Articles tagged with Robots
Researchers developed a computational model of flying snakes' undulation to understand lift production. The snake's cross-sectional shape creates pressure differential across its body, lifting it and allowing it to glide through the air.
Researchers have developed a robot capable of sorting, manipulating, and identifying microscopic marine fossils. Forabot uses robotics and artificial intelligence to automate the tedious process of evaluating foram shells and fossils.
University of Missouri engineers are working on a collaborative human-robot order picking system to speed up the online delivery process. The proposed model aims to optimize key decisions in warehouse operations, allowing robots to navigate efficiently and collaborate with humans to increase efficiency.
Researchers developed a new machine-learning framework that enables cooperative or competitive AI agents to consider the future behaviors of all agents, not just their teammates or competitors. This framework, FURTHER, uses two modules: an inference module and a reinforcement learning module, to enable agents to adapt their behaviors a...
A new study finds that automation has contributed significantly to the growth in income inequality in the US, with 50-70% of the increase attributed to technological changes. The study analyzed data from 49 industries and 500 demographic subgroups, finding that automation has disproportionately affected low-skill service workers.
Researchers at NC State University have created an energy-efficient soft robot that can swim more than four times faster than previous models. The 'butterfly bots' use bistable wings for propulsion and achieve speeds of up to 3.74 body lengths per second.
Researchers have developed a new miniature robot called Joey that can explore real pipe networks completely on its own, weighing just 70g. The robots are small enough to fit in the palm of your hand and are equipped with energy-efficient sensors to navigate through narrow sections and obstacles.
A team of researchers developed a new method for 3D-printing microrobots with multiple component modules inside the same microfluidic chip. The 'assembly line' approach allowed for the combination of various modules, such as joints and grippers, into a single device. This innovation may help realize the vision of microsurgery performed...
Researchers at Georgia Tech discovered that wingless springtails control their jump, self-right in midair, and land on their feet due to their unique appendages for jumping and adhesion. This unique posture creates aerodynamic torque, effectively self-righting them within 20 milliseconds.
Researchers controlled magnetic bacteria to cross blood vessel walls and infiltrate tumor tissue, delivering liposomes with fluorescent dye to demonstrate their ability to carry therapeutic agents. This approach may revolutionize bacterial cancer therapy by increasing efficacy and reducing side effects.
Researchers at Carnegie Mellon University's Robotics Institute have developed a sensor called ReSkin that allows robots to feel cloth layers, enabling tasks such as folding laundry. The team taught the robot to grasp and manipulate cloth using tactile sensing, overcoming challenges of computer vision-based approaches.
MIT researchers have developed a magnet-based system to track muscle length during movement, which could improve the accuracy of prosthetic limb control. The system uses small magnets implanted in muscle and measures distances between them using a credit-card-sized sensor.
Researchers developed a compact robotic finger with adjustable stiffness to withstand physical impacts and mimic human finger dexterity. The finger mechanism is based on gear transmission and mechanically passive compliance, providing an advantage in terms of reliability, ease of manufacture, and maintenance.
Researchers propose a broader definition of learning that includes behavioral adaptation to environmental features, enabling collaboration across fields and promoting new research. This 'mechanism-free' approach highlights the importance of system-level responses to environment in various domains.
Working with robots may lead to increased reports of burnout and incivility among employees. Self-affirmation exercises can help mitigate fears about being replaced by machines.
Researchers identified 7 core categories of behaviors important for human-dog bonds, including attunement, communication, and physical affection. These behaviors may be incorporated into robotic systems to provide mental health benefits for humans.
Researchers used small wheeled robots to study indirect mechanical interactions on deformable surfaces, finding that active matter can interact through non-contact forces. They created a model to control collective behavior by modifying robot design, mirroring celestial bodies' paths in Einstein's General Relativity.
UC Riverside engineers develop low-cost robotic clothing to help children with cerebral palsy. The soft machine garments contain sealed regions that inflate to provide force for movement, enabling natural limb functioning.
A four-legged robot trained through artificial intelligence has mastered jumping to navigate the Moon's rugged terrain. The robot can collect samples and deploy scientific instruments, overcoming limitations of traditional rovers in loose soil and steep slopes.
Researchers at Kyoto University designed a shared-laughter AI system to build empathy into dialogue between robots and humans. The system was tested on the Japanese android Erica, performing better than baseline models in evaluating empathy, naturalness, and human-likeness.
Researchers designed an integrated system to support joint operations between UAVs and mobile robots for surveillance, epidemic prevention, and rescue operations. The system aims to improve public safety while ensuring privacy and security.
A study by Simon Dubé examines the personality traits of people willing to engage with sex robots, revealing that erotophilia, sexual sensation-seeking, and enthusiasm for new experiences are key drivers. The research highlights an opportunity for manufacturers to cater to a female customer base as technology improves and becomes more ...
Researchers have made significant progress in designing and controlling continuum robots, which can be used for targeted therapy and precise control. However, challenges remain, including miniaturization, perception accuracy, and stable simulation engines.
Researchers found that ants and robots can be modeled using the same algorithms, despite differences in slipping motions. The discovery provides a universal model for location that applies to various movements, including walking and slithering.
A study using child-sized humanoid robots found that they can assess mental wellbeing in children more effectively than parent-reported or self-reported testing. The robots were able to encourage children to share their thoughts and feelings, leading to more accurate assessments of their mental health.
Researchers at Rice University have developed a pneumatic robotic arm powered by compressed air that can grasp objects and go, using textile-based energy harvesting system. The device is designed for individuals with disabilities and can produce equivalent of 3 watts of power, outperforming other energy harvesting strategies.
Researchers at WVU are using robots to analyze potential hazards and provide walkability maps in retail environments, aiming to reduce occupational injuries. The team plans to test the robots after hours in an actual retail space, combining camera data with wheel speed measurements to estimate slip risks.
A new study by the University of Central Florida reveals that workers in countries with greater income inequality are more likely to perceive robots and artificial intelligence as job threats. This association was found despite the potential benefits of these technologies to improve work and increase flexibility.
Researchers create accurate hydrodynamic model of the RobDact underwater robot to improve its control in turbulent waters. The team combined computational fluid dynamics and a force measurement experiment to study the RobDact, enabling better understanding of its motion state and control.
MIT researchers developed a method to create 3D-printed materials with tunable mechanical properties and embedded sensors, enabling real-time feedback on movement and interaction. The sensing structures use air-filled channels that deform when moved or squeezed, providing accurate feedback for robotics and wearable devices.
Researchers at UNH will develop and test social assistive robots to aid in the care of individuals with Alzheimer’s disease and related dementia in their own homes. The robots will be equipped with smart home devices, artificial intelligence, and wearables to track patients' activity levels and health management.
QUT researchers have created a method to tell an autonomous vehicle which cameras to use when navigating, allowing for better understanding of the world around them. The system learns which cameras are most useful at different locations based on previous experience.
A University of Washington team created a new tool that can design a 3D-printable passive gripper and calculate the best path to pick up an object. The designed grippers and paths were successful for 20 out of 22 objects tested, with two challenging shapes being the wedge and pyramid shape.
A study published in Science Robotics journal reveals that humans are unable to distinguish between a humanoid robot's response time variability and that of a human when interacting with the robot. This finding suggests robots can exhibit human-like behavior, raising questions about the blurring line between humans and machines.
Researchers at Carnegie Mellon University developed a novel learning method for robots called WHIRL, which allows them to learn household tasks in the wild. The method enables robots to gather video data from human interaction and generalize it to new tasks, making them suitable for learning household chores.
A team of researchers from Cornell University has developed a deformable pump for soft robots, mimicking the human heart's functionality. The pump uses hydrodynamic and magnetic forces to provide soft robots with a circulatory system, allowing them to store energy and power their movements more efficiently.
Researchers at Harvard University have developed inflatable actuators that can bend, twist, and move in complex ways using origami-inspired designs. The actuator's bistable origami blocks allow it to perform up to eight different motions with a single pressure source.
A Columbia University team created a robot that can learn and understand its own body, planning motion and avoiding obstacles without human assistance. The robot's self-model was accurate to about 1% of its workspace, paving the way for more self-reliant autonomous systems.
Researchers at AMOLF developed a soft robot that uses a 'hysteretic valve' to respond to changes in its environment, mimicking the movement of living organisms. The robot's natural gait and tactile responses were achieved through the use of air pressure, eliminating the need for computer control.
Researchers found that mere exposure to a human-like robot is not enough to make people believe it is capable of thoughts and emotions. Human-like behavior is crucial for being perceived as an intentional agent. The study aims to inform the design of social robots in the future.
Researchers created a new material and manufacturing process for creating artificial muscles with improved flexibility and durability. The resulting material, PHDE, is thin, lightweight, and can generate high forces while maintaining its shape under high-strain conditions.
A study published in Labour Economics found that US workers who work alongside industrial robots are more likely to suffer from adverse mental health effects, including substance abuse and increased suicide rates. In contrast, German workers saw no significant mental-health change when exposed to robotics.
A novel Kalman filter, GMCKF, was proposed to improve robot tracking accuracy in space with complex non-Gaussian noise. The algorithm achieves better performance under various non-Gaussian noises by utilizing a generalized Gaussian density function and automatic parameter selection.
A multidisciplinary approach reveals a continuum of locomotion dynamics in lizards, with short-limbed species exhibiting snakelike waves and long-bodied species bending like lizards. The findings deepen understanding of evolution's implications for locomotion and have applications for advanced robotics designs.
A novel algorithm, BLIND, enables robots to navigate through environments with obstacles by incorporating human feedback. Humans provide labels to refine the robot's trajectory, avoiding obstacles efficiently.
Researchers at the University of Manchester are developing AI-powered robots that can operate autonomously in hazardous environments. The 'hot-robotics' project aims to improve robot autonomy for tasks like decommissioning legacy power stations and inspecting nuclear reactors.
The study highlights opportunities for robotics to support human activities, foster innovation, and enhance monitoring. However, it also identifies potential threats such as exacerbating inequalities and diverting resources from tried-and-tested solutions. Researchers emphasize the need for early identification of negative impacts and ...
A new AI system uses artificial neural networks to recognize objects more accurately and stably, despite changing visual inputs. The system mimics human eye movements to improve machine vision capabilities, reducing errors in self-driving cars and other applications.
Researchers at MIT created insect-scale robots that can emit light during flight, allowing for precise motion tracking and potential communication between robots. The ability to emit light also enables the robots to call for help in search-and-rescue missions.
Researchers at Johns Hopkins University found that robots loaded with widely-used AI models exhibit significant gender and racial biases. The AI models were trained on biased internet data, which led to the robot making assumptions about people's jobs based on their appearance.
A team of UCLA engineers developed a new design strategy and 3D printing technique to build robots in one step. The breakthrough enables the manufacturing of mechanical and electronic systems needed to operate a robot all at once, resulting in lighter weights, bulkier volumes, and reduced force output.
Researchers at Stanford University have created millirobots that can precisely target specific areas of the body with medicines. These tiny robots, powered by magnetic fields, can navigate through narrow spaces and dispense medicine in real-time.
Researchers at Carnegie Mellon University developed an AI-powered method for robots to recognize and pour transparent liquids like water. The technique uses contrastive learning for unpaired image-to-image translation, enabling robots to see through different backgrounds and pour accurately.
Researchers at Carnegie Mellon University's Robotics Institute have developed an algorithmic planner that helps delegate tasks to humans and robots. The planner considers a list of tasks and decides how best to assign them, considering the time it takes for humans to complete tasks and teach robots new skills.
Researchers at UC San Diego developed a new technology using WiFi sensors to help robots navigate indoors, even in poor lighting. The system accuracy rivals commercial camera and LiDAR sensors.
A physicist at TU Graz has developed a three-in-one hybrid material that reacts to force, moisture and temperature with high spatial resolution. The smart skin has potential applications in robotics, smart prosthetics and healthcare, and its production can be easily scaled and implemented.
Researchers at EPFL's School of Life Sciences create a digital twin of Drosophila called NeuroMechFly, which uses biomechanical modeling and machine learning to simulate the fly's movements. The model is validated through experiments that demonstrate its accuracy in replicating real animal behaviors.
Researchers at Singapore University of Technology and Design developed a new machine learning approach to model underwater robot dynamics, allowing for efficient swimming in complex environments. The approach, published in IEEE-RAL, uses deep neural networks to predict required flapping motions for a set of given propulsive force targets.
Studies in fruit flies reveal coordinated movements of heads and bodies to stabilize vision and improve flight performance. Similar synchronization is observed in other animals, including primates, suggesting evolutionary benefits for energy efficiency and performance.
Daniel Preston, an assistant professor of mechanical engineering at Rice University, has won the National Science Foundation CAREER Award for his proposal on textile-based wearable robots. The grant aims to develop a platform for non-electronic computation that can be integrated directly into wearable robots, addressing problems with s...