Off-Policy Reinforcement Learning (RL) for a Production Robotics Application

Kindred offers eCommerce retailers a solution to assist with rapid order fulfilment from their distribution centres. The solution (SORT) is a combination of a so-called put-wall and a humanoid robot. The robot picks up items from orders, scans them, and puts each item in a cubby of the put-wall according to the scan code. The […]

Read More
Optimizing heuristics for spin-glass problems for diverse solutions

Optimization problems, such as finding the shortest or fastest path to a destination are ubiquitous in industry. Hower, for some industrial applications it may be desirable to have a set of few diverse, yet nearly optimal solutions. The goal of this project is to create new optimization problem solvers that focus on both quality and […]

Read More
Thermal Performance Study of Switch Module Redesign

Thermal analysis is performed on a proposed design change on electronic assembly to ensure that it meets customer requirements (temperature ranges) and is a more cost-effective design. Such design change should be cost efficient. The important aspect, in addition to the design, is interacting with different engineers at different positions in the company. Working with […]

Read More
Electro-bioreactor (EBR) upgrading for high ammonium removal

The objective of this project is to build up an electro-biological system of high potential capacity for the removal of ammonium and phosphorus. Conventional biological treatment methods have limited capacity for removal of ammonia at higher concentrations. However, anammox bacteria have a high capacity to remove ammonium. The electro-biological treatment aims to enhance this capacity […]

Read More
Improved transductive regression using interconnected data

The explosion of data from personal phones, apps, and sensors have enabled powerful machine learning algorithms to help computers identify, categorize, and evaluate information without the help of humans. However, teaching computers how to identify, categorize, and evaluate information usually requires feeding the computers a lot of data pre-labelled by humans. The pre-labelling process is […]

Read More
Large-scale optimization algorithms for optical and fiber networks

Networks are moving towards being adaptive. This means that automation will be used to replace processes which are today highly manual. This project proposes a development of knowledge in the area of algorithms required to enable adaptive networks. The project will train two PhD students to understand optical networks and devise optimization algorithms in the […]

Read More
Study of DME Injection in Oil Sands Reservoirs

Thus far Steam-Assisted Gravity Drainage (SAGD) has been the sole commercially viable in-situ recovery method to extract Canadian oil sands that are too deep for mining. It involves high pressure steam injection and bitumen production using horizontal well pairs located near the base of oil sands formations. While it has enabled conversion of significant resources […]

Read More
Paper-Based Weather Resistant Membrane for Building Applications

Currently, petroleum-based water resistance membranes are used in the construction industry in order to create a barrier against water. These make recycling a challenge during building demolition, as well as create a significant carbon footprint of their own. The purpose of this project is to develop a paper-based water barrier to replace the petroleum-based alternatives. […]

Read More
Technology Advancement in existing AED

In Canada, approximately 40,000 out of hospital cardiac arrests (OHCAs) occur annually. Survival rates are under 15%, and the only treatment is immediate use of an Automated External Defibrillator (AED), coupled with CPR. This project will focus on finding solutions to identified problems associated with locating and using an AED. Some of these solutions will […]

Read More
Stability and Functionality of Oleosome-Containing Mixtures

The stability of commercial ingredient emulsions is hugely important to the end-user. To that end, Botaneco’s oleosome-containing emulsions are characterized by the absence of changes over time in physical parameters such as particle size, pH and colour. Botaneco’s Hydresia® and CapsolTM products, which contain safflower and almond oleosomes, exhibit proven physical stabilities of up to […]

Read More