Laser sensors used by most driverless cars today cannot read and follow street signs or differentiate between a footpath and the driveable road. Computer vision allows a machine to see and understand the environment the way humans do and react to hazards.
The Commonwealth Scientific and Industrial Research Organisation’s (CSIRO) Data61 entered into a partnership with a Chinese self-driving technology company, ZongMu Technology last month. The partnership aims to solve the problem of avoiding pedestrians and vehicle collisions by equipping vehicles with computer vision.
Data61 is Australia’s leading data innovation group, while Shanghai-based ZongMu is a vendor of Advanced Driving Assistance Systems (ADAS), technology used in vehicles to enhance driver and road safety.
Currently, most self-driving cars use laser sensors to understand the environment around them, by detecting objects and their distance from the vehicle. But lasers cannot read and follow street signs or differentiate between a footpath and the driveable road. Computer vision allows a machine to see and understand the environment the way humans do and react to hazards.
The Smart Vision Systems Group at Data61, led by Dr Nick Barnes, will work with ZongMu to develop algorithms to estimate the space between objects according to the vehicle’s motion and predict the potential hazards of moving objects.
“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,” Dr Barnes explained.
Dr Shaodi You, senior research scientist at Data61, said the technology would allow autonomous vehicles to quickly react to any hazards at a distance of 10 metres or further to avoid collisions.
In addition to being less effective at avoiding hazards, laser sensors used by the majority of companies are prohibitively expensive. The computer vision algorithms Data61 is developing with ZongMu cost one-tenth the amount and could allow commercial and truly autonomous cars to reach the road in a much shorter time frame.
The collaboration between Data61 and ZongMu will extend from research through to development with the final product available to the company’s customers in China and internationally, including original equipment manufacturers and partners in the mobility service industry.
The benefits of the technology could extend beyond driverless cars. The research is building on previous work at Data61 in developing a bionic eye, using computer vision that has given sight to the visually impaired. Using electrodes in a bionic eye, patients are able to get a sense of distance, with the electrical signals intensifying as the individual gets closer to an obstacle. A consortium seeking to commercialise the technology received A$23 million in corporate funding recently.
“Our self-driving technology is 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,” said ZongMu’s chief executive, Mr Tang Rui.
“We pride ourselves on providing our partners with high-level autonomous driving technology affordably and with the highest safety standards.”
Data61 CEO, Mr Adrian Turner said the partnership would speed up the hotly anticipated arrival of commercially viable self-driving cars and ultimately contribute towards seeding a new industry and ancillary services.
“From smart vision and distributed sensor systems to robotics and signal processing, Data61 has a world-leading capability in cyber-physical systems,” Mr Turner said.
“Through partnerships with forward-thinking companies like ZongMu, we aim to accelerate our data-driven future.”