Robustness of Reinforcement Learning to Attacks and Adversarial environments

Reinforcement learning algorithms are successfully employed in diverse industries, for instance in autonomous driving, trading or gaming. However, their generalization especially in critical-decision making systems has raised concerns about their robustness to attacks. The 22nd recommendation issued by the White House (2016) to prepare for the future of AI states: ”Agencies (…) should ensure that […]

Read More
TRLUP–The Nexagon

The Nexagon project aims to develop an innovative neck collar designed to help prevent concussions in sports like hockey by reducing rapid head and neck movements during impact. Inspired by natural structures such as the honeycomb, the collar will be lightweight, comfortable, and effective in absorbing and redistributing forces that can cause brain injuries. Using […]

Read More
TRL ^ Multispectral Sensor Development

This project aims to develop a cost-effective imaging system for the early detection of crop diseases, with a particular focus on Fusarium Head Blight which is a disease responsible for an estimated $1 billion in annual losses to Canadian agriculture. Fusarium Head Blight produces deoxynivalenol (DON), a mycotoxin that renders grain unusable at concentrations as […]

Read More
TRLUP – LinkedWell Companion: Bridging Families and Clinicians Through Intelligent Care Communication

The LinkedWell Companion project is creating an intelligent and compassionate digital tool that helps families and healthcare providers communicate more clearly and stay connected beyond short medical appointments. In many clinics, appointments last only a few minutes, and patients often leave with unanswered questions, forgotten details, or confusion about what to do next. LinkedWell aims […]

Read More
TRLUP– Zester

Many Canadian companies and researchers struggle to find affordable, secure, and easy-to-use data labelling tools. Most existing platforms are foreign-owned, which can cause privacy issues and make it harder for small teams to work with sensitive information. It also prevents us from building local expertise and jobs in AI data management. Zester aims to solve […]

Read More
TRLUP – ML Insights and Metrics

More than 90% of pharmaceuticals fail to impact fail to pass regulatory approval due to toxicity or lack of effectiveness. 50% of those failures have the potential to impact patient lives and existing therapeutics can be repurposed to expand therapeutic options if they can be delivered in smaller dosages to where they are needed most. […]

Read More
TRLUP – Intelligent Automation of Phased Array Ultrasonic Testing for Quantitative Defect Characterization and Evaluation

This project develops an intelligent automation system to revolutionize how we inspect safety-critical components in industries like aerospace, energy, and manufacturing. It focuses on Phased Array Ultrasonic Testing (PAUT), a powerful but skill-dependent method for finding hidden flaws in materials. Currently, interpreting PAUT data demands highly trained technicians to analyze complex signal patterns and images. […]

Read More
TRLUP – ParkSmart (AI-Powered Parking Slot Detection and Analytics)

ParkSmart is an AI-powered parking analytics platform designed to make parking management more efficient, accessible, and sustainable for cities, campuses, and organizations. The system utilizes existing camera footage and applies computer vision and artificial intelligence to detect parked vehicles and identify stall occupancy in real time. Through this approach, ParkSmart generates live parking availability simulation […]

Read More
A Scalable Nitrous Oxide (N2O) Emissions Predictor Utilizing Fuzzy Logic and Impulse Response Measurements

Nitrous oxide (N2O) is a powerful greenhouse gas with a global warming potential 298 times that of CO2, significantly contributing to climate change through agricultural activities, particularly the application of fertilizers. Accurate and scalable prediction of N2O emissions is essential for sustainable agriculture and climate mitigation. Current methods, such as LSTM-DLM neural networks proposed in […]

Read More
TRLUP – AI Tool for Structural Health Monitoring using Thermal Imaging

This project will create an AI-based tool that helps engineers detect hidden damage inside concrete structures—like bridges or buildings—using special thermal images. Right now, most damage is only found when it’s already serious, which can be costly and dangerous. This new tool uses heat patterns to find early signs of damage, making inspections faster, safer, […]

Read More
One Okanagan Watershed

The One Okanagan Watershed project explores sustainable financing mechanisms to support regenerative practices and watershed security in the Okanagan River basin. Led by SFU ACT – Action on Climate Team and Salmon Nation CoLabs, the project has fostered the Okanagan Catalyst Network, engaging diverse stakeholders, including regenerative farmers, organic wineries, Indigenous groups, NGOs, universities, and […]

Read More