Showing 20 articles starting at article 501
< Previous 20 articles Next 20 articles >
Categories: Engineering: Robotics Research, Space: Structures and Features
Published AI enabled soft robotic implant monitors scar tissue to self-adapt for personalized drug treatment
(via sciencedaily.com) Research teams have detailed a pioneering breakthrough in medical device technology that could lead to intelligent, long-lasting, tailored treatment for patients, thanks to soft robotics and artificial intelligence.
Published Challenge accepted: High-speed AI drone overtakes world-champion drone racers
(via sciencedaily.com) In a milestone for artificial intelligence (AI), the AI system 'Swift' has beaten the world champions in drone racing -- a result that seemed unattainable just a few years ago. The AI-piloted drone was trained in a simulated environment. Real-world applications include environmental monitoring or disaster response.
Published Surpassing the human eye: Machine learning image analysis rapidly determines chemical mixture composition
(via sciencedaily.com) Machine learning model provides quick method for determining the composition of solid chemical mixtures using only photographs of the sample.
Published People hold smart AI assistants responsible for outcomes
(via sciencedaily.com) Even when humans see AI-based assistants purely as tools, they ascribe partial responsibility for decisions to them, as a new study shows.
Published Tiny, shape-shifting robot can squish itself into tight spaces
(via sciencedaily.com) Imagine a robot that can wedge itself through the cracks in rubble to search for survivors trapped in the wreckage of a collapsed building. Engineers are working toward to that goal with CLARI, short for Compliant Legged Articulated Robotic Insect.
Published Telescopes help unravel pulsar puzzle
(via sciencedaily.com) With a remarkable observational campaign that involved 12 telescopes both on the ground and in space, including three European Southern Observatory (ESO) facilities, astronomers have uncovered the strange behavior of a pulsar, a super-fast-spinning dead star. This mysterious object is known to switch between two brightness modes almost constantly, something that until now has been an enigma. But astronomers have now found that sudden ejections of matter from the pulsar over very short periods are responsible for the peculiar switches.
Published Sensors harnessing light give hope in rehabilitation
(via sciencedaily.com) A research team overcomes limitations of conventional strain sensors using computer vision integrated optical sensors.
Published Care robots: Ethical perceptions and acceptance
(via sciencedaily.com) The global population of people older than 65 years of age is rapidly increasing the need for care. Although care robots are a promising solution to fill in for caregivers, their social implementation has been slow and unsatisfactory. A team of international researchers has now developed the first universal model that can be employed across cultural contexts to explain how ethical perceptions affect the willingness to use care robots.
Published AI helps robots manipulate objects with their whole bodies
(via sciencedaily.com) A new AI technique enables a robot to develop complex plans for manipulating an object using its entire hand, not just fingertips. This model can generate effective plans in about a minute using a standard laptop.
Published New framework for oceanographic research provides potential for broader access to deep sea scientific exploration
(via sciencedaily.com) Scientific exploration of the deep ocean has largely remained inaccessible to most people because of barriers to access due to infrastructure, training, and physical ability requirements for at-sea oceanographic research.
Published Mysterious Neptune dark spot detected from Earth for the first time
(via sciencedaily.com) Using ESO's Very Large Telescope (VLT), astronomers have observed a large dark spot in Neptune's atmosphere, with an unexpected smaller bright spot adjacent to it. This is the first time a dark spot on the planet has ever been observed with a telescope on Earth. These occasional features in the blue background of Neptune's atmosphere are a mystery to astronomers, and the new results provide further clues as to their nature and origin.
Published New dual-arm robot achieves bimanual tasks by learning from simulation
(via sciencedaily.com) An innovative bimanual robot displays tactile sensitivity close to human-level dexterity using AI to inform its actions.
Published Advancing trajectory tracking control of pneumatic artificial muscle-based systems
(via sciencedaily.com) Pneumatic artificial muscles (PAMs) are artificial devices that can simulate the mechanics of human muscles, and have shown great promise in industries requiring human-robot interaction systems. Despite their potential, controlling the trajectory performance of PAM-based systems is challenging owing to their nonlinear characteristics. Now, researchers have developed a novel adaptive sliding mode controller that uses fuzzy logic to estimate PAM-based system's parameters, promising enhanced tracking accuracy and adaptability compared to traditional control methods.
Published Rewriting the past and future of the universe
(via sciencedaily.com) Original source New research has improved the accuracy of the parameters governing the expansion of the Universe. More accurate parameters will help astronomers determine how the Universe grew to its current state, and how it will evolve in the future.
Published New type of star gives clues to mysterious origin of magnetars
(via sciencedaily.com) Original source Magnetars are the strongest magnets in the Universe. These super-dense dead stars with ultra-strong magnetic fields can be found all over our galaxy but astronomers don't know exactly how they form. Now, using multiple telescopes around the world, researchers have uncovered a living star that is likely to become a magnetar. This finding marks the discovery of a new type of astronomical object -- massive magnetic helium stars -- and sheds light on the origin of magnetars.
Published Brain recordings capture musicality of speech -- with help from Pink Floyd
(via sciencedaily.com) For those with neurological or developmental disorders compromising speech, brain machine interfaces could help them communicate. But today's interfaces are slow and, from electrodes placed on the scalp, can detect letters only. The speech generated is robotic and affectless. Neuroscientists have now shown that they can reconstruct the song a person is hearing from brain recordings alone, holding out the possibility of reconstructing not only words but the musicality of speech, which also conveys meaning.
Published Robotic exoskeletons and neurorehabilitation for acquired brain injury: Determining the potential for recovery of overground walking
(via sciencedaily.com) Developing a framework for future research requires a comprehensive approach based on diagnosis, stage of recovery, and domain.
Published Hundred-year storms? That's how long they last on Saturn
(via sciencedaily.com) Megastorms regularly appear on Saturn, marring the relatively bland surface before disappearing. But radio observations show that the storms have long-lasting effects deeper in the atmosphere, in particular in the distribution of ammonia. Using NRAO's Very Large Array, astronomers see such impacts from storms that happened hundreds of years ago. The findings will help explain the differences between storms on the gas giants Saturn and Jupiter.
Published Webb reveals colors of Earendel, most distant star ever detected
(via sciencedaily.com) NASA's James Webb Space Telescope has followed up on observations by the Hubble Space Telescope of the farthest star ever detected in the very distant universe, within the first billion years after the big bang. Webb's NIRCam (Near-Infrared Camera) instrument reveals the star to be a massive B-type star more than twice as hot as our Sun, and about a million times more luminous.
Published Self-supervised AI learns physics to reconstruct microscopic images from holograms
(via sciencedaily.com) Researchers have unveiled an artificial intelligence-based model for computational imaging and microscopy without training with experimental objects or real data. The team introduced a self-supervised AI model nicknamed GedankenNet that learns from physics laws and thought experiments. Informed only by the laws of physics that universally govern the propagation of electromagnetic waves in space, the researchers taught their AI model to reconstruct microscopic images using only random artificial holograms -- synthesized solely from 'imagination' without relying on any real-world experiments, actual sample resemblances or real data.