Collaborating Authors

South Australia

Fly brains can detect threatening drones


Bio-inspired design has been a hallmark of technological advancement, and that's still true in the age of flying robots. The latest proof comes out of Australia, where researchers have mapped the visual systems of hovering insects as a means of detecting the acoustic signatures of drones up to 2.5 miles away. Anthony Finn, University of South Australia Professor of Autonomous Systems, says that insect vision systems have been mapped for some time now to improve camera-based detections. But applying the same method to acoustic data represents a major innovation. This lineup of aerial hardware fits a variety of enterprise photography and video use cases.

Researchers Reverse-Engineer Hoverflies' Visual Systems to Detect Drones


A team of researchers at the University of South Australia has reverse engineered the visual systems of hoverflies to detect drones from nearly four kilometers away. The autonomous systems experts at the university worked alongside others at Flinders University and defense company Midspar Systems.

Q-CTRL touts error-correction methods boost quantum algorithm success by 1000 times


Australian quantum startup Q-CTRL claims it has increased the likelihood of quantum computing algorithm success on hardware by over 1000 times, after it carried out its latest hardware benchmarking experiments demonstrating its autonomous error-correction techniques. According to the company, most quantum computers are currently error prone meaning that only the shortest and simplest algorithms can run, inhibiting on quantum computational capabilities being delivered to end users. However, through its research activities, the company said it has identified methods using AI and automation to reduce the number of errors. At the same time, the research was completed using conventional cloud access to commercial quantum computers and did not require any special hardware access. "Our benchmarking experiments demonstrate that there's hidden performance inside today's quantum computers that can become available with the right error-correcting software tools -- no changes to hardware are needed," Q-CTRL founder and CEO Professor Michael J. Biercuk.

Machine learning may boost yields: ABARES - Grain Central


SARDI scientist Rhiannon Schilling showcases a demonstration application created by using paddock data and machine learning models. PINPOINTING the cause of paddock-yield variability using large data sets and innovative machine-learning models is the focus of a project led by the University of Adelaide and funded by the Grains Research and Development Corporation (GRDC). South Australian Research and Development Institute (SARDI) agriculture scientist Rhiannon Schilling gave an update of the project at ABARES Outlook online this week. Ms Schilling said the research looked at the challenge of working out what is behind variability in crop growth and yield across paddocks. "Often there has been a focus on improving grain yields of our varieties; but when we drive around and have a look at our paddocks, we can see that we are not always achieving uniform crop growth and yield across our paddocks," Ms Schilling said.

Facial recognition taken to the next level in virtual reality


Faces can unlock smartphones, provide access to a secure building, and speed up passport control at airports, verifying identities for numerous purposes. An international team of researchers from Australia, New Zealand and India has taken facial recognition technology to the next level, using a person's expression to manipulate objects in a virtual reality setting without the use of a handheld controller or touchpad. In a world first study led by the University of Queensland, human computer interaction experts used neural processing techniques to capture a person's smile, frown and clenched jaw and used each expression to trigger specific actions in virtual reality environments. One of the researchers involved in the experiment, University of South Australia's Professor Mark Billinghurst, says the system has been designed to recognize different facial expressions via an EEG headset. "A smile was used to trigger the'move' command; a frown for the'stop' command and a clench for the'action' command, in place of a handheld controller performing these actions," says Prof Billinghurst.

Australian Space Agency believes existing robotics can be used for terrestrial activities


The Australian Space Agency (ASA) has highlighted that over the next decade Australia has an opportunity to prioritise six areas when it comes to robotics and automation on earth and in space. In publishing its Robotics and Automation on Earth and in Space Roadmap [PDF] on Monday, the ASA detailed that these six areas are remote operations, interoperability, analogue facilities and services, robotic platforms, in-situ resource utilisation services (ISRU), and terrestrial foundation services, such as materials handling and transport. Specifically, the roadmap describes how Australia could leverage its existing expertise in robotics technology and systems, provide solutions in the global marketplace to support the sustainable build-up of space assets and infrastructure, and enable international collaboration with industry. "Robots go places and do things that humans can't, and advances in automation allow us to carry out complex tasks with more sophistication. These technologies are playing an ever-increasing role in supporting human operations on the moon," ASA CTO Nick Larcombe said.

Algorithm Helps Robots Avoid Obstacles in Their Path


University of South Australia's Habib Habibullah says their algorithm could be applied in many environments, including industrial warehouses where robots are commonly used, for robotic fruit picking, packing and pelletizing, and also for restaurant robots An algorithm developed by researchers at the University of South Australia (UniSA) aims to help robots avoid humans and other obstacles in their path while taking the fastest, safest route to their destination. The researchers based their model on the best elements of existing algorithms and used it to create a TurtleBot able to avoid collisions by adjusting its speed and direction. They performed simulations in nine different scenarios and found their model outperformed the online collision avoidance algorithms Dynamic Window Approach and Artificial Potential Field. Said UniSA's Habib Habibullah, "Our proposed method sometimes took a longer path, but it was faster and safer, avoiding all collisions."

Using artificial intelligence for bushfire detection, management


Two years later, the country could be facing another dangerous fire season. However, a University of South Australia PhD candidate, Liang Zhao, has devised a way to use satellites orbiting above Australia to detect very small fires before they become problematic. Zhao is collecting smoke imagery from multiple satellites and then designing and training artificial intelligence (AI) models to recognise small outbreaks, to prevent a repeat of the 2020 summer. Zhao's algorithm will use satellites to improve fire detection, even from 30,000 kilometres away. "The problem with satellites is that those with high spatial resolution, focusing on small areas, tend to have low temporal resolution, taking much longer to capture images for the same location," Zhao said.

University of Adelaide built a robot spider to scan Australia's Naracoorte Caves


In the southeast of South Australia lie the Naracoorte Caves. The national park is an UNESCO World Heritage Site known for its stalactites, stalagmites and prehistoric fossils. Recently, a group of students from the University of Adelaide built a robot to complete a 3D scan of the site. The project, called CaveX, saw the group create 15 iterations of the model you see above before they settled on a final design. They went with a robot that walks on a set of six legs out of a fear that one with treads or wheels would damage the surface of the caves.

World's first electric flying race-cars take to the skies over Adelaide

Daily Mail - Science & tech

Airspeeder, a flying racing car that can go from 0-62 miles per hour in just 2.8 seconds akin to Formula One racing cars, has had a successful dual test run for the first time. The test flight of two unmanned Airspeeder vehicles, in skies over an undisclosed location near Adelaide, South Australia at the end of September, marks the first time two units have taken to the air together. This is an important milestone because Airspeeder has been designed to race other vehicles in the air in close proximity. Airspeeder is an electric'octocopter' craft being assembled in Adelaide by Alauda Aeronautics, as a mixture of helicopter, fighter jet and Formula One car. This model, unveiled in February this year and currently going through the testing phases, is the third Airspeeder prototype, called Mk3.