Researchers at UC Berkeley developed an AI-powered training method called Human-in-the-Loop Sample Efficient Robotic Reinforcement Learning (HiL-SERL) that enables robots to perform complicated tasks with precision and speed. With human feedback, robots learn from demonstrations and real-world attempts, achieving a 100% success rate in...
Researchers developed a novel 3D printing technique called IPS 3DP to create personalized implants with specific mechanobiological properties. The method enables the creation of structurally complex hydrogels with hierarchical microstructures and strain-stiffening behavior, paving the way for advanced biomedical applications.
Researchers developed a bio-inspired bistable robotic gripper with tunable energy barrier, achieving rapid, compliant, and powerful grasping behavior. The gripper can adapt to different tasks and environments through dynamic energy barrier modulation, enabling efficient interaction with objects.
Researchers developed an alginate-based microrobot that can be tracked using Magnetic Particle Imaging (MPI) and performs real-time localization, selective thermal therapy, and cell delivery. The robot is powered by a single magnetic actuation system independent of conventional medical imaging devices.
A team of scientists has developed microrobots that use sound waves to coordinate into large swarms exhibiting intelligent-like behavior. The swarms can navigate tight spaces and re-form themselves, making them suitable for tasks like cleaning up pollution and delivering drugs directly to a problem area.
Researchers have developed a catalyst-free ionogel made from cellulose and an ionic liquid that exhibits exceptional strength and conductivity, outperforming synthetic analogues. The gel is also eco-friendly and low-cost, making it suitable for fully compostable high-performance electronics.
Researchers at ETH Zurich create a novel three-dimensional heart patch for intraventricular implantation, integrating into existing heart tissue. The RCPatch combines a fine mesh, 3D-printed scaffold, and hydrogel with living cells to promote complete repair and regeneration of damaged heart tissue.
A large-scale study found that Green AI significantly improves operational and environmental performance in Pakistani SMEs, but only when leaders invest, and institutions are in place. Adoption works under the right conditions, with perceived ease of use and usefulness driving behavior.
Developed by a research team at POSTECH, the robot uses human muscle proteins as inspiration to generate strong force while navigating through tight spaces. The technology has potential applications in various fields, including medical settings, industrial environments, home cleaning, and caregiving robots.
The research develops a comprehensive family assistant capable of performing various tasks like picking up toys and fetching items. The robot uses YOLOv11 object recognition and flexible gripper to recognize objects of varying sizes and weights with high accuracy.
The new book highlights the transformative role of artificial intelligence (AI) and machine learning (ML) across various domains, including mechatronics, cybersecurity, digital health, and automation. Readers will gain practical insights into AI-based techniques in power systems, social media management, and healthcare diagnostics.
Lydia Kavraki, a pioneering researcher in robotics and AI, has been elected to the European Academy of Sciences. Her work on physical AI, transforming robotics and biomedicine, and leadership at Rice University's Ken Kennedy Institute have earned her this prestigious honor.
Researchers create a technique to model organic objects, creating photorealistic 3D images of complex shapes for autonomous sorting. This method improves robotic systems that sort microscopic marine fossils used in climate research.
Researchers have developed soft artificial muscles that provide the performance and mechanical properties required for building robotic musculoskeletal systems. The new muscles can be battery-powered, enabling robots to move more naturally and safely in unstructured environments.
Researchers found that Earth's gravity pulls down on sand more strongly than previously thought, making it more rigid and reducing the likelihood of getting stuck. This discovery highlights the importance of physics-based simulation in analyzing rover mobility on granular soil.
A new robotic slip-prevention method has been developed to improve robots' grip and handling of fragile or slippery objects. This bio-inspired approach allows robots to predict when an object might slip and adapt their movements in real-time, outperforming traditional strategies.
MIT engineers developed a versatile demonstration interface that allows users to teach robots new skills in three intuitive ways: remote control, physical manipulation, or demonstration. This innovation expands the type of users and 'teachers' who interact with robots, enabling robots to learn a wider set of skills.
Researchers highlight the potential of solvent-based recycling and AI-assisted sorting to recycle complex plastics. However, the study emphasizes that replacing fossil-based plastics with biobased alternatives poses significant challenges, requiring comprehensive approaches and life cycle assessments.
Scientists at Columbia University have developed a process called 'Robot Metabolism' that enables machines to absorb and reuse parts from other robots or their surroundings. This new paradigm allows robots to physically sustain themselves, grow, adapt, and repair using materials from their environment or from other robots.
Researchers are creating generalized digital twins for machines, aiming to improve coordination up and down the production line. The center also plans to develop digital twins for human-robot collaboration and use software for simulation and analysis.
Researchers developed a self-driving lab that collects at least 10 times more data than previous techniques, dramatically expediting materials discovery research while slashing costs and environmental impact. The system uses dynamic flow experiments to continuously characterize samples, capturing data every half second.
Researchers demonstrated R-STDP synaptic plasticity in a single ferroelectric floating-gate device, enabling SNN to simulate robotic capture tasks with excellent performance. The network achieved a success rate up to 85.5% in dynamic capturing tasks.
Researchers developed an AI system that enables a four-legged robot to adapt its gait to different terrain, just like animals. The robot learned to switch gaits on the fly and navigate uneven surfaces without any alterations to the system itself, overcoming previous limitations around adaptability.
Yen-Ling Kuo, a UVA computer scientist, has been awarded the NSF CAREER Award to help robots understand and respond to human behavior. Her research focuses on building AI systems that can reason, communicate, and collaborate like humans, enabling robots to support people in various settings.
Artificial intelligence (AI) is revolutionizing medical needle procedures by providing unprecedented levels of accuracy and precision. AI-powered robots can assist physicians in complex tasks, enabling safer and more effective procedures. The four components of AI guidance are formalized, categorizing current systems into Eyes-on/Hands...
Researchers developed a soft electroactive polymer eel-like robot that can explore underwater environments with minimal impact on wildlife and fragile structures. The robot uses dielectric elastomer material, enabling it to swim efficiently without causing harm to the environment.
New humanoid surgical robots offer a solution to the growing healthcare labor shortage, allowing for more efficient surgeries and reduced burnout among doctors. By taking on routine tasks, these robots can free up surgeons to focus on more complex procedures.
Researchers at the University of Colorado Boulder have created a new way to build and control tiny particles that can move and work like microscopic robots. The team's method combines high-precision 3D printing and microstenciling, allowing for precise surface patches on active particles of arbitrary shape.
The FiLM-Scope surgical microscope offers precise 3D imaging using 48 tiny cameras, creating a detailed 3D map of the scene in real time. This technology can expand possibilities in manual and robotic microsurgery.
A fully autonomous robotic system developed by MIT researchers can measure important material properties like photoconductivity, increasing the speed and precision of research. The system uses machine learning and robotics to analyze new semiconductors and optimize the development of more powerful solar panels.
A new study published in the Journal of Experimental Psychology found that interacting with robots through social games makes them seem more human-like. The researchers used a box-shaped robot called Cozmo and found that participants who played games with it considered it more human-like, whereas those who interacted mechanically did not.
A team of undergrads at CU Boulder has created a digital twin for their robot, Armstrong, which is being used to train human operators on how to navigate the moon's surface. The study found that training in a digital environment resulted in faster task completion and reduced stress.
Researchers from Empa's Soft Kinetic group studied the rare scaly-tailed squirrels' unique bodily structure, discovering that their thorn-covered scales help them maintain position and grip onto tree bark. The study aims to inform robotics by adopting morphological structures and behaviors honed through millions of years of evolution.
Researchers created a machine vision sensor that adapts to extreme changes in light faster than the human eye, using quantum dots to mimic key behaviors. The device can respond dynamically to bright and dim lighting, outperforming existing systems by reducing redundant data and computational burden.
A new imaging technique developed by MIT researchers leverages reflections from wireless signals like Wi-Fi to create accurate 3D reconstructions of objects blocked from view. This approach achieved 96 percent reconstruction accuracy on everyday objects with complex shapes.
The AI for Good Global Summit 2025 will showcase AI innovations delivering better healthcare and education, reducing disaster risks, ensuring water and food security, and bolstering economic resilience. The event, organized by the International Telecommunication Union (ITU), features talks from AI leaders and 100+ demos.
Researchers have successfully controlled a dexterous robotic hand using noninvasive EEG-based Brain-Computer Interfaces (BCIs) for individual finger movements. The study demonstrates real-time brain decoding and motor imagery control, paving the way for potential applications beyond basic communication to intricate motor control.
A team of researchers at Princeton University and Harvard found that fish schools do not form diamond shapes as previously believed. Instead, they adopt a dynamic ladder pattern, allowing them to stagger in multiple planes and reduce energy expenditure.
Scientists from Institute of Science Tokyo create photo-switchable binding of DNA nanostructures that generate two distinct directional motions. The research paves the way for innovative fluid-based diagnostic chips and molecular computers.
The study analyzed 50 countries' national AI strategies, finding that only 13 gave high priority to training the current workforce and improving AI education. Common themes included establishing AI-focused programs in universities and on-the-job training, with a focus on human soft skills such as creativity and collaboration.
The Digits framework uses compressed air to produce shape changes, vibrations, and haptic feedback, offering a versatile platform for virtual reality and physical therapy. The device's modular design and pneumatic actuation enable adaptable and scalable control methods.
A research team developed AI technology that analyzes individual personality traits and values to generate personalized analogies, allowing people to understand others' feelings through familiar experiences. This approach significantly improved emotional understanding and empathy in participants compared to traditional methods.
Researchers at IIT have successfully demonstrated the first flight of a humanoid robot, iRonCub3, which can lift off the floor and maintain stability. The robot's AI-powered control system enables it to handle high-speed turbulent airflows, extreme temperatures, and complex dynamics.
International Journal of Extreme Manufacturing (IJEM) achieves a new Impact Factor of 21.3, surpassing 20 for the first time and maintaining its position as top journal in the field. IJEM has attracted submissions from 853 institutions in 81 countries.
Researchers at the University of Texas at Austin discovered a novel way to accelerate brain-computer interface (BCI) learning: gentle electrical nudge to the spine. This stimulation helps focus the brain on the task, significantly speeding up the learning curve.
Scientists created a low-cost, durable, highly-sensitive robotic 'skin' that can detect various types of touch and pressure. The technology senses multiple physical inputs simultaneously, allowing robots to interact with their environment in a more human-like way.
Researchers at MIT developed a machine learning-based adaptive control algorithm that enables autonomous drones to adapt to unknown disturbances like gusting winds. The system achieves 50% less trajectory tracking error than baseline methods in simulations.
A Chinese research team developed a magnetic microrobot capable of manipulating small droplets in the presence of magnetic fields. The robot achieved speeds 20 times faster than previous models and could interact with highly corrosive compounds without damage.
Rice University students have developed a cutting-edge wearable haptic wristband that can deliver two distinct forms of tactile feedback. The device aims to make virtual reality more immersive and accessible, and is entirely self-contained with a modular design that makes it easy to repair and integrate into different environments.
The Rice University team created a soft robotic arm capable of performing complex tasks using smart materials, machine learning, and an optical control system. The arm is guided and powered remotely by laser beams without any onboard electronics or wiring.
The research team developed a novel auditory technology that allows sound-based interaction between humans and robots, even in noisy environments. The technology facilitates sound-based recognition of human positions using only a single microphone.
Professor Shalom Lappin argues that tech companies' dominance in AI development poses a threat to public benefit and environment. He calls for comprehensive international regulation, intellectual property reform, and preparation for workforce disruption to address these challenges.
Researchers at KAIST developed a quadrupedal navigation system that enables the robot to reach its target destination quickly and safely in complex terrain. Inspired by cat's paw placement, they significantly reduced computational complexity.
Researchers developed an algorithm that lets a robot think ahead and consider thousands of potential motion plans simultaneously, solving multistep manipulation problems in a matter of seconds. The new method enables robots to rapidly determine how to manipulate and pack items without damaging them, even in narrow spaces.
Researchers at Stanford University developed a new technique called the milli-spinner thrombectomy that significantly improves success rates in treating strokes and other clot-related diseases. The milli-spinner can reduce clots to as little as 5% of their original volume, making it a promising tool for improving patient outcomes.
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.
Researchers created a soft robotics technology that can identify damage, pinpoint its location, and autonomously initiate self-repair. The system uses a multi-layer architecture featuring liquid metal microdroplets, thermoplastic elastomer, and electromigration to melt and seal damaged areas, effectively self-healing the wound.
Researchers developed VR Co-Lab to ease confusion while training employees digitally for disassembling recyclables without damaging materials. The program provides feedback on task completion time and mistake rates.
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.
A multidisciplinary team will utilize cutting-edge imaging technology and underwater robotics to discover and describe exotic marine species in the deep ocean. The project aims to transform how scientists understand the ocean's vast midwater region.