a ��TV Engineering master’s student who has been a member of aUToronto since 2021, acted as technical director of the autonomy team this year – part of a new leadership structure introduced by Cui.  

“In the past, it was a lot of work for our team’s principal to keep track of all the systems,” Cheong says. “So instead of having to work directly with all 15 sub teams, Kelvin created groups of sub teams that we called stacks, and each stack had a director.”

The restructuring and technical innovations paid off, with aUToronto completing its first clean sweep in the AutoDrive Challenge II, placing first in all static and dynamic events, including the concept design presentation and intersection challenge.

“The intersection challenge was a big highlight for us,” says Cheong. “Kelvin and Robert were in the car, and I was on the sidelines watching with the rest of the team. Each time we saw an obstacle – a stop sign, a red light, the railroad bar coming down – and the car reacted by stopping and then continuing, we let out a big cheer or a sigh of relief.

“And then we were all silent as the car approached the final obstacle, which was a deer. We watched as Artemis slowed down to a stop and the deer moved by. Then we screamed and cheered, and we could hear cheering from inside the car.”

“Our success is entirely a team effort,” adds Cui. “It was not smooth sailing before the competition. The only reason we won is because everybody put in so much effort to test our vehicle every day.

“That’s how we were able to get this reliable system across the line.” 

��TV researchers enhance object-tracking abilities of self-driving cars

rahul.kalvapalle — Wed, 29 May 2024 14:59:42 +0000

��TV researchers enhance object-tracking abilities of self-driving cars

rahul.kalvapalle Wed, 05/29/2024 - 10:59

Cutline

Sandro Papais, a PhD student, is the co-author of a new paper that introduces a graph-based optimization method to improve object tracking for self-driving cars (photo courtesy of aUToronto)

Safa Jinje

Topic

Breaking Research

Subheadline

The new tools could help robotic systems of autonomous vehicles better track the position and motion of vehicles, pedestrians and cyclists

Researchers at the University of Toronto Institute for Aerospace Studies (UTIAS) have introduced a pair of high-tech tools that could improve the safety and reliability of autonomous vehicles by enhancing the reasoning ability of their robotic systems.

The innovations address multi-object tracking, a process used by robotic systems to track the position and motion of objects – including vehicles, pedestrians and cyclists – to plan the path of self-driving cars in densely populated areas.

Tracking information is collected from computer vision sensors (2D camera images and 3D LIDAR scans) and filtered at each time stamp, 10 times a second, to predict the future movement of moving objects.

“Once processed, it allows the robot to develop some reasoning about its environment. For example, there is a human crossing the street at the intersection, or a cyclist changing lanes up ahead,” says Sandro Papais, a PhD student in UTIAS in the Faculty of Applied Science & Engineering. "At each time stamp, the robot’s software tries to link the current detections with objects it saw in the past, but it can only go back so far in time.”

In a new paper presented at the 2024 International Conference on Robotics and Automation in Yokohama, Japan, Papais and co-authors Robert Ren, a third-year engineering science student, and Professor Steven Waslander, director of UTIAS’s Toronto Robotics and AI Laboratory, introduce Sliding Window Tracker (SWTrack) – a graph-based optimization method that uses additional temporal information to prevent missed objects.

The tool is designed to improve the performance of tracking methods, particularly when objects are occluded from the robot’s point of view.

A visualization of a nuScenes dataset used by the researchers. The image is a mosaic of the six different camera views around the car with the object bounding boxes rendered overtop of the images (image courtesy of the Toronto Robotics and AI Laboratory)

“SWTrack widens how far into the past a robot considers when planning,” says Papais. “So instead of being limited by what it just saw one frame ago and what is happening now, it can look over the past five seconds and then try to reason through all the different things it has seen.” 

The team tested, trained and validated their algorithm on field data obtained through nuScenes, a public, large-scale dataset for autonomous driving vehicles that have operated on roads in cities around the world. The data includes human annotations that the team used to benchmark the performance of SWTrack.

They found that each time they extended the temporal window, to a maximum of five seconds, the tracking performance got better. But past five seconds, the algorithm’s performance was slowed by computation time.

“Most tracking algorithms would have a tough time reasoning over some of these temporal gaps. But in our case, we were able to validate that we can track over these longer periods of time and maintain more consistent tracking for dynamic objects around us,” says Papais.

Papais says he’s looking forward to building on the idea of improving robot memory and extending it to other areas of robotics infrastructure. “This is just the beginning,” he says. “We’re working on the tracking problem, but also other robot problems, where we can incorporate more temporal information to enhance perception and robotic reasoning.”

Another paper, co-authored by master’s student Chang Won (John) Lee and Waslander, introduces UncertaintyTrack, a collection of extensions for 2D tracking-by-detection methods that leverages probabilistic object detection.

“Probabilistic object detection quantifies the uncertainty estimates of object detection,” explains Lee. “The key thing here is that for safety-critical tasks, you want to be able to know when the predicted detections are likely to cause errors in downstream tasks such as multi-object tracking. These errors can occur because of low-lighting conditions or heavy object occlusion.

“Uncertainty estimates give us an idea of when the model is in doubt, that is, when it is highly likely to give errors in predictions. But there’s this gap because probabilistic object detectors aren’t currently used in multi-tracking object tracking.” 

Lee worked on the paper as part of his undergraduate thesis in engineering science. Now a master’s student in Waslander’s lab, he is researching visual anomaly detection for the Canadarm3, Canada’s contribution to the U.S.-led Gateway lunar outpost. “In my current research, we are aiming to come up with a deep-learning-based method that detects objects floating in space that pose a potential risk to the robotic arm,” Lee says.

Waslander says the advancements outlined in the two papers build on work that his lab has been focusing on for a number of years.

“[The Toronto Robotics and AI Laboratory] has been working on assessing perception uncertainty and expanding temporal reasoning for robotics for multiple years now, as they are the key roadblocks to deploying robots in the open world more broadly,” Waslander says.

“We desperately need AI methods that can understand the persistence of objects over time, and ones that are aware of their own limitations and will stop and reason when something new or unexpected appears in their path. This is what our research aims to do.”

Three takeaways from Waabi CEO Raquel Urtasun’s entrepreneurial journey

mattimar — Wed, 15 Mar 2023 16:00:54 +0000

Three takeaways from Waabi CEO Raquel Urtasun’s entrepreneurial journey

mattimar Wed, 03/15/2023 - 12:00

Cutline

Raquel Urtasun, a professor of computer science and founder and CEO of self-driving startup Waabi, delivers a talk during the Desjardins Speakers Series at ��TV's Entrepreneurship Week (photo by Polina Teif)

Mariam Matti

Topic

Entrepreneurship Week

��TV Entrepreneurship

Centre for Engineering Innovation & Entrepreneurship

Raquel Urtasun

Desjardins Speaker Series: Driving Innovation with Raquel Urtasun, Founder of Waabi from ��TV Entrepreneurship on Vimeo.

Raquel Urtasun may be a world-leading expert in machine learning and computer vision – but that doesn’t mean she likes to talk about her abilities.

In fact, the CEO of self-driving vehicle company Waabi says she had to overcome her humble nature when trying to convince big-name investors she had the winning formula to transform the self-driving industry.

“You need to say [to venture capitalists] – why you, why this team and why this technology in a way that’s very convincing,” says Urtasun.

The approach worked. Urtasun, a professor in the department of computer science in the University of Toronto’s Faculty of Arts & Science, secured $100 million in initial capital – one of the largest rounds of seed funding in Canadian history. She’s since worked on developing the next-generation of AI-powered technology for self-driving trucks.

She recently spoke about her entrepreneurial journey during a keynote speech at True Blue Impact Day, which marked the culmination of the seventh annual ��TV Entrepreneurship Week.

Here are three takeaways from her talk:

Be bold and aim high

As someone who prefers to show others she can do something, Urtasun says she knew that asking for $100 million from a slew of big-name investors would not come naturally.

But she was confident in her detailed plan.

“In front of the venture capitalists, you cannot be humble,” she says. “They will never fund you.”

Urtasun says she made sure to draw a roadmap of how she intended to use the money.

“I didn’t want to worry about fundraising in six or nine months,” she adds. “I wanted the money so we could execute and build this transformational technology.”

Be strategic about your team

Urtasun is the sole founder of Waabi, but she says her team and the investors she’s worked with have been incredibly important in building the company. She adds that she knew from the beginning she wanted to work with investors from the technology and AI sector – including fellow ��TV AI luminaries Geoffrey Hinton and Sanja Fidler – because they would better understand Waabi’s mission.

“I think it’s important to have people you can rely on and that have each other’s back,” she says.

The investments from Uber, Khosla Ventures, BDC Capital and others have allowed the company to develop Waabi World, an advanced simulator to test its autonomous vehicles, and Waabi Driver, its first generation of self-driving trucks.

Ignore the competition

“My philosophy is to write a strategy and focus on that,” Urtasun says, adding that it’s important to tune out naysayers.

Case in point: When she first founded the company two years ago, she says she heard people say that she was getting into the self-driving sector “too late.”

“What I heard a lot was ‘everybody’s in this path, what are you doing?’ What I hear today is ‘how did you perfectly time this?’” she says. “And nothing changed, right? I just focused on doing my thing.”

��TV Entrepreneurship Week 2023: Top 10 startups to watch

Christopher.Sorensen — Thu, 02 Mar 2023 16:01:59 +0000

��TV Entrepreneurship Week 2023: Top 10 startups to watch

Christopher.Sorensen Thu, 03/02/2023 - 11:01

Cutline

(supplied images)

Mariam Matti

Topic

Temerty Faculty of Medicine

Black Founders Network

Entrepreneurship Week

Dalla Lana School of Public Health

Entrepreneurship

Faculty of Kinesiology & Physical Education

Leslie Dan Faculty of Pharmacy

Psychology

St. Michael's Hospital

��TV Mississauga

��TV Scarborough

A plant-based alternative to conventional plastic. Using drones to tackle reforestation in wildfire-ravaged locations. And a new generation of self-driving technologies that leverage the full potential of artificial intelligence.

These are just some innovative ideas that have emerged from the University of Toronto’s entrepreneurship community in recent years.

Ranked one of the top five university business incubators in the world, ��TV Entrepreneurship is set to celebrate these and other startups, as well as their founders, during its annual ��TV Entrepreneurship Week from March 6 to 9. The schedule includes pitch competitions, workshops, panel discussions and the popular True Blue Expo, which will feature the founders of more than 40 of ��TV’s top startups.

Another highlight: Raquel Urtasun, founder and CEO of Waabi and a ��TV professor of computer science, will discuss lessons learned while building her self-driving vehicle company at the Desjardins Speakers Series on March 9.

Here are 10 exciting ��TV startups to keep an eye on in 2023:

Arma Biosciences

The ability to give patients agency over their own health monitoring was one of the reasons Surath Gomis co-founded Arma Biosciences. The startup’s goal is to develop a new sensor technology for biomarker-informed digital health care. In partnership with Analog Devices, work on the company’s first product is underway – a handheld finger-prick blood test for patients with heart failure.

With a PhD in electrical and computer engineering from ��TV, Gomis established the company in 2020 with his supervisor Shana Kelley, a researcher in ��TV’s Leslie Dan Faculty of Pharmacy and Temerty Faculty of Medicine.

Gomis hopes future products will include wearable, implantable and ingestible sensors for monitoring applications.

Erthos

��TV alumnae Nuha Siddiqui and Kritika Tyagi are working to transform the plastic industry for the better. In 2018, the pair co-founded Erthos, a company that offers fully biodegradable plant-based material as a replacement for single-use plastics.

Erthos creates resins using materials that are both compostable and microplastic-free – and compatible with existing manufacturing technology. Siddiqui and Tyagi recently made the Forbes list of 30 under 30 in the social impact category, which noted that Erthos has raised more than US$5.5 million in funding.

TransCrypts

Ali Zaheer and Zain Zaidi co-founded TransCrypts to transform digital privacy and security. Back in 2020, they set out to answer a simple question: “Why can’t consumers own their important documentation digitally and in a way that can be easily verified?”

TransCrypts – which took home a $10,000 second-place startup prize at a ��TV pitch competition during last year’s Entrepreneurship Week – is a blockchain-based document verification platform that gives people direct access to their official documents, such as medical records. Supported by ��TV Scarborough’s The Hub, Zaheer and Zaidi have already helped thousands of Ukrainian refugees access medical records through a pilot project and landed US$2.4 million in funding from backers including Shark Tank investor Mark Cuban.

Waabi

A world-leading expert in machine learning and computer vision, Raquel Urtasun was inspired to start Waabi when she recognized a need for a new generation of self-driving technologies that leverage AI’s full potential. Backed by high-profile investors, including Volvo and Uber, the company is leading the way when it comes to the next generation of self-driving solutions.

The company recently launched Waabi World, an advanced simulator to test its autonomous vehicles, and Waabi Driver, its first generation of self-driving trucks. Urtasun says she focused on the long-haul trucking sector because it’s one of the most dangerous occupations – not to mention an industry that suffers from a shortage of drivers.

WooYourBoo

Husband-and-wife co-founders La Vance and Colleen Dotson – head coach of the ��TV Track & Field Club – are the entrepreneurial force behind a slick dating app for people already in relationships.

WooYourBoo aims to help partners reconnect and better communicate with each other through quizzes, activities and rewards.

“Our goal is to create depth and help you reconnect with this person that you’ve committed to – and make it fun,” Colleen recently told ��TV News.

The Dotsons say that ��TV’s Black Founders Network was instrumental in building WooYourBoo, which was among the inaugural cohort of the BFN Accelerate Program.

OTI Lumionics

OTI Lumionics could change the look of the smartphone in your pocket.

Founded by ��TV alumnus Michael Helander, the company has been working on expanding its line of organic LED technology solutions – including smartphone screens that are uninterrupted by notches, which are currently needed to house front-facing cameras and other equipment in some smartphone designs.

The company, which was spun out of research at ��TV, has collaborated with Microsoft Quantum and, most recently, their name has been connected to Apple as a key supplier for a future notch-free iPhone.

Flash Forest

Flash Forest, a startup with ties to ��TV Mississauga, is fighting climate change and restoring forests by leveraging the use of drones, AI, geographic information systems and plant science technology.

The company – which received support from ��TV’s Mississauga’s ICUBE incubator – recently inked a federal contract to use drones to plant more than one million trees over the next two years in wildfire-ravaged locations across Canada.

The co-founders, brothers Bryce and Cameron Jones, say they are focused on restoring severe wildfire sites where the seed pods and cones are lost.

Signal 1

Signal 1 is looking to transform health care by equipping doctors and nurses with real-time AI predictions.

The company, co-founded by CEO Tomi Poutanen, a ��TV alumnus, and Mara Lederman, professor of strategic management at the Rotman School of Management, has built a machine learning tool called CHARTWatch that can help predict how much support a patient will need.

The tool was originally developed at St. Michael’s Hospital by a team led by Signal 1's clinical adviser Muhammad Mamdani, who is vice-president of data science and advanced analytics at Unity Health Toronto and holds cross-appointments at ��TV’s Leslie Dan Faculty of Pharmacy, Temerty Faculty of Medicine and Dalla Lana School of Public Health.

The surgical unit at St. Michael’s Hospital has already begun using CHARTWatch to help care teams communicate and make decisions.

Mounib Real Food Only

When ��TV Scarborough alumna Iman Mounib encountered gut health issues, she took it upon herself to create products that are free of refined sugars, palm oils, gluten and dairy.

She founded Mounib Real Food Only, which sells a chocolate hazelnut spread made of just three local ingredients. The company also makes a peanut chocolate spread, as well as an almond chocolate version. Mounib’s goal was to create alternatives to popular products that are both tasty and good for you.

The products are sold in almost 20 restaurants, cafes and stores in the Greater Toronto Area, as well as one location in Ottawa.

HippoCamera

HippoCamera is a smartphone application that helps to improve memory recall, which could be beneficial for individuals in the early stages of Alzheimer’s disease or other forms of memory impairment.

Backed by years of research at ��TV, the app has an easy-to-use interface and is a personalized way to boost recall of daily experiences and enhance activity in the hippocampus, a part of the brain that plays a key role in memory.

Morgan Barense, a professor in the department of psychology in the Faculty of Arts & Science and co-author of a recent study on the technology, said her team found that memories that were associated with the HippoCamera were long-lasting – and that the device worked for both healthy older adults and those starting to show cognitive decline.

Learn more about U of Entrepreneurship Week

Raquel Urtasun’s self-driving startup Waabi brings on Volvo as strategic investor: Reports

bresgead — Fri, 20 Jan 2023 21:00:46 +0000

Raquel Urtasun’s self-driving startup Waabi brings on Volvo as strategic investor: Reports

bresgead Fri, 01/20/2023 - 16:00

Cutline

(Photo courtesy of Waabi)

Topic

Robotics

Vector Institute

University of Toronto researcher Raquel Urtasun’s self-driving startup Waabi has added the venture capital arm of Swedish carmaker Volvo to its list of high-profile investors.

Volvo Group Venture Capital AB is investing an undisclosed amount in Toronto-based Waabi’s AI-powered autonomous trucking technology, according to TechCrunch.

“We’ve been extremely selective in terms of who we bring on board as an investor and this is the right time for Waabi to bring on a strategic OEM [original equipment manufacturer],” Urtasun, a ��TV professor of computer science and Waabi’s founder and CEO, tells the high-profile U.S. tech website.

Waabi has already raised more than $100 million from investors including Khosla Ventures, Uber and other Silicon Valley giants. Also among its backers are AI luminaries Geoffrey Hinton, a ��TV University Professor Emeritus of computer science, and Sanja Fidler, an associate professor of computer science.

Urtasun tells the Globe and Mail that Volvo’s investment “significantly” increases Waabi’s valuation.

Waabi’s self-driving technology set to be road-tested, Raquel Urtasun tells Globe and Mail, Forbes

bresgead — Fri, 18 Nov 2022 18:05:17 +0000

Waabi’s self-driving technology set to be road-tested, Raquel Urtasun tells Globe and Mail, Forbes

bresgead Fri, 11/18/2022 - 13:05

Cutline

(Photo courtesy of Waabi)

Topic

Entrepreneurship

Vector Institute

The University of Toronto’s Raquel Urtasun, a leading expert in machine learning and computer vision, is taking her startup’s self-driving technology for long-haul trucks out for a spin, with several autonomous vehicles ready to hit the road in the United States, according to reports.

The CEO and founder of Waabi told the Globe and Mail that a handful of trucks are “ready to be deployed” with human drivers and engineers on-board for safety. In Forbes magazine, Urtasun – a professor of computer science in the Faculty of Arts & Science and faculty member at the Vector Institute for Artificial Intelligence – said that Waabi will train the self-driving system to navigate any number of virtual scenarios using a simulator that harnesses the full power of AI.

She added that the approach gives Waabi an advantage over bigger competitors since it’s more efficient – and effective – than relying on real-world testing.

“Because we can do everything on the simulator we are already ready with a generation that is much more advanced,” Urtasun told the magazine.

Waabi emerged from stealth mode in June 2021 after raising more than $100 million in funding from Silicon Valley giants such as Khosla Ventures and Uber, as well as AI luminaries including ��TV's Geoffrey Hinton, a University Professor Emeritus and Sanja Fidler, an associate professor of computer science.

��TV's aUToronto team wins first competition of AutoDrive Challenge sequel

Christopher.Sorensen — Tue, 14 Jun 2022 19:49:13 +0000

��TV's aUToronto team wins first competition of AutoDrive Challenge sequel

Christopher.Sorensen Tue, 06/14/2022 - 15:49

Cutline

The aUToronto team, made up mostly of ��TV undergraduate students, won the first phase of the AutoDrive Challenge II, which took place earlier this month in Ann Arbor, Mich. (photo courtesy aUToronto)

Tyler Irving

Topic

Graduate Students

Undergraduate Students

A self-driving vehicle team from the University of Toronto’s Faculty of Applied Science & Engineering has taken the top spot overall in the first competition of the four-year AutoDrive Challenge II.

The achievement by aUToronto continues an impressive winning streak for the team, which consistently placed first throughout the original four-year AutoDrive Challenge.

In the current contest, the intercollegiate competition’s original concept has been expanded with more teams and more sophisticated tasks as participants develop and demonstrate an autonomous vehicle (AV) that can navigate urban driving courses.

“This year was a fresh new start for us,” says Frank (Chude) Qian, a master’s candidate at the ��TV Institute for Aerospace Studies (UTIAS) and team principal for aUToronto. “We have a very young team, with nearly 90 per cent of the students new to the competition.”

Approximately 85 per cent of these students are undergraduates from across ��TV Engineering’s departments and divisions. The remainder are graduate students or undergraduates from other parts of ��TV, including the department of computer science in the Faculty of Arts & Science.

Throughout the fall of 2021 and winter of 2022, the aUToronto team spent hours designing, training and testing their perception cart, pictured here at the ��TV Institute for Aerospace Studies. (photo courtesy of aUToronto)

A total of 10 institutions from across North America sent teams to AutoDrive Challenge II. They assembled earlier this month at Mcity in Ann Arbor, Mich., a unique purpose-built proving ground for testing the performance and safety of connected and automated vehicles.

“This is the first year of the second round of the AutoDrive competition, so the team was required to design, build and code everything from scratch,” says Steven Waslander, an associate professor at UTIAS who advises the team along with fellow faculty members Tim Barfoot, Jonathan Kelly and Angela Schoellig.

“It was a monumental effort and one that shows the true depth of talent and dedication of all the members of this amazing group of students.”

In the first phase of the four-year competition, the teams were using what are known as perception carts.

“We use these to validate the design of our perception system, which we will incorporate onto a real vehicle for next year’s competition,” says Qian. “Our brand-new sensor suite is based on a new solid-state LiDAR modality.”

LiDAR is a sensing technology that works in a similar way to radar, except that it uses laser light instead of sound. It is a key component of the sensor suite – which also includes traditional radar and visual cameras similar to those found in smartphones – that enables a self-driving vehicle to build up a 3D representation of its surroundings.

Members of the aUToronto team with their winning perception cart at MCity in Ann Arbor, Mich (photo courtesy of aUToronto)

In addition to being declared the overall winner, the ��TV Engineering team received top marks in a wide range of categories, including the concept design event, the traffic light challenge and mobility innovation.

One of the most dramatic parts of the competition was the dynamic object detection challenge, during which the cart had to detect and avoid a mannequin of a deer.

“In the final testing session, the team realized their segmentation code was failing due to a change to the deer mannequin being used,” says Waslander.

“Having planned for just such an event, they immediately switched to high gear. They took and labelled over 2,000 images of the new deer, then spent the whole night training and tweaking a brand-new detector. It worked brilliantly in competition the next day, securing first place.”

Qian says he is very proud of all that the team has accomplished.

“This year with so many newer members, training became very important,” he says. “We also lost some precious development time due to challenges associated with COVID-19. I cannot give enough credit to the aUToronto flight team members who really took one for the team and pulled through together.”

In Globe and Mail, Raquel Urtasun discusses 'milestone' in self-driving car development

geoff.vendeville — Wed, 09 Feb 2022 16:36:41 +0000

In Globe and Mail, Raquel Urtasun discusses 'milestone' in self-driving car development

geoff.vendeville Wed, 02/09/2022 - 11:36

Cutline

(Photo courtesy of Waabi)

Topic

Vector Institute

Raquel Urtasun, a professor of computer science in the University of Toronto’s Faculty of Arts & Science and CEO of Waabi Innovations, says the company has hit on a new strategy for training self-driving cars: an artificial intelligence-driven simulator.

The simulator puts a virtual driver through different traffic scenarios, flagging problems with its performance and helping it improve faster.

“We’ve flipped the equation for how much simulation versus real world [training] you need‚” Urtasun, the company’s founder, told the Globe and Mail this week. “It’s really the key for unlocking self-driving technology.”

A former chief scientist and head of Uber's autonomous vehicle unit, Urtasun left Uber after the division was sold to Aurora Innovation in 2020. She founded Waabi with more than $100-million in seed financing.

WinTOR’s on its way: ��TV partnership to train self-driving cars to handle tough winter conditions

Christopher.Sorensen — Mon, 12 Jul 2021 18:24:24 +0000

WinTOR’s on its way: ��TV partnership to train self-driving cars to handle tough winter conditions

Christopher.Sorensen Mon, 07/12/2021 - 14:24

Cutline

��TV Engineering's Steven Waslander is leading a project, one of six at the university to receive support from the Ontario Research Fund, that focuses on teaching self-driving cars to handle winter road conditions (photo by PinkBadger via Getty Images)

Tyler Irving

Topic

Faculty of Dentistry

Companies around the globe are racing to create fully autonomous vehicles that can handle anything the road throws at them. But, according to the University of Toronto’s Steven Waslander, there’s one scenario that hasn’t yet received nearly as much attention as it deserves: winter.

“Winter conditions aggravate the remaining challenges in autonomous driving,” says Waslander, an associate professor at the ��TV Institute for Aerospace Studies in the Faculty of Applied Science & Engineering.

“Reduced visibility limits perception performance, and slippery road surfaces are a big challenge for vehicle control.”

To drive safely in all conditions, including winter, Waslander says autonomous vehicles need to fully observe their surroundings despite limits to their sensor range to get advanced warning of challenging situations and to react quickly to changing conditions.

Along with fellow ��TV Engineering researchers and members of the ��TV Robotics Institute – including Timothy Barfoot, Jonathan Kelly and Angela Schoellig – Waslander is leading a new partnership that will address these challenges by bringing together the best minds from academia and industry. The project, called WinTOR: Autonomous Driving in Adverse Conditions, is a new collaboration that aims to transform Toronto into a global hub for research and development related to autonomous driving in winter. Corporate partners include leading companies in the autonomous vehicles sector such as General Motors Canada, LG Electronics, Applanix and Algolux.

It's one of six projects from ��TV to receive support from the Ontario Research Fund. Five of the projects are led by researchers from the Faculty of Applied Science & Engineering, while the sixth is led by a researcher at the Faculty of Dentistry. (See the full list below.)

“With this investment, the Ontario Research Fund is supporting important work of ��TV researchers that will benefit all Canadians,” says Christine Allen, associate vice-president and vice-provost, strategic initiatives. “And it’s exciting to see that two of the initiatives to receive funding, focused on advanced robotics and innovative mobility, are among ��TV’s key areas of strategic, interdisciplinary focus.

“Through these Institutional Strategic Initiatives we’re mobilizing interdisciplinary cross-divisional research and collaboration to address societal challenges. We’re committed to developing these initiatives to a scale that can attract support from government, philanthropic or industry sources – and WinTOR is a terrific example.”

The WinTOR team already has a track record of success. Last year, Waslander and his collaborators published the Canadian Adverse Driving Conditions (CADC) dataset. Created using the Autonomoose, a self-driving vehicle designed by Waslander and his team, the open-source data record real winter driving conditions on roads in southwestern Ontario.

The valuable dataset is already being used by researchers from around the world to train new AI software. It joins a long list of research accomplishments from the project’s research team, whose combined expertise covers the full extent of autonomous driving perception and planning domains, including object detection and tracking, robust state estimation and calibration, localization and mapping, prediction and planning and safety-critical learning control.

All four professors are advisers to the aUToronto team, a group of undergraduate and graduate students who have designed and built a self-driving electric vehicle called Zeus. The ��TV Engineering team has placed first in the international AutoDrive Challenge in each of the four annual competitions to date.

The new partnership is supported by more than $12 million in funding from a variety of sources. In addition to the Ontario Research Fund, that includes funding from the Natural Sciences and Engineering Research Council of Canada, as well as direct and in-kind donations from the project partners. More than 20 individuals will work as part of the team, including graduate and undergraduate students, professors and engineers.

“We are excited to understand how we can apply the collaborative research under this program to real-world scenarios,” says Louis Nastro, director, land and autonomous vehicle strategy at Applanix. “It gives us an opportunity to attract highly talented individuals with the experience needed to join our team, and helps Canada establish itself as a leading provider of advancement in autonomy.”

“Algolux’s mission is to solve the issue of computer vision robustness in harsh driving conditions, a fundamental problem not effectively addressed by current approaches,” says Felix Heide, co-founder and chief technology officer of Algolux. “As a Canadian company, we are thrilled to bring our expertise to this project and continue to advance the state-of-the-art in perception technologies.”

“We are excited and proud to be a partner of this initiative,” says Kevin Ferreira, director of the LG Electronics Toronto AI Lab. “It is challenging to drive social impact with game changing technology in a fast-moving industry such as autonomous driving.

Partnerships and collaborations, such as this initiative, are an effective strategy to make contributions to the research community, and to deliver impactful applications that improve safety while driving.”

The WinTOR project is divided into three broad themes:

Sensor filtering for object detection: New ways of analyzing the data from sensors such as visual cameras, radar and lidar will help to separate the signals that represent real objects from the noise caused by falling or blowing snow. Strategies will include both pre-processing techniques and improved artificial intelligence algorithms trained to be aware of the limits of their own performance.
Sensor fusion, localization and tracking: While today’s self-driving cars can reliably determine where they are in relation to their surroundings, the techniques they use begin to break down under adverse driving conditions. The team will leverage new algorithmic strategies in vision and lidar registration, as well as new sensing options, such as ground-penetrating and automotive radar, to make localization algorithms more resilient in adverse conditions.
Prediction, planning and control: self-driving cars of the future will need to change the way they drive in response to winter hazards. For example, they might take a slightly different path to avoid a snowdrift or slow down when driving over a section of road that their sensors have perceived as particularly slippery. They will learn the implications of adverse weather on the vehicles around them and be able to assess the increased uncertainty of outcomes, enabling them to plan actions that can be executed reliably in winter conditions.

As ambitious as the current plan is, the team is just getting started. They are leveraging their network – including the ��TV Robotics Institute, one of more than a dozen institutional strategic initiatives at the university – to grow their team.

“We continue to seek additional faculty, partners and funding to grow the effort,” says Waslander. “We have many more ideas to work on, from multi-hypothesis prediction and interaction planning to attentive perception and explainable, efficient AI for autonomous driving.”

Here is the full list of ��TV researchers who are leading projects that received Ontario Research Fund support:

Konstantinos N. Plataniotis, Faculty of Applied Science & Engineering, Transforming Pathology Using Artificial Intelligence to Improve Patient Outcome and Hospital Efficiency
Philippe Lavoie, Faculty of Applied Science & Engineering, Characterization, Prediction and Control of Flap Noise Sources from Aircraft
Eric Miller, Faculty of Applied Science & Engineering, iCity 2.0: Urban Data Science for Future Mobility
Patrick Chang Dong Lee, Faculty of Applied Science & Engineering, Innovative and Cost-Effective Micro/Nanocellular Foaming Technology for Sustainable Lightweight Applications
Steven Waslander, Faculty of Applied Science & Engineering, All-Weather Autonomy: Securing Ontario’s Leadership in the Self-Driving Revolution
Christopher McCulloch, Faculty of Dentistry, The Fibrosis Repair Team

��TV Engineering team places first in AutoDrive Challenge for fourth straight year

Christopher.Sorensen — Wed, 16 Jun 2021 15:25:36 +0000

��TV Engineering team places first in AutoDrive Challenge for fourth straight year

Christopher.Sorensen Wed, 06/16/2021 - 11:25

Cutline

A team of students from ��TV Engineering won the annual competition with their self-driving electric car "Zeus," pictured here outside the MarsDome at the University of Toronto Institute for Aerospace Studies (photo by Chude Qian)

Tyler Irving

Topic

Global

Graduate Students

Sustainability

Undergraduate Students