Researchers introduces the first toroidal, light-driven micro-robot that can move autonomously in viscous liquids, such as mucus. This innovation marks a major step forward in developing micro-robots capable of navigating complex environments, with promising applications in fields such as medicine and environmental monitoring.
Miniature robots on the millimeter scale often lack the strength to transport instruments for endoscopic microsurgery through the body. Scientists are now combining several millimeter-sized TrainBots into one unit and equipping them with improved 'feet'. For the first time, the team was able to perform an electric surgical procedure on a bile duct obstruction experimentally with a robotic convoy.
Researchers explored how infants act purposefully by attaching a colorful mobile to their foot and tracking movements with a Vicon 3D motion capture system. The study tested AI's ability to detect changes in infant movement patterns. Findings showed that AI techniques, especially the deep learning model 2D-CapsNet, effectively classified different stages of behavior. Notably, foot movements varied significantly. Looking at how AI classification accuracy changes for each baby gives researchers a new way to understand when and how they start to engage with the world.
Engineers developed a system that helps robots quickly map a scene and identify items they need to complete a set of tasks.
Conventional robotic grippers struggle to adapt to complex shapes and sizes, such as those found in crops. This has created a demand for more adaptable robotic grippers that can be utilized in agriculture. In a new study, researchers introduced an innovative soft robotic gripper named ROtation-based Squeezing grippEr (ROSE) and optimized its unique wrinkling-based grasping mechanism using simulations. ROSE's soft yet secure grasp can make it a vital tool for agriculture.
Large language models (LLMs) have developed rapidly in recent years and are becoming an integral part of our everyday lives through applications like ChatGPT. An article explains the opportunities and risks that arise from the use of LLMs for our ability to collectively deliberate, make decisions, and solve problems.
Scientists at MPI-IS have developed electrically driven robotic components, called HEXEL modules, which can snap together into high-speed reconfigurable robots. Magnets embedded along the outside of the modules allow them to electrically and mechanically connect to other modules, forming robots with diverse shapes and capabilities. HEXEL modules are a promising technology for use in resource-limited environments, such as on space or rescue missions, and can be used to construct versatile robots from redundant parts, altogether promoting a sustainable robot design.
Researchers have developed a new framework to make complex AI tasks more accessible and transparent to users. The framework specializes in providing solutions to deep reinforcement learning (DRL) requests. The framework pairs developers, companies and individuals that have specific but out-of-reach AI needs with service providers who have the resources, expertise and models they require. The service is crowdsourced, built on a blockchain and uses a smart contract -- a contract with a pre-defined set of conditions built into the code -- to match the users with the appropriate service provider.
A new review shows that this process of thinking is not exclusive to humans. Artificial intelligence, too, is capable of self-correction and arriving at new conclusions through 'learning by thinking.'
Researchers have created microscale robots less than 1 millimeter in size that are printed as a 2D hexagonal 'metasheet' but, with a jolt of electricity, morph into preprogrammed 3D shapes and crawl.
With maps of the connections between neurons and artificial intelligence methods, researchers can now do what they never thought possible: predict the activity of individual neurons without making a single measurement in a living brain.
Scientists have developed a new AI algorithm that can separate brain patterns related to a particular behavior. This work promises to improve brain-computer interfaces and aid with the discovery of new brain patterns.
An assist from a Google Artificial Intelligence tool has helped scientists discover how the proteins of a heat-loving microbe respond to the crushing conditions of the planet's deepest ocean trenches, offering new insights into how these building blocks of life might have evolved under early Earth conditions.
Integrating artificial intelligence into today's environmental control systems could reduce energy consumption for indoor agriculture by 25% -- potentially helping to feed the world as its population rises, engineers have found.
Researchers are designing real-time, intelligent tutors powered by AI. These systems mimic human surgical instructors in brain surgical training. Intelligent tutors help the learner acquire excellent skills by continuously assessing hand movements during simulated brain procedures and providing personalized verbal feedback.