Robotics

Yao to receive NSF CAREER Award

Frontiers in Science Deep Dive webinar series: AI-embodied surgical robots can revolutionize surgery—if regulatory questions addressed

AI-embodied surgical robots can revolutionize surgery—if regulatory questions addressed

Experts warn that AI-enhanced surgical robotics could enable true personalized surgery and enhance surgical team performance. However, regulatory reforms are needed to address risks from adaptive systems and ensure patient benefits.

Aston University finds new way to train robots for real-world tasks using AI

Researchers at Aston University have created an AI-based training method that enables robots to adapt to real-world conditions without extensive data collection. This breakthrough could significantly accelerate innovation in sustainable manufacturing, recycling, and autonomous industrial systems.

Hidden math link helps designers build fantastic shapes

Researchers at Princeton University developed a system to mimic natural structures' microstructural patterns and mechanical properties. By combining origami and tensegrity, they found that the same equation describes both engineering structures, enabling designers to create irregular shapes with less computational complexity.

WVU legal expert finds judges cautiously adopting AI while guarding human authority

New research from West Virginia University finds that judges are adopting generative artificial intelligence in courtrooms, but remain committed to human control over judicial decision-making. Judges use AI for administrative tasks like document summarization and case organization, but prioritize legal reasoning and final judgment.

Mining the sky: A review maps key technologies for small-body sampling robots

Small-body sampling robots rely on sampling, mobility, and anchoring technologies to interact with weak-gravity surfaces. The review summarizes the development of these technologies and discusses their interaction in real mission scenarios.

Aquatic robot to monitor species, advance hydropower

The eDNA-bot revolutionizes biological monitoring by providing comprehensive results at lower cost than conventional surveying methods. It can detect elusive species and monitor wastewater for pathogens, streamlining environmental assessments in hydropower licensing.

Ultralight mesoscale carbon fiber lattices achieve aluminum-level performance at up to 1/100 the weight

Researchers developed a new class of ultralight structural materials with 3D node winding, achieving compressive strengths comparable to concrete and up to ten times stronger than conventional lattice structures at equal weight. The approach enables continuous load paths, reducing inactive material and improving system-level performance.

What it will take to make AI-enabled robots safer

Researchers emphasize the need for more thorough frameworks to ensure AI-enabled robots embody human values. The field should focus on three complementary lines of defense: rules that shape robot decisions, checks that monitor behavior, and safety reasoning.

Handle with care: Mobile microgrippers pick up cells in a pinch

Researchers designed a force-sensing miniature robot to handle delicate cell spheroids with precision. The mobile microgripper uses magnets for controlled movement and gentle gripping, allowing successful assembly of spheroids into patterns.

With a swipe of a magnet, microscopic “magno-bots” perform complex maneuvers

Engineers at MIT and their collaborators create a new type of soft magnetic hydrogel that can be made into complex, magnetically activated three-dimensional structures. The new gel enables the creation of microscopic, magnetically responsive robots and materials with micron-scale precision.

Tiny, knotted robots jump, fly and plant seeds

Researchers at the University of Pennsylvania have designed a tiny robot that uses a knotted fiber to store energy, which is released when heated. The robot can leap meters into the air, flip mid-flight, and even plant seeds with high local pressure.

Artificial intelligence is reshaping environmental science into a predictive and precision-driven discipline

Emerging AI technologies are enabling faster, smarter, and more integrated solutions to global challenges. AI-powered systems can track pollution levels, detect anomalies, and predict future risks in water, soil, air, and waste systems.

Smarter than slithering only: AI boosts snakebot movement efficiency

Researchers at Osaka Metropolitan University developed a new AI-powered snake-like robot that optimizes its movement using deep reinforcement learning. The robot's 'rolling motion' achieves twice the travel speed per unit of power consumption compared to traditional slithering motion, making it more efficient on flat surfaces.

Language-model-guided robotic boxes advance perovskite solar cell discovery

Researchers developed a language-model-guided robotic system for perovskite solar cell research, accelerating device fabrication and characterization. The system achieved a record-breaking power conversion efficiency of 27.0% and generated over 578 million tokens for recipe optimization.

Too many cooks, or too many robots?

The study, led by Lucy Liu and L. Mahadevan, shows that adding the right amount of noise to individual robot movements can ease gridlock and improve efficiency in crowded environments. The researchers used computer simulations and experiments with small robots to test their ideas.

No motors? No gears? No problem.

Soft robots could work as medical implants, deliver drugs inside the body, and explore dangerous environments. The researchers designed a reconfigurable robot that can move repeatedly without degradation, using targeted heating to control motion and embedded temperature sensors for closed-loop control.

These AI-powered guide dogs don’t just lead – they talk

Researchers at Binghamton University have created a talking robot guide dog system that determines ideal routes and guides visually impaired users safely to their destinations. The system offers real-time verbal feedback and provides situational awareness, significantly enhancing the user experience.

Watering smarter, not more

A new system can map soil moisture tree by tree, allowing growers to water specific trees if they're dry. Maintaining the right moisture level is crucial for plant health, as too little water can stress trees, while too much water can deprive roots of oxygen.

MirrorBot: Fostering human connection

A study by Cornell University researchers found that MirrorBot, a mirror-equipped robot, can spur conversations and playful exchanges between strangers. The device facilitates eye contact, which is the first step in forming social connections.

A smarter way to move in tight spaces using ‘flexible’ robots

IITGN researchers develop a novel control framework for flexible continuum robots, called virtual actuation space (VAS), to improve their precision and scalability. VAS reduces the complexity of controlling multi-section robots by using just two parameters: direction and magnitude.

HEAPGrasp: A faster, smarter way for robots to handle tricky objects using only RGB camera

HeapGrasp uses RGB images to analyze object silhouettes and estimate its 3D shape, reducing the need for depth information. The approach achieves high accuracy while minimizing camera movement and execution time.

Snail inspired soft robots to transform precision drug delivery in bowel cancer

Researchers are developing snail-inspired soft robots to deliver targeted therapy directly to tumor sites in bowel cancer patients. The robots aim to increase drug bioavailability and reduce off-target toxicity., Transforming colorectal cancer treatment by enabling precise drug release at tumour sites.

Bats inspire advance in aerial robots

Researchers at Worcester Polytechnic Institute developed a palm-sized aerial robot that uses ultrasound sensors and AI to navigate through fog, smoke, and other difficult conditions. The drone achieved a success rate of 72% to 100% in navigating challenging courses during 180 tests.

Wristband enables wearers to control a robotic hand with their own movements

Researchers at MIT have developed an ultrasound wristband that precisely tracks hand movements, allowing users to control a robotic hand or manipulate virtual objects. The device produces high-quality images of the wrist's muscles and tendons, which are then translated into specific hand positions, enabling precise movement control.

Radiation-resistant Wi-Fi chip could enable wireless robots for nuclear decommissioning

Researchers developed a 2.4 GHz wireless receiver chip that can withstand up to 500 kGy of radiation, enabling wireless control of robots in ultra-high-radiation environments. The chip's design reduces charge trapping and increases stability under high radiation exposure.

New AI models could slash energy use while dramatically improving performance

Researchers at Tufts University developed a proof-of-concept for efficient AI systems using neuro-symbolic AI, reducing power consumption by 100 times while providing accurate results. The approach uses symbolic reasoning to limit trial and error during learning, leading to faster completion and significant energy savings.

Can DNA be used to build robots?

Scientists create functional machines using DNA, adapting macro-scale robotics principles for nanoscale performance. Control strategies use biochemical methods and physical stimuli to direct movement.

How Chicago robot tutors are teaching SEL effectively–without pretending to be human

Researchers tested robots with factual and fictional dialogue on SEL lessons, finding that the factual robots encouraged deeper engagement and improved mastery. The study challenges conventional wisdom on robot design for education, suggesting that robots can be powerful supplements to human teaching.

Generative AI improves a wireless vision system that sees through obstructions

Researchers at MIT have developed a new technique using generative artificial intelligence models to overcome the precision bottleneck in wireless vision systems. The method produces more accurate shape reconstructions, which could improve robots' ability to grasp and manipulate objects blocked from view.

Toward autonomous self-organizing biological robots with a nervous system

In a breakthrough study, researchers successfully integrated neuronal precursor cells into biobots, resulting in the formation of functional nervous systems. This development has significant implications for neuroscience, bioengineering, and regenerative medicine, enabling the investigation of fundamental questions about the origin of ...

Position transmission control in tendon-sheath mechanisms: A critical review and a promising solution

Scientists develop a simpler route-sensing signal to support accurate control in tendon-sheath mechanisms, opening doors to more compact and adaptable robotic systems. They found that friction-induced elongation is governed by the accumulated curve angle, enabling a comprehensive feedforward control framework.

What can dogs tell us about how robots can locate objects? Gestures may be as important as words

Researchers at Brown University develop a way for robots to use inputs from both human language and gesture to reason about object location. The approach, which incorporates insights from dog behavior, achieved an 89% success rate in finding the correct object in complex environments, outperforming other methods.

Chinese Neurosurgical Journal reports faster robot-assisted brain angiography

A Chinese study reports a 100% technical and clinical success rate for robot-assisted brain angiography, with median procedure times 11 minutes shorter than manual angiography. No added radiation or complications were observed, showcasing the feasibility and safety of the YDHB-NS01 system

A folding magnetic soft sheet robot: Enabling precise targeted drug delivery via real-time reconfigurable magnetization

Researchers developed a novel magnetorheological fluid-based soft robot with reversible t robot with reversible for precise targeting of gastrointestinal tract diseases. The robot demonstrated stable flip, steering, and folding motions, as well as reliable movement performance under load, and successfully attached to the drug release p...

A better method for planning complex visual tasks

MIT researchers developed a generative AI-driven approach for planning long-term visual tasks, surpassing existing techniques with a 70% success rate. The system combines vision-language models with formal planners, enabling robots to navigate complex environments and assemble multi-robot teams with high efficiency.

Advancing brain–computer interfaces for rehabilitation and assistive technologies

A novel AI-based framework, EDGCN, decodes dynamic variations in EEG patterns for better brain-computer interface technology. The model outperforms current state-of-the-art methods with high classification accuracies and decoding accuracy, enabling more seamless communication between the human brain and machines.

Press program now available for the world's largest physics meeting

The Global Physics Summit will feature over 12,000 individual presentations on new research in astrophysics, particle physics, and quantum information science. Registered journalists and public information officers will receive daily emails with information during the meeting.

Dual-coil magnetic guidewire robot: a new smooth steering solution for vascular interventional navigation

The dual-coil magnetic guidewire robot offers improved steering capabilities, switching between three modes for better curvature control and branch entry. The robot's design and control enable safer and more consistent procedures by reducing unintended vessel-wall interaction and enhancing access to small, tortuous, and branching targets.

New robotic microfluidic platform brings ai to lipid nanoparticle design

Engineers at the University of Pennsylvania have developed LIBRIS, an automated microfluidic platform capable of generating lipid nanoparticle formulations at high speed and scale. This enables the creation of large, systematic datasets needed to train predictive AI models, accelerating the design of lipid nanoparticles for mRNA delivery.

New ultra-low-cost technique could slash the price of soft robotics

Researchers at Oxford University developed an ultra-low-cost technique for manufacturing soft robots, using common lab equipment. The new method enables rapid and affordable production of soft robotic actuators, with a material cost of less than $0.10 per unit, and demonstrated strong mechanical performance and durability.

NASA robot’s 10-year mission complete as uni marks rare feat

Researchers have advanced humanoid robot control, motion planning, and perception using Valkyrie, a 10-year mission robot developed by NASA. The university will continue research with Talos, a 1.75-metre-tall robot, to study human-robot cooperation and adapt to changing environments.

Evolved robots are born to run and refuse to die

Researchers at Northwestern University have developed AI-designed robots called 'legged metamachines' that can combine and recombine in the wild, recover from injury and transform into new shapes. The robots can adapt to the environment, survive catastrophic damage and even recover from being chopped in half or cut into pieces.

Listening to the body’s quietest, yet most dynamic movements

Researchers developed a wearable vibration sensor capable of detecting subtle body movements without external power, opening new possibilities for healthcare technologies. The sensor accurately captures physiological signals and detects extremely faint vibrations across a broad frequency range.

FAU lands $4.5M US Air Force T-1A Jayhawk flight simulator

Florida Atlantic University has received a $4.5 million grant from the US Air Force to establish a high-fidelity platform for autonomous decision-making and real-time sensor fusion research. The T-1A Jayhawk simulator will be used to study cognitive performance, situational awareness, stress and decision-making under pressure.

‘Mesoscale’ swimmers could pave way for drug delivery robots inside the body

Researchers at Aalto University have discovered how tiny organisms break the laws of physics to swim faster, offering new pathways for engineering and medicine. The team found that non-reciprocal motion, known as time reversal symmetry breaking, is key to efficient swimming in the mesoscale realm.

Simulated cats and elephants with touch-based memory help usher in new age of robotics

Researchers at King's College London develop SimTac platform to simulate biologically inspired robotics, creating artificial sensors with a human-like sense of touch. This approach reduces the design and training time of tactile robots from 18 months to just two weeks.

Not either, but both: making a highly precise and highly mobile precision positioning robot

Researchers from Yokohama National University created a highly precise mobile robot with a wide range of motion using piezoelectric actuators, achieving path errors of under 0.5-4.75 µm. The robot's performance demonstrated its suitability for precise positioning and wide transportation of objects of various sizes.

Latest research in the fields of robotics, biomimetics, artificial intelligence, and the innovative integration of them.

Recent advances in robotics, biomimetics, artificial intelligence, and their innovative integration are reviewed. The article highlights key findings in human-robot object handover, aquatic unmanned aerial vehicles, variable stiffness methods for flexible robots, and more.

Robotic wing inspired by nature delivers leap in underwater stability

Researchers created a robotic wing that senses and adapts to water flow, achieving double the stability of a barn owl's glide. The wing consumes five times less energy than traditional AUVs, paving the way for more agile and efficient underwater robots.

Magnetic microrobot swarms enable contactless manipulation of objects through fluidic torque

Researchers demonstrated a breakthrough in microrobotics: swarms of magnetic microrobots can manipulate objects without physical contact by harnessing fluid-generated torque. The microrobots act as motors to move millimeter-sized passive objects, opening new pathways for precision manufacturing and biomedical applications.

MambaAlign fusion framework for detecting defects missed by inspection systems

Researchers developed an efficient system to detect subtle defects missed by existing inspection systems. The MambaAlign framework captures long-range and orientation-aware context using state-space refinement, achieving improved localization and detection accuracy without excessive computational overhead.

Rise of the rice robots – creating active smart materials

A new material composed of rice grains can bend, buckle, or stiffen differently under slow movements versus sudden impacts without electronics or sensors. This innovative material has potential applications in soft robotics, creating machines lighter, safer, and more adaptable.

Ionogel actuators: a review

This review constructs a tripartite analytical framework for ionogel actuators, covering material construction, actuation mechanisms, and system integration. It presents a function-oriented classification of materials and evaluates the applicability of seven distinct actuation modes.

Max Planck spin-off draws Epic Games to Tübingen

Epic Games has acquired Meshcapade, a Max Planck startup that develops solutions for creating and animating digital humans. The technology, based on the SMPL body model, enables realistic human movement and expression in 3D.

3D printing soft robots

Researchers at Harvard's John A. Paulson School of Engineering and Applied Sciences have developed a new fabrication method for printing robotic devices with long filaments featuring precisely placed hollow channels. This allows the device to bend and deform in predetermined ways, enabling the creation of soft robots with predictable s...

A more accurate measure of calories burned

A new machine learning model interprets leg motion as expended energy, providing a more accurate measure of calories burned. The device has been shown to have double the accuracy of commercial smartwatches and activity trackers.

How can you rescue a “kidnapped” robot? A new AI system helps the robot regain its sense of location in dynamic, ever-changing environments

A hierarchical 3D LiDAR localization method improves robot positioning in large outdoor spaces even after seasonal changes. The method integrates deep learning techniques to extract discriminative local features from 3D point clouds, making it robust to environmental variability.

Personal perception of body movement changes when using robotic prosthetics

Researchers found that participants initially overestimated the awkwardness of their gait but improved as they practiced using the prosthetic device. Despite significant performance gains, participants remained inaccurate in assessing their own body movement, focusing on torso position rather than prosthetic behavior.