In 1944, Edna Anita Clarke entered the records of UBC history, becoming the first woman to graduate in Electrical Engineering. The life of our first female graduate was one of determination, novelty, and a lifetime of living right on the frontiers of engineering and adventure.
Born in 1921 near Penticton, British Columbia, Edna grew up in a time when opportunities for women in engineering were extremely limited. In 1939, at age 18, she was accepted into UBC’s Engineering program, relocating to Vancouver with her mother and sister.
At UBC, she was well-known. She served as secretary on the student council of her graduating class. She was known two-fold: for being one of the few women in engineering and commuting to school by motorcycle. Edna’s academic path was ever-changing due to her many varied interests. She first enrolled in Mechanical Engineering, then shifted to Aeronautical Engineering, and finally graduated with a degree in Electrical Engineering in 1944. Her ability to successfully move between engineering disciplines would be a hallmark of her illustrious career.
Graduation saw Edna’s inclusion in the University of Toronto team, which worked on Canada’s first functional computer, the UTEC Mark I. Anointed by the Globe and Mail as a wonder capable of everything from forecasting weather to playing chess, the UTEC Mark I was a marvel indeed and a credit to the ingenuity of its creators. Edna’s involvement with this groundbreaking project had already begun to make her a forerunner in this growing field.
Canada’s first functional computer, UTEC Mark I
During this time in Ontario, Edna met and married Arthur Yuile, a Battle of Britain veteran. Later, they relocated to Connecticut, where Edna was employed as a civil engineer for Northeast Utilities. She had a successful career for those times, not frequently made available for women, and thus was remarkable in both talent and resilience.
Besides her professional achievements, Edna lived a life full of adventure and travel: she skied across North America, often went power boating, and converted to the Baha’i faith, which led her to visit India several times.
Edna was a trailblazer for all the women who came after her in Electrical Engineering. She proved it was possible to succeed as a woman in the field, opening the doors for the 240 women currently in the Electrical and Computer Engineering program. She was quite proud of being the first woman and would be proud to see young women continuing to thrive in the field.
Thank you to her niece, Noni Clarke, for interviewing with our team.
Professor Karthik PattabirmanAssistant Professor Guanpeng LiZitao Chen
January 10th, 2025
ECE Professor Karthik Pattabiraman and research group members ECE PhD student Zitao Chen, who is graduating this year, and Assistant Professor Guanpeng Li from the University of Iowa and alumnus of ECE, focus on machine learning (ML) applications in high-stakes environments such as autonomous driving and their reliability to the effect of hardware transient faults. Computer systems are composed of software and hardware working together. However, hardware can be subject to faults such as cosmic rays, stress on the system, and age; all can cause a system to malfunction. Dr. Pattabiraman’s team focuses on understanding and improving the error resilience of ML systems to hardware faults.
When the hardware isn’t working properly, the software will be affected, and computation errors are the result. In using these erroneous values for computation, the software can emit a faulty output, such as causing a self-driving system to misidentify the traffic sign. Usually, when a fault arises in a software’s computation, someone can step in and recompute it again. However, the process of recomputing can be laborious and is particularly challenging for use in time-sensitive applications, like when a self-driving car is operating.
“Therefore, the focus of this study is, how can we effectively mitigate hardware faults to ensure the functional safety of ML systems without causing significant runtime delays?”
Dr. Pattabiraman
Process of Developing the Research
To prevent hardware faults from corrupting the program output, Dr. Pattabiraman’s team starts by analyzing why these faults can lead to output corruption. Dr. Pattabiraman explains how his team focused on their area of research, “In a previous study by our team [1], we found that a specific fraction of hardware faults are more prone to causing incorrect program output. We identified that these faults tend to result in abnormally large computation values during software computation, a characteristic influenced by the mathematical properties of ML models [1].
“Building on this insight, in this research, we introduced a technique called Ranger [2] to automatically reduce the damage caused by hardware faults, thereby preventing the program output from being corrupted. Ranger performs range restriction during software computation (hence the name), ensuring the values of the software computation fall within an accepted statistical range. If there is a value that falls outside this range, it brings this erroneous value back to a safe region.”
In the above example, Ranger is correcting an autonomous vehicle’s faulty computer vision. On the far left, the vehicle recognizes the road correctly. In the center, a fault has occurred, affecting the vehicle’s ability to infer which way to go- and directing it into traffic. In the right image, Ranger has corrected this error and the vehicle can proceed safely.
Future Impacts
“As ML applications continue to rely on high-performance hardware, we believe Ranger will have a broader impact in both academia and industry.”
Dr. Pattabiraman
Academic researchers have been building improved solutions on top of the Ranger system to combat hardware faults in emerging ML applications such as Vision Transformers. Meanwhile, the Ranger system has been adopted by Intel’s OpenVINO toolkit for practical use, and Dr. Pattabiraman and his group believe it can benefit practitioners in building dependable ML systems in wider application domains, such as large language models.
[1] Zitao Chen, Guanpeng Li, Karthik Pattabiraman, Nathan DeBardeleben “BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems” In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2019
[2] Zitao Chen, Guanpeng Li, Karthik Pattabiraman “A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction” The 51st Annual IEEE/IFIP International Conference on Dependable Systems and Networks, 2021
A University of British Columbia researcher is being recognized for his groundbreaking work to develop a mixed reality, immersive environment that makes it easier and more affordable for Canadians to receive ultrasound procedures without having to travel far distances to a medical centre.
The game-changing work has earned David Black (pictured) a Mitacs Innovation Award – Outstanding Innovation, presented by Mitacs, a Canadian innovation leader.
Supported by the Government of British Columbia, Mitacs connects businesses and researchers to drive competitiveness and productivity in sectors such as clean technology, life sciences, emergency management, advanced timber, and agritech. The award will be presented at a ceremony at the National Arts Centre in Ottawa on November 19.
Black – a University of British Columbia PhD student in the Department of Electrical and Computing Engineering under the supervision of Professor Tim Salcudean – is being recognized for his innovative work to build a compact tele-ultrasound system that allows a novice to perform an ultrasound on a patient while being guided by an expert sonographer or radiologist from a remote location.
The system consists of a mixed reality headset, point-of-care ultrasound probe – equipped with force and position sensors – and tablet or smartphone at the patient end, and a haptic device attached to a dummy ultrasound probe and connected to a computer display at the expert end.
As the remote expert maneuvers the virtual probe, guided by real-time video images transmitted over a high-speed connection, they are able to ‘feel’ the patient as if performing the procedure in person, thanks to the haptic interface.
At the point-of-care, the novice – or even the patient in some cases – aligns their probe with the movements of the virtual probe as they follow along using the mixed reality headset. Two-way verbal communication between the novice and expert is also supported.
“Other emerging teleoperation systems rely on robots to mirror the expert’s motion and, though the technology is impressive to look at, there’s a great deal of complexity and calibration that needs to happen to make it work. The robots are also very expensive,” Black explained.
“By replacing the robot with a human novice and relying on lower cost technology that can perform well over a 5G cellular network, our system is much more viable in the real-world.”
Black, who decided to focus on improving access to healthcare after personal experiences with remote medical emergencies, said Mitacs support is truly impactful.
“It allowed us to advance our technology rapidly to the point of testing and helped enable our partnership with industry leader Rogers Communications, who not only shares their communications infrastructure knowledge, but also helps forge valuable connections with other partners in the community and government,” he said.
The highly functional prototype system developed by Black, with the help of several Mitacs interns, was recently tested in the town of Skidegate, where ultrasounds were accurately performed at a distance of 750 kilometres away.
To date, testing has involved simplistic scans of the abdomen. Moving forward, Black is continuing to optimize the system to handle more complex scans, such as obstetrics, with the aim of launching a start-up company to commercialize the technology in the coming years.
The goal is to offer a lower cost solution that would make it possible to bring expert ultrasound knowledge to remote communities, people at home, or paramedics in the field. For example, Bella Bella, a community of 1,400 people in B.C., spends as much as $500,000 each year transporting patients to Vancouver by airplane in order to receive an ultrasound, said Black, a process that turns a one-hour appointment into a three-day excursion.
“That’s where we aim to come in and divert some of those appointments to a local community centre, medical centre or even to their home,” he said.
The Mitacs Innovation Award – Outstanding Innovation recognizes extraordinary talent from across Canada whose Mitacs-funded research has potential to achieve larger societal and economic impacts, driving innovation and broadening our understanding of the world around us. Mitacs programs are supported by funding from the Government of Canada and provincial and territorial governments across the country.
Black is one of eight Mitacs Innovation Award winners nationally, chosen from thousands of innovators who take part in Mitacs programs each year, and one of four winners in the Outstanding Innovation category. Additional 2024 categories, updated with a fresh look to better reflect Canada’s innovation landscape, include: Canadian Start-Up Innovator of the Year, Canadian Enterprise Innovator of the Year, Outstanding Research Leadership, and Inclusive Innovator of the Year.
In congratulating the winners, Mitacs’ CEO Dr. Stephen Lucas reflected on the organization’s long history and proven track record as a Canadian innovation leader. “Not only do these awards recognize achievements of exceptional innovators across B.C. and Canada, but they also highlight the infinite potential for impact when creative leaders work together,” Dr. Lucas said.
“As Mitacs celebrates 25 years as a leader in Canadian innovation, we reaffirm our belief that partnerships between research, enterprises, and talent – like the ones we honour with the Mitacs Innovation Awards – are key to a successful, prosperous Canada,” he said.
For more information about the Mitacs Innovation Awards and a full list of winners, visit www.mitacs.ca/newsroom.
About Mitacs As Canada’s innovation organization, Mitacs connects businesses and researchers with unrivaled access to talent, financial support, and the partnerships needed to turn ideas into impactful innovations. Through unique collaborations, Mitacs is driving productivity and positioning Canada as a global innovation leader. Mitacs is funded by the Government of Canada, the Government of Alberta, the Government of British Columbia, Research Manitoba, the Government of New Brunswick, the Government of Newfoundland and Labrador, the Government of Nova Scotia, the Government of Ontario, Innovation PEI, the Government of Quebec, the Government of Saskatchewan, and the Government of Yukon.
This joint position reflects the collaborative and interdisciplinary nature of mobile robotic platforms in both research and industry applications.
Robotics for marine vessels have the potential to enable more efficient and sustainable vessel operations. Developing Canadian expertise and applications opens the door to an important export market, as international interest grows in using autonomous systems, collaborative robotics and integrated sensing in the marine industry.
“The collaboration has huge potential to have a transformative impact on marine engineering innovation in Canada within a short time,” said Dr. Desjardins. “I am excited to develop new paradigms for rapidly accessing and navigating underwater environments. With interdisciplinary teams that include collaboration between UBC and Seaspan, we will move quickly from ideation to solutions that are successfully deployed in the ocean.”
Dr. Desjardins has an extensive background in sensing and robotics. His interdisciplinary research is focused on the development of novel sensing methods, machine learning, and autonomous robotic platforms for navigating complex environments, with marine, ocean science, and biomedical applications.
He will research and teach in emerging areas such as adaptive sensing and imaging, autonomous navigation, underwater inspection, monitoring of natural environments, and collaborative swarms.
This is the third chair to be funded by Seaspan, further enhancing a joint commitment to advance Canadian shipbuilding and support technological innovation in the marine sector.
“We are proud to continue and strengthen our partnership with Seaspan in driving forward innovative teaching and research within our local and Canadian marine communities,” said Dr. James Olson, Dean, Faculty of Applied Science. “Strategic partnerships like this play a critical role in building BC’s economy, fulfilling our commitment to protecting our environment, and attracting and training talented students to this important sector.”
UBC Applied Science is committed to addressing emerging areas of research to reduce the impacts of climate change, while fostering local and global collaboration. Dr. Desjardins will bring together a wide range of academic and industrial expertise in robotics, advanced sensing, data analytics and AI to develop new solutions for autonomously inspecting marine vessels, measuring environmental impact, and monitoring vessel performance.
Seaspan’s $1-million investment into this chair over the next five years—which will be equally matched by the UBC President’s Academic Excellence Initiative—is part of the company’s broader commitment to supporting innovation, sustainability, and skills development under Canada’s value proposition program within the National Shipbuilding Strategy.
“We are excited to build on our existing relationship with UBC and further invest in the future of Canadian marine technology,” said Dave Hargreaves, Senior Vice President, Strategy, Business Development and Communications, Seaspan Shipyards.
“Dr. Desjardins will lead important research that advances novel sensing and robotic systems that support high-functioning fleets and sustainable ship operations. At Seaspan, we believe this kind of forward-thinking collaboration is essential to ensuring Canada’s shipbuilding industry remains competitive on the global stage.”
Capstone design projects are a major component of the Department of Electrical and Computer Engineering curriculum. Students design a product or service of significance and solve an open-ended problem in their field of study.
ECE hosted a project showcase for the summer term on August 8th, 2024.
Wirelessly-Powered Tire Pressure Monitoring System
Ardavan Pourkeramati, Mihir Nimgade, Nick Zhao, Ethan Joyce Partner: UBC ECE Communications Lab and Sierra Wireless
Project and Solution
A common problem in the trucking industry is the need to remap tire pressure sensors after tire swaps. Without remapping, the system is unable to determine which pressure readings originate from which tire. This remapping requires manual technician labor and is an additional expense for trucking companies. Our team has developed a battery-free, wirelessly powered, Tire Pressure Monitoring System (TPMS) capable of performing this remapping automatically. Our system is able to selectively power the individual sensors in each tire, allowing it to always know which tire each pressure reading originates from, eliminating the need for manual remapping.
Challenges
During this project, we encountered several challenges that pushed us to expand our engineering skills. One of the key challenges was applying the theoretical Radio-frequency (RF) knowledge we learned in class to real-world scenarios. This required hands-on experience with testing and debugging using specialized RF equipment such as spectrum analyzers and VNAs. We also had to dive deep into researching and understanding RF energy harvesting, a field that is intricate and full of complexities. Identifying the most suitable harvesting solution took considerable time and experimentation to ensure it met our specific needs.
Designing the RF printed circuit boards (PCBs) presented its own set of difficulties. Our project required two PCBs–one for transmitting and one for receiving RF power. This process wasn’t just about creating a functional design; it demanded extensive research and testing to effectively integrate RF principles with embedded systems for optimal performance.
Future Impact
We hope that this project has successfully demonstrated an alternative method for performing automatic tire location mapping (i.e. “auto-localization”) for large vehicles such as tractor-trailers. Our solution favours a hardware-based approach by using RF energy harvesting (RFEH) technology to individually power on the embedded tire sensors. For our system, it was the application of RFEH that made the auto-localization problem tractable.
Computer Vision Processing for High-Resolution Angle Sensor in Computer-Assisted Surgery
Eddy Nangia, Michael Perkins, Charlotte Luo, Yifeng Liu, Zelin Li Partner: ISTAR Group, Vancouver General Hospital, and UBC Department of Mechanical Engineering
Project and Solution
The ISTAR group at the University of British Columbia is pioneering a new surgical system for mandibular reconstruction surgery. This system integrates mechanical devices with intraoperative surgical guidance to improve surgical outcomes. A critical aspect of this system is accurately tracking the positions of objects in the surgical field, such as mechanical devices and bone segments, using optical markers. However, the current optical markers are large and often obstructed, leading to suboptimal performance.
Our team’s objective was to replace these markers with a newly developed system called LentiMark. When used with a standard camera, LentiMarks can accurately measure position and orientation while being smaller and less obtrusive. This innovation aims to enhance ISTAR’s surgical guidance system, resulting in more effective operations.
The project focuses on developing and implementing a high-resolution angle sensor for computer-assisted surgery, using advanced computer vision techniques to improve surgical precision and reliability. The core innovation is the LentiMark, a novel optical marker combining ArUco markers with Variable Moiré Patterns (VMPs). While ArUco markers provide preliminary pose information, VMPs offer greater angle detection accuracy by varying visual effects with the viewing angle. Experimental results show that angle measurements maintain an error margin within 1 degree, significantly enhancing the accuracy and efficiency of surgical tools and thereby benefiting surgical navigation.
Challenges
Our team members come from diverse backgrounds, each with different strengths. Effective teamwork allowed us to support each other throughout the term, overcoming challenges and learning together. One significant challenge was the initial research, as some aspects of the project involved medical and optical knowledge not directly related to electrical or computer engineering. The design of Variable Moiré Patterns (VMPs) was particularly challenging due to the limited research available, so we had to learn from scratch and adapt the design to meet our project requirements.
Computer vision programming was another complex area that required extensive self-learning, testing, and iterations. Our team invested considerable effort in building from basic libraries to optimizing for more stable and accurate outcomes. This involved refining the Otsu binarization method for automatic image thresholding to better suit LentiMark detection and developing a custom angle calibration procedure tailored to our project’s specific needs.
Future impact
In computer-assisted surgical systems, precisely tracking objects like surgical instruments, anatomical structures, or mechanical devices is crucial. Instead of developing complex algorithms to identify and track each object individually, visual markers are attached directly. Once detected, the system infers the position and orientation of the associated object based on information from the marker. This method allows for precise control and accurate tracking while offering flexibility across different procedures and equipment with minimal adjustments.
Our project delves deeply into the design of the LentiMark visual marker. In the future, LentiMark could be used not only in surgical applications but also in robotics and beyond. LentiMarks presents a compelling alternative by combining enhanced accuracy with the compact size and durability needed for advanced applications. This positions LentiMarks as a superior option for a wide range of tasks requiring visual markers.
Assistant Professor Prashant Nair, from the University of British Columbia (UBC) Department of Electrical and Computer Engineering, is the recipient of the 2024 IEEE Technical Committee on Computer Architecture (TCCA) Young Computer Architect Award. Professor Nair received this award “In recognition of outstanding contributions to mitigate scaling-related DRAM faults and security vulnerabilities.”
The TCCA annually honours early-career researchers with the TCCA Young Architect Award. This award is considered the highest honour for early-career researchers in the field of computer architecture across the world, recognizing outstanding research contributions. The award was presented at the banquet ceremony during the International Symposium on Computer Architecture (ISCA) 2024. UBC is the first Canadian University with a faculty member to receive the TCCA Young Architect award.
Professor Nair’s primary roles include teaching and research, with some time dedicated to service. He primarily teaches computer engineering courses, specifically Digital Design and undergraduate and graduate Computer Architecture. His research focuses on secure, reliable, and scalable memory systems. In addition, Professor Nair works on alternative computing paradigms, such as quantum computing, from a computer engineering perspective.
What were some of your recent works that contributed to you being selected for the TCCA Young Computer Architect Award?
The efforts of my research group, Systems and Architectures STAR Lab, to mitigate the Rowhammer vulnerability in Dynamic Random Access Memories (DRAM) were a significant factor. Rowhammer is a security vulnerability that enables adversarial users to manipulate the data of other users who share the same memory system. Rowhammer enables adversarial users to repeatedly access their data in memory systems and indirectly tamper the data of other users (victims) in the shared memory system.
Additionally, my decade-long efforts in mitigating resilience issues with DRAM, which have had a notable industry impact, likely contributed to my selection for this award.
How do you feel about this award?
I am honoured to have been chosen for this award. To put things in perspective, UBC is the first Canadian University, and the first university outside of the United States to have its faculty receive this recognition. I am glad that the Department of Electrical and Computer Engineering has been incredibly supportive of my research vision and growth.
“The award reinforces my motivation to continue doing good work and to expand my research mandate. I am also delighted that my community recognizes and supports the importance of simple, creative, and industry-friendly solutions.”
What impact could this research have?
My research in the area of DRAM scaling could significantly impact the development and enablement of applications in edge devices, client devices, and servers. It can also influence the design of current and future computing systems. This is because, memory systems often act as bottlenecks in terms of latency, capacity, and bandwidth.
“My work aims to address these issues while also highlighting the importance of resilient, secure, and efficient solutions.”
What are your future research plans?
My research group is currently investigating memory capacity issues for large-scale machine learning models, such as large language models (LLMs) and recommender systems. The overheads of serving and training these models are driven not only by GPUs but also by the architecture of their memory systems.
Additionally, we are exploring industry-friendly and practical solutions to mitigate Rowhammer and investigating security vulnerabilities beyond Rowhammer. Memory systems at scale also present sustainability challenges, and we are currently exploring strategies to address these from both over-provisioning and resilience standpoints.
Many city infrastructures worldwide were long ago transformed to require single-occupancy vehicles if people wanted to get around. People made due and it became a way of life, though this wasn’t accessible for some. For years, planners have theorised that a new transformation is possible, one that benefits more people, and makes for more efficient streets, healthier air, and more affordable options.
This year, students from SCARP’s PLAN 341 course may have just come up with a real plan.
The course and its students
PLAN 341 is about Smart Cities, the pursuit of analysing information about people’s needs to provide those needs. Taught this past spring by SCARP PhD candidate Madison Lore (whose research identifies paths to sustainable behaviours through machine learning), this Planning course is part of UBC SCARP and UBC Geography’s Major in Urban Studies.
Urban Studies is interdisciplinary by its very nature, and these students come from many academic pursuits, including Computer Science, Computer Engineering, Electrical Engineering, Political Science, Sociology, and Urban Studies itself.
The students who produced Streetwise Solutions proudly includes:
Hazel Chongoti
Michael Claassen
Kieran Freitag
David McPherson
Noa Nibbelink
Ben Torry
A bold solution
As these students’ final project, they produced a plan to help sustainable transit modes thrive.
While the tool they eventually developed has potential applications worldwide, the project began as a spirited response to Vancouver’s traffic challenges. Vancouver has the second-worst traffic in Canada, at an average rate of 23 minutes for every 10 km and, on weekdays bus delays amounting 2,400 hours/day.
The students of PLAN 341 have a bold solution to this challenge: Smart Traffic Lights, which dynamically adjust green-light windows by traffic density and prioritise sustainable modes of travel, a contrast to the historical and default domination by single-use vehicles. These intersections would interface with a downloadable app in the pockets of drivers and passengers as well as on board buses (analysing how many people are present and what they’re driving) and then adjust green-light timelines to best serve the most people and the most sustainable transit. Their research carefully measured velocities, scalability, and impact over time, and the simulations the students produced is confirmed mathematically accurate.
Then, not content with merely presenting their findings, these students went above and beyond and actually created a full working simulator of their invention, as well as the hardware it would instantaneously interact with in an urban scenario.
With their simulation, the students confirmed their ability to vastly increase the number of people who can safely and easily traverse a busy intersection.
The prototype
Hazel’s, Michael’s, Kieran’s, David’s, Noa’s, and Ben’s Streetwise Solutions start-up incentivises public transport and carpooling (as well as emergency vehicles). Theoretically, participating cities deploying Streetwise would gradually expand public transportation infrastructure, making sustainable choices more accessible to broader populations and easing congestion.
To make Streetwise Solutions as feasible as possible, their plan takes into account data privacy, cybersecurity, possible system errors, and algorithm bias.
The tool is designed specially to be:
Robust Automatic failsafe: revert to normal intersection pattern
Scalable More people using the system = better traffic management
Fair No mandatory participation: each traffic direction has a minimum guarantee to consider those not using the system
Extendable Can extend to include more complex traffic phasing and intersection coordination, further improving management efficiency
Transparent Always accessible to the public
Following software and lab testing, a single intersection in Vancouver can be chosen to pilot the infrastructure, before the proof of concept is potentially rolled out on a larger scale (including the public release of the mobile app). More than a proof-of-concept simulation, Streetwise Solutions is a comprehensive plan involving government partnerships, financial models, and staggered roll-out. In short: this could happen.
View it in action
The students have launched a demo of their simulation that you can view from home. How to use it:
The dual interface shows how both a normal intersection and a StreetWise Solutions smart intersection would handle any scenario you throw at it.
Select any combination of vehicles to arrive at the intersection.
When ready, press PLAY to watch the scenario play out with or without the tool, and sum up how many people are serviced each time!
Implementing the scope of this plan would of course be a hardware and software feat, and of course involve strong governmental partnerships. Some may also think it requires a cultural shift in how we view transportation, but it may be a keener insight to say this tool reflects a cultural shift already underway. This model could be a catalyst for a revolution in accessibility and sustainability, one already craved by many.
Some words about the project’s significance from PLAN 341 student Kieran Freitag
“As with many others taking the smart cities class I was always interested in urbanist ideas of how we can make our cities better. I found it really engaging to work on a project where we could be at the helm of not only coming up with these ideas, but also how to be realistic in terms of implementation strategies and potential consequences.
Also, since every one of us in our group are in different majors, we were able to contribute something unique to our own skill sets. I’m in a second degree computer science program here at UBC and so I wanted to create a simulation of our idea to test its viability. This was quite fun as I was able to use the concepts I learned in my other computer science courses – such as how to appropriately model systems with objects, properties, and the relationships between them – in a more “real-life” environment with the traffic simulation.
Ultimately, I think this simulation was very helpful since it was much easier to find what works and what doesn’t with our smart traffic algorithm. You can theorize about potential effects and consequences of implementing something, but the most effective way to know what happens is to actually implement it (and the second best way is through a simulation of the process)!”
Praise for the students’ excellent work from instructor Madison Lore
Madison Lore, SCARP PhD candidate and PLAN 341 instructor in 2024WT2
“The goal of the final project is to think through a Smart City solution that uses technology to improve the quality of life for people. Students need to consider cost constraints, environmental and social impacts, and evaluate their system against a criteria that measures the unintended consequences of their solution on vulnerable groups.
The students in the class produced great projects that ranged from healthcare solutions, to sustainable and efficient transportation solutions, to urban gardens and waste management solutions. Each solution included innovative aspects from the course mixed with creativity and lived experience of the students.
The Streetwise Solutions group went above and beyond to build an online simulation of their solution to illustrate its effectiveness. The group have diverse majors and passions and you can see how it came together to produce an urban smart city solution. This is representative of the different backgrounds and skill sets we need to solve some of these major urban challenges.”
Pritam Dash, 4th year PhD Candidate in UBC’s Department of Electrical and Computer Engineering, supervised by Professor Karthik Pattabiraman, was named a 2024 Rising Star in Cyber-Physical Systems (CPS) research. On May 29th, 2024, Pritam was invited to participate in the CPS Rising Stars workshop at the University of Virginia (UVA), funded by the National Science Foundation (NSF) and ACM SIGBED.
Area of Research
My research focuses on making autonomous systems safe and secure. The advancements in robotics and AI have made autonomous systems, such as unmanned aerial vehicles (UAV), autonomous vehicles (AV), and robotic surgery, a reality. We are also seeing machines we use in our daily lives increasingly feature autonomous capabilities for convenience or improved safety such as emergency braking and lane-keeping assists in cars.
Autonomous systems like AVs and drones are essentially computer systems that rely on sensors to perceive the world and make decisions accordingly. The problem is sensors can fail, malfunction, or be subject to malicious intervention (security breach), which poses serious threats. Imagine you’re walking on a sidewalk, and a car suddenly veers off the road or a drone crash-lands on a busy street, causing chaos because its sensors have failed or are tampered with. Not good, right?
“My ultimate vision is to develop methods to ensure that autonomous systems can handle even the worst-case scenarios and uphold safety standards.”
My research focuses on identifying vulnerabilities and developing robust AI and control methods to mitigate the potential points of failure. To fully realize the socio-economic benefits and accelerate the adoption of autonomous technologies, it is crucial to address the safety and security concerns.
What was your process of developing your research and area of focus?
Early in my grad school, I was diving deep into AI and Control theory, learning about all the incredible research that made autonomous systems that were considered science fiction a reality. I had a background in computer security.
“I started asking – what happens when an AV or a drone encounters a system failure? Imagine a security breach taking over control of an AV; how do we respond to such a security breach? Are there methods to recover from such situations?”
Traditional computer security techniques are not enough to handle these threats. I realized that amidst the drive for advancements in autonomy and functional efficiency, some of the real-world challenges of deploying autonomous tech have largely been ignored, which motivated me to pursue research in this area and develop solutions to make autonomous systems safe and secure.
Congratulations on being named a 2024 CPS Rising Star! How do you feel about this recognition?
I’m honoured to be named one of the 2024 CPS Rising Stars. It is incredibly rewarding to see our work recognized by the research community. I’d also like to express my gratitude to my advisor, Prof. Karthik Pattabiraman, for his guidance and to my collaborators, Dr. Guanpeng Li (University of Iowa), Dr. Mehdi Karimibiuki, and Ethan Chan, whose contributions have been instrumental.
Can you describe the CPS Rising Star workshop that occurred on May 29th?
Photo Credits: Jennifer Burman, Amanda Maglione
The University of Virginia (UVA) has hosted the CPS Rising Stars workshop for the past three years, and this year, they expanded the program to non-US candidates. There was an application process, and the organizing committee, consisting of senior Professors and researchers, selected 45 PhD students and Postdocs from around the world.
The workshop at UVA was a great opportunity to connect with rising stars and established senior researchers working on cyber-physical systems. It was inspiring to meet in person the researchers whose work I’ve admired and who I’ve previously only interacted with via email. Engaging with them, learning about their journey, and hearing firsthand about their career paths was an enriching experience. The workshop also had great panel discussions on establishing a research group, fostering collaborations, and how to write good grant proposals. Overall, fantastic blend of learning, networking and fun.
What are your future research and work plans?
I am currently working on safe reinforcement learning (RL) for autonomous systems. RL is widely used for control and decision making in many autonomous systems. However, a critical gap remains; we do not know how these algorithms perform under uncertainty and anomalies. After completing my PhD, my goal is to work in a research lab pursuing research in AI safety and autonomous systems.
Yasaman Best graduated from the Department of Electrical and Computer Engineering at UBC with a biomedical specialization in 2011 and continued her studies to pursue a Master’s in Software Systems. Yasaman currently works as an IT Team Lead for the Federal Government of Canada (Department of National Defence).
Learn more about Yasaman’s experience at ECE, her current work for the Federal Government of Canada, and advice for ECE students!
Why did you choose ECE?
Choosing electrical engineering as a woman offers a unique opportunity to challenge stereotypes and contribute to a field that is constantly evolving. As a person with disabilities, pursuing a minor in the biomedical option not only expands one’s knowledge but also provides a pathway to understanding and developing assistive devices that can positively impact lives. This combination allows for both personal and professional growth, empowering individuals to make meaningful contributions to technology and society.
What was your student experience like while in ECE?
During my time at UBC, I had the privilege of encountering incredibly accommodating professors who supported my academic journey every step of the way. The UBC disability office played a crucial role in ensuring my success by providing accommodations such as hiring an assistant to write notes for me during class, which greatly facilitated my learning experience. Their dedication to inclusivity and accessibility truly made a difference. Overall, UBC proved to be a wonderful school, not only for its academic excellence but also for its commitment to fostering an inclusive environment where every student can thrive.
Where was your favourite place on campus?
Kaiser building! It’s so modern and accessible. I spent hours there studying with my classmates.
How did you get to where you are now?
Despite the life-altering car accident in 2002 that left me quadriplegic, I remained determined to pursue my academic goals. I successfully completed my undergraduate studies in electrical engineering with a biomedical option and went on to earn my Masters in computer systems. Throughout this journey, my friend, who has served as both a guide and mentor, suggested exploring career opportunities within the federal government due to their strong commitment to inclusion. Following this advice, I applied for a developer position and after passing rigorous technical assessments and interviews, was added to the pool of candidates. A month later, receiving the call from my manager offering me the job was a moment of immense pride and accomplishment. With the unwavering support of my husband, we made the decision to embark on a new chapter in Ottawa, where both of our careers could flourish.
What do you enjoy most about your career?
As the IT Team Lead for the federal government, I find immense satisfaction in knowing that my work directly benefits Canadians. Whether it’s improving digital services for citizens, ensuring the security of sensitive information, or implementing innovative technologies to enhance efficiency, every task I undertake has a tangible impact on the lives of individuals across the country. This sense of purpose and responsibility makes my role incredibly rewarding, as I play a vital part in contributing to the well-being and prosperity of fellow Canadians through the power of technology.
What are some challenges you have faced in your career?
Navigating accessibility challenges as a quadriplegic has been a significant aspect of my journey. However, I’ve been fortunate to have managers who consistently go above and beyond to accommodate my needs. Their unwavering support, coupled with the federal government’s steadfast commitment to inclusion, has provided me with a sense of assurance and empowerment. Knowing that there is a dedicated effort to ensure accessibility and support for individuals like myself within the organization has been invaluable. It underscores the importance of fostering an inclusive work environment where everyone, regardless of their abilities, can thrive and contribute meaningfully.
Do you have any advice or suggestions for ECE students
My advice to fellow students with disabilities is never to allow your condition to hinder your pursuit of your goals. Before embarking on your academic journey, it’s crucial to reach out to the disability office at your institution to explore the various accommodations available to you. Communication is key; make sure to regularly engage with your professors to discuss your specific needs and how they can best support you throughout your studies. Remember, your disability does not define you, and with determination and the right support system in place, success is entirely within reach. Additionally, UBC stands out as an excellent engineering school, offering a supportive environment conducive to academic achievement and personal growth.
