robotics

Robotics

Magnetic microbots tumble through blood vessels to dissolve clots faster

Engineers at ETH Zurich have developed magnetically driven microbots that roll along blood vessel walls to help clot-dissolving drugs reach arterial blockages. The university filed a patent application for the technology after laboratory and animal trials demonstrated that artificial flow speeds up clot breakdown.

Robotics

Diden Spider Climbs Shipyard Steel Walls to Weld Overhead

South Korean startup Diden Robotics has built a four-legged climbing machine designed to weld steel bulkheads and ceilings inside commercial vessels. The machine, known as the Diden Spider, uses switchable magnetic feet to scale vertical plates and hold heavy tools in places where human crews would otherwise need staging platforms and rigging. Field units have already entered shipyard production lines in South Korea.

AI

Seoul National University unveils TACToC and mzCache to speed up mobile AI

Engineers at Seoul National University have developed two software tools designed to reduce data traffic and latency when mobile devices offload tasks to remote artificial intelligence servers. The frameworks cut bandwidth consumption by up to 14.5 times and shorten initial smartphone response times by more than fivefold.

Robotics

A 3D-printed robot moth grows UV sensors using its own artificial blood

Engineers have built a moth-shaped prototype that uses an internal fluid circulation to grow light detectors directly on its wings. The development in soft robotics, carried out by teams at the University of Tartu in Estonia and the Italian Institute of Technology, enables a machine to form new hardware components after manufacturing rather than relying solely on pre-installed parts.

Robotics

Hopcopter Adds an Articulated Foot Pad for Rough Terrain

Engineers at the University of Toronto and two Hong Kong universities have upgraded the Hopcopter, a hybrid monopedal drone that hops and flies. By adding an articulated foot pad, the team stabilized landings on unpredictable ground, bringing the dual-mode robotics platform closer to commercial use.

Robotics

FlexiQuad: the collision-resistant ring drone from ETH Zurich

Robotics researchers at ETH Zurich have designed a quadcopter without a rigid central body that absorbs collisions without crashing. Invented by Luca Girardi and Stefano Mintchev, the ring-shaped FlexiQuad drone uses an elastic frame that flexes laterally on impact while retaining the vertical stiffness required for flight. The inventors have filed a patent application for the device, which has also earned a nomination for the university's Spark Award.

Robotics

Humanoid Robot Learns Complex Sequences Without Unified Training Data

Teaching a bipedal machine to walk across a room and manipulate objects usually requires unbroken demonstration sequences that are difficult to record reliably. A research team at Seoul National University has built a vision-language-action architecture called RISE, which connects independently gathered walking and handling data to perform sequential tasks. The system advances practical robotics by cutting the burden of training physical machines.

Makers

Dr. Kun Dániel Builds an AI-Guided Lockpicking Robot

Maker Dr. Kun Dániel has designed an autonomous lockpicking device that replaces the human touch with robotic actuators and artificial intelligence. The compact invention mounts onto an ordinary lock cylinder to manipulate internal pins through real-time physical feedback.

Letizia Giugliano

Robotics

China tests experimental submersible trimaran warship

Naval shipbuilders in China are testing an uncrewed missile vessel at Huludao on the Bohai Sea that conceals its hull beneath the surface before emerging to fire. The experimental trimaran design measures roughly 65 metres in length and reflects a growing convergence of naval engineering and autonomous robotics.

Letizia Giugliano

Robotics

Magnetic Bead Implants Give Robotic Prosthetics Real Time Muscle Tracking

Three human amputees have successfully tested an implantable magnetic tracking system that measures muscle movements in real time. The study from the Massachusetts Institute of Technology, published in the journal Nature Sensors, offers a new physical interface for robotics controllers that guide advanced prosthetic limbs.

Letizia Giugliano

Construction

ETH Zurich turns sand into solid biocement using bacteria

Engineers at ETH Zurich have developed an architectural innovation that binds ordinary loose sand into rigid building components using living bacteria. Led by Karen Antorveza Paez, the team created two fabrication methods that avoid the high heat and heavy carbon emissions of conventional cement production, as reported by [New Atlas](https://newatlas.com/materials/biocement-solid-sand/).

Giovanni Sapere

Robotics

Penn Engineers Speed Up Event Camera Vision to 440 Times per Second

Engineers at the University of Pennsylvania have developed an artificial intelligence tool that processes event-camera visual data up to 440 times per second. The software invention, called Fast Feature Field, allows machines to interpret rapid environmental changes between two and five times faster than earlier methods. Reported in the journal Science Robotics, the system helps autonomous drones, wheeled vehicles, and walking robots react quickly in cluttered spaces and low-light conditions.

Letizia Giugliano

Robotics

MIT engineers build a snake-inspired soft robot to explore the small intestine

Engineers at the Massachusetts Institute of Technology have built a flexible robotic enteroscope designed to navigate the narrow curves of the human small intestine. The new system combines soft robotics with snake-like locomotion to inspect tissue, apply medication and remove small polyps deep inside the digestive tract.

Giovanni Sapere

Space

JAXA Launches MMX Mission to Retrieve Martian Moon Samples by 2031

Japan has sent its Martian Moons eXploration spacecraft toward Mars, marking an ambitious step forward in deep space exploration. Led by the Japan Aerospace Exploration Agency, the mission seeks to become the first to land on a Martian moon, collect surface material, and bring it back to Earth.

Giovanni Sapere

Robotics

Bio-Inspired Feather Star Robot Masters 3D Underwater Maneuvers

Engineers at North Carolina State University have created an aquatic robot modeled after the marine feather star to navigate underwater environments in three dimensions. The new invention achieves multi-directional swimming and hovering using just two actuators, relying on smart structural design instead of complex electronic control systems.

Letizia Giugliano

Robotics

Dexterity and Motion Control Advance Across Quadrupeds and Humanoid Robots

Recent milestones in robotics highlight how machines are mastering delicate manipulation and dynamic mobility without relying on conventional human-like approaches. Engineering reports from October 2026 demonstrate that quadruped platforms, stabilization frameworks, and humanoid systems are rapidly closing the divide between sensory perception and physical action. These developments signal a wider shift toward resilient, high-speed machines designed for complex physical tasks.

Letizia Giugliano

Tech

Low-Cost Sensor Identifies Incoming Drones by Motor Magnetic Fields

Engineers at Florida International University have created a passive detection method that identifies airborne drones solely through the magnetic signatures produced by their electric motors. The hardware costs only a few hundred dollars to assemble and pinpoints drone models with up to 98.52% accuracy at close range, offering an alternative to active radar and noisy acoustic systems.

Letizia Giugliano

Robotics

Lab-Grown Neurons Decode Braille and Steer Robot Dogs

Recent breakthroughs in biohybrid robotics have demonstrated that cultured human neural tissue can process tactile information and steer physical machines. Researchers from the University of Bristol and Melbourne-based Cortical Labs are pairing biological neurons with silicon electronics to achieve adaptable learning using minimal computational power.

Letizia Giugliano