Researchers created dynamic metashells that leap into the air on a predetermined schedule without intervention, jumping up to nine times their height. The structures were engineered to store energy and release it at a controlled timing, with scheduled jumps possible from three seconds to 58 hours in advance.
The Association for Computing Machinery has recognized five individuals with awards for their impactful service to the computing field. Manish Parashar received the ACM Distinguished Service Award for his leadership in furthering the transformative impact of computer science on science and engineering.
Aerial robots are limited to manipulating rigid objects, but Lehigh University researcher David Saldaña aims to expand their capabilities with an adaptive controller and reinforcement learning. His research has potential applications in construction, disaster response, and industrial automation.
Researchers developed novel haptic devices to enable precise robot control with tactile feedback, reducing collisions and improving user proficiency. The devices integrate digital twin technology and augmented reality for enhanced immersion.
SWORD accelerates robotics development by reducing manual coding required for complex applications, integrating CAD with open-source ROS tools to streamline automation. The software models, plans, and executes automation in a user-friendly environment.
A team of Brown University researchers has developed an artificial intelligence model called MotionGlot that can generate movement in robots and animated figures. The model enables users to type an action and generates accurate representations of that motion, translating across different robot and figure types.
Researchers at MIT created a table tennis bot that can return shots with high-speed precision, achieving a hit rate of 88% in tests. The technology could be adapted to improve the speed and responsiveness of humanoid robots for search-and-rescue operations.
Researchers developed an intelligent autonomous robot capable of automating hospital disinfection processes through dual disinfection system, increasing efficiency and precision. The robot's performance was validated through real-world testing, reducing the risk of infection in hospitals.
A new robotic system uses cues in a scene to determine a human's objective and quickly identify relevant objects, enabling intuitive assistance in household, workplace, and warehouse settings. The approach achieved 90% accuracy in predicting human objectives and 96% accuracy in identifying relevant objects.
A new brain-like computer uses analog computing to process and store information in the same location as biological neurons, reducing power consumption by 0.25%. The device, called a memristor network, is more efficient than conventional transistor-based computers and has implications for autonomous vehicles and drones.
A new coffee-making robot, developed by the University of Edinburgh, demonstrates cutting-edge AI and motor skills that enable it to adapt to challenging kitchen environments. The robot can interact with objects and people seamlessly, solving complex problems like accessing drawers and measuring ingredients.
The Harvard robot uses latch-mediated spring actuation to jump high and cover long distances relative to its size. It combines walking and jumping modes for effective navigation in natural environments.
A team of researchers has created a robotic material-like collective that can change shape and stiffness in response to internal signals. The robots, composed of disk-shaped autonomous units, use light sensors, magnets, and force fluctuations to achieve this behavior, reducing power consumption compared to traditional robotic systems.
The University of Virginia's AI-powered vision system, mimicking praying mantis eyes, has been selected as the best paper of 2024 by Science Robotics. The innovative system enables machines to track objects in 3D space, addressing limitations in current visual data processing.
Researchers developed a platform to help AI learn complex tasks through nuance and real-time instruction, achieving up to a 30% increase in success rates. The GUIDE framework allows humans to provide ongoing, nuanced feedback, fostering incremental improvements and deeper understanding.
Researchers at TUM developed a new tool that makes intrinsic dynamics calculable, enabling robots like BERT to mimic natural oscillation patterns. The method results in effortless and dynamic movement, surpassing conventional movement patterns.
Scientists at Max Planck Institute for Intelligent Systems developed a novel method for deploying multiple magnetic miniature robots to navigate through complex networks resembling blood vessels. The system allows for simultaneous treatment of multiple locations, saving critical time and enabling localized care.
Researchers developed a wearable ultrasound device that tracks muscle function without invasive procedures, offering high-resolution imaging and wireless monitoring capabilities. The technology has potential applications in respiratory health and human-machine interfaces.
Scientists at Princeton University develop a system of two robots connected by flexible tether, enabling them to solve complex problems like maze navigation and object gathering. The innovative approach harnesses physical characteristics rather than digital calculation to achieve remarkable abilities.
A new knee exoskeleton has been developed to support the quadriceps muscles during lifting tasks, helping workers maintain better posture even when fatigued. The device, which uses a complex algorithm to predict assistance needs, enabled participants to lift faster and with improved posture.
The Human AugmentatioN via Dexterity (HAND) center aims to develop robots capable of enhancing human labor through engineered systems of dexterous robotic hands, AI-powered fine motor skills, and human interface. The center's goal is to make robotic assistance accessible and applicable to a wide range of physical actions.
Researchers created RoboFabric, a wearable fabric that can stiffen on demand for medical applications and soft robotics. The technology reduces muscle activity by up to 40% when assisting joints while lifting loads.
The University of Maryland team created a camera mechanism that mimics the involuntary movements of the human eye, resulting in sharper and more accurate images. The Artificial Microsaccade-Enhanced Event Camera (AMI-EV) has implications for robotics, national defense, and industries relying on accurate image capture.
Researchers at Princeton University and North Carolina State University have combined ancient paperfolding and modern materials science to create a soft robot that can bend and twist through mazes with ease. The new design allows the flexible robot to crawl forward and reverse, pick up cargo and assemble into longer formations.
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 at the University of Sydney and Queensland University of Technology have developed a new approach to designing cameras that process and scramble visual information. The approach, known as 'sighted systems,' creates distorted images that can still be used by robots to complete tasks but do not compromise privacy.
Researchers at Georgia Tech have developed a universal approach to controlling robotic exoskeletons that requires no training, calibration, or adjustments. The system uses deep learning to autonomously adjust assistance levels for walking, standing, and climbing stairs, reducing user effort and metabolic expenditure.
Researchers at Bar-Ilan University discovered that each filter recognizes small clusters of images, with sharpened recognition as layers progress. This breakthrough can improve AI performance by reducing latency and memory usage while maintaining accuracy.
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 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 at Princeton University and Google have developed a new technique to teach robots to ask for help when they're unsure. The method uses large language models to gauge uncertainty in complex environments, allowing robots to reduce the amount of help required while maintaining high accuracy.
Researchers at ETH Zurich developed an autonomous excavator called HEAP to construct a 6-meter-high and 65-meter-long dry-stone wall. The excavator uses sensors, machine vision, and algorithms to place stones in the desired location, achieving a high level of precision and speed.
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 new project aims to help robots assess risks and make autonomous decisions. The research focuses on quantifying ambiguity in robot perception to improve safety and efficiency.
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 from Bar-Ilan University improved AI classification tasks by choosing the most influential path to the output, rather than learning with deeper networks. This approach can enhance existing architectures and pave the way for improved AI systems without additional layers.
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.
The robot uses two front limbs mimicking turtle hatchlings' oversized flippers to detect obstacles and navigate through sand. It has the potential to inspect grain silos, measure soil contaminants, and aid in search and rescue operations.
A team of researchers at Harvard University has developed a compact, soft pump that can power soft robots in various applications. The pump uses dielectric elastomer actuators and can control pressure, flow rate, and flow direction, making it suitable for biomedical settings.
Researchers from Osaka University developed a biomimetic robot that uses dynamic instability to navigate uneven terrain. The robot can switch between straight and curved walking motions, making it suitable for search and rescue operations or planetary exploration.
Researchers from Carnegie Mellon University have created a fabric and sensing system, RobotSweater, that allows machines to better interact with humans. The knitted textile 'skin' can sense contact and pressure, enabling robots to move in response to human gestures.
Researchers at Bar-Ilan University have discovered that efficient learning on artificial shallow architectures can achieve the same classification success rates as deep learning architectures, but with less computational complexity. This breakthrough has significant implications for the development of unique hardware and advanced GPU t...
Researchers at Bar-Ilan University have developed a new type of artificial neural network that outperforms traditional deep learning architectures. By using tree architecture with single routes to output units, they achieve better classification success rates, paving the way for efficient and biologically-inspired AI hardware.
Researchers at KAIST developed a quadrupedal robot control technology that enables robots to walk robustly on deformable terrain like sandy beaches. The technology uses artificial neural networks to simulate ground characteristics and adapt to changing environments, allowing the robot to maintain balance and perform high-speed walking.
Scientists successfully used lab-produced tissue samples to remotely control muscle-driven miniature robots with this innovative technology. The device allows researchers a new level of interaction and exploration in the field of biological robots.
Researchers from Singapore University of Technology and Design developed a new reconfigurable workspace soft robotic gripper that can pick and place a wide range of consumer items. The RWS gripper's adaptive capabilities make it particularly useful in logistics and food industries where robotic automation is crucial.
Researchers found that providing language descriptions of tools can accelerate a simulated robotic arm's learning of tool manipulation. The team used GPT-3 to obtain tool descriptions and showed improved performance in tasks such as pushing, lifting, sweeping, and hammering with new tools.
A team of simple robots, nicknamed RAnts, use photormones to escape a corral and perform complex tasks. The research reveals how collective cooperation can arise from simple rules, applicable to solving problems like construction, search and rescue, and defense.
The MARM robotic platform has three limbs for enhanced mobility and manipulation flexibility, allowing it to transport large payloads and assemble components. The robot's unique design enables full-body motions and facilitates assembly operations by adjusting its central pelvis base.
Researchers from City University of Hong Kong developed an advanced wireless haptic interface system called WeTac. The system provides a vivid touch experience with personalized tactile sensation data and overcomes the shortcomings of existing bulky gloves.
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.
Gwangju Institute of Science and Technology researchers have developed a rabbit-scale three-dimensional magnetic particle imaging system that can scan large volumes at high resolution. The system uses amplitude modulation to minimize peripheral nerve stimulation while maintaining high image quality.
A new optimization tool can quickly improve performance of various autonomous systems, including walking robots and self-driving vehicles. The tool uses automatic differentiation to identify tweaks that achieve desired outcomes, reducing trial-and-error simulations.
MIT researchers develop an interactive design pipeline enabling users to create customized robotic hands with tactile sensors. The platform streamlines the process, allowing users to adjust palm and fingers and integrate tactile sensors, resulting in complex tasks like picking delicate items or using tools being performed flawlessly.
Researchers are refining COBRA, a repair robot inspired by snakes, for medical use in throat cancer and injury surgery. The robot offers more dexterity, accuracy, and high-definition views for surgical teams.
Researchers at MIT developed a framework for robotic manipulation systems that can perform complex tasks using a two-stage learning process. This allows robots to learn abstract ideas about manipulating deformable objects, such as pizza dough, and execute skills to complete tasks.
A team of engineers and scientists has developed a proof-of-concept for a magnetic tentacle robot that can navigate the narrow tubes of the lung, enabling doctors to take tissue samples or deliver cancer therapy. The device measures just 2 millimeters in diameter and uses an autonomous magnetic guidance system to guide it into place.
Researchers created BirdBot, a robotic leg inspired by the ostrich's anatomy, which achieves energy efficiency through a mechanical coupling of muscles and tendons. The robot leg requires fewer motors than other machines, making it suitable for large size applications.
Researchers at Imperial College London developed a bendy robotic arm that can twist and turn in all directions, allowing for customizable shapes. The team created an augmented reality system to enhance user-friendliness, enabling users to easily configure the robot using motion tracking cameras and smartglasses.