Interactive Reinforcement Learning Speedup with Confidence-based Transfer Learning

Reinforcement learning (RL) is a type of machine learning that focuses on allowing a physical or virtual agent to complete sequential decision-making tasks, such as video games. It has had many successes, but can be slow in practice, requiring large amounts of data. This project aims to speed up such learning problems by leveraging information from an existing agent. This existing agent need not be perfect – the algorithm developed will leverage information from the existing agent whenever possible and learn to outperform it where it is suboptimal.

Energy storage integration into electrified vehicle systems for shared and transit mobility applications

The deployment of electric and alternatively-fuelled vehicles in urban transportation constitutes a core component of current federal and provincial policies vis-a-vis Climate Action Strategies across Canada.

Efficient face recognition for wearable camera devices

Titan Sécurité Inc. has deployed wearable video camera devices for security and surveillance applications, and seeks to accurately detect and recognize objects appearing in captured videos. This project focuses on video-based face recognition (FR), where facial trajectories captured with video cameras are compare against one (or few) reference stills for each individual of interest. The performance of these FR systems is typically poor due to complex and changing video surveillance environments, e.g., variations of facial appearance due to pose, illumination, blur, etc.

Development of improved power quality detection methods suitable for modern applications

Discontinuities of service, variations in voltage magnitude, and distortions in AC voltage waveforms constitute the different aspects poor power quality. A poor quality of power supply can cause malfunction of sensitive equipment and interrupt industrial processes, resulting in significant economic losses. Utilities and consumers are taking actions to maintain the power quality set by the standards. Monitoring of power quality at all levels in the power system is necessary to ensure adherence to standards, but specialized power quality monitoring equipment are expensive.

Efficient design and implementation of concatenated error-correction coding for high-throughput fiber-optic links

The project targets design and implementation of error-correction codes for high-throughput fiber-optic communication links. We focus on the error-correction encoding at the transmitter side as well as decoding at the receiver side considering the simplicity of implementation and low power consumption at both transmitter and receiver.

Investigating Driving Condition Impact on Millimeter-wave (77GHz) Automotive Radar for Autonomous Vehicles

To enable the development of self-driving vehicles, an accurate characterization of automotive radar modules under various road or weather conditions is required to ensure reliability is maintained under all circumstances. With this fundamental building-block established, ACAMP will be able to support Canadian technology companies in the development of autonomous vehicles.

Development of a new conductive carbon ink for printed sensors for smart diapers

Urinary incontinence has been always a tedious and a distressing health problem, especially for elderly people in nursing home residents. To address this issue, an effective management system is highly required to enhance the quality care, prevent health issues, and reduce labor costs. This project is focusing to develop a flexible and wearable sensor based on carbon nanomaterials. The final product, in addition to the sensor, consists Wi-FI module and app.

Augmented Guidance Navigation and Control for Unmanned Aerial Vehicles

Sense and Avoid is a capability that is required by Unmanned Aerial Vehicles (UAV) to ensure that they do not enter into collision with other manned and unmanned aircraft. Obstacle avoidance of stationary objects is an important first step toward building Sense and Avoid systems. For stationary objects, after the object has been detected and its location has been determined, it is necessary to plan a path around the object, using a path planner, a key component of obstacle avoidance.

Electrochemical Fischer-Tropsch Synthesis of Renewable Liquid Fuels from CO2

Despite a rapid decline of electricity costs, there is still demand for energy-dense liquid fuels, such as in heavy freight and air transportation. Liquid fuels can be synthesized from a mixture of carbon monoxide and hydrogen called synthesis gas (syngas). However, this process requires high temperatures and pressures, and is itself responsible for significant greenhouse gas emissions. We propose the use of electrocatalysis to produce these liquid fuels.

Machine learning towards intelligent steel refining processes

In the steelmaking industry, process control models need to be based on a sound physical understanding of the process but should also account for many uncertainties due to the nature and complexity of the environment in which the process is carried out. As a result, it is crucial to extract useful process control information from the raw data stream acquired by the industrial sensors.