Evaluating the real-world effectiveness of ADAS

This project is a partnership between Insurance Australia Limited (IAG), the University of Sydney and iMOVE. It aims to assess the real-world effectiveness of Advanced Driver Assistance Systems (ADAS) and develop a proof-of-concept sensor platform to collect naturalistic driving data for systems such as Lane Departure Warning (LDW) and Lane Keep Assist (LKA), replacing subjective assessments with empirical metrics.

Participants

• IAG
• University of Sydney
  

Project background

Accidents involving vehicles continue to cause deaths and injuries, with significant negative impacts on society. The rapidly evolving technology behind ADAS offers a unique opportunity to reduce these impacts and enhance road safety through technologies such as autonomous emergency braking and lane departure warnings.

IAG is uniquely positioned to understand and influence community safety and resilience. The company’s commitment to making the world a safer place through collaborative risk reduction, avoidance, and resilience-building initiatives aligns with the goals of this project. IAG’s involvement ensures a practical perspective on insurance, risk management, and the societal impacts of ADAS technologies.

As ADAS technologies become more common in modern vehicles, understanding their real-world impact on driver safety is essential. While ADAS developed by OEMs aim to meet NCAP/ANCAP criteria for system fitment, the quality of system performance—and consequently, the potential safety benefits—vary markedly between manufacturers.

IAG currently has a program for evaluating ADAS effectiveness, but it relies on subjective measures and lacks the objective data needed to rigorously evaluate and compare the performance of systems installed in different vehicle makes and models. This project aims to address this by creating a proof-of-concept system that can be installed in vehicles to provide empirical evidence of the safety benefits of ADAS.

Project objectives

1. Produce a proof-of-concept computing platform that can collect naturalistic driving data capable of generating metrics that measure the performance of vehicle ADAS.
2. .Evaluate the performance of LDW and LKA in a vehicle under real-world conditions.
3. Evaluate driver engagement with ADAS.

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!