BETTER “SIGHT” FOR AUTONOMOUS CARS

CSIRO-backed organisation Data61 has partnered with Shanghai-based ZongMu Technology to develop more effective “computer vision” systems for self-driving vehicles.

Dr Nick Barnes, leader of Data61’s Smart Vision Systems Group, said: “Computer vision is the technology that allows autonomous vehicles to determine the difference between what is pavement and what is a drivable road.

“Unlike laser sensors which rely on a series of points to identify hazards, computer vision offers richer information and a deeper understanding of road scenes through 3D image analysis, enabling safer automated driving.”

The camera-based vision systems and software developed by Data61, which is drawing on expertise gained from a bionic eye project,` should consequently allow ZongMu’s autonomous car projects to better perceive what’s going on around them. 

Getting an autonomous car to comprehend its surroundings is currently one of the largest technological hurdles in the field. Many brands, however, are tackling it by using laser-based scanning systems – which are expensive and unlikely to get cheaper in the near future. 

Dr Shaodi You, senior research scientist at Data61, said: “The computer vision algorithms we’re developing with ZongMu cost one-tenth the amount [of laser] and will allow commercial and truly autonomous cars to reach the road more quickly.”

The global autonomous vehicle market is rexpected to increase in value from $56 billion in 2025 to more than $102 billion in 2035, driven by the race to produce a “Level 5” vehicle – one which handles the task of driving from door-to-door by itself. 

Tang Rui, ZongMu’s chief executive, said: “Our driver assistance systems are already being used by China’s leading car makers but Data61’s expertise in computer vision will be imperative to our goal of bringing self-driving cars to market.”

Data61, which is owned by the Commonwealth Scientific and Industrial Research Organisation (CSIRO), currently has 14 sites around Australia.