Articles tagged with Robots
Researchers combined robotics data from different sources using generative AI models to train better multipurpose robots. The approach, known as Policy Composition (PoCo), enables a robot to perform multiple tool-use tasks and adapt to new tasks in unfamiliar environments.
The hybrid-driven origami gripper, showcased in a recent study, demonstrates unprecedented versatility and precision in grasping objects. Its adjustable finger stiffness and variable finger lengths enable it to handle diverse materials without causing damage.
Researchers developed a novel methodology utilizing digital twins to establish the usefulness of built environment design guidelines for robots. Digital twins allow for real-time monitoring, hazard identification, and training a robot's algorithm before deployment.
A novel electromagnetic driving system is presented for 5-DOF magnetic manipulation in intraocular microsurgery. The system employs an optimized configuration, control framework based on ADRC and virtual boundary, and achieves precise and stable manipulation with reduced errors.
A US Army research collaboration with Boston University's KABlab used an AI machine learning robot to create a record-breaking energy-absorbing shape, breaking the known record of 71% efficiency. The shape has four points, like thin flower petals, and is taller and narrower than early designs.
A Washington State University study found that robot-phobia increases job insecurity and stress among hospitality workers, leading to greater intentions to leave their jobs. The impact is pronounced even for managers, highlighting the need for employers to communicate technology's limitations and human workers' roles.
A novel therapy leverages technology and robots to enhance joint attention and imitation skills in children with autism. The RoboCA3T program showed significant improvements in these areas, indicating a potential cost-effective treatment option.
Researchers developed a new AI algorithm called Maximum Diffusion Reinforcement Learning (MaxDiff RL) to improve robot reliability. The algorithm enables robots to learn complex skills more efficiently by encouraging exploration of their environments.
A recent study published in Science Robotics found that robots struggle to outperform biological organisms in foot races. The researchers analyzed data from dozens of studies and concluded that the failure of robots to outrun animals is not due to shortfalls in individual components, but rather inefficiencies in system design.
Researchers developed a robot that uses machine learning to automate microinjection in genetic research, enabling large-scale experiments. The technology has the potential to expand genetic research capabilities while reducing costs.
A new robotic suction cup mimics the adhesive properties of octopus suckers to grasp complex surfaces like rocks and shells. The device uses a multi-layer soft structure and artificial fluidic system to achieve long-lasting suction with minimal overflow.
The new metafluid can transition between Newtonian and non-Newtonian states, allowing for programmable viscosity and compressibility. The researchers demonstrated the fluid's capabilities in a hydraulic robotic gripper, picking up objects of varying weights without crushing them.
A new type of actuator uses springs and clutches to accomplish dynamic movements with a fraction of the energy used by traditional electric motors. The device has been tested in various motion tests and has shown significant power reduction, making it suitable for robots that need to perform complex tasks.
Researchers at ETH Zurich taught ANYmal, a quadrupedal robot, to perform parkour and navigate rubble using machine learning. The robot uses its camera and artificial neural network to determine obstacles and perform movements likely to succeed based on previous training.
Researchers developed RedirectedDoors+ to overcome VR door-opening challenges, providing users with realistic haptic feedback and guiding them around real walls. The system has been successfully tested in various environments, reducing physical space size by up to 50%.
Researchers from Carnegie Mellon University developed an adaptive robot interface called Head-Worn Assistive Teleoperation (HAT) to help people with paralysis control a mobile robot. The device uses head motion and speech recognition, allowing users to manipulate their environment according to their will.
A new AI model developed by MIT researchers breaks down complex warehouse navigation into smaller chunks, identifying optimal areas for decongesting robots. The technique improves efficiency by nearly four times, opening up potential applications in other complex planning tasks.
Researchers from Tokyo Institute of Technology developed an ultraviolet laser-processing technique for fabricating complex microstructures, enabling the creation of biohybrid actuators capable of complex, flexible movements. The method involves forming curved microgrooves on a substrate and aligning muscle cells in an anisotropic manne...
The USC team created a low-cost, customizable learning kit for students to build their own 'robot friend' using the Blossom robot. The three-part module provides hands-on experience and instruction on various AI aspects, including robotics, machine learning, and software engineering.
Researchers developed a way for robots to recognize objects even when partially obscured, using a visual perception system and topology. The THOR (Teaching Humans Object Recognition) method outperforms current state-of-the-art models in cluttered spaces, including warehouses and homes.
A groundbreaking study explores how humans perceive and interact with a pneumatically-driven edible robot. The research reveals that the dynamic movement of the robot intensifies perceptions, including emotion, animateness, and guilt, while altering texture experiences during consumption.
A study found that people prefer social robots speaking the same dialect as them, and those who are comfortable with a local accent trust robots that speak it more. The researchers suggest that this is because familiarity and similarity contribute to trustworthiness and competence perceptions.
Researchers in Japan have developed a two-legged biohybrid robot that uses muscle tissues to achieve fine movements and efficiency. The robot can walk, stop, and make precise turning motions, paving the way for future advancements in robotics.
Researchers used a robot dinosaur named Robopteryx to test the hypothesis that small dinosaurs flapped their primitive wings to scare prey. The results showed significant positive associations between the use of proto-wings in display behavior and the likelihood of grasshoppers fleeing.
A research group from Tohoku University Graduate School of Engineering has replicated human-like variable speed walking using a musculoskeletal model steered by a reflex control method reflective of the human nervous system. The breakthrough in biomechanics and robotics sets a new benchmark in understanding human movement.
The hip-assist robot EX1 improves walking ability, dynamic balance, and one-leg standing endurance in older adults. The four-week exercise program using EX1 significantly reduces the risk of falls and enhances overall health.
Researchers at the University of Oxford have created a standardized safety test to assess how dangerous robotic lawnmowers are to hedgehogs. The test uses specially designed hedgehog crash test dummies and has found that many models pose a threat to these animals, especially at night when they are most active.
Researchers aim to create robots that can change tasks autonomously and explore settings to optimize performance. The project will focus on battery recycling and energy efficiency, with the goal of reducing industrial waste.
Researchers have developed twisted ringbots that can roll forward, spin like a record, and follow an orbital path around a central point. These devices can navigate and map unknown environments without human or computer control.
Researchers have discovered that whirligig beetles use a lift-based thrust mechanism to achieve record-breaking speeds, challenging previous explanations of their propulsion system. This finding offers valuable insights for bio-inspired robotic ship design and uncrewed boat development.
A study redevelops a framework for teaching artificial intelligence and robotics to preschool children, providing five big ideas that can be grasped by young kids. The framework aims to prepare children to understand and use AI tools effectively, promoting healthy and responsible learning in the rapidly developing digital society.
Researchers developed a robot prototype inspired by a snail's ability to collect food particles at the water-air interface. The device uses an undulating motion to suck in microplastics from the surface of oceans and seas.
Researchers created multicellular bots from human tracheal cells that move across surfaces and promote healing of damaged neurons in a lab dish. The discovery could lead to new therapeutic tools for regeneration, healing, and disease treatment using patient-derived biobots.
A team from the University of Bristol has successfully inspected a steel pipe using a network of robots equipped with guided acoustic wave sensors. The approach achieved 100% detection coverage for defects on a three-meter long pipe, minimizing communication between robots and reducing data transfer costs.
A new technology enables the printing of complex robots with soft, elastic, and rigid materials in one go. This allows for the creation of delicate structures and parts with cavities as desired.
A novel robotic system developed by USC researchers can help clinicians accurately assess a patient's rehabilitation progress. The method generates an 'arm nonuse' metric using machine learning and a socially assistive robot to track how much a patient is using their weaker arm spontaneously.
A team of researchers at Penn State found that a moderate talking speed for digital assistants increases user likelihood to use them. Conversation-like interactions also mitigate negative effects and increase user trust.
A Cornell University-led team used an underwater robot to explore the ocean conditions beneath an Antarctic ice shelf, discovering a new circulation pattern involving a jet funneling water sideways through crevasses. The findings improve modeling of ice shelf melting and freezing rates, which can impact global sea-level rise.
A research group led by Professor Kaspar Althoefer has been awarded a €10m ERC Synergy grant to develop a revolutionary new system for screening and treating colorectal cancer. The system, which combines medical robotics, artificial intelligence, and minimally invasive surgery, aims to improve patient outcomes and quality of life.
Researchers created a hydrogel mat with magnetic microparticles that mimic the forces of exercise. The team found that regularly exercising muscle cells resulted in longer, aligned fibers, and improved contraction capabilities.
Researchers found that humans who worked with robots were more likely to catch fewer defects later in the task, indicating a 'looking but not seeing' effect. This could lead to safety implications and negative impacts on work outcomes if not addressed in real-world environments.
Lerrel Pinto aims to create robots that can perform a variety of tasks using algorithms and data collection methods. He seeks to address the trade-off between dexterity and generality in robotics.
Researchers studied how insects evolved two distinct flight strategies using robots and biophysicists. They found that asynchronous flight evolved together in a common ancestor, but some groups reverted back to synchronous flight.
Researchers discovered that insects evolved ultrafast flight from a single common ancestor, with asynchronous beating and synchronous activation modes. They used physics models and robotics to test how these transitions could occur, finding that evolution can turn on and off this particular mode of flight.
Researchers at Tohoku University have developed a model predicting torque generated from electrical stimulation in stick insect leg muscles, allowing for precise control of insect movement. The study's findings have the potential to refine motor control of tuned biohybrid robots and enable adaptable devices with various applications.
Researchers at Colorado State University have developed three morphing robotic schemes that can change shape on demand, mimicking nature's adaptability. The robots can sense their surroundings, adjust their shape to grasp or navigate obstacles, and potentially aid humans in disaster areas.
Researchers at Queen Mary University of London and their colleagues have found that supernumerary robotic arms can be used as effectively as a partner, enabling tasks like opening doors while carrying packages. The study suggests these arms could aid people with various tasks, such as surgery or industrial work.
Researchers at Cornell University have created an insect-scale quadrupedal robot powered by combustion that can outrace, outlift, and outflex its electric-driven counterparts. The robot's actuators produce 9.5 newtons of force and operate at frequencies greater than 100 hertz.
A research team at Toyohashi University of Technology has developed a technique to create training data for robots that estimate the state of users using machine learning. The method uses a human body link model without requiring movement analysis, enabling care robots to assist elderly with reduced burden and improved safety.
Researchers at the University of Washington have developed small robotic devices that can change their shape in mid-air using a Miura-ori origami fold, enabling battery-free control over descent. The devices can transition from tumbling to falling states, allowing for precise landings in turbulent wind conditions.
Researchers have developed a tiny, squishable robot called CLARI that can change its shape to pass through narrow gaps. The robot's modular design allows it to be customized and expanded with additional legs, enabling potential applications in search and rescue operations after major disasters.
Researchers created a robot-assisted dressing system using artificial intelligence to accommodate various human body shapes, arm poses, and clothing selections. The system was evaluated in a human study with 510 trials across 17 participants, achieving an average success rate of 86% in pulling the sleeve of each garment onto their arm.
Researchers at MIT developed a method to simplify the process of whole-body manipulation for robots, enabling them to reason efficiently about moving objects. The technique uses AI and smoothing to reduce the number of decisions required, making it possible for robots to adapt quickly in complex environments.
Researchers at the University of Texas at Austin created a noninvasive EEG sensor that can measure brain activity during immersive VR interactions. The device has potential applications in helping people with anxiety, measuring mental stress, and giving humans insight into robot behavior.
Researchers found a U-shaped effect on profit margins due to the relationship between reducing costs, developing new processes, and innovating products. Initially, firms focus on cost reduction, but as robot adoption increases, they shift to product innovation, leading to higher profits.
Researchers have created a one-of-a-kind shape-shifting display that can generate scrolling text and fast enough to shake a chemistry beaker. The device uses soft robotic muscles that sense outside pressure, pop up to create patterns, and could potentially deliver the sense of touch in a digital age.
Researchers at UC San Diego developed a robotic hand that can rotate objects solely through touch without relying on vision. The system uses low-cost, binary signals from multiple sensors to detect object contact and perform precise rotations.
Hang aims to develop general-purpose robots that can handle complex physical interactions without requiring perfect input from sensors or extensive instructions. His project seeks to improve robotic manipulation tasks by reducing assumptions about how the robot acts in real-world conditions.
Researchers at North Carolina State University have developed a new robot called RoboMapper that can conduct experiments more efficiently and sustainably to develop new semiconductor materials. The robot automates the process of testing multiple samples simultaneously, reducing time and energy consumption by nearly 10 times.
Researchers developed a cost-effective method using LEGO robots to purify complex DNA structures. The technique, called rate-zonal centrifugation, utilizes the LEGO kit's gradient-mixing capabilities to separate and isolate individual components of the nanostructures.