Projets novateurs réalisés

Item Identification for Robotic Pick and Place Applications

This research project aims to develop a robot pick and place model that can be used in Kindred AI’s robotic arms to improve efficiency and reduce production costs. The intern will work closely with the partner organization’s experts in computer vision and MLOp to design and build new models, modify existing ones, and experiment with them on robotic arms. The project will benefit Kindred AI by enhancing its product offerings and increasing their competitiveness in the market. Additionally, this research will contribute to the advancement of robotics technology in Canada, which can potentially have significant implications for various industries.

Research and Implementation of Streaming Data Analytics Based on IoT Big Data Environment for Safer Fleets and Smart Cities

Road safety affects everyone, not just Geotab customers. With several years of driving and environmental data from over 2 million connected vehicles we have an opportunity to make our customers safer, as well as our communities and cities.
In an effort to reduce accidents, we need to understand both the driving behavioural patterns that are predictive of accidents, and the environmental factors involved. To achieve this, the data infrastructure should be capable of processing a series type of real-time video and telematics data, as well as time-series historical records generated from existing machine learning models to respond to real world incidents within a short period of latency.

Towards making graphics accessible to blind people

There has been a lot of effort in making printed media accessible to low vision or blind individuals. Braille has been extensively utilized to make text accessible to the blind. Software that automatically converts text to speech has also been employed for this. However, the existing solutions are not adequate for conveying graphical information to low vision or blind individuals. Common practice is based on manually converting images to tactile. A tactile is a representation of an image that is accessible by touch. Manual conversion by tactile designers is a tedious and expensive process. This project aims to develop Artificial Intelligence models for converting graphics to tactile format. More specifically, this project aims to develop methods that can generalize to new categories of images.

Optimization of Interventions to Reduce Combined Sewer Overflows

The dissertation title is “Optimization of Interventions to Reduce Combined Sewer Overflows (CSOs) (Quebec City as a Case Study)”. For cities where combined sewer systems are designed to transport both wastewater and stormwater flows in a single pipes network, during wet weather conditions, the volume of runoff may exceed the system capacity which results in the discharge of untreated or only partially treated water to the nearest outfall, this is known as combined sewer overflows (CSOs).The goal is to propose a practical solution to mitigate stormwater overflows and CSOs cities which are currently critical concerns for the existing infrastructures. To achieve this aim, integration of traditional and most recent techniques solutions will be assessed to better cope with CSOs’ quality and quantity adverse impacts on the environment at a minimum cost. The outcome will make a noticeable contribution in providing a framework for resiliency and infrastructure sustainability in big cities.

Multi-material 3D printing with FFF and SLA

We propose a solution to achieve a strong interfacial connection between FFF-printed materials and SLA-printed materials by utilizing an ester exchange reaction. Common FFF materials such as PETG and PLA contain an ester structure that can undergo ester exchange reactions with other alcohols in the presence of a strong base such as Triazabicyclodecene (TBD) and alter the original cross-linked structure. We can leverage this property by incorporating monomers containing hydroxyl groups into the resin of SLA and adding a certain concentration of alkali.

Our goal is to develop a multi-material printing technology that combines FFF and SLA methods, which we anticipate will be useful for the production of multi-material soft robots, as well as other applications, including the manufacturing of microfluidic chips using engineering materials. By achieving a strong interfacial bond between FFF-printed and SLA-printed materials, we aim to enable the production of multi-material parts with varying mechanical and physical properties. This technology has the potential to revolutionize the field of soft robotics, where the ability to combine materials with different elasticity and hardness can lead to the creation of complex and functional robotic systems.

Object Tracking for High-Speed Pick-and-Place Robot

The demand for eCommerce and online orders has risen rapidly in recent years, this drives the need for highly efficient and automated item sortation systems. Kindred AI is a technology company with the objective to bring artificial intelligence and robotic technologies into the workforce of eCommerce, parcel and order fulfillment. As a part of the effort to achieve accurate and robust robot grasping and placing tasks in such workforces, this research project aims to leverage modern machine learning and computer vision algorithms to enable safe, accurate, and fast item handling operations. In particular, the proposed research project will focus on designing and prototyping an intelligent and efficient item tracking system capable of predicting an item’s location in the near future in a robotic manipulation environment. Successes in this research will bring advancement in the partner organization’s robotic product and improve the safety and productivity in the human-robot workforce.

Machine learning-driven molecular classification of pediatric brain tumors

Brain tumors are the leading cause of cancer-related death in childhood and are generally categorized as low-grade or high-grade. More granularly however, there can be over 100 types of brain tumors which can vary widely in both prognosis and treatment. Machine learning has increasingly been applied to classify brain tumors and other cancer types but despite the success of these algorithms in classifying adult brain tumors, performance for pediatric tumors has been suboptimal in part due to the lack of sufficient training data. With larger sample sizes now available and extensive archives of in-house pediatric molecular and clinical data, the aim is to develop methods to better classify and diagnose these pediatric brain tumors, utilizing new computational techniques to analyze and integrate diverse biological datasets. By having a better understanding of what drives these tumors and more refined classification frameworks, improvements can be made to the process of matching patients with the most effective therapeutic options.

Molten metal membranes for H2 separation

Reducing green house gas emissions (GHG) from the energy and industrial sectors is crucial to meet this goal and the hydrogen economy will play a big role in accomplishing a greener and more sustainable future. Nearly 70 million tons of hydrogen are produced annually via conventional steam reforming of natural gas today. This results in over 700 million tons of carbon dioxide, which would be avoided if low carbon hydrogen were available and affordable. New thermochemical hydrogen production processes are being developed which produce significantly less GHG such as biomass gasification, methane pyrolysis, and thermal water splitting; however, all of these operate at very high temperatures and result hydrogen mixed with other gases, which need to be separated and purified. This project intends to develop molten metal membranes that can survive in these aggressive conditions and enable more efficient, low GHG, hydrogen production and purification.

Integrated crop management for industrial hemp

Industrial hemp – grown for stem fibers and seeds – is a sustainable high-yielding and environmentally friendly crop with typically, low cannabinol content. Industrial hemp is used to make over 25,000 green products and have the potential to sequester between 10 and 22 t/ha of carbon dioxide emissions. However, industrial hemp productivity and quality are constrained by genotypic, climatic and management factors. Therefore, developing an integrated and innovative method can help address these concerns. In the proposed research, seed germination, plant growth and yield responses to pyroligneous acid (PA) biostimulant will be investigated followed by studies to understand PA mechanism of action. Plant growth, fiber yield and carbon sequestration capability in response to combined compound fertilizer (nitrogen-phosphorus-potassium) and compost will be evaluated. Ultimately, agronomic recommendations will boost industrial hemp fiber production and quality and thereby, creating new marketing streams and increasing revenues in the Canadian industrial hemp value chain.

Broca – a large language model to draft highly personalized preliminary radiology reports for x-rays

The proposed research project aims to develop a machine learning model that can draft preliminary radiology reports for x-rays. The project will use a large language model based on transformer neural networks to analyze x-rays and generate reports that are personalized to the reporting radiologist and based on the patient’s x-ray images. The goal is to help radiologists be more efficient and reduce the risk of burnout. By automating the repetitive and tedious task of reporting x-rays, radiologists can focus on more complex and important tasks. The end result will be a tool that can improve the quality of healthcare and make it more accessible for all patients, supporting the mission of the partner organization, 16 Bit.

Review of the Mining Adjustments to the In-Situ Rock Mass Rating (IRMR) and their impact on cavability assessment

As the attention on mining of large orebodies by low-cost underground methods has increased, cave mining (block and panel caving) and other related methods like sub-level caving have become one of the preferred approaches. However, one of the main challenge of this method is realistic prediction of the undercut dimension at which caving will initiate and propagate. For this purpose, a good understanding of the rock mass and mining induced factors is crucial.
This research will focus on one of the most used rock mass classification systems and its adjustment factors, with the aim of reducing the subjectivity and producing a standardized guide for its application during caving assessments. The research will focus on data collection from existing projects and numerical modeling to calibrate and quantify the influence of the mining adjustments to different rock masses. This research will represent a contribution to cavability prediction for early stages of a project when the data is still limited, and mining method is under evaluation.

Enhancing Linamar’s big data analytics capability for continuous improvement in production

Digital transformation is a global trend for many industry sectors, and it is extremely important for manufacturing companies to avoid being excluded from the global digital supply chain. Linamar which operates 60 advanced manufacturing facilities worldwide, as a leader in manufacturing solutions, has been investing in this new trend with the ultimate goal of achieving data-informed continuous improvement in production since 2010. A large volume of machine-related big data has been collected across its global facilities using sensors and gauges. Linamar and the University of Guelph have previously formed a partnership to develop a pilot development environment that was able to extract data from Linamar’s distributed database and conduct some preliminary analysis such as machine utilization and production constraints. However, there are several challenges that need to be further addressed to fully maximize the value of such industry data, including inconsistency in data description, lack of data quality governing scheme, deficiency in machine performance metrics, and low efficiency in data analysis. As such, this proposed project will build on the pilot development environment and enrich its functionality by focusing on improving data quality and enhancing data analytic capacity.