CARRS-Q Research Projects

Visual driver surveillance: Monitoring monotony
In current research on driver monotony there is no general agreement on its causes, symptoms and road safety implications. Most of the research on monotony focuses on driver's psychological and physiological performance and does not place road safety aspects at the heart of the study. Fatigue, monotony and hypovigilance are often confused without a clear statement of the inter-relationships between them. This project studies the relationship between fatigue, monotony and hypovigilance. Intelligent Transport Systems (ITS) with a broad range of sensors and biomedical instrumentation will be used to monitor monotony.
Status: completed
Contact: Andry Rakotonirainy

Context awareness and ambient computing for vehicles
The ever increasing use of ICT (Information Communication Technology) in cars to improve mobility, comfort and safety has sparkled interests of Pervasive, Ubiquitous and Ambient Intelligent research community. The use of advanced in-vehicle technology could contribute to driver's distraction. Information overload or inappropriateness of the methods and time to convey information to the driver are among the potential drawbacks of the use of in-vehicle technology. This project identifies and implements concepts that preserve or enhance driver's ability to drive safely in an unobstrusive way .
Status: completed
Contact: Andry Rakotonirainy

Integrating vehicle dynamics, environmental perception and drivers' behaviours to assess vigilance
Most existing Advanced Driving Assistance Systems (ADAS) are monolithic and provide dedicated functionalities such as lane detection, speed limitation or eye blink detection. Furthermore, systems which assess drivers’ physiological states  are often built independently from systems that monitor car dynamics or perceive the environment. The integration of a wide range of functionalities and information related to the driver’s behaviour, environment and vehicle dynamics could potentially improve the reliability of ADAS. Our goal is to comprehensively integrate information about car dynamics, drivers’ behaviour and environmental perception in order to increase the accuracy of hypovigilance prediction. Our approach uses statistical means to merge existing functionalities and data in order to build a better assessment of the current driving situation and then predict future situations. This project  is in collaboration with INRETS.
Status: current
Contact: Andry Rakotonirainy

Ubiquitous data mining and situation-awareness for improving road safety
This project develops a computational model that analyses situational driver behaviour and proposes real-time countermeasures to minimise fatalities/casualties.  We develop and evaluate a novel intelligent transport system that assesses and acts upon drivers’ risks. This multidisciplinary project integrates recent models of data mining, context-awareness computing, physiological metrics, ubiquitous computing, driver distraction models, risk perception and road safety. This project yields a new understanding of driver behaviour and countermeasures in risk situations. This project is an ARC Linkage project with  Monash University and IAG
Status: current
Contact: Andry Rakotonirainy

Predicting vigilance impairment in drivers and operators functioning under monotonous contexts
In current research on driver monotony there is no general agreement on its causes, symptoms and road safety implications. This project addresses the fundamental problem of improving the effectiveness of vigilance impairment management in monotonous context. The aims of this project are to (i) define and characterise monotony and assess its impact on road and workplace safety; (ii) develop a statistical model of vigilance states in monotonous contexts; (iii) develop a context-aware on-line statistical model which can predict the decline of vigilance in monotonous contexts and (iv) develop novel statistical methods to achieve (ii) and (iii). The outcome of this research will be basic knowledge leading to the development of a statistical model to predict monotony and an in-vehicle prototype capable of monitoring vigilance. The resulting in-depth understanding of the causes and mechanisms of monotony and the development of advanced diagnostic tools will be a major contributor to reducing Australia’s death and injury rates due to fatigue-related errors occurring in the driver/operator environment and car/machine/truck contexts. There has been very little research examining the role of monotonous tasks or contexts as contributing to this error. Collaboration with Transport Canada and University of Montreal.
Status: submitted
Contact: Andry Rakotonirainy