Advanced driver state monitoring system
This PhD project aims to develop a system with a data-driven human driver behaviour model that can help detect the attention level of drivers and help them maintain a high level of attention while driving semi-autonomous vehicles.
Fully autonomous vehicles with level 5 ADAS (advanced driver-assistance systems) are the future of the transport vehicle industry. Semi-autonomous vehicles (level 1-4) face the potential risk caused by driver distraction.
A system is proposed to detect the driver distractions and assist the driver to restore the attention and alertness. The system has an artificial neural network-based multi-sensor analysis module (including image, heart rate, and body movement analysis algorithms) for driver attention detection and attention restoring module.
The proposed device will be used to increase driver attention with knowledge of the psychophysical response of humans to vibration. This system can also be applied to prevent the hazards of heart disease, epilepsy, and other diseases that might occur while driving.
Although excessive speed and intoxication are leading contributors to vehicle accidents, more than 50% of these accidents are due to a loss of attention caused by distractions such as using a mobile phone, excessive alcohol or drug consumption, and drowsiness.
Existing driver state monitoring methods are reactive and have limited accuracy/reliability when detecting distraction. Proactive monitoring and warning of driver distractions can significantly reduce the road toll and promote safety in urban and country roads. Even if the development of self-driving cars is already on the agenda, the self-driving algorithm is still not fully autonomous.
There is currently no feasible method for monitoring driver distraction and warning the driver that they are driving in a hazardous fashion, and no device to restore the driver’s alertness.
This project is focused on developing a novel AI-powered technology that can detect any distractions such as those associated with mobile phone use, interacting with passengers, drowsiness, or when driving in a dangerous manner such as when intoxicated
This project has three major tasks:
- Driving simulation data collection
- Developing a driver distraction detection algorithm/system
- Developing a prototype of the distraction alarm and alertness restoring device
Update: April 2022
We’ve interviewed Kun Zou about his research, and about his PhD journey. Read his profile at Kun Zou – iMOVE PhD student.
Please note …
This page will be a living record of this project. As it matures, hits milestones, etc., we’ll continue to add information, links, images, interviews and more. Watch this space!