Over the past decade, MIT researchers have developed aerial microrobots with bumblebee-like speed, agility and durability for tasks like precision agriculture or search and rescue. But these featherweight microrobots couldn’t carry the electronics needed for navigation, forcing them to remain connected to a motion-capture system in the lab.Over the past decade, MIT researchers have developed aerial microrobots with bumblebee-like speed, agility and durability for tasks like precision agriculture or search and rescue. But these featherweight microrobots couldn’t carry the electronics needed for navigation, forcing them to remain connected to a motion-capture system in the lab.[#item_full_content]
The fastest robot to be made entirely of soft materials can reach speeds of up to 4.72 meters—a little more than 5 yards—per second, engineers at the University of California San Diego have shown. The six-legged robot can run on a wide range of terrain, from sand to mulch to concrete. It can also swim in water and walk underwater. The robot, designed, built and tested at the UC San Diego Jacobs School of Engineering, is 3D-printed in one go using only one material and doesn’t need electronics to function.The fastest robot to be made entirely of soft materials can reach speeds of up to 4.72 meters—a little more than 5 yards—per second, engineers at the University of California San Diego have shown. The six-legged robot can run on a wide range of terrain, from sand to mulch to concrete. It can also swim in water and walk underwater. The robot, designed, built and tested at the UC San Diego Jacobs School of Engineering, is 3D-printed in one go using only one material and doesn’t need electronics to function.[#item_full_content]
Navigating a bustling train station or airport is a major challenge for people with visual impairments. New research from Örebro University teaches robots to follow the “unwritten rules” of human movement and make their way through dense crowds. In the long term, the technology could serve as a digital complement to guide dogs.Navigating a bustling train station or airport is a major challenge for people with visual impairments. New research from Örebro University teaches robots to follow the “unwritten rules” of human movement and make their way through dense crowds. In the long term, the technology could serve as a digital complement to guide dogs.[#item_full_content]
A research team from the Department of Mechanical Engineering in the Faculty of Engineering at The University of Hong Kong (HKU) has developed a single-propeller autonomous drone powered by only one motor. It can not only fly at high speed in complex environments such as forests and underground parking lots, but also observe space in all directions—up, down, left and right—while in flight and maintain controlled flight in collision tests.A research team from the Department of Mechanical Engineering in the Faculty of Engineering at The University of Hong Kong (HKU) has developed a single-propeller autonomous drone powered by only one motor. It can not only fly at high speed in complex environments such as forests and underground parking lots, but also observe space in all directions—up, down, left and right—while in flight and maintain controlled flight in collision tests.[#item_full_content]
A joint research team from the Korea Advanced Institute of Science and Technology (KAIST) and Yonsei University has developed a flexible display that can communicate information to both humans and robots. Human workers can interpret information through visible color changes, while robots can detect near-infrared patterns invisible to the human eye. The technology could serve as an “electronic tag” attached to products or equipment, allowing humans and robots to monitor work status using the same display.A joint research team from the Korea Advanced Institute of Science and Technology (KAIST) and Yonsei University has developed a flexible display that can communicate information to both humans and robots. Human workers can interpret information through visible color changes, while robots can detect near-infrared patterns invisible to the human eye. The technology could serve as an “electronic tag” attached to products or equipment, allowing humans and robots to monitor work status using the same display.[#item_full_content]
A research team led by Professor Soon Moon Jeong of the Department of Advanced Technology at the Graduate School of Engineering Practice at DGIST, has developed a new sensing technology for soft robots that emits light whenever the robot moves, providing an intuitive visual representation of its movement trajectory without requiring separate batteries or complex electronic circuits. The study is published in the journal Small Structures.A research team led by Professor Soon Moon Jeong of the Department of Advanced Technology at the Graduate School of Engineering Practice at DGIST, has developed a new sensing technology for soft robots that emits light whenever the robot moves, providing an intuitive visual representation of its movement trajectory without requiring separate batteries or complex electronic circuits. The study is published in the journal Small Structures.[#item_full_content]
Humans can create loose maps of environments they are exploring in their minds, using their senses and navigation skills. Many robots, on the other hand, rely on set maps of known environments or new maps produced using data collected by their sensors.Humans can create loose maps of environments they are exploring in their minds, using their senses and navigation skills. Many robots, on the other hand, rely on set maps of known environments or new maps produced using data collected by their sensors.[#item_full_content]
Operating a drone manually requires pilots to watch a screen while coordinating controls. This divides attention between the aircraft and its surroundings. Researchers are exploring ways to make drone operation more intuitive and less dependent on continuous visual monitoring. A wearable interface developed at Jeonbuk National University combines hand gestures for sending commands with abdominal vibrations that indicate the drone’s position relative to the user.Operating a drone manually requires pilots to watch a screen while coordinating controls. This divides attention between the aircraft and its surroundings. Researchers are exploring ways to make drone operation more intuitive and less dependent on continuous visual monitoring. A wearable interface developed at Jeonbuk National University combines hand gestures for sending commands with abdominal vibrations that indicate the drone’s position relative to the user.[#item_full_content]
A new neural network component, developed at University of Michigan Engineering, challenges a common assumption in robot learning: that the same general-purpose neural networks used for image recognition are equally suited to controlling physical movement.A new neural network component, developed at University of Michigan Engineering, challenges a common assumption in robot learning: that the same general-purpose neural networks used for image recognition are equally suited to controlling physical movement.[#item_full_content]
If “to err is human,” you could say robots are superhuman. They’re more error-prone than we are, even when tasked with things like home and factory chores, which we might consider easy. One reason for these mistakes is that robots struggle to extract relevant details from the past and act on them in real time, even with vision-language models (VLMs), which interpret visual inputs such as videos and images along with natural language.If “to err is human,” you could say robots are superhuman. They’re more error-prone than we are, even when tasked with things like home and factory chores, which we might consider easy. One reason for these mistakes is that robots struggle to extract relevant details from the past and act on them in real time, even with vision-language models (VLMs), which interpret visual inputs such as videos and images along with natural language.[#item_full_content]