Safa Jinje

Healthy aging in place: New pilot program to provide high-tech cognitive, physical enrichment for seniors

rahul.kalvapalle — Thu, 22 Aug 2024 13:32:02 +0000

Healthy aging in place: New pilot program to provide high-tech cognitive, physical enrichment for seniors

rahul.kalvapalle Thu, 08/22/2024 - 09:32

Cutline

2RaceWithMe, a tool developed by Professor Mark Chignell from the department of mechanical and industrial engineering in ��˾��ֱ��'s Faculty of Applied Science & Engineering, combines physical and cognitive engagement by requiring users to pedal to be able to watch scenic videos (photo by Justin Greaves/Centivizer)

Safa Jinje

Topic

Our Community

department of mechanical and industrial engineering

Institutional Strategic Initiatives

Connaught Fund

Faculty of Applied Science & Engineering

Subheadline

The initiative, supported by a Connaught Community Partnership Research Program award, explores the use of interactive tools to promote active lifestyles among older adults

Older adults living in a Toronto co-operative apartment building will soon have access to high-tech activity spaces designed to promote cognitive, physical and social enrichment, thanks to a new pilot project led by the University of Toronto’s Mark Chignell.

The activity spaces aim to promote healthy aging for older adults who are aging in place – meaning they have the social and health supports to live safely and independently. They will be located in the communal area of a City Park co-op building that is considered a naturally occurring retirement community, where more than 30 per cent of occupants are over the age of 65.

The initiative was launched by Chignell, a professor in the department of mechanical and industrial engineering in ��˾��ֱ��’s Faculty of Applied Science & Engineering, in collaboration with HelpAge Canada, a non-profit that supports community-based services for seniors, and AGE-WELL, a research network and ��˾��ֱ�� institutional strategic initiative.

It’s one of nine projects to be supported by 2024-25 Community Partnership Research Program awards, given by ��˾��ֱ��’s Connaught Fund with the aim of accelerating research carried out in collaboration with community partners and driven by their needs and priorities.

“My work is motivated by the fact that physical and cognitive health can decline very quickly for older adults,” says Chignell.

“We know the physical body and brain work together, and that physical exercise is important for cognitive status and preventing dementia. So being able to promote more active lifestyles for people who are still living independently in the community can have an immense benefit for our society.”

The activity spaces will feature products from Centivizer, a ��˾��ֱ�� startup spun off from Chignell’s research, that specializes in creating interactive activities, games and cognitive assessment tools to support healthy aging.

These include 2RaceWithMe, a device that promotes both physical and cognitive engagement by having users pedal while watching scenic videos that only play when the pedals are in motion.

Centivizer has also developed a suite of whack-a-mole-style games for cognitive assessment that Chignell hopes can be used to promote cognitive safety in clinical practice.

A two-time recipient of Connaught Innovation Awards, Chignell says he feels honoured to now receive support from the Connaught Fund's Community Partnership Research Program.

“The Connaught is a great validation as I start this project in naturally occurring retirement communities,” says Chignell. “I am also continuing to work with retirement homes and long-term care centres, including a new collaboration with a long-term care home in Tokyo, Japan.

“I’m hoping that this project will demonstrate the value of using our products in the community to help older people retain their physical and cognitive abilities for longer.”

��˾��ֱ�� team takes top spot in self-driving car challenge for 6th time in 7 years

Christopher.Sorensen — Wed, 07 Aug 2024 17:42:55 +0000

��˾��ֱ�� team takes top spot in self-driving car challenge for 6th time in 7 years

Christopher.Sorensen Wed, 08/07/2024 - 13:42

Cutline

As part of the competition, the ��˾��ֱ�� team’s autonomous vehicle had to react to obstacles such as a fake deer moving across the road (photo courtesy of aUToronto)

Safa Jinje

Topic

Our Community

��˾��ֱ��

Artificial Intelligence

Faculty of Applied Science & Engineering

Graduate Students

Research & Innovation

Self-Driving Cars

Undergraduate Students

UTIAS

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 ��˾��ֱ�� 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 ��˾��ֱ�� 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 ��˾��ֱ�� 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.” 

What makes a chess move brilliant? Researchers use AI to find out

Christopher.Sorensen — Wed, 07 Aug 2024 17:25:51 +0000

What makes a chess move brilliant? Researchers use AI to find out

Christopher.Sorensen Wed, 08/07/2024 - 13:25

Cutline

��˾��ֱ�� Engineering researchers Kamron Zaidi, left, and Michael Guerzhoy, right, use game trees and deep neural networks to enable chess engines to recognize brilliant moves (photo by Safa Jinje)

Safa Jinje

Topic

Breaking Research

��˾��ֱ��

Artificial Intelligence

Faculty of Applied Science & Engineering

Mechanical & Industrial Engineering

Research & Innovation

Subheadline

AI system developed by ��˾��ֱ�� researchers is being used to study human creativity and make a chess computer that is more entertaining to play against

Researchers at the University of Toronto have designed a new AI model that understands how humans perceive creativity in chess.

In a recent paper presented at an international conference, researchers in ��˾��ֱ��’s Faculty of Applied Science & Engineering describe how they used techniques such as game trees and deep neural networks to enable chess engines to recognize brilliant moves.

The development could lead to chess engines that can find the most creative and clever path to victory in game, rather than just making moves to maximize win rates. That, in turn, could have implications for other AI systems tasked with creative endeavours.

“A chess move can be perceived as brilliant, or creative, when the strategic payoff isn’t clear at first, but in retrospect the player had to follow a precise path in gaming out all the possibilities to see so far into the future,” says paper co-author Michael Guerzhoy, an assistant professor, teaching stream, of mechanical and industrial engineering and engineering science who wrote about the research on his Substack.

“We wanted our system to understand human perception of what constitutes brilliance in chess and distinguish that from just winning.”

Most of the current research into chess AI is focused on enabling moves that create a higher chance of winning. But this doesn’t always make for an exciting game.

Skilled human chess players, on the other hand, can play in a more dramatic or imaginative way by making moves that may break traditional rules –for example, sacrificing a piece in a way that may initially look like a mistake, but ultimately, paves the way to a win.

A chess board depicts a move from the “Game of the Century” in 1956, when future American chess grandmaster Bobby Fischer (black) sacrificed his queen in a move that was celebrated as brilliant (photo by Safa Jinje)

The team worked with Leela Chess Zero, a top chess engine that learns through self-play and has played over 1.6 billion games against itself. They also employed Maia, a human-like neural network chess engine developed by ��˾��ֱ�� computer science researchers.

“We used the two neural network chess engines to create our game trees at different levels of depth in a game,” says paper co-author Kamron Zaidi, a recent ��˾��ֱ�� Engineering graduate.

“Using these game trees, we extracted many different features from it. We then fed the features into a neural network that we trained on the Lichess database of online chess games, which are labelled by human users of the database.”

A game tree in chess represents the current state of a chess board along with all the possible moves and counter moves that can occur. Each board position is represented as a node and the game tree can be expanded on until the game is either won, drawn or lost.

The researchers began with small game trees then slowly increased the size, adding more nodes to the tree. They found that when the neural network looks at all the game tree features and makes a prediction as to whether the move is brilliant or not, it reached an accuracy rate of 79 per cent using the test data set.

The research – based on Zaidi’s undergraduate engineering science thesis, which was supervised by Guerzhoy – was presented at the International Conference on Computational Creativity in Jönköping, Sweden.

“There were people from all over the world presenting research on more traditional aspects of creativity, but we were all focused on the same thing, which is, ‘How can we use AI to enhance our interactions and understandings of creativity?’” says Zaidi. 

The work has also received media coverage in outlets, including New Scientist, where English chess grandmaster Matthew Sadler says that a model that can understand brilliance could be used as a training tool for professionals and potentially lead to a more entertaining engine opponent for amateur players.

The team sees their system as having broad applicability when it comes to perception of creativity and brilliance.

“One of the biggest areas that is of interest to me is characterizing what we perceive as creativity,” says Guerzhoy.

“Not just in board games but in other creative endeavours, including music and art, where there is a formal framework and rules that need to be followed. Highly creative work involves planning in advance and gaming out the possibilities.

“But everyone I’ve talked to since the paper came out wants to know when they can play against our brilliant chess engine. So, I think making that possible is the obvious next step for us.”

��˾��ֱ�� researchers design new method of recycling steel that could reduce industry's carbon footprint

rahul.kalvapalle — Fri, 26 Jul 2024 16:09:57 +0000

��˾��ֱ�� researchers design new method of recycling steel that could reduce industry's carbon footprint

rahul.kalvapalle Fri, 07/26/2024 - 12:09

Cutline

PhD candidate Jaesuk Paeng (left) and Professor Gisele Azimi from the department of chemical engineering and applied chemistry in ��˾��ֱ��'s Faculty of Applied Science & Engineering display an electrochemical cell that's vital to their novel steel-recycling method (photo by Safa Jinje)

Safa Jinje

Topic

Breaking Research

Chemical Engineering

Faculty of Applied Science & Engineering

Materials Science

Research & Innovation

Sustainability

Subheadline

“Our study is the first reported instance of electrochemically removing copper from steel and reducing impurities to below alloy level”

Researchers at the University of Toronto’s Faculty of Applied Science & Engineering have designed a novel way to recycle steel that could help decarbonize several manufacturing industries and usher in a circular steel economy.

The new method introduces an innovative oxysulfide electrolyte for electrorefining, an alternative way of removing copper and carbon impurities from molten steel. The process also generates liquid iron and sulfur as by-products.

It’s outlined in a new paper published in Resources, Conservation and Recycling and co-authored by Jaesuk (Jay) Paeng, a PhD candidate in the department of chemical engineering and applied chemistry, William Judge, a PhD alum from the department of materials science and engineering, and Professor Gisele Azimi from the department of chemical engineering and applied chemistry.

“Our study is the first reported instance of electrochemically removing copper from steel and reducing impurities to below alloy level,” says Azimi, who holds the Canada Research Chair in Urban Mining Innovations.

Currently, only 25 per cent of steel produced comes from recycled material. But the global demand for greener steel is projected to grow over the next two decades as governments around the world endeavour to achieve net-zero emission goals.

Steel is created by reacting iron ore with coke – a prepared form of coal – as the source of carbon and blowing oxygen through the metal produced. Current processes generate nearly two tonnes of carbon dioxide per tonne of steel produced, making steel production one of the highest contributors to carbon emissions in the manufacturing sector.

Traditional steel recycling methods use an electric arc furnace to melt down scrap metal. Since it is difficult to physically separate copper material from scrap before melting, the element is also present in the recycled steel products.

“The main problem with secondary steel production is that the scrap being recycled may be contaminated with other elements, including copper,” says Azimi.

“The concentration of copper adds up as you add more scrap metals to be recycled, and when it goes above 0.1 weight percentage in the final steel product, it will be detrimental to the properties of steel.”

Copper cannot be removed from molten steel scrap using the traditional electric arc furnace steelmaking practice, so this limits the secondary steel market to producing lower-quality steel product, such as reinforcing bars used in the construction industry.

“Our method can expand the secondary steel market into different industries,” says Paeng. “It has the potential to be used to create higher-grade products such as galvanized cold rolled coil used in the automotive sector, or steel sheets for deep drawing used in the transport sector.”

To remove copper from iron to below 0.1 weight percentage, the team had to first design an electrochemical cell that could withstand temperatures up to 1,600 degrees Celsius.

Inside the cell, electricity flows between the negative electrode (cathode) and positive electrode (anode) through a novel oxysulfide electrolyte designed from slag — a waste derived from steelmaking that often ends up in cement or landfills.

“We put our contaminated iron that has the copper impurity as the anode of the electrochemical cell,” says Azimi. “We then apply an electromotive force, which is the voltage, with a power supply and we force the copper to react with the electrolyte.”

“The electrolyte targets the removal of copper from the iron when we apply electricity to the cell,” adds Paeng. “When we apply electricity on the one side of the cell, we force the copper to react with the electrolyte and come out from iron. At the other end of the cell, we simultaneously produce new iron.”

Azimi’s lab collaborated on the research with Tenova Goodfellow Inc., a global supplier of advanced technologies, products and services for metal and mining industries, where study co-author Judge works as a senior research and development engineer.

Looking forward, the team wants to enable the electro-refining process to remove other contaminants from steel, including tin.

“Iron and steel are the most widely used metals in the industry, and I think the production rate is as high as 1.9 billion tonnes per year,” says Azimi.

“Our method has great potential to offer the steelmaking industry a practical and easily implementable way to recycle steel to produce more of the demand for high-grade steel globally.” 

Study identifies sources of indoor air pollution in Toronto subway system

Christopher.Sorensen — Fri, 05 Jul 2024 19:02:08 +0000

Study identifies sources of indoor air pollution in Toronto subway system

Christopher.Sorensen Fri, 07/05/2024 - 15:02

Cutline

A study led by researchers at the Faculty of Applied Science & Engineering identified friction braking – used in the Toronto subway system's Line 2 – as having a significant influence on indoor air quality (photo by Roberto Machado Noa/UCG/Universal Images Group via Getty Images)

Safa Jinje

Topic

Breaking Research

Chemical Engineering

Faculty of Applied Science & Engineering

Research & Innovation

Subheadline

Wear of train wheels and rails - caused by braking - was found to be a key cause of particulate pollution along the Toronto Transit Commission (TTC) subway system

Research carried out by University of Toronto experts in partnership with Health Canada has identified braking of trains – and resulting wear of wheels and rails – as the major cause of particulate pollution in Toronto’s subway system.

For the study, which was published in Transportation Research Part D: Transport and Environment, researchers measured the chemical composition of particulate matter, which refers to fine particles of airborne solids or liquids that are smaller than 2.5 micrometres per cubic metre of air, and coupled this with modelling.

They found that most of the particulate pollution was coming from wheels and rails when brakes were applied – a discovery that marks an important step towards improving indoor air quality along the Toronto Transit Commission (TTC)'s subway system.

“Our early results pointed to the brake pads themselves as being the major cause of the emissions. However, we were surprised to find that the main source of this indoor air pollution is wear of wheels and rails during braking, rather than coming from the brake pads,” says Greg Evans, a professor in the department of chemical engineering and applied chemistry in the Faculty of Applied Science & Engineering, who led the study alongside PhD alum Keith Van Ryswyk, a senior air pollution exposure researcher at Health Canada.

“The amount of wear is influenced by the degree of braking applied, that is, how quickly the trains come into the station.

“We can’t replace the wheels and rails across the entire system, but if we can change the way that drivers apply the brakes, so they aren’t hit as hard or as often, that offers an interim way to reduce the emissions.”

A: View of a track bed with running and contact third rails. B: Close-up of a train bogie with brake and wheel contact. C: Full view of train bogie with wheels, brake pads and contact shoe. (image courtesy of Keith Van Ryswyk)

The study continues research published in 2021 which found that concentrations of particulate matter in 2018 had increased in the TTC’s Line 2 along Bloor-Danforth, while Line 1 along Yonge-University saw a drop in emissions.

Braking technology has a significant influence on emissions, Evans said, noting the TTC’s Line 2 uses older trains that are nearing the end of their 30-year design life cycle and reduce speed through regenerative and friction braking, whereas Line 1 has a fleet of newer trains which largely use regenerative braking to convert the train’s energy back into electricity.

“On Line 1, the braking is mostly regenerative, which involves no direct physical friction contact between the brake materials themselves,” says Evans. “They are also putting in automatic train control on Line 1, a system where braking is automated, which further reduces friction braking. These are all positive steps, but Line 2 has not benefitted from these changes yet.”

While the adverse health effects of outdoor particulate matter have been well established, the consequences of inhaling particles in subways are not as clear.

“The particulate matter in the subway is actually very different from what we find in ambient, outdoor pollution,” Evans says. “It’s very metal-rich and mostly made up of iron. So, there is good reason to think that it may be more hazardous.” 

Beyond reducing emissions, improving ventilation is the second way to improve air quality on subway trains and platforms.

Subway systems in cities such as Montreal and Barcelona use continuous mechanical ventilation for cooling, which also results in lower levels of particulate pollutant concentrations. But Toronto’s system uses limited forced ventilation, says Evans.

“It really relies on trains pushing the air like a piston as they go through the tunnels. And eventually the trains come to an open area, where the train goes outside and pushes the contaminated air out with it, which is what provides most of the ventilation,” he says.

Evans hopes these new findings will not only accelerate the technological changes needed to improve indoor air quality on Line 2, but also influence the plans for new subway lines in Toronto, such as the Ontario Line, and support the design of subways in other cities across the globe.

“We hope this work will help design better subway lines given that so much valuable work is going into creating better transit systems,” says Evans.

“Good transit is central to both decarbonization and the smooth operation of modern cities. It’s important for transit systems like subways to provide a healthy environment rather than expect passengers themselves to take precautionary steps in response to poor air quality.”

��˾��ֱ��'s top undergraduate says he fell in love with the process of learning

rahul.kalvapalle — Tue, 25 Jun 2024 14:13:32 +0000

��˾��ֱ��'s top undergraduate says he fell in love with the process of learning

rahul.kalvapalle Tue, 06/25/2024 - 10:13

Cutline

Jeff Chen achieved perfect grades in 17 of his 46 courses on his way to graduating with a bachelor of applied science in civil engineering (photo by Bronson Lo)

Safa Jinje

Topic

Our Community

Convocation 2024

Faculty of Applied Science & Engineering

Subheadline

Jeff Chen was awarded the 2024 John Black Aird Scholarship as the top student from an undergraduate degree program at ��˾��ֱ��

Jeff Chen says he's always prioritized his academics, but what really elevated his performance to the next level was pouring his energies into the process of learning and self-improvement – rather than obsessing over the outcome.

“In my first year, I spent a lot of time anticipating the marks I would need to get a 4.0 GPA,” says Chen. “I stopped doing that in second year and cared more about the effort I put in to get the result.”

The approach bore fruit. Chen graduated this June with his bachelor of applied science in civil engineering, achieving 100 per cent in 17 of his 46 courses for an overall average of 96.5 per cent – the highest among his cohort of graduates across ��˾��ֱ��’s three campuses.

His performance earned him the 2024 John Black Aird Scholarship, which is awarded annually to the top student from an undergraduate degree program at ��˾��ֱ��. His stellar academic record also led to him receiving a Governor General’s Silver Medal.

“This honestly wasn’t something I was expecting but I am immensely grateful,” says Chen. “I am treating these awards as a culmination of four years of hard work.”

Chen adopted a methodical process to course work, starting his mornings by writing a list of what he wanted to accomplish that day. The items would be small, such as studying lecture notes for 15-minute increments, and he preferred to spread assignments and projects across several days. “I found that breaking things up helped me not get distracted and everything was continually fresh in my mind,” he says.

Chen also applied the same approach to his pastimes, which include playing chess, hiking and working out. “My hobbies allow for me to set and fulfill goals in the same way I approach my academics,” he says. “I’ve recently gotten into powerlifting, and I always aim to hit higher weights for the squat, bench and deadlift.”

One of the highlights of Chen’s undergraduate career at ��˾��ֱ�� was his fourth-year thesis, which explored the use of deep neural networks – a form of artificial intelligence – to predict the behaviour of structures during earthquakes.

The research focused on the seismic response of structural systems that exhibit non-linear stress-strain behaviour when subjected to strong forces. “Under an earthquake, dynamic forces on the structure are often strong enough that they enter this non-linear range, which has complex, difficult-to-predict behaviour,” Chen says.

The work, supervised by Professor Oh-Sung Kwon of the department of civil and mineral engineering, began when Chen received an undergraduate summer research award from the Natural Sciences and Engineering Research Council of Canada (NSERC).

“The thesis project was completely open-ended and self-directed, unlike my course work, where outcomes are determined by the professors,” Chen says. “I got to explore the intersection between artificial intelligence and structural engineering, and how we can utilize deep neural networks to design better and more resilient structures in the case of disasters.

“I really enjoyed the challenge of working on this research, so I spent a lot of time on it.”

This fall, Chen will take on his next academic challenge as a law student at the University of California, Berkeley. He says he’s looking forward to gaining foundational legal knowledge during his first year of law school before committing to a specific area of law. “I am keeping my options open, but I know my engineering degree will be useful, especially if I go into intellectual property law, since working on patents can be very technical.”

Reflecting on his time at ��˾��ֱ��, Chen says he hopes his experiences will inspire other students to enjoy the journey of higher learning.

“��˾��ֱ�� has opened many doors for me and there are many paths I can take going forward.”

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

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

��˾��ֱ�� 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

Artificial Intelligence

Faculty of Applied Science & Engineering

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.”

��˾��ֱ�� Engineering to launch new certificate in electric vehicle design

Christopher.Sorensen — Mon, 29 Apr 2024 13:22:03 +0000

��˾��ֱ�� Engineering to launch new certificate in electric vehicle design

Christopher.Sorensen Mon, 04/29/2024 - 09:22

Cutline

(photo by Justin Sullivan/Getty Images)

Topic

Faculty of Applied Science & Engineering

Sustainability

The University of Toronto’s Faculty of Applied Science & Engineering will launch a new electric vehicle design certificate for undergraduate students this fall.

The program aims to prepare the next generation of electric vehicle (EV) engineers for professional and research opportunities in the growing industry.

“EVs have tremendous potential to improve local and global climates, which fits right in with our faculty’s broader goals of sustainability and environmental considerations,” says Professor Dionne Aleman, the faculty’s associate dean of cross-disciplinary programs.

“From battery design to sustainability to infrastructure, engineering is a big part of advancing EV technology. We want engineering students to be able to hit the ground running in this exciting and growing field if they want careers in electrification.”

The widespread adoption of EVs has come into greater focus as governments across the globe develop new policies to achieve net-zero emissions goals by 2050. In Canada, the federal government has set a zero-emissions vehicle sales target by 2035, which will require all new cars, trucks and SUVs to be battery operated.

To meet this demand, the EV industry will require a workforce that can advance all facets of electrification technology, from vehicle design and charging technologies, to battery capacity and thermal management of power systems. This work is multidisciplinary, spanning mechanical, electrical, chemical, industrial, computer and materials science engineering.

While many ��˾��ֱ�� Engineering courses include aspects of EV design, the faculty has delved deeper into EV-focused topics in the past year with two graduate-level courses in electric vehicle systems and thermal science.

The new certificate will expand on these offerings to provide eligible undergraduate students with an understanding of the technical and environmental implications of engineering in EV design. It includes a new course, APS380: Introduction to Electric Vehicle Design.

“The EV Design certificate is the beginning of a start-to-finish investigation into both the design of EVs and their integration into society,” says Matthew Mackay, an associate professor, teaching stream, in the department of mechanical and industrial engineering, who worked with Olivier Trescases, a professor in the Edward S. Rogers Sr. department of electrical and computer engineering (ECE), to design the introductory course.

“Since EVs are inherently multidisciplinary, having students first encounter this content through the certificate and a multidisciplinary design course will expose them to the challenges and knowledge they would not otherwise see through a single-program outlook.”

The APS380 course is a broad-based introduction to EV design, which makes the technical content accessible to students across engineering programs.

“This certificate is part of a multi-year effort to bring EV teaching to our departments. It will take some time for us to grow the capacity of this effort as new lab spaces, lecturers and courses are brought in,” says Mackay.

“But we want this to be an inclusive experience for students. If someone is interested but doesn’t have the required experience, we hope that they can come to see us anyway – there may always be opportunity to join.”

Trescases says there is a growing demand for engineers with specialized EV skills in Ontario.

“In ECE we’ve been teaching core EV topics like electric motors and power electronics to undergraduates for a long time, in courses like ECE314, ECE463 and ECE520. This new multi-disciplinary course takes a more ‘systems/application’ perspective and I think that it will be a great complementary offering for our students,” he says.

“In developing the labs and the course content for APS380 we leveraged elements of our research at [the ��˾��ֱ�� Electric Vehicle Research Centre, or UTEV], our new EV graduate course, as well as the new Porsche EV microcredential that we offer to industry through the School of Continuing Studies.”

��˾��ֱ�� research team hits bullseye with strategy to improve fairness in darts

Christopher.Sorensen — Thu, 11 Apr 2024 15:54:34 +0000

��˾��ֱ�� research team hits bullseye with strategy to improve fairness in darts

Christopher.Sorensen Thu, 04/11/2024 - 11:54

Cutline

(photo by Zac Goodwin/PA Images via Getty Images)

Safa Jinje

Topic

Our Community

Faculty of Applied Science & Engineering

Subheadline

Researchers in ��˾��ֱ��'s Faculty of Applied Science & Engineering take home first place at MIT Sloan Sports Analytics Conference

A research team from the University of Toronto is rethinking how darts can be played more fairly.

The team, led by Timothy Chan, a professor in the department of mechanical and industrial engineering in the Faculty of Applied Science & Engineering, recently took home first place in the 2024 MIT Sloan Sports Analytics Conference Research Papers Competition by designing a new framework to level the playing field in dart games.

“Winning this competition, at the world’s most prominent and competitive sports analytics conference, is a testament to the excellence and ingenuity of our students here at the University of Toronto,” says Chan, who is also ��˾��ֱ��’s associate vice-president and vice-provost, strategic initiatives.

With millions of players around the world, including an estimated 17 million in the United States, according to the National Sporting Goods Association, the game of darts continues to grow in popularity.

“Darts is a great sport because almost anyone can play and it doubles as a fun mental puzzle,” says Rachael Walker, an alumna who is a co-author of the conference paper along with PhD candidate Craig Fernandes and Chan.

From left to right: Professor Timothy Chan, Rachael Walker and Craig Fernandes are the co-authors of a paper that introduces a new framework designed to level the playing field in dart games (photo by Safa Jinje)

The research, which expands on work Walker did for her undergraduate thesis, focuses on the game of 501 darts, where players begin with a score of 501 and take turns throwing darts at the dartboard. Points are deducted from their total depending on where the darts land. The first player to reach zero wins.

“We looked at 501 darts played in recreational and professional settings,” says Fernandes. “In a recreational setting, the game is often played amongst players that have different skill sets – and when that happens, the stronger player often wins, which can lead to unexciting matches.”

As in golf, the imbalance is often addressed by introducing a system that gives the less-skilled players an advantage so that all players have an equal chance at winning.

“[But] our research first proved that the current approach of giving the weaker player a head start doesn’t actually give all players a fair chance at victory,” says Fernandes. “Instead, we used a Markov decision process to understand the nuances of the game and then come up with a new system that actually leads to mathematical fairness.”

The new framework first determines a player’s skill level by having them throw several darts at the centre of the board before the start of a game. Players are then assigned a skill level based on where their darts land – players who get most of their darts in the centre are determined to be higher skilled, while those whose darts are spread out across the board are deemed less-skilled players who would benefit from an advantage.

The new system gives the lesser-skilled player credits that they can cash in at any point in the game. The credits can be used to claim the outcome of a throw – that is, the region of the board they intend the dart to land in – without physically throwing the dart.

The researchers found that credits create fairness by using a Markov decision process, a mathematical framework that models scenarios where the outcomes are partly in control of the decision-maker and partly random. However, the number of possible decisions and outcomes in darts made the model difficult to implement and solve at scale.

“To accurately model a dart game that assigns an advantage to a single player, we needed to consider over half a million possible game states and hundreds of possible actions at each state,” says Walker.

“In a traditional implementation, you optimize across all states simultaneously, which may require considering billions, or even trillions, of possible outcomes.”

The researchers overcame the challenge of scale by starting simply and slowly adding complexity to the model. The first version did not consider the fact that darts is played in turns of three throws for each player; this helped build intuition and develop implementation tricks that later allowed them to solve the true model.

The first-place finish at the MIT Sloan Sports Analytics Conference was affirming for the researchers.

“It was a very strong competition featuring many major North American sports such as football, baseball and basketball, and a lot of research was focused on generative artificial intelligence and machine learning,” says Fernandes, who presented the research at the Sloan conference.

“Winning with our operations research and optimization approach was exciting for us.”

The team is now looking to implement the framework with collaborators, including local dart leagues, to see it work in practice.

“My lab tackles complex decision-making problems in health care and sports using techniques from operations research,” says Chan.

“The tools we develop are general, so the insights we obtain from solving a problem in darts may then be applied towards solutions in patient scheduling or medical decision-making.”

��˾��ֱ�� Engineering program introduces Black high school students to STEM careers

Christopher.Sorensen — Mon, 12 Feb 2024 20:48:52 +0000

��˾��ֱ�� Engineering program introduces Black high school students to STEM careers

Christopher.Sorensen Mon, 02/12/2024 - 15:48

Cutline

Jadesola Babalola-Lucas, 16, explored her passion for engineering during ��˾��ֱ�� Engineering's Blueprint program last summer (supplied image)

Safa Jinje

Topic

Our Community

Black

Faculty of Applied Science & Engineering

Outreach

Undergraduate Students

Subheadline

The free Blueprint program, open to students who have completed Grades 10 or 11, runs for four weeks during the summer and includes workshops throughout the year

Jadesola Babalola-Lucas, 16, has felt an affinity for math and science since she was in elementary school, but it was not until the summer of 2020 that she discovered her passion for engineering.

“I was stuck at home because of COVID-19 and watching a lot of TV, especially the Smithsonian Channel,” says Babalola-Lucas, who is now in Grade 11. “And I kid you not, I had an epiphany watching Planes That Changed the World.”

She was struck by aeronautical feats involved in the design of aircrafts such as the Lockheed SR-71 Blackbird, the fastest crewed aircraft with air-breathing engines, and the way the engineers overcame their challenges with creativity.

“I began to understand how interdisciplinary engineering really is, and it was at that moment that I realized engineers really do make the world go round,” says Babalola-Lucas. “Who wouldn’t want to be a part of something that big?”

A few years later, Babalola-Lucas stumbled upon a posting for Blueprint, an academic enrichment program run by the University of Toronto’s Faculty of Applied Science & Engineering for Black high school students who are passionate about science, technology, engineering and math (STEM). She could not pass up the opportunity to apply and step closer to her goal of studying either materials science or mechanical engineering, and then pursuing graduate studies in aerospace engineering.

The free, four-week Engineering Outreach program, which is taking applications for this summer until March 24, introduces students who have just finished Grades 10 and 11 to the engineering design process. Through course offerings, hands-on activities and collaborative projects, participants apply what they have learned to create innovative solutions for global issues.

Students are also connected with mentors, who are current undergraduate engineering students – some of whom have gone through the Blueprint program themselves. The mentors help participants understand the day-to-day experience of studying STEM subjects in university.

Blueprint students continue their engagement with ��˾��ֱ�� Engineering over the next school year through two programs – Prepare for Grade 11 students and My Academic Planning Sessions (MAPS) for Grade 12 students. From October through March, weekly virtual sessions guide the prospective university students through the obstacles they may face during their transitions from high school to university.

Additionally, Blueprint participants who are accepted into a ��˾��ֱ�� Engineering undergraduate program are eligible to receive one of five fully funded entrance scholarships that is renewable for four years.

“Blueprint allows Black students to meet successful individuals with similar racial and academic backgrounds. We do this by inviting Black STEM professionals and current engineering students as guest speakers over the summer and yearlong engagement,” says Cassandra Abraham, a co-ordinator at Engineering Outreach and Blueprint director.

“This representation can be empowering, instilling a sense of belonging and motivating students to pursue STEM careers.”

Students had opportunities to code robots in the Mechatronics and Automation course (photo by Shenile Ellis)

The program is structured to facilitate connection among peers. Students are initially divided into groups based on their hobbies and interests – information that is collected during the onboarding process – to encourage them to communicate with each other and form friendships, says Abraham.

When Shenile Ellis, 17, first applied to Blueprint, the then-Grade 11 student thought it would be a great opportunity to learn more about different engineering disciplines.

While she was already interested in mechanical engineering because she enjoyed 3D modelling and seeing projects come to life, she was keen to meet other Black students who were interested in STEM and get a glimpse of what it is like to learn on a university campus.

“I wasn’t sure I would get in, but when I did, I realized I should never count myself out,” Ellis says. “One of the Blueprint leaders always told us that we were there for a reason and that we are all capable.”

For Christine Martins-Ezeifeaku, 17, some of the most memorable moments from the summer were the hands-on activities that were a part of the two courses: Engineering and Human Health, and Mechatronics and Automation.

“In the biomedical engineering lab, we got to do many things we wouldn’t have had the opportunity to do in a typical high school experience,” Martins-Ezeifeaku says. “We got to diagnose sickle cell anemia and create E. coli bacteria.

“Getting to code the robots in the mechatronics lab and seeing them move after we finished was also an amazing experience.”

Martins-Ezeifeaku, who has always gravitated towards working with computers and sees herself studying computer engineering or computer science at university in the fall, says she knows how important it is to see people like herself in the technology field.

“In Grade 10, I took a computer science course that was taught by a teacher who is a Black woman and I was surprised at first because I wasn’t expecting her,” she says. “I loved that class; it really sparked my interest.

“Everyone who has helped me work towards the technology field has been really encouraging.”

As part of a month-long engineering design challenge, Blueprint participants were placed in groups and tasked with designing a solution to a client’s problem. This culminated with a presentation in front of judges, ��˾��ֱ�� Engineering Dean Chris Yip, graduate students and family members at the Myhal Centre for Engineering Innovation & Entrepreneurship.

“I really enjoyed the project because it allowed me to work on my presentation and teamwork skills,” says Ellis. “The experience also gave us experience that we could use in a first-year engineering design course.”

Babalola-Lucas, meanwhile, was part of a team tasked to create a product that repelled locusts on a farm in Jamaica. Together, they designed and built an ultrasonic 40 kHz speaker with a high-enough frequency to disrupt the locusts, but too high for humans to hear – so it didn’t affect human quality of life or wildlife.

“It was really innovative for us, and we ended up winning the competition, which was an extraordinary moment for me,” Babalola-Lucas says. “The entire experience was also an important lesson because I learned that no engineer works alone. You need to know how to work with anyone and everyone. You need to know how to collaborate. Blueprint taught me that from day one.

“I think any Black student who knows they love STEM should join Blueprint. You’re not only going to be exposed to the different disciplines within engineering, but you’re also going to experience a taste of campus life and learn how to study like a university student. You won’t regret it.” 