Articles tagged with "tactile-sensing"
Watch: ALLEX shows how humanoid robots can shake hands safely
ALLEX is a Korean-developed humanoid robot unveiled by WIRobotics at CES 2026, designed to enable safe and natural physical interaction between humans and robots. Its standout feature is a high degree of force sensitivity and control, allowing it to detect forces as low as 100 gram-force without tactile sensors while exerting up to 40 newtons of fingertip force. This capability enables ALLEX to perform human-like tasks such as shaking hands with a controlled grip that adjusts in real time, balancing strength and flexibility to avoid injury. The robot’s hands and arms are back-drivable, meaning they can be safely pushed or guided, and its arm system features low friction and rotational inertia to facilitate smooth, fluid motion suitable for close human interaction. ALLEX’s design includes 15 degrees of freedom, gravity compensation from the waist to upper body, and a lightweight build—its hand weighs about 1.5 pounds and the shoulder-down assembly about 11 pounds—yet it can lift over
robothumanoid-robotforce-controlhuman-robot-interactionroboticstactile-sensingautomationMicrosoft launches new AI model for real-world robotic learning
Microsoft has unveiled Rho-alpha, a new AI model designed to enable robots to operate effectively in unpredictable, real-world environments beyond traditional factory settings. Developed by Microsoft Research as part of its Phi vision-language AI family, Rho-alpha represents a shift toward "physical AI," where intelligent agents interact directly with the physical world. Unlike conventional industrial robots that follow rigid scripts, Rho-alpha translates natural language instructions into control signals for complex, two-handed robotic manipulation tasks. The system incorporates tactile sensing alongside visual input, allowing robots to adapt their movements based on touch and learn from human corrective feedback in real time. Microsoft is currently testing Rho-alpha on dual-arm and humanoid robots and plans to expand its sensory capabilities in future versions. A key challenge addressed by Rho-alpha is the scarcity of training data for robotics. Microsoft combines physical robot demonstrations, simulated tasks, and large-scale visual question-answering datasets to train the model. The company leverages reinforcement learning pipelines and robotics simulation tools on Azure to generate synthetic
roboticsartificial-intelligencerobotic-learningtactile-sensingadaptive-robotsmachine-learningMicrosoft-Research'World’s most advanced' robotic hand pairs vision and touch sensing
Sharpa Robotics has advanced its flagship robotic hand, SharpaWave, into mass production, marking a significant milestone in the general-purpose robotics market. Headquartered in Singapore, the company has implemented a rolling production process supported by automated testing systems to ensure the durability and reliability of thousands of microscale gears, motors, and sensors within each hand. Initial shipments began in October, with a broader launch planned at CES 2026. SharpaWave is designed to match human hand size and dexterity while providing exceptional strength and precision, attracting early orders from global technology firms. The SharpaWave hand features 22 active degrees of freedom and integrates proprietary Dynamic Tactile Array technology, combining miniature cameras with over 1,000 tactile pixels per fingertip to deliver visuo-tactile sensing capable of detecting forces as small as 0.005 newtons. This enables six-dimensional force sensing for adaptive grip control and slip prevention, allowing the hand to manipulate both delicate and heavy objects intelligently. Sharpa Robotics
roboticsrobotic-handtactile-sensingautomationdexterous-manipulationsensorsindustrial-robotsChina’s Xiaomi taps ex-Musk engineer to advance robot hand tech
China’s Xiaomi has hired Zach Lu Zeyu, a former senior robotics engineer from Elon Musk’s Tesla Optimus humanoid robot team, to lead the development of its dexterous robot hand technology. Lu’s expertise in dexterous grasping and tactile sensing—critical capabilities that enable robots to manipulate objects with human-like precision and sensitivity—signals Xiaomi’s strong commitment to advancing embodied AI and robotics. This move is part of Xiaomi’s broader strategy to become a major player in the global humanoid robotics market, following its initial ventures into electric vehicles and robotics prototypes such as a quadrupedal robot dog and a humanoid robot. Xiaomi’s recruitment drive includes over 200 robotics-related roles and recent hires like AI researcher Luo Fuli, underscoring its ambition to build a world-class robotics team. The company also released MiMo-Embodied, an open-source foundation model combining autonomous driving and embodied AI technologies. This expansion occurs amid a competitive U.S.-China race in humanoid robotics
roboticshumanoid-robotsdexterous-handtactile-sensingXiaomirobotics-engineeringembodied-AIUS: Robot dog balances rolling load on back with tactile sensing tech
Researchers at Carnegie Mellon University have developed LocoTouch, a novel tactile sensing system that enables quadrupedal robots to carry loose, unsecured cylindrical and irregularly shaped objects on their backs without the items rolling off during movement. Unlike traditional robots that rely on rigid containers or mounted boxes to secure cargo, LocoTouch uses a high-density tactile sensor array made from piezoresistive film and conductive electrodes spread flat across the robot’s back. This sensor continuously detects shifts in the load’s position and orientation, allowing the robot to adjust its posture and gait in real time to maintain balance, similar to how humans instinctively stabilize objects while walking. The system was trained through reinforcement learning using over 4,000 digital twins in simulation, enabling the robot to experience a wide variety of object movements and disturbances. The learned balancing skills transferred directly to a physical Unitree Go1 quadruped robot, which successfully carried various objects over 60 meters, navigating obstacles and remaining stable even when bumped. This represents the
robottactile-sensingquadrupedal-robotsreinforcement-learningrobotic-balancepiezoresistive-sensorsrobotic-assistantsBoston Dynamics humanoid robot gets new hands for heavy lifting
Boston Dynamics has introduced a significant upgrade to its humanoid robot Atlas by developing a new three-fingered gripper designed to improve its ability to handle both delicate and heavy objects. Unlike attempts to fully replicate the human hand, the company focused on creating a rugged, reliable gripper with seven degrees of freedom and seven actuators, including an articulated thumb joint. This design enhances Atlas’s dexterity, allowing it to perform complex tasks such as sorting, picking, packing, and manipulating objects with precision. The gripper also incorporates tactile sensing on the fingertips and cameras embedded in the palm, enabling the robot to adjust its grip based on the shape and delicacy of items. In addition to hardware improvements, Boston Dynamics has partnered with the Toyota Research Institute to develop a Large Behavior Model (LBM), an AI system trained on extensive human action datasets. This AI enables Atlas to understand, generate, and adapt human-like behaviors without the need for manual programming of each task. Demonstrations showed Atlas performing tasks such
roboticshumanoid-robotBoston-Dynamicsrobot-handstactile-sensingAI-in-roboticsrobot-gripperHow BrainCo robotic hands are changing lives - The Robot Report
BrainCo, a company founded in 2015 and incubated by Harvard Innovation Lab, has developed an advanced non-invasive brain-computer interface (BCI) that enables users to control prosthetic hands with remarkable dexterity. The technology notably transformed the life of Jian, a teenager who lost his right arm in an accident. Using BrainCo’s Intelligent Bionic Hand, Jian regained the ability to perform complex tasks such as rock climbing and playing the piano, restoring both his physical capabilities and his sense of hope. The company’s latest product, the Revo 2 Dexterous Hand, is a lightweight (383 g) prosthetic capable of generating a grip force of 50 newtons, allowing it to lift up to 20 kg. It features biomimetic joint optimization, precision transmission, and a 3D tactile sensing system that can perceive hardness, texture, force direction, and distance, enabling delicate tasks like lighting a match. The device operates quietly (below 50 decibels)
robotroboticsprostheticsbrain-computer-interfacebionic-handhumanoid-robotstactile-sensingSensing robot hand flicks, flinches, and grips like a human
A student team at USC Viterbi, led by assistant professor Daniel Seita, has developed the MOTIF Hand, a robotic hand designed to mimic human touch by sensing multiple modalities such as pressure, temperature, and motion. Unlike traditional robot grippers, the MOTIF Hand integrates a thermal camera embedded in its palm to detect heat without physical contact, allowing it to "flinch" away from hot surfaces much like a human would. It also uses force sensors in its fingers to apply precise pressure and can gauge the weight or contents of objects by flicking or shaking them, replicating human instincts in object interaction. The MOTIF Hand builds on previous open-source designs like Carnegie Mellon’s LEAP Hand, with the USC team also committing to open-source their work to foster collaboration in the robotics community. The developers emphasize that this platform is intended as a foundation for further research, aiming to make advanced tactile sensing accessible to more teams. Their findings have been published on Arxiv, highlighting a significant step toward
robotrobotic-handsensorshuman-robot-interactiontactile-sensingthermal-detectionrobotics-researchRobots can sense when something might slip from grip with new method
Engineers at the University of Surrey have developed a novel, bio-inspired method enabling robots to sense and prevent objects from slipping during manipulation by predicting slip events and adjusting their movements in real-time. Unlike traditional robotic grip strategies that rely solely on increasing grip force—which can damage delicate items—the new approach mimics human behavior by modulating the robot’s trajectory, such as slowing down or repositioning, to maintain a secure hold without excessive squeezing. This method, demonstrated through a predictive control system powered by a learned tactile forward model, allows robots to anticipate slip risks continuously and adapt accordingly. The research, published in Nature Machine Intelligence, shows that trajectory modulation significantly outperforms conventional grip-force-based slip control in certain scenarios and generalizes well to objects and movement paths not included in training. This advancement holds promise for enhancing robotic dexterity and reliability across various applications, including healthcare (handling surgical tools), manufacturing (assembling delicate parts), logistics (sorting awkward packages), and home assistance. The study highlights the importance of
roboticsrobotic-manipulationslip-preventionautomationtactile-sensingpredictive-controlbio-inspired-robotics