Method for Measuring the Pose of a Microrobot

This technology measures the pose of a microrobot using image processing and marker-based coordinate tracking. It separates the microrobot from noise in captured images through differential imaging, color binarization, and size comparison, overlays a marker onto the robot, and calculates the robot's pose by determining the coordinates of color boundary points.

When microrobots are inserted into the human body, noise from light scattering, body tissues, and blood vessel walls occurs during image acquisition. Conventional technologies, which directly recognize markings on the microrobot's surface, suffer from frequent recognition errors and low pose measurement accuracy due to this noise.

This technology consists of a preprocessing step to identify the microrobot by separating it from noise, a step to virtually display a marker that intersects the robot's outline based on the identified geometric information, and a step to calculate the robot's pose by analyzing the boundary coordinates of binarized colors (first and second colors) on the marker. Applicable to robot gripping, precision measurement, and automated equipment, it improves the accuracy of microrobot pose measurement in noisy environments, thereby enhancing measurement reliability and enabling precise measurement.

‍

‍

Key Features:

• A step of displaying a marker on the recognized microrobot in the captured image that intersects the microrobot's outline, with a diameter larger than the width of the recognized microrobot and smaller than its length.
• A step of binarizing colors such that among a plurality of points, those located outside the microrobot have a first color, and those located inside the microrobot have a second color.
• A step of recognizing the microrobot by distinguishing it from noise in the captured image.
• A step of displaying a plurality of points on the displayed marker.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of a micro-medical robot system for the treatment of chronic total occlusion in myocardial infarction.

Method for Generating Intersection Pattern Recognition Models Using Mobile Robot Sensor Data and Intersection Pattern Recognition System

This technology is a control mechanism that recognizes intersection patterns and determines the absolute position of a mobile robot by converting pre-established guide lines or structural data into a grid-based path map and training a normalized virtual map alongside sensor data, without the need for additional landmark installations.

Conventional technologies require landmark sensors at every intersection to estimate a mobile robot's position, leading to high installation costs, a lack of flexibility when environmental changes necessitate reinstallation, and difficulties in maintaining real-time performance due to increased data transmission volume when operating multiple robots.

This technology generates a path map based on usage environment information within a management server, creates a virtual map normalized so that the distance between intersections is an integer multiple of a unit length, and provides the robot with a model that classifies and recognizes 'L', 'T', and '+' shaped intersection patterns by training this data with sensor data. It can be applied to logistics transport, service robots, and autonomous driving platforms, enabling real-time movement control of mobile robots without separate landmark sensors, thereby improving the efficiency and cost-effectiveness of such physical distribution systems.

‍

‍

Key Features:

• A training unit that generates an intersection pattern recognition model using virtual maps and mobile robot sensor data as training data.
• A map generation unit where the management server receives usage environment information for the mobile robot and generates a path map based on that information.
• A normalization unit that generates a virtual map by normalizing the path map according to pre-set rules.
• An intersection pattern recognition system using mobile robot sensor data, wherein the path map consists of a grid-based map, and the normalization unit generates the virtual map by normalizing the path map so that the distance between intersections is an integer multiple of a unit length.

‍

This invention was developed with the support of the Ministry of Science and ICT's AI-based Anti-Drone Active Control Technology Development project.

Microrobot for Guidewire Steering

This technology features a microrobot structure and a guidewire steering mechanism where a flexible first magnetic body bends at varying angles and changes its stiffness in response to the direction and intensity of an external magnetic field.

Conventional guidewires have limited steering ranges, which can lead to buckling during navigation through blood vessels, causing vascular damage. Furthermore, the frequent need to replace guidewires based on the hardness of thrombi reduces procedural efficiency and increases the risk of vessel injury.

This technology utilizes a flexible first magnetic body (polymer and magnetic powder) and a rigid second magnetic body arranged in series at the tip of the guidewire. By applying an external magnetic field, the bending angle of the first magnetic body is precisely controlled, and the stiffness of the microrobot is adjusted by varying the magnetic field intensity, thereby ensuring superior guidewire steerability. Applicable to industrial robots and automated systems, this technology enables precise guidewire control and prevents vascular damage, significantly improving navigation and safety in medical procedures.

‍

‍

Key Features:

• A first magnetic body mounted on the guidewire that bends at different angles according to changes in the direction of an external magnetic field
• A second magnetic body, less flexible than the first, positioned in one direction from the first magnetic body
• A configuration where the first magnetic body is mounted to surround the tip of the guidewire
• A biocompatible tube made of biocompatible material that surrounds portions of the first and second magnetic bodies

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of a microrobotic system for the treatment of chronic total occlusion in myocardial infarction.

Microrobot for Guidewire Steering

This technology features a mechanism where one or more magnetic elements are placed inside a flexible body, which is connected to a guidewire via an elastic component. When an external magnetic field is applied, the microrobot bends, thereby improving the steerability of the guidewire.

Conventional guidewires have fixed shapes and angles, requiring high levels of skill for navigation through complex blood vessels. This leads to longer procedure times, increasing radiation exposure for both physicians and patients.

This technology utilizes a flexible body and an elastic connection, with at least one magnetic element embedded within the body to allow it to bend in response to an external magnetic field. Specifically, by placing a primary magnetic element at the distal end and setting the body length to at least three times the length of the magnetic element, the steering angle is maximized. Applicable to industrial robots and automated systems, this technology reduces surgical time and minimizes radiation exposure for patients and medical professionals, ultimately improving the precision and efficiency of vascular treatments.

‍

‍

Key Features:

• A microrobot mounted on a guidewire, comprising a body portion that extends along the longitudinal direction of the guidewire and includes a flexible material to allow for lateral bending.
• An elastic portion connecting the guidewire to one end of the body portion, such that the distal end of the guidewire is positioned toward one end of the body portion.
• A body portion including a flexible material to allow for lateral bending of the guidewire.
• An elastic portion connecting the guidewire to one end of the body portion.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of a micro-medical robot system for the treatment of chronic total occlusion in myocardial infarction.

Biodegradable microrobots for hyperthermia therapy and drug delivery

This technology involves dispersing magnetic and drug particles within the body of an implantable microrobot. By applying an external alternating magnetic field, the magnetic particles generate heat, which accelerates the degradation of the biodegradable polymer body, allowing for precise control over the dosage and release rate of the drug.

Conventional technologies suffer from issues such as the loss of magnetic particles and drugs due to blood flow, as well as limitations in surface-coating methods that prevent real-time adjustment of drug release rates, making it difficult to deliver the appropriate dosage to the target lesion.

This technology embeds magnetic and drug particles within a biodegradable polymer body. By adjusting the duration and intensity of the external magnetic field, it induces heat in the magnetic particles to control the polymer degradation rate, thereby regulating the amount and timing of drug release. Applicable to surgical robots, interventional systems, and medical automation, it minimizes the loss of magnetic particles and drugs and prevents them from migrating to unintended areas, significantly improving the efficiency of hyperthermia therapy and drug delivery.

‍

‍

Key Features:

• A body formed of biodegradable polymer that determines the shape of the microrobot
• A configuration containing magnetic particles and drug particles distributed within the body
• Drug release dosage within the body is controlled based on the duration of the external magnetic field application
• A structure where magnetic particles heated by a magnetic field accelerate polymer degradation to release the drug

‍

This invention was developed with support from the Ministry of Science and ICT for the Intelligent Microrobot-based Body-on-a-Chip for Precision Medicine project.

System Control Device and Method

This technology is an algorithm that calculates sliding variables based on a system's position error and rate of change over time, applying them to a nonlinear adaptive load model to adjust PID controller gains in real time.

Conventional PID controllers use fixed gain constants, which can lead to degraded control performance or difficulty in maintaining robustness when system loads change, often requiring repetitive trial and error by the user to determine optimal gains.

This technology uses sliding variables as inputs for a nonlinear adaptive load model to adaptively calculate PID gains. It includes control logic that reduces gains to a lower limit to maintain stability when sliding variables increase due to load changes, and resets gains upon detecting load variations via sensors. Applicable to industrial robots and automation systems, this method improves the robustness of the system controller against significant load fluctuations by adaptively modifying the PID gains.

‍

‍

Key Features:

• A gain determination unit that applies sliding variables, which vary according to system load changes, to a preset adaptive load model, and adaptively adjusts gains using the adaptive load model to which the sliding variables are applied.
• A system control device wherein the gain determination unit reduces the gain until a preset lower limit is reached when the sliding variable increases.
• A gain determination unit that adaptively adjusts gains using an adaptive load model to which sliding variables are applied.
• A PID controller configured to control system behavior and having adjustable gains.

‍

This invention was developed with support from the Ministry of Science and ICT for brain mapping-based robot rehabilitation.

Robot Joint Structure

This technology forms a joint by connecting two spaced-apart bodies with a cross-flexure hinge consisting of two pairs of intersecting connectors. When applied to the finger joints of a robotic hand, it achieves both high rigidity and a compact design.

Conventional robot joint structures often lack sufficient rotational rigidity, limiting their precision in gripping tasks. Furthermore, the bulky nature of these joints makes it difficult to achieve a compact, miniaturized design for robotic hands.

This technology connects the first and second bodies using two joint units arranged in mirror symmetry (each containing two intersecting connectors) to enhance rigidity. By integrating a pulley and wire drive system within the bodies, it maximizes the spatial efficiency of the robotic hand. Applicable to industrial robots and automation systems, it improves the stability and rotational stiffness of robotic hands, enabling them to effectively mimic human hand movements.

‍

‍

Key Features:

• A second joint unit positioned to face the first joint unit, connecting the first body and the second body
• A robot joint structure where the first joint unit and the second joint unit are cross-flexure hinges.
• A first joint unit connecting the first body and the second body
• A second body positioned at a distance from the first body

Microrobot for Temperature Control in Targeted Regions Within the Body

This technology is a mechanism that heats magnetic particles within an internally administered microrobot using an external alternating magnetic field. It utilizes light-emitting particles (quantum dots) that emit near-infrared light based on temperature, allowing for non-invasive, real-time feedback control of heating temperatures from outside the body.

Conventional hyperthermia treatments carry a high risk of damaging surrounding healthy cells due to overheating, as they cannot directly measure or control the temperature of the magnetic particles.

This technology features a microrobot composed of a polymer embedded with magnetic particles and temperature-dependent near-infrared-emitting quantum dots. An external measurement device detects the intensity of the emitted light, allowing for precise adjustment of the external magnetic field intensity via PID control. This can be applied to robotic gripping, precision measurement, and automated equipment, improving temperature control accuracy and preventing overheating and damage to healthy cells during medical treatment.

‍

‍

Key Features:

• Light-emitting particles administered into the body to reach a target region, emitting light with intensity that varies according to temperature
• Configuration including magnetic particles whose temperature changes according to the intensity of an external magnetic field
• Structure characterized by the light-emitting particles being quantum dots and the emitted light being near-infrared
• Configuration where light passes through the skin to be emitted outside the body, with its intensity measured by an external measurement device

‍

This invention was developed with support from the Ministry of Science and ICT for the Intelligent Microrobot-based Body-on-a-Chip for Precision Medicine project.

Self-Propelled Microrobots Using Bio-Based Organisms

This technology is a hybrid microrobot system that combines the chemotaxis of therapeutic cells (bacteria/immune cells) with the magnetic propulsion of magnetic nanoparticles. It prevents internal accumulation by inducing a dissociation temperature (Td) through external heat sources (near-infrared/alternating magnetic fields) to separate the cells from the nanoparticles.

Existing microrobots face limitations in precise targeting during magnetic propulsion, and the magnetic nanoparticles injected into the body can remain, causing cytotoxicity and side effects. Furthermore, bacteria-based robots often suffer from low lesion-reaching rates due to blood flow resistance.

This technology uses ligand-receptor binding (such as biotin-avidin) to attach magnetic nanoparticles to therapeutic cells. After transporting them to the lesion via an external magnetic field, the system applies localized heat to break the bond, allowing the separated magnetic nanoparticles to be retrieved using an external magnetic field, thereby resolving the retention issue. Applicable to industrial robots and automated systems, it enables selective drug release through cell sorting for therapy, improving treatment efficiency and minimizing side effects.

‍

‍

Key Features:

• Microrobot comprising ligand-introduced therapeutic cells and receptor-introduced magnetic nanoparticles
• Magnetic nanoparticles are attached to the surface of therapeutic cells via ligand-receptor binding
• Therapeutic cells include attenuated genetically modified bacteria or immune cells
• Structure that dissociates at temperatures above body temperature due to heat generated by magnetic nanoparticles when an external magnetic field is applied

‍

This invention was developed with support from the Ministry of Science and ICT for brain mapping-based robot rehabilitation.

Method for Manufacturing Ultra-Fine 3D Microrobots Using Laser-Processed Polymer Molds

This technology involves creating a polymer mold using 3D laser lithography, then injecting and sintering a non-polymer material containing magnetic metal particles via plating or dipping to form the entire microrobot structure out of magnetic metal.

Existing photocurable polymer-based microrobots suffer from non-uniform magnetization distribution during magnetic material deposition, and mixing in magnetic particles leads to reduced laser transmittance, lower manufacturing precision, and insufficient structural rigidity.

This technology first creates a high-precision mold using 3D laser lithography, then injects and sinters a non-polymer material (containing magnetic substances) into the mold to metallize the entire structure, ensuring uniform magnetization intensity and high rigidity. Applicable to industrial robots and automation systems, it enhances the rigidity of 3D microrobots and improves magnetization intensity for better control within magnetic fields.

‍

‍

Key Features:

• Preparing a mold containing microstructures using a 3D laser lithography system
• Manufacturing a 3D microrobot by injecting non-polymer material into the mold
• Producing a sintered body by injecting non-polymer material with a magnetic film formed via plating or dipping into the empty spaces of the mold
• A manufacturing method where the magnetic metal is homogeneously distributed once the sintered body is separated from the mold

‍

This invention was developed with support from the Ministry of Science, ICT and Future Planning for the development of 3D precision microstructures and foundational technology for cell/drug delivery.

Dual-Grip Robotic Hand

This technology features a mechanism that performs dual-stage gripping and hemostasis by first securing an irregular object (such as a patient's limb) with mechanical fingers, followed by applying physical pressure using an inflatable air cuff. It maintains the grip state using a ratchet gear and locking member, while controlling gripping stability through pressure sensors and a through-type primary sensor unit.

Conventional robotic hands struggle to accurately grip irregular objects like human limbs due to structural limitations in their finger design, making it difficult to perform precise tasks such as arterial compression for hemostasis.

This technology consists of a link-structured finger unit, a finger drive unit, an air cuff, an air supply unit, a laser sensor (primary sensor) for object positioning, a pressure sensor (secondary sensor) for grip force detection, and a grip maintenance unit based on a ratchet/locking member to secure the mechanical grip. It can be applied to logistics picking, service robots, and manufacturing automation to improve object handling capabilities, enhance the accuracy of hemostasis, and prevent excessive clamping force or skin damage.

‍

‍

Key Features:

• A grip maintenance unit featuring a locking member that engages with the teeth of a ratchet gear to prevent the fingers from rotating in the direction of extension, along with an elastic member that biases the locking member toward the ratchet gear.
• A finger drive unit that actuates the fingers in either a bending or extending direction.
• A pair of opposing finger units arranged to grip an object.
• An air supply unit that provides air to the air cuff.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of safety-guaranteed soft manipulators and multifunctional gadgets for relief operations.

Implementation Method of Parallel Processing Algorithm for Real-Time Path Generation of High-Degree-of-Freedom Robot Manipulators

This technology is a path post-processing algorithm that determines optimal, collision-free joint configurations in real time by parallelizing the search for all possible joint combinations across multiple sub-paths, thereby efficiently improving the manipulator's motion trajectory.

Existing adaptive partial shortcut (APSC) techniques sample and select a fixed number of joints during iterative path refinement, which leads to increased computation time as iterations grow and makes it difficult to respond to dynamic environments.

This technology divides the manipulator's motion path into multiple sub-paths and performs parallel computations on all possible joint combinations for each sub-path to select and apply the optimal configuration in real time, maximizing path refinement efficiency. Applicable to logistics transport, service robots, and autonomous platforms, it reduces total computation time and enables parallel processing in dynamic environments, improving path generation efficiency for high-degree-of-freedom robot manipulators.

‍

‍

Key Features:

• Determining sub-paths from the existing path and initializing each sub-path
• Determining all possible joint combinations for each sub-path
• Performing parallel path refinement for each joint combination to generate improved sub-paths
• Replacing existing sub-paths with those that provide the greatest path refinement effect

‍

This invention was developed with support from the Ministry of Science and ICT's Human-Centric CPS research program.

Autonomous Floor Finishing Installation System

This technology is a system where multiple autonomous robots (for coating, loading, transporting, installing, and charging) collaborate to install floor finishing materials. It features precise positioning using 3D localization devices and active markers, as well as a high-precision installation mechanism based on vision-sensor-driven obstacle avoidance and floor surface recognition.

Relying solely on manual labor for the transport and installation of increasingly large and heavy construction materials results in low work efficiency. Existing remote-controlled robots are limited by the operator's line of sight, making fine adjustments difficult, and the high rate of human error on construction sites poses significant safety risks.

This technology establishes an autonomous robot swarm control system. A 3D localization device transmits positional data to the robots via active markers, while a manipulator structure—combining floor-sensing sensors and vertical/horizontal arms—precisely installs finishing materials according to the floor's coordinate system. By improving the efficiency and safety of material installation on construction sites, this system can also be adapted for rehabilitation training, gait assistance, and various medical and welfare services.

‍

‍

Key Features:

• 3D localization device that recognizes the position and orientation of multiple active markers installed on the job site using vision-integrated distance sensors
• Vertical arm attached to one side of the horizontal arm, operating in an up-and-down motion to install floor finishing materials
• Work-oriented vision sensor mounted on one side of the vertical arm for moving and installing floor finishing materials
• Multiple floor-imaging sensors that recognize the shape of the floor surface where adhesive has been applied to a uniform thickness

‍

This invention was developed with support from the Ministry of Science and ICT for the development of intelligent painting and masking collaborative robots.

Series Elastic Actuator

This technology is a Series Elastic Actuator (SEA) structure that measures torque and controls rotation angle without changes to the moment arm by utilizing wire tension during relative rotation between a first body (including a motor) and a second body. The wire's center is wound around a pulley seat, with both extended ends connected to preloaded first and second springs and adjustment devices.

Conventional series elastic actuators suffer from difficulties in accurate torque measurement and control because the spring is positioned between the output stage and the link, causing the spring to bend or rotate during deformation, which alters the moment arm.

This technology maintains a constant moment arm by securing the center of the wire to the outer circumference of the pulley and supporting the extended ends through a preloaded spring system within the second body. It establishes a structure that allows for precise control and measurement of wire tension via adjustment devices and a housing design. Applicable to robotic gripping, precision measurement, and automation equipment, it improves torque measurement accuracy and facilitates torque measurement based on external forces.

‍

‍

Key Features:

• A wire comprising a central portion curved around a seating area, and first and second straight extension portions extending from both ends of the central portion.
• A pulley configured to rotate about a first rotation axis when the rotor rotates, equipped with a seating area that forms an arc around the first rotation axis.
• A first adjustment housing accommodating a first spring, a first neck portion, and a first adjustment nut.
• A first adjustment device coupled to the first extension portion to move in tandem with it.

‍

This invention was developed with support from the Ministry of Science and ICT for the commercialization of immersive human-robot multi-sensory interaction technology.

Underground Utility Tunnel Maintenance Robot System

This technology is an integrated management system that utilizes a rail-based mobile platform to continuously monitor facilities within underground utility tunnels and deploys precision inspection and maintenance robots when hazardous areas are detected.

Existing single-robot systems struggle with precision inspections due to the extensive length of underground utility tunnels and are limited to basic monitoring, making them incapable of performing complex facility maintenance tasks.

This technology deploys continuous inspection robots, precision inspection robots, and fire suppression robots along a rail system. A control server identifies hazardous areas and automates precision scanning and maintenance using specialized tools. Applicable to robotic gripping, precision measurement, and automated equipment, it enables remote monitoring, predictive maintenance, and repairs for power lines, communication cables, and various piping systems, thereby enhancing the efficiency and safety of underground utility tunnel maintenance.

‍

‍

Key Features:

• A battery control unit that communicates with the continuous inspection robot; when the robot stops at a designated location, the unit opens the battery cover to charge the battery via wired or wireless methods, or replaces the battery by retrieving the depleted one and inserting a pre-charged unit.
• A control server that identifies target areas within the underground utility tunnel where risks are anticipated based on video and environmental sensor data received from the continuous inspection robot, and transmits commands for precision inspection of those target areas.
• An underground utility tunnel maintenance robot system that commands the fire suppression robot located closest to the target area among a pair of fire suppression robots to perform fire extinguishing operations.
• A continuous inspection robot that travels along rails installed on the floor or ceiling, collecting video footage of facilities including lines and pipes, as well as environmental sensor data, and transmitting this information to the control server.

‍

This invention was developed with support from the Ministry of Science and ICT's AI-based Anti-Drone Active Control Technology Development project.