Software using artificial intelligence (AI) to detect dugongs in aerial photographs has been developed by QUT computer engineer Dr Frederic Maire to help scientists monitor diminishing global seagrass meadows.
Can robots see the future?
Developing robots that understand what they see is the key to an array of emerging applications in robotics and automation. However vision is a complex process requiring rapid and continuous feedback for control.
Robotics is a transformative technology with potential applications across a range of industries, including manufacturing, agriculture and construction. Automation can transform these industries, but only if it can perform complex interactive tasks in unstructured environments.
We're working toward developing robots that perceive their environment: that sense, understand and learn in order to improve performance over time. Robots with visual perception - that can see and respond as humans do - will have the potential to increase productivity in industries critical to Australia’s economy.
Australian Centre for Robotic Vision
The Australian Centre for Robotic Vision is navigating the challenge of applying robotics in the real world.
The centre hosts an interdisciplinary research team, with researchers from QUT working alongside specialists from other world-leading universities and research organisations including:
- The University of Adelaide, the Australian National University, and Monash University
- Data61 (previously known as NICTA)
- international universities and organisations including INRIA Rennes Bretagne, Georgia Institute of Technology, Imperial College London, the Swiss Federal Institute of Technology Zurich, and the University of Oxford.
Already, the centre has created:
- an underwater robot that culls crown of thorns starfish
- an agricultural robot that can see the difference between weeds and crops and apply the correct herbicide precisely on the weed
- a fruit picking robot that can pick the right fruit, the right way, day and night
- a free global university-level course in robotic vision, with over 30,000 students from 100 countries participating in the course so far.
An article just published in Science Robotics suggests people are more willing to respond to a social robot with ‘humanoid’ qualities rather than obviously mechanical ones when given the choice.