Add BrightSurf on Google Email

3-D scans for the automotive industry

The automotive industry is shifting towards more frequent model changes and smaller volumes, requiring increased flexibility in production. Researchers are using 3D scans to generate virtual three-dimensional images of production facilities, simulating how to convert lines for new models.

Mimicking biological movements with soft robots

Researchers have developed a method to automatically design soft actuators for complex motions, enabling the creation of soft robots that can bend and twist like living tissues. This breakthrough streamlines the process of designing soft robots, allowing for the creation of robots with enhanced mobility and dexterity.

SourceHarvard John A. Paulson School of Engineering and Applied Sciences·JournalProceedings of the National Academy of Sciences·DateDec 19, 2016

Artificial muscle for soft robotics: Low voltage, high hopes

Researchers at Harvard John A. Paulson School of Engineering and Applied Sciences have developed a dielectric elastomer with broad motion range that requires relatively low voltage and no rigid components. This innovation addresses key challenges in soft actuation and opens doors for various applications in soft robotics.

Robotic motion planning in real-time

A new computer processor designed specifically for robotic motion planning can plan movements up to 10,000 times faster than existing approaches while using significantly less power. This breakthrough technology has the potential to revolutionize robotics and automation in manufacturing environments.

Fish-eyed lens cuts through the dark

University of Wisconsin-Madison engineers developed a biologically inspired artificial eye that can see in the dark using a lobster-inspired fish-eye design. The system improves image-taking through lenses rather than sensor components, resulting in fourfold sensitivity improvement.

SourceUniversity of Wisconsin-Madison·JournalProceedings of the National Academy of Sciences·DateApr 15, 2016

Gestures improve communication -- even with robots

Researchers found that robot avatars using multi-modal communication, combining speech and iconic hand gestures, are as easily understood as human actors. The study demonstrated that avatars can convey their message more effectively when using gestures with speech.

SourceFrontiers·JournalFrontiers in Psychology·DateApr 4, 2016

Drones learn to search forest trails for lost people

Researchers developed AI software to teach a quadrocopter to autonomously recognize and follow forest trails. The drone was able to find the correct direction in 85% of cases, outperforming humans who guessed correctly 82% of the time. This breakthrough enables drones to complement rescue teams and accelerate searches for missing people.

SourceUniversity of Zurich·JournalIEEE Robotics and Automation Letters·DateFeb 10, 2016

Snake bellies help scientists get a grip

Researchers studied three species of snakes to understand how their unique belly shapes aid in climbing. Brown tree snakes have sharp-edged keels that allow them to grip and propel themselves up trees efficiently, a trait also seen in some corn snakes but not boa constrictors.

SourceUniversity of Cincinnati·JournalJournal of Experimental Biology·DateDec 17, 2015

UW roboticists learn to teach robots from babies

Researchers at the University of Washington have created a new probabilistic model that allows robots to learn new skills by watching people and imitating them. The team combined child development research with machine learning approaches, inspired by infants' ability to infer adult intentions through self-exploration.

SourceUniversity of Washington·JournalPLOS ONE·DateDec 1, 2015

Strategy based on human reflexes may keep legged robots and prosthetic legs from tripping

A robotic prosthetic control strategy based on human reflexes has shown promise in simulation and laboratory testing, producing stable walking gaits over uneven terrain and improved balance recovery from trips. The technology will be further developed and tested using volunteers with above-the-knee amputations over the next three years.

SourceCarnegie Mellon University·JournalIEEE Transactions on Biomedical Engineering·DateNov 18, 2015

'Spring-mass' technology heralds the future of walking robots

Researchers at Oregon State University have developed a 'spring-mass' walking system that combines passive dynamics with computer control, allowing robots to blindly react to rough terrain and maintain balance. The technology has the potential to enhance legged robots and enable new roles in industries such as manufacturing and firefig...

SourceOregon State University·JournalIEEE Transactions on Robotics·DateOct 27, 2015

On soft ground? Tread lightly to stay fast...

Researchers developed a test-bed to study animal movement on soft ground, revealing key principles for robotic design. The findings, published in Bioinspiration & Biomechanics, suggest that robots can mimic the locomotion strategies of animals, such as sandrunners and forest dwellers, to improve their performance on challenging terrain.

SourceIOP Publishing·JournalBioinspiration & Biomimetics·DateOct 8, 2015

Self-driving golf carts

Researchers at MIT's SMART program conducted a six-day experiment using autonomous golf carts to ferry tourists around winding paths. The system, which used off-the-shelf sensors and dynamic algorithms, demonstrated a 98% user satisfaction rate and showed potential for elderly transportation applications.