Showing 20 articles starting at article 81
< Previous 20 articles Next 20 articles >
Categories: Computer Science: Artificial Intelligence (AI), Geoscience: Landslides
Published New study finds AI-generated empathy has its limits
(via sciencedaily.com) Original source Conversational agents (CAs) such as Alexa and Siri are designed to answer questions, offer suggestions -- and even display empathy. However, new research finds they do poorly compared to humans when interpreting and exploring a user's experience.
Published Caterbot? Robatapillar? It crawls with ease through loops and bends
(via sciencedaily.com) Original source Engineers created a catapillar-shaped robot that splits into segments and reassembles, hauls cargo, and crawls through twisting courses.
Published Lake tsunamis pose significant threat under warming climate
(via sciencedaily.com) Original source The names might not be familiar -- Cowee Creek, Brabazon Range, Upper Pederson Lagoon -- but they mark the sites of recent lake tsunamis, a phenomenon that is increasingly common in Alaska, British Columbia and other regions with mountain glaciers. Triggered by landslides into small bodies of water, most of these tsunamis have occurred in remote locations so far, but geologists say it may just be a matter of time before a tsunami swamps a more populated place.
Published Stretchable e-skin could give robots human-level touch sensitivity
(via sciencedaily.com) Original source A stretchy electronic skin could equip robots and other devices with the same softness and touch sensitivity as human skin, opening up new possibilities to perform tasks that require a great deal of precision and control of force.
Published Robots invited to help make wind turbine blades
(via sciencedaily.com) Original source Researchers have successfully leveraged robotic assistance in the manufacture of wind turbine blades, allowing for the elimination of difficult working conditions for humans and the potential to improve the consistency of the product.
Published Random robots are more reliable
(via sciencedaily.com) Original source New algorithm encourages robots to move more randomly to collect more diverse data for learning. In tests, robots started with no knowledge and then learned and correctly performed tasks within a single attempt. New model could improve safety and practicality of self-driving cars, delivery drones and more.
Published Machine listening: Making speech recognition systems more inclusive
(via sciencedaily.com) Original source One group commonly misunderstood by voice technology are individuals who speak African American English, or AAE. Researchers designed an experiment to test how AAE speakers adapt their speech when imagining talking to a voice assistant, compared to talking to a friend, family member, or stranger. The study tested familiar human, unfamiliar human, and voice assistant-directed speech conditions by comparing speech rate and pitch variation. Analysis of the recordings showed that the speakers exhibited two consistent adjustments when they were talking to voice technology compared to talking to another person: a slower rate of speech with less pitch variation.
Published Trotting robots reveal emergence of animal gait transitions
(via sciencedaily.com) Original source A four-legged robot trained with machine learning has learned to avoid falls by spontaneously switching between walking, trotting, and pronking -- a milestone for roboticists as well as biologists interested in animal locomotion.
Published Researchers introduce new way to study, help prevent landslides
(via sciencedaily.com) Original source Landslides are one of the most destructive natural disasters on the planet, causing billions of dollars of damage and devastating loss of life every year. A global team of researchers has provided help for those who work to predict landslides and risk evaluations.
Published Built-in bionic computing
(via sciencedaily.com) Original source The use of pliable soft materials to collaborate with humans and work in disaster areashas drawn much recent attention. However, controlling soft dynamics for practical applications has remained a significant challenge. Researchers developed a method to control pneumatic artificial muscles, which are soft robotic actuators. Rich dynamics of these drive components can be exploited as a computational resource.
Published Computer vision researcher develops privacy software for surveillance videos
(via sciencedaily.com) Original source Computer vision can be a valuable tool for anyone tasked with analyzing hours of footage because it can speed up the process of identifying individuals. For example, law enforcement may use it to perform a search for individuals with a simple query, such as 'Locate anyone wearing a red scarf over the past 48 hours.'
Published Why can't robots outrun animals?
(via sciencedaily.com) Original source Robotics engineers have worked for decades and invested many millions of research dollars in attempts to create a robot that can walk or run as well as an animal. And yet, it remains the case that many animals are capable of feats that would be impossible for robots that exist today.
Published Computer game in school made students better at detecting fake news
(via sciencedaily.com) Original source A computer game helped upper secondary school students become better at distinguishing between reliable and misleading news.
Published How 3D printers can give robots a soft touch
(via sciencedaily.com) Original source Soft skin coverings and touch sensors have emerged as a promising feature for robots that are both safer and more intuitive for human interaction, but they are expensive and difficult to make. A recent study demonstrates that soft skin pads doubling as sensors made from thermoplastic urethane can be efficiently manufactured using 3D printers.
Published New computer vision tool wins prize for social impact
(via sciencedaily.com) Original source A team of computer scientists working on two different problems -- how to quickly detect damaged buildings in crisis zones and how to accurately estimate the size of bird flocks -- recently announced an AI framework that can do both. The framework, called DISCount, blends the speed and massive data-crunching power of artificial intelligence with the reliability of human analysis to quickly deliver reliable estimates that can quickly pinpoint and count specific features from very large collections of images.
Published Star Trek's Holodeck recreated using ChatGPT and video game assets
(via sciencedaily.com) Original source Star Trek's Holodeck is no longer just science fiction. Using AI, engineers have created a tool that can generate 3D environments, prompted by everyday language.
Published A faster, better way to prevent an AI chatbot from giving toxic responses
(via sciencedaily.com) Original source A new technique can more effectively perform a safety check on an AI chatbot. Researchers enabled their model to prompt a chatbot to generate toxic responses, which are used to prevent the chatbot from giving hateful or harmful answers when deployed.
Published Engineers design soft and flexible 'skeletons' for muscle-powered robots
(via sciencedaily.com) Original source Engineers designed modular, spring-like devices to maximize the work of live muscle fibers so they can be harnessed to power biohybrid robots.
Published New privacy-preserving robotic cameras obscure images beyond human recognition
(via sciencedaily.com) Original source In a bid to restore privacy, researchers have created a new approach to designing cameras that process and scramble visual information before it is digitized so that it becomes obscured to the point of anonymity.
Published Revolutionary biomimetic olfactory chips to enable advanced gas sensing and odor detection
(via sciencedaily.com) Original source A research team has addressed the long-standing challenge of creating artificial olfactory sensors with arrays of diverse high-performance gas sensors. Their newly developed biomimetic olfactory chips (BOC) are able to integrate nanotube sensor arrays on nanoporous substrates with up to 10,000 individually addressable gas sensors per chip, a configuration that is similar to how olfaction works for humans and other animals.