Remember The Jetsons—the animated sitcom that reflected popular 1960s imaginings of technology as having all the answers? Life, it envisaged, would continue much the way it had, but with our every whim served by platoons of sentient robots.

So, where are all our subservient robots?

“Robots in factories are 60-year-old technology—highly effective, yet simple,” Peter Corke, the Centre’s Director, explains. “They have no idea what they are doing and they don’t work outside the factory.

“Say you take them to an apple orchard—the robot doesn’t know where it is; it doesn’t even know what an apple is or where to find one.”

Essentially, for awareness of environment, the robots need to ‘see’.

“The contextual understanding of the environment is impossible without vision,” says Ian Reid, our Deputy Director.

“(It’s) the missing link that will let robots operate in an unstructured environment.”

This is where the Australian Centre for Robotic Vision comes to the rescue. Using cameras to guide robots to carry out tasks requires a mind-bogglingly complex set of algorithms and advanced 3D geometry. When we take into account a dynamic environment, where random objects can appear on the scene and move at speed across it, the challenges rise exponentially.

The biggest problem is image recognition, where a robot can understand what it “sees” and find an answer to a question like “What is an apple?” But this can quickly spin off into something not-so-simple at all. What happens when the robot is confronted, not with an apple, but a pear?

Recent advances in the field of machine learning over the past four to five years “has a huge role to play in robotic vision,” says Ian.

“Computer vision has become much better at seeing the world through a camera and converting the images it sees into geometric information.”

The breakthrough, he explains, came in about 2012 with “deep neural networking”, algorithms that learn and improve on their own.

“In this way, robots will help each other learn about their worlds and how they can be interpreted,” Peter  says.

“Only one robot needs to get the knowledge, which it can then share,” he explains. “In some ways they will be like the Borg (the cybernetic aliens from science-fiction series, Star Trek). If the knowledge that one acquires is imperfect, then it can be shared with and improved by other robots.”

Maybe our Jetson’s dream will become a reality sooner than we think!