A recent study reveals that AI can contribute to a more sustainable construction industry by optimizing energy use, improving resource efficiency, and enhancing climate resilience. However, the technology is not a standalone solution and has its own environmental footprint, which must be considered when evaluating its climate benefits.
Researchers at Colorado State University have developed flexible robots with a tensegrity design, allowing them to bend, collapse and change shape as needed. The robots can grip objects, attach to partner robots and manipulate items, making them suitable for tasks like search and rescue and manufacturing.
Researchers have developed a new approach called agentic robotics, which enables teams of AI agents to generate, test, and refine robot programs quickly and efficiently. This method addresses the challenges of collecting and processing large amounts of data and programming robots, allowing for faster and more adaptable robot development.
Researchers at Tohoku University developed a mechanical reflex module that reproduces the patellar tendon reflex in robots, enabling bipedal walking. The module combines sensing, computation, and actuation within its physical structure, reducing system complexity and computational demands.
Engineers create predictive model to synchronize light exposure, eliminating gaps and ensuring functional parts. The technique enables the production of free-moving gearboxes and open channels with dimensions smaller than projected pixels.
A new system called UQ-DAAAM identifies and corrects unreliable object descriptions in a robot's memory, improving its ability to interact with its environment. This method boosts the robot's confidence and improves the accuracy of its answers to questions about objects, their locations, and when it saw them.
Researchers at Northwestern University have developed a new 3D printing method called DIAL, which combines the speed and precision of light-based printing with the broad ink compatibility of extrusion-based printing. DIAL rapidly prints complex, finely detailed, free-standing objects without the need for scaffolding.
Researchers at Virginia Tech developed a method combining vibrations and AI to determine rock depth, enabling robots to clear terrain efficiently on planets like Mars. The tool can also aid in Earth-bound applications, such as analyzing construction or disaster scenarios.
A research team developed a humanoid AI system called RISE that learns jointly from locomotion and object-manipulation data to perform multiple stages of a task in sequence. RISE achieved an average success rate of 87.3% in simulation and 50.0% in real-world experiments, outperforming a baseline by 20 percentage points.
Penn's Fast Feature Field transforms event-camera data into information that many different kinds of robots can use, improving robots' ability to recognize objects, estimate distances and perceive motion. The tool could transform robotics by allowing for the widespread use of event cameras in self-driving cars and drones.
A new robotic enteroscope can inch through the hard-to-reach small intestine, making biopsies and drug delivery easier. The robot uses a snake-like locomotion strategy and textured coating to gain traction on the mucosal lining, allowing for automated evaluation and treatment of intestinal complications.
The team's research on reducing environmental noise in AI and generating diverse synthetic training data for large language models has been accepted to top AI conferences. Their methods have been shown to improve AI performance and efficiency across various fields, including robotics, reinforcement learning, and quantum AI.
Researchers at the University of Toronto have developed a flexible foot pad for the 'Hopcopter', a one-legged hopping robot, significantly enhancing its performance on challenging terrain. The new design enables the robot to traverse sand, ice, and other difficult surfaces with improved efficiency and accuracy.
Researchers at ETH Zurich developed bioactuators that combine living skeletal muscle tissue with a soft hydrogel scaffold, achieving greater movement range and strength. The actuators can flex, jump, swim, and grasp objects, showcasing the potential of living organisms in robotics.
The project aims to develop shared cyberinfrastructure that enables realistic, reproducible experiments for AI-enabled robots and cyber-physical systems. The framework will provide research-grade workflows, digital twin environments, and experimental examples to support hands-on training and mentored research.
A team of researchers at Tohoku University has developed an automated experimental system for bulk metallic materials, enabling continuous workflow from heat treatment to structural analysis and mechanical property evaluation. The system evaluates mechanical properties with accuracy comparable to conventional measurements, conducting t...
A new manufacturing method enables the creation of flexible devices that can crawl, move, and shield electromagnetic interference. The technique uses laser-induced selective metallization and magnetic liquid metal to form precise metallic patterns on complex 3D-printed polymer surfaces.
Researchers have developed a unified robot AI system that can understand human instructions, predict future scenes, and carry out tasks. The technology achieved an average success rate of 78.4% in real-world robot manipulation settings, outperforming comparison models.
Researchers created a mechatronic metamaterial that behaves like a 'time crystal,' allowing individual units to organize into a single rhythm. The material, made of elastic structures, sensors, electronics, and actuators, can be used to develop multifunctional robots that coordinate themselves without central control.
A new study published in Hernia examined 39 robotic hernia repairs, with most patients returning home after one day and no hernias recurring during follow-up. Robotic technology enables greater precision and flexibility, making complex operations less invasive and more effective.
The soft robotic fish achieves high-speed swimming and 3D maneuverability by combining electrohydraulic propulsion with dynamic buoyancy regulation. It sets a new speed record for soft robotic fish using body-caudal-fin propulsion, reaching 2.13 body lengths per second.
Researchers at Johns Hopkins University have created tiny robots called 'millirobots' that can deliver medicine directly to infected heart tissue, reducing treatment time from weeks to just hours. The robots use magnetic guidance and are designed to replace open-heart surgery and ineffective IV-drug therapy.
Researchers created a small soft robot called BeetleBot that combines artificial muscles, a camera, and tactile sensors to perform tasks like gripping objects and avoiding obstacles. The robot uses bidirectional feedback to connect user control with sensory information, enabling practical tasks to be carried out.
Researchers find that AI agents must forget information to maximize energy efficiency, even if it improves predictions. This conflict arises from fundamental laws of physics and has implications for sustainable AI development.
Researchers at MIT developed a new navigation system, called SANDO, that charts an efficient and safe flight path for drones in unknown environments. The system provides a mathematical guarantee of safety, even in dynamic environments with moving obstacles.
A new multimodal 4D dataset, InterPet4D, provides a detailed model of human–dog interactions through movement, gestures, and speech. The dataset was used to develop an AI framework, InterPetMoGen, which generates plausible dog motion from human body and hand movements and accompanying audio cues.
The feather star robot uses only two actuators to achieve three-dimensional movement, powered by a design inspired by mechanical intelligence. By rapidly activating and deactivating the actuators, the robot can flap its wings to rise or descend, and rotate on its axis to steer.
A new path-tracing method simulates event camera data from virtual 3D scenes efficiently, reducing computational costs for applications like autonomous driving and robotics. The method uses physically-based path tracing and adaptive temporal search to precisely determine event timings, enabling more efficient training-data generation.
SourceChiba University·JournalIEEE Transactions on Visualization and Computer Graphics·TypeComputational simulation/modeling·DateOct 1, 2026
Researchers at the University of Tokyo have developed a pill-shaped device that can collect samples from the small intestine using a tiny extendable brush. The device is designed to be magnetically controlled, allowing it to move through extracted intestines and sweep useful samples from the intestinal surface. The technology has the p...
A study on on-orbit autonomous assembly of deployable modules reveals the importance of real-time deformation control and motion control during assembly. Numerical simulations demonstrate the effectiveness of a proposed control strategy, reducing geometric errors to below 0.013 mm.
ALBATROSS, a nature-inspired robotic platform, uses passive autorotation and sail technology to navigate remote waters, reducing the need for separate parachute or landing mechanisms. The platform's simplicity and reduced components enable lower-cost and more scalable sensing platforms for environmental monitoring and other applications.
Studies comparing robotic and conventional joint replacement surgeries found no differences in implant survival, revision risk, or surgical complications. However, robotic surgery was associated with a lower risk of hip revisions. Further research is needed to compare patient functional outcomes and evaluate the technology's effectiven...
KAIST researchers created a single soft material that combines sensing and actuation, holding its deformed shape for over 10 minutes after light is turned off. The material detects charged objects and is actuated by UV light, with potential for reducing components and wiring in soft robots.
A new paper-thin robot powered by muscle cells can swim through a watery maze, offering a way to design small, efficient biohybrid robots. The robot uses a layer of live muscle cells that twitch in response to light, allowing it to control its direction and speed.
Researchers highlight the importance of human moderation and algorithmic misinformation tagging in online patient support communities and online research. Mobile apps and patient simulator robots also play a crucial role in digitizing health records and training rural clinicians for rare emergencies.
A quadruped robot, RAIBO2, completed a 42.195 km marathon without battery swap, capturing 4 hours and 19 minutes of real-world running data. The research team developed design principles for long-distance operation, focusing on system-level efficiency and reliability.
DirectHop, a 1-gram robot, can perform multiple hops in sequence and jump high enough to clear a standard stair step with single centimeter accuracy. The robot uses a tiny electric motor and three folding legs to launch itself to a specified jump height, and can twitch to right itself after landing for another jump.
A startup collaboration between Silly Surfacing and the University of Pittsburgh's IDEA Lab has led to the development of a pothole-filling robot, utilizing 3D scanning, mapping, and computer vision to repair road damage. The system uses a time-of-flight camera and can fill a pothole at full scale.
The EMERGE project establishes a philosophical, mathematical and technological framework for collaborative awareness in artificial systems. Researchers found that people can understand an artificial system as aware without assuming subjective experience, and that increasing awareness can improve performance.
The WorMa robot uses a pump to shift water between its head and tail to adapt to changing terrain, successfully crossing a course with flat ground, a step, a slope, and open water. The robot's ability to redistribute mass allows it to traverse various environments without redesigning its mechanism.
A new robotic system utilizes twisting elastic rods to produce powerful, repeatable motions, enabling small robots to hop, flip, and swim across challenging terrain. The snapping mechanism stores and releases built-up energy, allowing a small, low-power motor to trigger rapid movements.
New research reveals the rise of AI-generated deepfake physician scams and the potential of robotics in bedside nursing care. While robots can perform repetitive tasks, human involvement is still necessary due to the complexity and flexibility of real-life clinical settings. Additionally, deepfakes are used to exploit online users for ...
Researchers at UCLA and University of Michigan have developed a mechanism that enables small robots to hop and swim using low-power twisting. The twisting of bent elastic rods produces a snapping motion that enables the robot to move efficiently on challenging surfaces, such as slippery cloth and grass-covered ground.
Researchers from SUTD developed a control method that enables a one-motor flying robot to anticipate its next movements and track complex paths more accurately. The approach, described in a study, outperformed a benchmark controller in reducing positional errors by up to 39.5% on certain trajectories.
Researchers at Harvard and Georgia Tech have developed RLE-Bench, a benchmark that tests AI coding agents' ability to engineer physical robots. The benchmark contains 48 tasks that test the agent's ability to perform engineering work required to build and operate robotic systems, including control and perception algorithms, designing r...
The robotic lab can autonomously assemble and fine-tune optics experiments, reducing manual setup time from days or months to minutes. This could enable scientists to focus on theoretical work and accelerate innovation in fields like quantum technologies and renewable energy.
Researchers at ETH Zurich have developed a flexible foetoscope with magnets to navigate and seal blood vessels in the placenta, reducing the risk of twin-to-twin transfusion syndrome. The new robotic platform combines panoramic imaging and magnetic navigation for improved precision and control.
The National Science Foundation has awarded $2 million to Worcester Polytechnic Institute to support scholarships and mentoring for low-income undergraduate and graduate students in STEM fields. The funding will contribute to increasing the size of the U.S. workforce in science, technology, engineering, and mathematics.
Researchers at MIT created a new computing platform that mimics the firing behavior of a neuron, enabling brain-inspired computing with low power and high efficiency. The device uses reconfigurable motion to remember and process information, similar to how neurons behave in the brain.
The initiative explores how AI-assisted ultrasound can support nephrologists in acquiring images, discussing interpretation, and exploring new technological capabilities. Targeting AI & Nephrology aims to build bridges between AI research, technological innovation, and real-world clinical practice.
Scientists systematically map the Biginelli reaction to uncover a previously unknown branch that produces complex bicyclic structures and molecules with unusual supramolecular behavior
Rocky Scopelliti argues that AI systems' growing self-awareness and moral dispositions require immediate practical ethical concerns to be addressed. He suggests protocols for AI systems, especially those trained to care, to understand context and make moral judgments.
MIT researchers developed a new technique to help generative AI models meet strict safety requirements without sacrificing output quality. The 'HardFlow' algorithm reformulates hard-constrained sampling as a trajectory-optimization problem, enabling subtle corrections while enforcing hard constraints.
Researchers developed an AI-guided laser technique to carve micro-pyramids for robots to sense soft surfaces gently. The technique enables the creation of flexible conductive skins with high sensitivity and linearity, outperforming conventional designs.
The consortium aims to improve inspection and maintenance tasks using robotics, focusing on corrosion detection and surface maintenance in extreme environments. SwRI will manage the project, leveraging its expertise in manufacturing robotics, mechanical engineering and oil and gas services to deliver pioneering robotic solutions.
The HKU Robocon team, consisting of 40 students, won the Asia-Pacific Broadcasting Union's Asia-Pacific Robot Contest 2026, defeating teams from 15 countries. The team's exceptional collaboration, innovative engineering, and operator training contributed to their victory.
The SMASH Team, led by Professor Ping LUO, won the silver medal in robot table tennis at the World Humanoid Robot Games. The team's autonomous humanoid table tennis system, SMASH, is the world's first to use onboard sensing to achieve consecutive strikes and rallies with human players.
Duke University has received a $24 million award to develop foundational science for engineering systems to counter unmanned aerial attacks. The center, led by Miroslav Pajic, brings together experts in wireless systems, cybersecurity, and AI to develop tools and automated procedures for detecting, thwarting, and controlling enemy drones.
A scoping review found that only 77 studies validating 52 medical AI products reported demographic data, highlighting the need for more transparent reporting to confirm safe and unbiased performance. The review also showed that performance reporting for demographic subgroups is inadequate, posing a risk to patient care and outcomes.
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle's AI system into understandable concepts that explain its behavior. CW-Net explains the decisions of machine learning-based planners using concepts like