Grant: Discovery Launch Supplement

A vast majority of severe road accidents in Canada - over 90% - arise from human errors caused by distraction, fatigue, or impairment. Modern technologies, especially artificial intelligence (AI), are presenting new ways to keep our roads safer. Think of AI as the brain behind self-driving cars, helping them drive for long stretches without human intervention. However, there are still questions about whether we can trust these AI systems completely. In partial/conditional automation, the car might need to give control back to the driver due to technical challenges or legal mandates. This research proposal aims to design an innovative system that can help with the control transition between the driver and self-driving car, making sure it is safe based on the context - such as "how busy the road is" or "how alert the driver seems". The long-term goal of the proposed research program is to advance driving autonomy, improve accessibility, and elevate road safety. My research revolves around three themes: A) Driver monitoring: Designing a real-time system that can check if the driver has a normal physical/mental state and is attentive and ready to control the vehicle. A cornerstone of this endeavor is to eliminate potential biases in this monitoring technology, ensuring every driver is perceived through a lens of equity. B) Enhancing how cars perceive surroundings: By harnessing insights from human attention patterns, specifically their eye movements, we aim to amplify the reliability of the automated driving system by teaching the vehicle to focus on important objects the way humans concentrate. C) Intelligent control transition: Designing a control handover system that seamlessly navigates the optimal switch between the human driver and automated driving system. Depending on various driving situations, this system will decide the best time for either the car or the driver to control the vehicle, using a special kind of learning, called reinforcement learning (RL). With the help of advanced machine learning methodologies, this research program will address the outlined objectives and train highly qualified personnel. Ultimately, my goal is to improve road safety, using an optimal balance of driver state and smart car technology.