Case Study: Data61
CSIRO's Data61 is working to give vehicles sight
Artificial Intelligence (AI) holds strong potential to unlock new efficiencies in transportation. CSIRO's Data61 is playing a central role in the application of AI technologies, including machine learning, analytics, robotics and autonomous systems to make transportation safer, more productive and more environmentally friendly.
Intelligent Transport Networks
Data61's researchers are using advanced machine learning and algorithms to model and improve transport networks to maximise operational performance. This work helps transport operators to understand and simulate the impact disruptions have on their networks, and better understand traffic demand and distribution. This results in quicker and smarter analysis of transport networks.
By using AI and machine learning, Data61 is supporting governments and industry to achieve new efficiencies and create impact. As Australia's largest data-driven innovation group, some recent examples of Data61's work include:
- working with Australia's leading road and transport government bodies to model and visualise transport networks
- developing tools to enable travellers to make more informed travel choices
- working with transport planners and decision makers to develop robust fact-based transportation models to guide new infrastructure decisions.
One of the largest technical challenges in autonomous driving is giving vehicles 'human' sight, a vital component in detecting and understanding everything from road signs and traffic conditions to avoiding pedestrians and vehicle collisions.
The partnership between Data61 and Chinese self-driving technology company ZongMu Technology aims to solve this problem by equipping vehicles with computer vision, an intuitive way to allow a machine to see and understand the environment the way humans do, and react to hazards. Drawing on advanced image analytics capabilities and bionic eye technology, Data61 is working with ZongMu Technology to help future cars 'see'.
The Smart Vision Systems Group within Data61, led by Dr Nick Barnes, develops algorithms to estimate the space between objects according to the vehicle's motion, and identify objects or potential hazards in a moving landscape.
Computer vision technology will also allow autonomous vehicles to determine the difference between what is pavement and what is a drivable road, more rapidly detect and avoid hazards, understand and obey road rules, and determine their exact location in relation to other moving vehicles.
While most competitors in this domain are exploring the use of laser sensors, which are prohibitively expensive, the computer vision algorithms Data61 is developing with ZongMu Technology are expected to cost one-tenth the amount, accelerating the potential for autonomous vehicle technology to reach the road in a much shorter time frame.