Save Lives and Make A Difference with a Fatigue & Distraction Tool for Motor Vehicle Drivers
Engineering, IT, Mathematics and Statistics
Please Note: This internship has an assigned Academic Mentor from The University of Melbourne. This internship is available to all PhD students at Australian Universities. Applicants will be required to re-locate to Melbourne if they are from interstate.
Due to funding requirements, students must have Australian or New Zealand Citizenship or Permanent Residency to apply. Any applicants not meeting this requirement will automatically be deemed ineligible for this project.
Each year, motor vehicle accidents contribute to over 1.2 million fatalities globally. In the majority of these crashes, human error, including driver drowsiness, is a contributing factor. For example, in the United States, crashes related to driver fatigue led to over 800 fatalities in 2014 and 37,000 injuries per year between 2005 and 2009.
The association between driver drowsiness and crash risk has been confirmed in various studies. Various studies have identified that drowsy drivers are four to six times more likely to be involved in a crash or near-crashes than attentive drivers and that cumulative sleep debt, increases the risk of crashing. Drowsy drivers demonstrate more fast corrective movements of the steering wheel, larger deviations from the ideal trajectory, and are less likely to adhere to the speed limit.
There is an ongoing call for research to determine the multitude of reasons contributing to driver fatigue. Various approaches have been implemented to reduce road trauma, such as educating drivers on managing fatigue e.g., taking sufficient rest breaks. However, this relies on self-assessment of a driver’s drowsiness levels and previous research has shown that drivers can indeed identify their current state of sleepiness and the likelihood of falling asleep, yet they may not take evasive action to counteract the levels of fatigue.
Urban Analytica is working to create cost-effective tools that can be widely deployed to mitigate insurance risk based on sound driver safety principles. Until the roll-out of fully autonomous vehicles is completed, driver drowsiness will continue to increase a driver’s crash risk and cause substantial road trauma each year. A drowsiness detection method that is widely available as a smartphone application has the potential to reduce drowsiness-related motor vehicle crashes and consequent road trauma well into the future.
RESEARCH TO BE CONDUCTED
Urban Analytica has secured a significant repository of telematics and corresponding facial expression data which requires analysis.
Currently, there are research methods, based on computer vision, that identify features such as eye-lid closure and head position to determine levels of drowsiness. Research has, identified various facial expressions important for drowsiness prediction by data mining human behaviour. Such research has identified expressions for drowsiness include outer brow raise, frowning, chin raise and nose wrinkle. Some of these expressions may be indicative of early stages of fatigue (e.g., outer brow raises in an attempt to keep eyes open). However, many existing methods for drowsiness detection focus solely on (a selection of) eye, mouth and head position.
New methods are applying neural network architectures to identify drowsiness extending research from 2 to 3-dimensions. The current research project will apply these 3-dimensional research applications and link them to the unique telematics data. The research will then extend the findings to the development of algorithms suitable to apply in insurance related environments using an enhanced app.
In summary, the research program will involve accessing unique data and applying the latest AI/Machine Learning approaches to train models to achieve practical ways to detect drowsiness/fatigue and distraction and work collaboratively with our team to deploy this in practical smartphone apps in market.
SKILLS WISH LIST
If you’re a PhD student and meet some or all the below we want to hear from you. We strongly encourage women, indigenous and disadvantaged candidates to apply:
- Extensive experience using AI/Machine Learning approaches
- Background in computer science and or mathematics and statistics
- Application of neural network architectures in 3-dimensions
- Excellent programming skills
- Experience using super-computers
Urban Analytica develops driver safety tools for the motor vehicle insurance industry and has android and apple developers on staff to assist the practical deployment of the research and real-time monitoring of driver drowsiness on mobile platforms. Specific outcomes include:
- A drowsiness detection system that produces driving points to apply for risk purposes against telematics driving behaviour data.
- Optimal deployment of units, whether an OEM (original equipment manufacturer) device, after-market accessory or app based to meet the challenges of data accuracy, analysis processing and real-time warning or trend results.
- The algorithm will be deployed in various driver safety apps used for novice and at-risk drivers to reduce crash incidence.
There is an opportunity to continue working with Urban Analytica beyond the intern period should the program progress successfully.
The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.
It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner. The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
CONNECT WITH APR.INTERN