Constrained Batch Estimation for Train Positioning with Inertial Sensors

Similar to current efforts in the automotive industry, there is a substantial interest in developing fully autonomous trains. One of the key steps towards enabling autonomous operation is being able to accurately estimate train position and speed. In addition to this, better estimates will also increase safety and reduce distance between trains, allowing more frequent trains in peak hours. The current project deals with a method of estimating the velocity and position without using GPS measurements, which is the standard method.

Balancing organic nutrient solution for hydroponics using specific ion monitoring.

Cannafish is a Startup working with hydroponic farmers to include manure and compost in their fertilisation plan. Doing so, they reduce the use of chemical fertilizer in hydroponics while valorizing organic residual matter. However, to replace chemical with organic fertilizers requires good practice and precision to achieve competitive yield. Hence, using a specific ion monitoring strategy in organic hydroponics can allow the preparation of a nutrient solution that is rich in nutrients and optimal for hydroponic plant growth.

Gated and RGB Fusion for Robust Perception

Robust perception in all weather conditions is a critical requirement for autonomous vehicles. This project proposes fusing gated and conventional RGB camera images for robust scenes encoding, depth estimation and trajectory prediction. Conventional approaches using lidar and RGB camera fail to perform robustly in rain, fog and snow. By extending existing computer vision algorithms to Gated-RGB camera pair the fusion algorithms developed will utilize features that are robust in one sensor modality but not the other.

Effects of cell culture plastics on dendritic cells activated using ImmunyrTM

Cancer is the leading cause of death in Canada. A promising new way to treat cancer is through the administration of immune cells that target the cancer – an approach called cancer immunotherapy. The goal of this project is to engineer better culture vessels to produce dendritic cells. Dendritic cells are the "gatekeepers" of our immune system. They can have the capacity to activate other immune cells to attack cancers. The project involves two industrial partners: Kanyr Pharma, Inc. and Saint- Gobain, Inc.

Optimization of rice and other protein based extrusion encapsulation

The proposed project deals with the extrusion encapsulation of bioactive components using rice and corn protein based food matrix. It is well recognized that the performance properties of natural lake pigment encapsulated products are influenced by the structural properties of the matrix protein used for the extrusion encapsulation. The type, mixture and nature of proteins can have a significant effect on the extrusion encapsulated product as well as its functionality. Significant changes in the product properties can be expected due to the difference in the manufacturing steps.

Visualization of manufacturing complexity highlights on CAD file

Currently, the service provided by GRAD4 allows online storing and sharing of computer-aided design (CAD) models. However, there is no interface developed for visualization of CAD models in the service in a fast and comprehensible way to the users: both manufacturers and buyers. The main challenge of such implementations is in relatively high computational cost of such visualizations via tools used for web-development: while a regular PC handles such task efficiently, web-based tools have means insufficient for similar performance and, thus, mostly involve cloud computing.

Advancing Adjoint-Based Aerodynamic Design Optimization for Industrial Cases

The primary objective of this collaborative research project is to further advance an established industrial strength framework for the aerodynamic design optimization of Advanced Aerodynamic Systems. A major expense during a three-dimensional aerodynamic shape optimization (ASO) is the cost of obtaining design sensitivities or gradients at each design iteration. The computational cost grows rapidly as the number of cost functions and design variables are added.

Gardyn Home Optimization and Testing for Home-Based Plant Growth Production

Vertical farming is an agricultural approach that involves indoor, large-scale plant cultivation, at multiple levels, with controlled environmental conditions, a hydroponic nutrient solution and artificial light. This space-saving approach to growing fruit and vegetables has the potential to meet increasing fresh produce demand in dense urban areas. In recent years, several commercial entities have marketed smaller scale, vertical plant growth systems to consumers who want fresh and locally grown food.

Designing Soft+Stiff Haptic Interactions with Opensource Authoring Toolkits - Year two

Our sense of touch is vital to most daily activities we engage in, but is underused by most existing computing devices. Though haptics is an active research field, the main outcomes of three decades of research are limited to cost-effective vibrotactile feedback (as in mobile phones) or expensive force-feedback devices (mainly for surgical operation simulation). Software frameworks for haptics offer comprehensive haptics and physics simulation capabilities, however require expert engineering and software development skills.

Multi-agent reinforcement learning for distributed edge caching

There is an exponential increase in the network traffic worldwide due to the growth of social networks, multimedia sharing web services, streaming of video-on-demand (VoD) contents. However, the bandwidth isn’t growing at the same rate as the demand, resulting in a loss of Quality of Service (QoS) and Quality of Experience (QoE) for the users. Distributed edge caching provides an effective mechanism for mitigating the bandwidth requirements of the growing traffic demands by trading off bandwidth with storage.