Robots that are perceptive and work with better reflexes alongside humans are the next big thing, according to a world-renounced roboticist at the Queensland University of Technology (QUT).
Professor Peter Corke, director of the Australian Centre for Robotic Vision (ACRV) at QUT Science and Engineering Faculty, said these advancements in robotics help improve the vision and perception of robots.
He said it enables robots to work more intelligently alongside humans, together with faster reflexes, response time and understanding the terrain.
The QUT, a global front-runner in robotics research and development, has unveiled a new robot called Baxter that does just that. This assistant works alongside researchers in a safer and highly-interactive environment.
The more intuitive "seeing and perceiving" features have been built into Baxter, enabling it to perceive the world or environment as humans do, with better reflexes.
"Once robots can see and understand the environment they operate in they can make decisions that allow them to work safely beside us," said Professor Corke.
Working with humans
He noted that current industrial robots are dangerous for humans to work around. This is largely because they're simply not equipped to recognise and avoid obstacles suddenly in their way.
"Baxter uses a range of sensors to detect movement around it, as well as spring-loaded joints which stop it continuing a pre-programmed movement if it meets an unexpected obstacle," said Professor Corke.
Robotic vision is a key technology that enables robotics to transform labour-intensive industries. The more intuitive thinking machines will become a ubiquitous feature of the modern world, according to the Australian Centre for Robotic Vision's chief operating officer, Dr Sue Keay.
"We consider that 'seeing' is far more than just processing images," she said. "It's a complex process tightly coupled to both memory and action, which gives robots the understanding they need to robustly perform tasks that involve objects and places while at the same time providing rapid and continuous feedback for control."
Robots that can see, learn and respond as humans do will increase productivity across key sectors and industries, Dr Keay said.
Professor Arun Sharma, the QUT's deputy vice-chancellor (Research and Commercialisation) said a new generation of innovating robotic vision experts are converting ground-breaking research into new products, services and enterprises.
In a rush
The QUT's research team has tried to "rush" Baxter several times. This was to assess its reflexes, as well as quicker responses and turnaround times. These responses replicate how humans interact in a multi-dimensional environment.
Baxter was also tested to use computer vision, while testing its reflexes to play an unbeatable game of Connect Four. This robot is now being trained to recognise and pick a colour-coded vegetable.
Sign up for MIS Asia eNewsletters.