research

New research from HowToRobot in collaboration with Robotics Australia Group reveals how Australia’s robotics industry is leveraging the country’s unique strengths in the global robotics race.

At the University of Washington, a team of researchers has developed a robotic arm capable of performing a set of 11 actions, enabling it to pick up a wide variety of foods with a fork. This technology represents a significant step in the field of assistive robotics, particularly in addressing the challenges of feeding individuals who cannot eat independently.

A new study by researchers at Queen Mary University of London, Imperial College London and The University of Melbourne has found that people can learn to use supernumerary robotic arms as effectively as working with a partner in just one hour of training. 

Inspired by the unique ability of pangolins to quickly curl up into a ball, researchers from the Physical Intelligence Department at the Max Planck Institute for Intelligent Systems in Stuttgart have developed a robot that mimics this functionality. The research, published in Nature Communications on 20 June 2023, demonstrates the creation of a flexible robot that combines soft and hard components, capable of turning into a sphere and emitting heat when needed.

Unleashing the potential of drone swarms through dynamic response and coordinated control is one of the latest frontiers in robotics research. Associate Professor Aaron Becker, along with his team of experts from Northeastern University, is spearheading efforts to develop algorithms inspired by the collective movements of birds and fish. Their goal is to enable drones to make local, intelligent decisions in real-time, enhancing the efficiency and adaptability of swarm operations.

Today Matthijs Smakman will defend his doctoral thesis titled “Robots in Education: The Morally Responsible Deployment of Robot Assistants”. Conducted under the supervision of Prof. Dr. Elly Konijn, his empirically grounded research represents a significant milestone in achieving a morally responsible integration of social robots as educational assistants in primary schools. Previous studies have already indicated that the utilization of social robots yields better outcomes compared to traditional educational technologies.

A machine learning model can predict the locations of minerals on Earth—and potentially other planets—by taking advantage of patterns in mineral associations. Science and industry seek mineral deposits to both better understand the history of our planet and to extract for use in technologies like rechargeable batteries.

Exposure to an augmented reality (AR) or virtual reality (VR) environment can cause people to experience cybersickness — a special type of motion sickness with symptoms ranging from dizziness to nausea — and existing research to mitigate the severity of the symptoms often relies upon a one-size-fits-all approach. However, Khaza Anuarul Hoque, an assistant professor in the Department of Electrical Engineering and Computer Science at the University of Missouri, and a team of researchers are working to develop a personalized approach to identifying cybersickness by focusing on the root causes, which can be different for every person.

Bar-Ilan University researchers have shown that brain-inspired shallow neural networks can achieve the same classification success rates as deep learning architectures consisting of many layers and filters, but with less computational complexity. The findings suggest that efficient learning of non-trivial classification tasks can be achieved using shallow feedforward networks, potentially requiring less computational complexity.

MIT researchers have developed an algorithm that enables drones to avoid collisions while working together in the same airspace. The system, known as Robust MADER, is an improved version of the Multiagent Trajectory-Planner, or MADER, which was presented by MIT researchers in 2020.