Articles tagged with "soft-robotics"
US' new robots can snap into hundreds of shapes, work on tough terrains
Researchers at North Carolina State University have developed a new class of flat, motorless robots called "metabots," made from thin polymer sheets with patterned cutouts and coated with responsive thin films. These films act as actuators that respond to electrical or magnetic stimuli, enabling the sheets to snap into hundreds of stable shapes and execute diverse movements such as jumping, crawling, rotating, and grasping. By connecting multiple sheets, the metabots can fold into numerous configurations—up to 256 stable states with four connected units—allowing them to adapt their shape and gait to navigate complex terrains or perform various functions. The metabots leverage multistable thin-shell metastructures that store elastic energy and incorporate piezoelectric materials for controlled vibrations, enhancing their maneuverability and adaptability. This design enables energy-efficient, reconfigurable soft robotic platforms capable of operating in confined environments and performing tasks like noninvasive gripping and multi-gait locomotion. Although still at an early proof-of-concept stage, the
robotsoft-roboticsmetamaterialsadaptive-robotsshape-shifting-robotspiezoelectric-materialsmultistable-structuresVenom-inspired soft robot shapeshifts, stretches, and swings with ease
Researchers at the University of Bristol and Queen Mary University of London have developed a groundbreaking soft robot inspired by the comic book character Venom, capable of shapeshifting, stretching, and swinging with remarkable agility. This robot is powered by an innovative electro-morphing gel (e-MG), a soft polymer composite embedded with nanocrystalline conductors that respond to electric fields. When voltage is applied via ultralight electrodes, the gel can rapidly bend, stretch, or contract, enabling lifelike, multidirectional movements without the need for bulky external magnets or mechanical parts. The robot demonstrated exceptional endurance, maintaining consistent performance over 10,000 actuation cycles, and performed complex deformations beyond the capabilities of existing soft robots. The versatility of the e-MG technology opens up diverse applications across industries such as medical wearables, rescue operations, and space exploration. Its geometry can be customized for specific tasks, and it can be integrated with rigid robotic components to form hybrid machines capable of operating in high-st
soft-roboticselectro-morphing-gelshape-shifting-robotelectroactive-materialsflexible-roboticspolymer-compositerobotic-actuationVine-inspired soft robot grows its way through arteries, jet engines
Researchers at the University of California San Diego have developed a novel soft robotic vine equipped with a thin liquid crystal elastomer (LCE) skin that enables it to navigate extremely tight and delicate environments, such as human arteries and jet engine interiors. This vine-like robot, only a few millimeters wide, grows from its tip by everting its skin, allowing it to advance without dragging against surfaces. By integrating tiny, flexible heaters beneath the LCE actuators and precisely controlling internal pressure and temperature, the robot can be steered through complex paths, making multiple sharp turns and squeezing through gaps half its diameter. The technology has promising applications in minimally invasive medical procedures, such as navigating blood vessels, and in industrial inspections, exemplified by the robot’s successful maneuvering inside a jet engine model equipped with a miniature camera. Beyond these uses, the soft skin design could be adapted for wearable haptic devices, soft grippers, and other soft robotic systems. Future developments aim to make the robot remote-controlled or
robotsoft-roboticsliquid-crystal-elastomermedical-roboticsflexible-actuatorsrobotic-inspectionUC-San-DiegoWhat’s coming up at #IROS2025? - Robohub
The 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025) will take place from October 19 to 25 in Hangzhou, China. The event features a comprehensive program including plenary and keynote talks, workshops, tutorials, forums, competitions, and a debate. The three plenary talks scheduled for October 21-23 will cover topics such as humanoid and quadruped mobility in real-world applications (Marco Hutter), autonomous aerial manipulation for physically intelligent flying robots (Hyoun Jin Kim), and the integration of physical robots with artificial general intelligence agents (Song-Chun Zhu). Keynote presentations are organized under eleven thematic areas, highlighting cutting-edge research and developments in robotics. These areas include Rehabilitation & Physically Assistive Systems, Bio-inspired Robotics, Soft Robotics, AI and Robot Learning, Perception and Sensors, Human-Robot Interaction, Embodied Intelligence, Medical Robots, and Field Robotics. Notable topics include advancements in legged robots and
roboticssoft-roboticsAIhumanoid-robotswearable-robotsrobot-learningautonomous-systemsTiny robot muscle lifts 4,000 times its weight in lab breakthrough
Researchers at the Ulsan National Institute of Science and Technology (UNIST) in South Korea have developed a novel artificial muscle that can transition between soft and flexible to rigid and strong states, overcoming a major limitation in soft robotics. This tiny muscle, weighing just 1.25 grams, can stiffen under heavy loads to provide structural support and then soften to allow contraction and flexibility. Its core innovation lies in a dual cross-linked polymer network combining covalent bonds for strength and thermally responsive physical interactions for flexibility, along with embedded surface-treated magnetic microparticles that enable precise control via external magnetic fields. The artificial muscle can lift up to 5 kilograms—about 4,000 times its own weight—and stretch up to 12 times its original length when softened. It achieves an exceptional strain of 86.4% during contraction, more than double that of human muscles, and a work density of 1,150 kJ/m³, which is 30 times higher than human tissue. This
roboticsartificial-musclessoft-roboticsmaterials-sciencepolymer-networksmagnetic-actuationwearable-devicesRobot Talk Episode 128 – Making microrobots move, with Ali K. Hoshiar - Robohub
In the Robot Talk Episode 128, Claire interviews Ali K. Hoshiar, a Senior Lecturer in Robotics at the University of Essex and Director of the Robotics for Under Millimetre Innovation (RUMI) Lab. Hoshiar discusses the mechanisms behind microrobot movement and their collaborative behaviors. His research spans microrobotics, soft robotics, and data-driven mechatronic systems, with applications in medical and agricultural technologies. He leads the EPSRC-funded ‘In-Target’ project and has been recognized with the university’s Best Interdisciplinary Research Award. The episode highlights Hoshiar’s interdisciplinary approach, combining technical expertise with strategic and commercial insights, supported by his MBA. The discussion sheds light on the challenges and innovations in making microrobots move effectively and work together, emphasizing their potential impact in various fields. Robot Talk continues to explore advancements in robotics, AI, and autonomous machines through such expert conversations.
robotmicrorobotssoft-roboticsmechatronicsmedical-roboticsagri-tech-roboticsautonomous-machinesRethinking how robots move: Light and AI drive precise motion in soft robotic arm - Robohub
Researchers at Rice University have developed a novel soft robotic arm that can perform complex tasks such as navigating obstacles or hitting a ball, controlled remotely by laser beams without any onboard electronics or wiring. The arm is made from azobenzene liquid crystal elastomer, a polymer that responds to light by shrinking under blue laser illumination and relaxing in the dark, enabling rapid and reversible shape changes. This material’s fast relaxation time and responsiveness to safer, longer wavelengths of light allow real-time, reconfigurable control, a significant improvement over previous light-sensitive materials that required harmful UV light or slow reset times. The robotic system integrates a spatial light modulator to split a single laser into multiple adjustable beamlets, each targeting different parts of the arm to induce bending or contraction with high precision, akin to the flexible tentacles of an octopus. A neural network was trained to predict the necessary light patterns to achieve specific movements, simplifying the control of the arm and enabling virtually infinite degrees of freedom beyond traditional robots with fixed joints
roboticssoft-roboticssmart-materialsAI-controllight-responsive-materialsmachine-learningazobenzene-elastomerNew soft robot navigates land and water with 3 advanced senses
Chinese researchers from Guangdong University of Technology and Guangdong Polytechnic Normal University have developed an innovative 8-milligram soft robot inspired by ants and whirligig beetles that can navigate both land and water. Unlike most existing soft robots that respond to a single environmental trigger and operate in only one environment, this new robot integrates three advanced sensory responses—temperature, humidity, and magnetic fields—through a multi-layered composite film acting as an artificial muscle. This design overcomes previous challenges of signal interference by keeping the robot’s different responses separate, enabling coherent adaptation across dynamic boundaries between water and land. The robot’s structure consists of a triple-layer “sandwich”: a polyimide film chemically modified to be sensitive to temperature and humidity, bonded to a silicone rubber layer embedded with magnetic particles. It achieves speeds up to 9.6 cm/s on water, comparable to actual whirligig beetles, and uses a strong rolling gait controlled by rotating magnetic fields to traverse various terrains, including slopes
soft-roboticsamphibious-robotsartificial-musclemagnetic-sensorsenvironmental-sensingbiomimicryrobot-swarmsScientists craft strider-like robots that paddle and walk on water
Researchers at the University of Virginia have developed two insect-inspired soft robots, HydroFlexor and HydroBuckler, that can paddle and walk on water surfaces by mimicking the motions of aquatic insects like water striders. These tiny robots are powered by an overhead infrared heater that causes their layered polymer films to bend and move in response to heat, enabling controlled, repeatable motion including speed adjustment and directional changes. This breakthrough demonstrates the potential for miniature robots to perform tasks such as scouting flooded areas, monitoring pollutants, or collecting samples in environments challenging for humans. A key innovation enabling these robots is a novel fabrication technique called HydroSpread, pioneered by Professor Baoxing Xu. Unlike traditional methods that require transferring delicate films from rigid surfaces, HydroSpread allows ultrathin polymer films to be formed directly on water, providing a perfectly smooth platform and significantly reducing failure rates. This method enhances precision and yield, allowing for more complex and delicate designs in soft robotics. Beyond robotics, HydroSpread holds promise for producing thin,
robotsoft-roboticspolymer-filmsHydroSpreadinsect-inspired-robotsflexible-electronicswearable-sensorsTechnology behind ghostly water-powered humanoid robot revealed
Clone Robotics, a Polish startup founded in 2021, is pioneering lifelike humanoid robots powered by innovative synthetic muscle technology. Unlike traditional rigid, motor-driven robots, Clone’s androids use water-powered fluidic muscles based on the McKibben design—pressurized tubes that contract like human muscles when filled with fluid. This hydraulic system, driven by a compact pump dubbed the “hydraulic heart,” enables natural, versatile movements by mimicking human musculoskeletal structures such as tendons and ligaments. The company began by developing a robotic hand with high degrees of freedom, then expanded to a full-body prototype within a year, leveraging anatomical layouts to simplify design. In February 2025, Clone Robotics unveiled Protoclone V1, a synthetic human prototype featuring over 200 degrees of freedom, 1,000 artificial muscle fibers (Myofibers), and 500 sensors, closely replicating human anatomy. Later that year, they launched their first full-scale humanoid robot and are
roboticshumanoid-robotartificial-musclesfluidic-musclessoft-roboticshydraulic-systemandroid-technologyNew gel that stretches 4600%, heals itself can be used in robotics
Researchers in Taiwan have developed an innovative stretchable, self-healing gel that changes color under mechanical stress or temperature variations, potentially transforming wearable technology and soft robotics. This gel combines exceptional elasticity—able to stretch up to 4600% of its original length—with toughness and self-repair capabilities, addressing a common trade-off in soft materials that typically sacrifice either durability, healing, or sensing functions. The key to this breakthrough lies in the gel’s molecular design, which incorporates mechanically interlocked rotaxane molecules arranged in daisy chains, enabling spring-like expansion and contraction. These molecules are chemically bonded within a polyurethane gel reinforced by cellulose nanocrystals, which facilitate self-healing through reversible hydrogen bonds. A special fluorescent unit called DPAC is attached to the rotaxanes, shifting its glow from orange to blue when the gel is stretched or cooled, thus providing a visible indication of stress distribution and temperature changes. This dual-sensing capability allows the gel to act as both a structural material and a built
materialsself-healing-gelsoft-roboticswearable-technologystretchable-materialssmart-materialsmolecular-designSoft robotic intubation device enables 87% first-pass success rate
Researchers at UC Santa Barbara have developed a novel soft robotic intubation system (SRIS) that significantly improves the success rate and speed of endotracheal intubation, a critical procedure to maintain an open airway. Unlike traditional rigid laryngoscopes that require lifting the epiglottis and pushing a stiff tube into the trachea, the SRIS uses a soft, inflatable tube that everts and grows forward along the natural airway pathway, reducing tissue injury and friction. This innovative design allows the tube to automatically curve into the trachea, accommodating anatomical variations without the need for forceful manipulation. Testing on mannequins and cadavers demonstrated that expert users achieved a 100% success rate, while emergency responders such as EMTs and paramedics reached a 96% overall success after just five minutes of training. Non-experts attained an 87% first-pass success rate, placing the tube in an average of 21 seconds—less than half the time required by current
roboticssoft-roboticsmedical-deviceshealthcare-technologyemergency-medicinerobotic-intubationmedical-roboticsLightning-fast chameleon tongues may inspire medical, space tech
Researchers at the University of South Florida, led by postdoctoral researcher Yu Zeng and professor Stephen Deban, have uncovered a shared high-speed tongue-launching mechanism in both chameleons and salamanders. Despite their evolutionary distance and differing habitats, both animals use a similar "ballistic" slingshot-like system composed of ordinary tissues, tendons, and bone to project their tongues at speeds up to 16 feet per second. This discovery, based on over a decade of video analysis, presents a unified mechanical model that explains how these animals achieve rapid tongue strikes using common biological materials. The team highlights the potential for this mechanism to inspire innovative biomedical and industrial technologies. Because the system relies on simple, robust components that can be scaled and recreated with soft or flexible materials, it could lead to devices capable of precise, rapid extension and retraction. Possible applications include medical tools for clearing blood clots, equipment for retrieving objects in disaster zones, and mechanisms for handling debris in space. Future research will
biomimicrymedical-technologyspace-technologysoft-roboticsflexible-materialsengineering-innovationbio-inspired-designSnake-like robot with tentacles set to transform offshore subsea jobs
A new underwater robot with a soft, tentacle-like arm has been developed by the UK’s National Robotarium in collaboration with Brazil’s Senai Cimatec, aiming to revolutionize offshore subsea inspections and maintenance. Measuring 3.3 feet (one meter) long, the robot’s flexible design allows it to bend and conform to complex underwater structures, enhancing safety and efficiency compared to traditional rigid robotic arms. Equipped with sensors to track its shape and position, the robot can perform precise inspection tasks near subsea infrastructure such as wind farms and pipelines, even in turbulent water conditions. Tested successfully in harsh environments at the National Robotarium’s wave tank, the robot demonstrated stability under forces up to 300 g and the ability to quickly regain its position after disturbances. This adaptability makes it suitable for deployment from underwater vehicles, potentially reducing reliance on divers and large vessels, thereby lowering safety risks, costs, and environmental impacts. The project underscores the importance of international collaboration, with both UK and Brazilian teams
robotunderwater-robotsoft-roboticsoffshore-inspectionsubsea-technologyenergy-infrastructurerobotic-tentaclesJapan trials giant robot hand to scoop buried items at quake sites
Researchers from Japan and Switzerland have developed a giant robotic hand integrated with AI-driven excavation technology to enhance disaster recovery efforts, particularly in earthquake-affected areas. The project, named CAFE (Collaborative AI Field Robot Everywhere), is a five-year collaboration involving Kumagai Gumi, Tsukuba University, Nara Institute of Science and Technology, and ETH Zurich, funded by Japan’s Cabinet Office and the Japan Science and Technology Agency. The robotic hand uses pneumatic actuators and fingertip sensors to adapt its grip dynamically, handling both fragile and heavy objects up to 3 tons. Demonstrated in Tsukuba City, it successfully manipulated diverse debris types, showcasing its potential to operate in hazardous, unstable environments inaccessible to traditional heavy machinery. A key challenge addressed by the project is the formation of natural dams caused by landslides, which pose flooding risks to communities. The CAFE system combines the robotic hand with AI excavation software developed through Sim-to-Real reinforcement learning, enabling the machine to learn and adapt
roboticsdisaster-recoveryAIsoft-roboticspneumatic-actuatorsrobotic-handexcavation-technologySoft robot jacket offers support for upper-limb disabilities
Researchers at Harvard John A. Paulson School of Engineering and Applied Sciences, in collaboration with Massachusetts General Hospital and Harvard Medical School, have developed a soft, wearable robotic jacket designed to assist individuals with upper-limb impairments caused by conditions such as stroke and ALS. This device uses a combination of machine learning and a physics-based hysteresis model to personalize movement assistance by accurately detecting the user’s motion intentions through sensors. The integrated real-time controller adjusts the level of support based on the user’s specific movements and kinematic state, enhancing control transparency and practical usability in daily tasks like eating and drinking. In trials involving stroke and ALS patients, the robotic jacket demonstrated a 94.2% accuracy in identifying subtle shoulder movements and reduced the force needed to lower the arm by nearly one-third compared to previous models. It also improved movement quality by increasing range of motion in the shoulder, elbow, and wrist, reducing compensatory trunk movements by up to 25.4%, and enhancing hand-path efficiency by up
soft-roboticswearable-robotsupper-limb-supportassistive-technologymachine-learningrehabilitation-roboticshuman-robot-interactionNew soft 'robot’ may offer pain-free way to treat kidney stones
Researchers at the University of Waterloo, led by Dr. Veronika Magdanz, have developed a novel soft-bodied miniature robot designed to treat kidney stones in a less invasive and potentially pain-free way. The device is a tiny, 1 x 1 x 12 mm filament made from a hydrogel and elastomer blend, embedded with urease enzyme and a small magnet. It is inserted into the bladder via catheter and navigated through the urinary tract using an external robotic arm with a rotating magnet. Once positioned at the kidney stone, the filament releases urease, which raises the pH of the surrounding urine, dissolving the stone and facilitating its natural passage with reduced pain. In laboratory tests using a 3D-printed urinary tract model filled with synthetic urine, the device successfully increased the urine pH from 6 to 7, resulting in about a 30% reduction in stone weight over five days—enough to ease stone passage. The pH elevation effect lasted up
roboticsmedical-roboticssoft-roboticshydrogel-materialskidney-stone-treatmentmagnetic-actuationbiomedical-devicesNew super-thin robot mimics muscle to crawl, twist, and grab objects
Researchers from Samsung Electronics’ Future Robotics Division and Pohang University of Science and Technology (POSTECH) in South Korea have developed an ultra-thin, flexible robotic actuator inspired by human muscle protein myosin. Unlike conventional rigid metal robot parts, this paper-thin actuator incorporates a complex three-dimensional pneumatic network with tiny air chambers and multilayered air pathways. When air is injected, these small forces combine to produce strong, multi-directional movements, enabling the robot to bend, crawl, twist, and handle delicate tasks with precision comparable to human fingers. This bio-inspired actuator’s flexibility and strength allow robots to maneuver through tight spaces and perform delicate operations such as surgery or pipeline cleaning. The technology holds promise for diverse applications including surgical robots, collaborative industrial robots, and exploration devices. The actuator’s ability to move objects underwater and interact delicately with humans suggests future robots could be more responsive and capable in sensitive environments. The research, supported by Korean government agencies, was published in Nature Communications.
roboticssoft-roboticsrobotic-actuatorsbio-inspired-robotssurgical-robotsflexible-robotspneumatic-actuatorsAI robot arm builds meals and helps users with limited mobility
Engineers at Virginia Tech have developed an advanced robotic arm designed to assist people with limited mobility in performing everyday tasks, such as preparing meals. The system features adaptive grippers that combine rigid mechanics with soft, switchable adhesives, enabling the robot to handle a wide range of objects—from heavy items like metal pans to delicate ingredients like sprinkles. This innovation addresses the challenge that traditional robots face when gripping irregular or fragile items, by allowing the grippers to switch between strong adhesion and easy release. The robotic arm is controlled via a joystick-style interface, allowing users to guide the robot’s movements while artificial intelligence interprets and completes the tasks. This collaboration was demonstrated through complex activities like assembling a pizza, which involves handling diverse textures and shapes, and building an ice cream sundae with small, delicate toppings. Funded by over $600,000 from the National Science Foundation, the project aims to enhance independence for people with disabilities by making robotic assistance more intuitive and closely aligned with natural human motions. The research
roboticsassistive-technologyrobotic-armadaptive-grippersAI-controlsoft-roboticsdisability-aidMIT vision system teaches robots to understand their bodies
MIT researchers at CSAIL have developed a novel robotic control system called Neural Jacobian Fields (NJF) that enables robots to learn how their bodies move in response to motor commands purely through visual observation, without relying on embedded sensors or hand-coded models. Using a single camera and random exploratory movements, NJF allows robots—ranging from soft robotic hands to rigid arms and rotating platforms—to autonomously build an internal model of their 3D geometry and control sensitivities. This approach mimics how humans learn to control their limbs by observing and adapting to their own movements, shifting robotics from traditional programming toward teaching robots through experience. NJF’s key innovation lies in decoupling robot control from hardware constraints, enabling designers to create soft, deformable, or irregularly shaped robots without embedding sensors or modifying structures for easier modeling. By leveraging a neural network inspired by neural radiance fields (NeRF), NJF reconstructs the robot’s shape and its response to control inputs solely from visual data. This
roboticsmachine-learningsoft-roboticsrobotic-control-systemsneural-networks3D-printingcomputer-visionNew soft robot arm scrubs toilets and dishes with drill-level force
Researchers at Northeastern University have developed SCCRUB, a novel soft robotic arm designed to tackle tough cleaning tasks with drill-level scrubbing power while maintaining safety around humans. Unlike traditional rigid industrial robots, SCCRUB uses flexible yet strong components called TRUNC cells—torsionally rigid universal couplings—that allow the arm to bend and flex while transmitting torque comparable to a handheld drill. This combination enables the robot to apply significant force to remove stubborn grime without posing risks typical of hard robotic arms. Equipped with a counter-rotating scrubber brush and guided by a deep learning-based controller, SCCRUB can clean challenging messes such as microwaved ketchup and fruit preserves on glass dishes and toilet seats, removing over 99% of residue in lab tests. The counter-rotating brush design helps maintain firm pressure and stability by canceling frictional forces, enhancing cleaning effectiveness while preserving the arm’s soft and safe nature. The research team envisions expanding SCCRUB’s capabilities to assist humans
robotsoft-roboticsrobotic-armmachine-learningautomationcleaning-robothuman-robot-interactionElephant robot mimics muscle and bone with foam lattice design
Engineers at EPFL have developed a groundbreaking programmable foam lattice that combines softness and rigidity to mimic the musculoskeletal system of animals, enabling robots to bend, twist, and bear weight with unprecedented precision. This innovation was demonstrated through an elephant-inspired robot featuring a soft, twisting trunk and jointed limbs with varying stiffness, achieved by using two main types of foam cells—body-centered cubic (BCC) and X-cube—that can be blended continuously across the robot’s structure. This design allows smooth transitions between flexible and rigid areas, similar to how muscles transition into tendons and bones in animals. The programmable foam lattice offers immense configurational flexibility, with millions of possible geometric combinations by rotating, shifting, or superimposing individual foam cells. This capability enabled the creation of diverse joint types in the elephant robot, such as sliding, bending, and biaxial joints, facilitating lifelike movements like trunk twisting and leg articulation. Beyond locomotion, the lattice’s high strength-to-weight ratio and open foam structure
roboticssoft-roboticsprogrammable-foam3D-printingbiomimicrylattice-structuresmusculoskeletal-systemFlying squirrels' scaly tails inspire next-gen bionic robots, drones
Researchers at Empa in Switzerland, in collaboration with the Max Planck Institute in Germany, have studied the unique tail mechanics of African scaly-tailed squirrels to inspire the development of next-generation bionic robots and drones. These squirrels possess thorn-covered scales on the underside of their tails, which provide exceptional grip and stability when clinging to smooth or uneven tree bark. While biologists had long suspected the scales aid in climbing, this study is the first to scientifically test and confirm their role in preventing slipping and enhancing stability. The research team used a combination of analytical models and physical replicas, including 3D-printed artificial squirrels with scaled tails and claws, to experimentally validate how these tail spines contribute to secure perching. Moving forward, the team plans to incorporate dynamic movement into their models to better understand how the scaly tail absorbs impact and stabilizes the squirrels during rapid or emergency landings, such as when evading predators mid-glide. Ultimately, these insights into natural locomotion could inform
robotbionic-robotsdronesbiomimicryrobotics-researchsoft-roboticsenergy-efficient-robotics‘Shocking’ 3D resin may build soft robots with plastic-like strength
Researchers at the University of Texas at Austin have developed an innovative 3D printing technique that uses a custom liquid resin and a dual-light system to create objects combining both soft, rubber-like flexibility and hard, plastic-like strength within a single print. Inspired by natural structures such as human bones and cartilage, this method employs violet light to produce flexible material and ultraviolet light to harden the resin, enabling seamless transitions between soft and rigid zones without weak interfaces. This breakthrough addresses common issues in multi-material printing where different materials often fail at their boundaries. Demonstrations of the technology included printing a functional knee joint with soft ligaments and hard bones that moved smoothly together, as well as a stretchable electronic device with flexible and stiff areas to protect circuitry. The researchers were surprised by the immediate success and the stark contrast in mechanical properties achieved. An adjacent study published in ACS Central Science further highlights the potential of light-driven resin chemistry to advance additive manufacturing, offering faster production, higher resolution, and new design freedoms.
3D-printingsoft-roboticsadvanced-materialsresin-technologyflexible-electronicsdual-light-curingmaterial-scienceMIT CSAIL's new vision system helps robots understand their bodies - The Robot Report
MIT CSAIL has developed a novel robotic control system called Neural Jacobian Fields (NJF) that enables robots to understand and control their own bodies using only visual data from a single camera, without relying on embedded sensors or pre-designed models. This approach allows robots to learn their own internal models by observing the effects of random movements, providing them with a form of bodily self-awareness. The system was successfully tested on diverse robotic platforms, including a soft pneumatic hand, a rigid Allegro hand, a 3D-printed arm, and a sensorless rotating platform, demonstrating its robustness across different morphologies. The key innovation of NJF lies in decoupling robot control from hardware constraints, thus enabling more flexible, affordable, and unconventional robot designs without the need for complex sensor arrays or reinforced structures. By leveraging a neural network that combines 3D geometry reconstruction with a Jacobian field predicting how robot parts move in response to commands, NJF builds on neural radiance fields (NeRF) to
roboticssoft-roboticsrobotic-controlmachine-learningMIT-CSAILNeural-Jacobian-Fieldsautonomous-robotsShape-shifting soft robots offer 16 ways to simulate human touch
Engineers at EPFL’s Reconfigurable Robotics Lab have developed "Digits," a modular, shape-shifting soft robotic system that delivers realistic human touch through 16 distinct haptic modes. Powered by compressed air, Digits uses flexible joints and rigid links to change shape and tactile feedback, enabling vibrations, stiffness modulation, and dynamic responses. Two prototypes—TangiGlove, an exoskeleton for the hand, and TangiBall, a handheld module—demonstrate the system’s versatility by morphing into multiple shapes and providing nuanced tactile cues. This approach bridges the gap in haptic realism by combining open-chain and closed-chain robotic configurations, allowing complex interactions such as grasping and pressing that most existing devices cannot replicate. The Digits system is designed for user-friendliness, integrating with the open-source Feelix platform, which employs machine learning to generate intuitive, real-time haptic feedback without requiring users to write code. The pneumatic actuation underlying Digits offers precise control over shape
robotsoft-roboticshaptic-technologyvirtual-realitypneumatic-actuationmodular-robotstactile-feedbackColor-changing skins created for robots to react without wires, screens
Researchers at the University of Nebraska–Lincoln have developed stretchable, synthetic skins that mimic the color-changing abilities of cephalopods like squids and octopuses. These skins replicate chromatophores—pigment-filled sacs in cephalopod skin that change appearance when muscles spread the pigment—allowing the materials to dynamically alter color in response to environmental stimuli such as heat, light, pH, and humidity. Unlike traditional electronic displays, these autonomous materials operate without wires, rigid electronics, or user input, enabling soft, flexible devices that sense and react to their surroundings in real time. The technology holds significant promise for applications in soft robotics and wearable devices, where flexibility, adaptability, and water resistance are critical. By tuning the chemical composition, the skins can be programmed to respond to specific environmental triggers, potentially allowing a single wearable to monitor multiple parameters simultaneously. This innovation could replace conventional LED screens or fixed components in certain contexts, offering a new class of human-machine interfaces that display information through
robotmaterialssoft-roboticssynthetic-skinscolor-changing-materialswearable-technologystimuli-responsive-materialsTofu-like brain implant lets scientists track cyborg tadpole growth
Bioengineering researchers at Harvard SEAS have developed a soft, stretchable, tofu-like neural implant that can be integrated into the nervous system of live tadpole embryos to monitor brain development from its earliest stages. The implant, made from fluorinated elastomers that mimic the softness and flexibility of biological tissue, is embedded into the neural plate—the flat precursor to the brain and spinal cord—and can record electrical activity from individual neurons with millisecond precision without disrupting normal development or behavior. This innovation enables continuous, stable tracking of neural activity throughout the complex folding and formation of the brain, offering unprecedented insight into early brain development. The technology addresses a critical gap, as current methods cannot noninvasively monitor neural activity during early embryonic stages when disorders such as autism, bipolar disorder, and schizophrenia may originate. By leveraging the natural growth process, the implant can expand with the developing brain, potentially allowing widespread sensor implantation across the 3D brain structure. This advancement builds on previous work with soft bioelectronics in organ
bioelectronicsneural-implantsbrain-developmentbioengineeringfluorinated-elastomerssoft-roboticsneural-monitoringFlexible soft robot arm moves with light — no wires or chips inside
Engineers at Rice University have developed a flexible, octopus-inspired soft robotic arm that operates entirely through light beams, eliminating the need for wires or internal electronics. This innovative arm is powered by a light-responsive polymer called azobenzene liquid crystal elastomer, which contracts when exposed to blue laser light and relaxes in the dark, enabling precise bending motions. The arm’s movement mimics natural behaviors, such as a flower stem bending toward sunlight, allowing it to perform complex tasks like obstacle navigation and hitting a ball with accuracy. The control system uses a spatial light modulator to split a laser into multiple adjustable beamlets, each targeting different parts of the arm to flex or contract as needed. Machine learning, specifically a convolutional neural network trained on various light patterns and corresponding arm movements, enables real-time, automated control of the arm’s fluid motions. Although the current prototype operates in two dimensions, the researchers aim to develop three-dimensional versions with additional sensors, potentially benefiting applications ranging from implantable surgical devices to industrial robots handling soft materials. This approach promises robots with far greater flexibility and degrees of freedom than traditional rigid-jointed machines.
soft-roboticslight-responsive-materialsazobenzene-liquid-crystal-elastomermachine-learningflexible-robot-armremote-control-roboticsbio-inspired-roboticsCongratulations to the #ICRA2025 best paper award winners - Robohub
The 2025 IEEE International Conference on Robotics and Automation (ICRA), held from May 19-23 in Atlanta, USA, announced its best paper award winners and finalists across multiple categories. The awards recognized outstanding research contributions in areas such as robot learning, field and service robotics, human-robot interaction, mechanisms and design, planning and control, and robot perception. Each category featured a winning paper along with several finalists, highlighting cutting-edge advancements in robotics. Notable winners include "Robo-DM: Data Management for Large Robot Datasets" by Kaiyuan Chen et al. for robot learning, "PolyTouch: A Robust Multi-Modal Tactile Sensor for Contact-Rich Manipulation Using Tactile-Diffusion Policies" by Jialiang Zhao et al. for field and service robotics, and "Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition" by Shengchent Luo et al. for human-robot interaction. Other winning papers addressed topics such as soft robot worm behaviors, robust sequential task solving via dynamically composed gradient descent, and metrics-aware covariance for stereo visual odometry. The finalists presented innovative work ranging from drone detection to adaptive navigation and assistive robotics, reflecting the broad scope and rapid progress in the robotics field showcased at ICRA 2025.
roboticsrobot-learninghuman-robot-interactiontactile-sensorsrobot-automationsoft-roboticsrobot-navigationNew soft robot wriggles through tight spaces with kirigami skin
robotsoft-roboticskirigamibioinspired-designautonomous-explorationinflatable-actuatorshuman-machine-interfaceSnake and insect-inspired robots team up to do what humans can't
robotinspectionmicrorobotssoft-roboticsautomationengineeringtechnologyLight-powered underwater robots achieve 2x mammalian muscle strength
robotsoft-roboticsartificial-musclesunderwater-roboticslight-responsive-materialsphotochemical-actuatorsazobenzeneOctopus-inspired robot can decide how to grip objects with accuracy
robotoctopus-inspiredsoft-roboticssuction-intelligencedexterous-manipulationenvironmental-sensingmultimodal-perceptionWhat’s coming up at #ICRA2025?
robotroboticsautomationICRA2025human-robot-interactionsoft-roboticsmulti-robot-systemsNortheastern soft robotic arm wins MassRobotics Form & Function Challenge at Robotics Summit
robotsoft-roboticsrobotic-armrobotics-competitionMassRoboticsinnovationtechnologyRobot Talk Episode 113 – Soft robotic hands, with Kaspar Althoefer
roboticssoft-roboticsrobotic-handsKaspar-AlthoefertechnologyengineeringRobohubRobot Talk Episode 118 – Soft robotics and electronic skin, with Miranda Lowther
soft-roboticselectronic-skinroboticstechnologyMiranda-LowtherUniversity-of-BristolRobohub