Guide dogs are powerful allies, leading the visually impaired safely to their destinations, but they can't talk with their owners—until now. Using large language models, a team of researchers at Binghamton University, State University of New York has created a talking robot guide dog system that determines an ideal route and safely guides users to their destination, offering real-time feedback along the way.
SMU researchers have created an electromagnetic coil system that can control microrobots without requiring continuous visual tracking of their position—a significant advancement that could enable microrobots to operate inside the body, within industrial pipes and other places that aren't always visible with a camera.
In some settings and when completing some collaborative tasks, humans are required to coordinate their movements or actions with those of others. A clear example of this is musical performance, particularly instances in which two or more musicians play their instruments together.
Picture a futuristic swarm of robots deployed on a time-sensitive task, like cleaning up an oil spill or assembling a machine. At first, adding robots is advantageous, since many hands make light work. But a tipping point comes when too many crowd the space, getting in each other's way and slowing the whole task down.
To be safely and reliably deployed in outer space, underwater and in other extreme environments, robots need to be able to withstand harsh conditions without breaking. In addition, they should be able to promptly and rapidly adapt to dynamic changes in their surroundings.
While technology has made the world "smaller," it has also pulled individuals apart, thanks to mobile phones and other devices that command our attention. Cornell University researchers are using technology, in the form of a mirror-equipped robot, to help bring people together. Members of the Architectural Robotics Lab, led by Keith Evan Green, have built a four-foot-tall robot—dubbed MirrorBot—with dual mirrors that, when placed in front of a pair of strangers, let each participant see themself in one mirror and the other person in the other.
From birds flying in formation to students working on a group project, the functioning of a group requires not only coordination and communication but also trust—each member must be confident in the others. The same is true for networks of connected machines, which are rapidly gaining momentum in our modern world—from self-driving rideshare fleets, to smart power grids.
Researchers at Arizona State University are developing bio-inspired robotic "muscles" that will enable robots to operate in boiling water, survive abrasive surfaces, bypass impediments that keep their motorized counterparts benched, and still lift up to 100 times their own weight. The new heavyweight champions of robotics will be lighter, smaller, and disconnected from a power source.
A LEGO brick is not smart. It doesn't compute. It doesn't plug in. It just fits. A team of Georgia Tech researchers has applied that logic to robotics. Bolei Deng, an assistant professor in Georgia Tech's Daniel Guggenheim School of Aerospace Engineering, and Xinyi Yang, an aerospace engineering Ph.D. student, build swarms of tiny robotic particles that latch, release, and reorganize without a single electronic component. No sensors, no processors, and no code.
Over the past few decades, robotics researchers have developed a wide range of increasingly advanced robots that can autonomously complete various real-world tasks. To be successfully deployed in real-world settings, such as in public spaces, homes and office environments, these robots should be able to make sense of instructions provided by human users and adapt their actions accordingly.
We often imagine robots as machines with rigid arms, rotating joints, and targeted mechanical movements. The famous Optimus Prime and Bumblebee from the "Transformers" movies appear to fit these criteria. However, such robots would be unable to function in environments that are too confined and cramped.
A research team, including Huanyu "Larry" Cheng, James L. Henderson Jr. Memorial Associate Professor of Engineering Science and Mechanics at Penn State, is using pressure sensors—tiny devices, roughly the size of a paperclip, that can measure the force applied over an area—to design a highly sensitive electronic "skin" to use alongside robots and prosthetic limbs.
Robots are increasingly being used in manufacturing, agriculture and health care. But programming a team of robots to carry out individual tasks raises a question: How can robots learn from other robots if they are built differently? A multi-institutional team including Chongjie Zhang, an associate professor of computer science and engineering at WashU McKelvey Engineering, have developed a new method that enables robots to achieve intentions shown by their peers.
The fields of manufacturing, logistics, and even restaurants are increasingly moving toward automation, with robots being employed for a wide range of tasks. One of the most critical applications of robots is material handling, where grippers are used to move objects, such as automotive parts, logistics packages, food ingredients, and restaurant dishes. This reduces the burden on human workers while lowering the risk of accidents, thereby improving workplace safety.
No matter how sophisticated they are, robots can often be indecisive and struggle with multi-step chores in the real world. For example, if you tell a robot to tidy a messy room, it might understand the goal but not know where to grab each object. It could even end up inventing steps. To address these common mistakes, Microsoft and a group of academics have developed an AI benchmark system to improve the accuracy of robot planning. The details of their work are published in a paper on the arXiv preprint server.