Researchers developed soft robots inspired by manta rays, utilizing magnetic fields to move, recharge power supply, and perform tasks autonomously. The magnets stabilize electrochemical reactions in flexible batteries, enhancing performance and efficiency.
The UBC robotic platform helps scientists understand how the brain keeps us standing by mimicking delays in sensory feedback. By tweaking forces and adding short delays, the robot reveals that our sense of space and time work from the same playbook.
In a study by SWPS University, researchers found that children interact with polite robots almost always respond politely. Younger children and girls are more likely to anthropomorphise the robot, suggesting social cues in interactions between children and robots are crucial for positive learning outcomes.
Researchers develop soft fiber-like pumps powered by ambient energy to drive the next generation of robots and wearable devices. The innovation enables robots that operate autonomously and wearable devices that provide comfort without cumbersome batteries.
Researchers developed a new robot self-modeling approach using part-based Neural Radiance Fields, eliminating the need for depth sensors and human annotation. The system enables robots to build dynamic 3D models of themselves, accelerating the deployment of autonomous machines in unpredictable environments.
A new survey provides a three-module framework for Embodied AI, addressing perception, decision-making and execution. The goal is to develop general-purpose intelligent agents that can perform complex tasks like cleaning the room.
Researchers developed a 3D lattice iontronic sensor that accurately detects sophisticated tactile interactions by linearizing both electrical responses and mechanical behaviors. The sensor, comprising a hydrogel lattice encapsulated in an origami-inspired framework, enables precise detection under extreme dynamic loading.
The new statistical method adapts to data structure, resisting outliers and providing greater stability on non-Euclidean spaces. This improves the reliability of analysis in areas like medical imaging, computer vision, and machine learning.
Researchers at ETH Zurich developed microrobots that can navigate blood vessels with precision, delivering drugs directly to the target location. The robots use magnetic nanoparticles and advanced navigation systems to avoid obstacles and reach their destination.
The researchers developed a chromatic filtration strategy to narrow the emission spectrum of mechanoluminescent materials, resulting in high spectral resolution and reduced noise. The new technology has significant potential for applications such as wearable sensors and healthcare motion monitoring.
Oxford researchers have developed soft robots that operate without electronics, motors, or computers, using only air pressure to generate complex, rhythmic movements. The robots can automatically synchronize their actions and perform tasks like sorting beads into containers without external control.
The University of Houston is designing robotic hands with dexterity for industries such as healthcare, agriculture, and manufacturing. The team, part of the NSF Convergence Accelerator program, has received $5 million in funding to develop hybrid polymeric materials that can mechanically retract and perform motions like flexion.
Researchers explore Field-assisted Additive Manufacturing for micro/nano device fabrication, enabling targeted motion, cell growth, and flexible electronics. The technology holds promise for industries such as biomedical engineering and microrobotics.
The Omnia bionic leg, developed by the Italian Institute of Technology, won the Cybathlon 2024 leg prosthesis race with its semipowered knee and ankle system. Andrea Modica, a transfemoral amputee and pilot of the device, successfully completed 9 out of 10 tasks in just 2 minutes and 57 seconds.
Researchers have developed a new class of artificial muscles that respond to ultrasound, enabling precise movements and wireless control. The technology has vast potential for future medical and technical applications, including drug delivery, cardiac patches, and minimally invasive procedures.
Scientists develop molecular strategies for creating soft materials that can sense, move, and evolve in response to their environment. Three key principles of supramolecular robotics enable programmed motility, phase transitions, and prototissue formation.
A team of biomechanical engineers and surgeons has developed a 3D-printing soft robot that can accurately deliver hydrogels to the vocal cord surgical site. The device, which is only 2.7 mm in size, can reconstruct tissues removed during surgery and potentially prevent fibrosis and stiffening of the vocal cords.
Scientists have replicated the neural circuitry that allows zebrafish to react to visual stimuli and maintain their position in flowing water. The research, published in Science Robotics, used simulations and robots to study embodiment, or how the body affects perception, in larval zebrafish.
Worcester Polytechnic Institute Professor Nitin Sanket has been awarded a $704,908 NSF grant to develop sound-based navigation systems for small aerial robots. The project aims to enable drones to navigate in environments where cameras and light-based sensors fail.
A team of researchers has developed a tiny, spider-inspired robot that can navigate the digestive system with ease, delivering therapy precisely where it's needed. The soft robot overcomes challenges faced by traditional endoscopes, showcasing its adaptability in traversing complex environments.
Researchers created microscopic DNA 'flowers' that can change shape and behavior in response to their surroundings. These tiny robots, made from special crystals formed by combining DNA and inorganic materials, can perform tasks on their own, from delivering medicine to cleaning up pollution.
The LiteRBS algorithm outperforms classical algorithms like A* and Bidirectional A*, scaling well even in large or dense maps. It achieves fast and memory-efficient pathfinding through an aggressive bidirectional forward search with a reserve-queue fallback strategy.
SourceELSP·JournalRobot Learning·TypeComputational simulation/modeling·DateOct 17, 2025
Researchers develop novel dual-laser method to create adaptive, shape-locking devices. The material integrates a shape-memory polymer skeleton with magnetic microcapsules, allowing for 'writing' and 'bending' of instructions and shapes in situ.
Researchers developed a method to trigger magnetic jamming in materials using wireless magnetic fields, enabling reversible and programmable clumping. This technique allows for the creation of structures that can assemble, stiffen, relax, or break apart under magnetic control.
Researchers developed a soft robotic skin that allows vine robots to navigate convoluted paths and fragile environments. The robot is steered by controlling the pressure inside its body and temperature of the actuators.
A team of engineers at Harvard John A. Paulson School of Engineering and Applied Sciences designed a proof-of-concept walking robot using only four moving parts connected by rubber bands and powered by one motor. The robot can find its way through mazes, avoid obstacles, and sort objects by mass without electronic control systems.
A recent study reveals that the response to witnessing robot mistreatment depends on factors such as the robot's humanlike design and the observer's moral identity. Anthropomorphism influences empathy, encouraging customers to treat robots with dignity, while moral identity plays a crucial role in shaping behavioral contagion.
Researchers at North Carolina State University created a class of robots called metabots that can change shape and adapt to different environments. The devices can execute various actions despite having no motor or being made of a single flat material.
A recent study published in PLOS Biology found that combining non-invasive brain stimulation and robotic rehabilitation can significantly improve motor recovery in a mouse stroke model. The treatment restored parvalbumin interneuron dynamics, leading to better motor function.
Researchers develop autonomous nano-robotic systems that utilize scanning electron microscopy for real-time visual feedback, enabling high-precision manipulation of nano-objects. The integration of machine learning-enhanced vision algorithms and novel actuation techniques facilitates adaptive, perception-driven atomic engineering.
Researchers developed a new control algorithm that enables powered knee prostheses to mimic natural human motion, reducing tripping risks and strain on users' bodies. The study showed significant improvements in activities of daily living, such as sitting, standing, walking, and climbing stairs.
A study by Osaka Metropolitan University found that pairs outperformed individuals in a robotic arm-transporting task when roles naturally emerged. Role specialization was key to superior performance, rather than paired interaction. The research has implications for human-robot collaboration and rehabilitation settings.
MIT researchers developed a new framework that helps engineers design complex systems explicitly accounting for uncertainty. The framework allows them to model the performance tradeoffs of a device with many interconnected parts, each of which could behave in unpredictable ways. This approach can help engineers develop complex systems ...
A groundbreaking soft robot has been engineered to perceive and respond to multiple environmental cues simultaneously. Weighing just 8 milligrams, it can carry a payload 2.5 times its own body weight over complex terrain, showcasing impressive agility and strength.
The SRI model integrates swarm dynamics with dynamic graph neural networks, resolving existing method pitfalls. It demonstrates significant performance improvements over traditional methods, with reduced long-term prediction errors.
A novel detection framework, SORA-DET, is introduced for UAV remote sensing, achieving high accuracy and efficiency while being compact and fast. It outperforms large-scale models with up to 88.1% fewer parameters.
Researchers developed a platform called CRESt that incorporates insights from literature, chemical compositions, and imaging to optimize materials recipes. CRESt uses robotic equipment for high-throughput testing and large multimodal models to further optimize materials recipes.
The Leopoldina Annual Assembly focuses on the current developments and potential uses of artificial intelligence in various fields, including medicine, geosciences, and physics. The event features keynote lectures, panel discussions, and an award ceremony to recognize outstanding researchers in AI.
Researchers at CARS create detailed maps of chemical reactivity, discovering regions of unexpected outcomes and reconstructing intricate reaction networks. This new understanding enables control over the formation of different major products from a set of starting materials.
The International Telecommunication Union (ITU) has launched an initiative to bring artificial intelligence and robotics training to students across Africa. The programme combines hands-on AI and robotics training for young people in underserved communities, with a focus on reaching girls and other underrepresented groups.
Frasky, developed by IIT, combines robotics and AI to address environmental sustainability and labor shortages in agriculture. The robot can navigate autonomously, map its surroundings, and apply selective treatments to grape clusters with precision.
Researchers cataloged octopus arm movements in six different locations, revealing diverse behaviors such as foraging and locomotion. The study provides insights into the complex motions of octopus arms, which are guided by sensory organs and can perform a variety of tasks, including manipulating objects.
Aniket Pal's team creates viscoelastic polymers for soft robotics, which exhibit both elastic and viscous properties. These materials can be used to make soft robots more functional and intelligent.
The Wits MIND Institute has received a $1 million boost from Google.org, enabling it to drive next-generation breakthroughs in natural and artificial intelligence. The partnership aims to advance the scientific understanding of both natural and artificial intelligence, foster breakthrough research and technological innovation.
Researchers created a new approach that integrates visual and tactile information to manipulate robotic arms, outperforming conventional vision-based methods. This breakthrough represents a significant advancement in multimodal physical AI.
Researchers at the University of Minnesota developed AI-guided aerial robots to detect, track and analyze wildfire smoke plumes. The technology provides high-resolution data collection across large areas at a lower cost than satellite-based tools, enabling more accurate computer models for air quality predictions.
A flexible skin-mounted haptic interface can replicate diverse motions using a single actuator, providing rich tactile feedback and versatility. The technology aims to assist humans in various applications, including wearable human-machine interfaces and medical operations.
Researchers developed a hybrid kiri-origami structure to overcome the trade-off between flexibility and function in stretchable electronics. The design features a mutual orthogonal cutting line pattern, allowing simultaneous mounting of rigid components and stretching.
Researchers at Pusan National University have developed a novel, multi-resin dispensing process for fiber-reinforced polymer fabrication, enabling precise patterning of mechanical properties within a monolithic structure. The breakthrough composite material combines flexibility and strength for advanced robotic applications.
The Seoul National University of Science and Technology has developed a novel 3D AMM-based tactile sensing platform that offers high-performance pressure sensing. The technology leverages auxetic metamaterials to enhance sensitivity, stability, and scalability.
Researchers developed AI models that can identify signs of heart failure in patients from Appalachia using low-tech electrocardiogram results. The models achieved high accuracy and could potentially provide clinicians with an edge in protecting patients' cardiac health.
Researchers developed algorithms that enable robots to create the best possible outcomes from their actions while minimizing uncertainty and risk. The new strategies allow robots to anticipate human actions, adapt to different scenarios, and prioritize human safety.
Researchers at the University of Michigan created woven metamaterials that return to their original shape after repeated compressions, while continuous sheets permanently deform. The structures demonstrated high stiffness and resilience, making them suitable for applications like soft robotics, car parts and architectural components.
Vasile's research aims to map and model an agent's capabilities, particularly in motion, manipulation, and perception, to reliably predict their behavior. The goal is to use this understanding to plan effectively for large teams of agents.
Researchers at North Carolina State University unveiled Rainbow, a self-driving laboratory that autonomously discovers high-performance quantum dots. The system combines advanced robotics and AI to conduct up to 1,000 experiments per day, accelerating materials discovery.
Researchers developed ProTac, a novel vision-based soft sensing skin for robots, enabling real-time environmental perception and dual-mode sensing. The system can detect approaching objects from multiple angles and recognize multiple touch points with high accuracy.
Research finds that fish use twice as much energy while staying still due to instability caused by their swim bladder. This has significant implications for the design of miniature aquatic robots.
A wearable robot has been upgraded to provide personalized assistance to ALS and stroke patients. The device uses machine learning and a physics-based model to adapt to an individual user's movements, offering more nuanced help with daily tasks.
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...
A team of researchers has developed a way to harness the swimming abilities of moon jellyfish, enabling them to steer the animals toward remote ocean areas. The cyborg jellies have the potential to aid in deep-sea research and provide inspiration for next-gen underwater vehicles with improved energy efficiency.