Educational Robot Combining Wearable Object Recognition and Power-Responsive Control

This technology is an educational robot device that receives images of objects captured by a user's wearable device to identify the object type, outputs information about the recognized object via video and audio, and controls the robot's movement. It also features a technology that monitors reserve and demand power levels within the power supply system to manage operating modes.

Cognitive and language education for infants and toddlers has historically been difficult to provide consistently due to time constraints faced by parents.

This technology proposes an educational robot that communicates with a wearable device to capture the direction the user is pointing, recognizes objects, and outputs relevant educational content. By dynamically controlling the robot's operating mode based on power status, it enables both efficient educational support and optimized power management. It can be applied to early childhood cognitive and language education as well as home service robotics, enriching the learning experience by recognizing objects based on the user's line of sight and providing tailored educational content.

‍

‍

Key Features:

• A communication unit that receives images of objects in the direction pointed to by the user from a wearable device.
• A control unit that identifies the type of object in the received image and manages operations in response to power status.
• An output unit for displaying video and audio corresponding to the type of recognized object.
• A mobility unit that allows the robot to move within a certain range of the user, and a control configuration responsive to reserve and demand power.

‍

This invention was developed through the "Development and Demonstration of National DR Business Models for Activating Demand Response for Small-Scale Electricity Consumers" project supported by the Ministry of Trade, Industry and Energy, and the "Development of IoT Platforms for Energy Efficiency and Creative Talent Development" project supported by the Ministry of Science and ICT.

Body-Powered Wearable Variable Impedance Device for Posture Correction Using Upper/Lower Cables and Elastic Elements

This technology is a non-powered wearable variable impedance device that corrects posture and assists muscle strength by inducing cable tension and elastic deformation based on the user's body movement. It features a mechanism that increases tension during upper body flexion by positioning upper and lower strings around a spinal connection point.

There is a risk of injury from improper posture, such as bending the waist during squatting and lifting tasks, and existing posture correction exercise equipment has significant limitations in usability due to its bulkiness and lack of portability.

This technology proposes a structure that combines a wearable cable system with elastic elements. By adjusting the separation distance and tension between strings according to changes in the user's joint angles, it encourages back straightening and provides muscle support during knee flexion, enabling variable impedance through body movement alone without an external power source. It reduces the risk of injury in environments where repetitive strain on the lower back occurs, such as logistics loading/unloading, construction site work, and nursing care, and is easy to implement in the field due to its lightweight, portable, and power-free design.

‍

‍

Key Features:

• A connection point located on the user's back between the neck and hips, serving as the reference point where the upper and lower cables intersect and connect.
• An upper cable system worn on both sides of the upper body, featuring first and second upper strings and an upper connecting string that extend toward the connection point.
• A lower cable system equipped on each leg, featuring first and second lower strings and a lower connecting string that extend toward the connection point.
• An elastic component that deforms according to changes in the user's joint angles to generate elastic force, thereby performing posture correction and muscle strength assistance.

‍

This invention was developed with support from the Human-Centered Soft Robotics Research Center of the Ministry of Science and ICT.

Passive gait assistance device that recovers and releases walking energy using multi-stage elastic members

This technology features multi-stage elastic members (first and second) that operate sequentially based on the pitch angle changes of the leg link to recover and release walking energy, and utilizes a physical constraint mechanism with a rotating locking pin and a rotation guide slot to control the timing of energy storage.

Existing lower-limb exoskeleton robots are heavy and expensive due to motor-based drive systems, cause a sense of gait unnaturalness, and increase the burden on the wearer due to the lack of an optimized passive mechanism for ankle muscle assistance during the gait cycle.

This technology constructs a multi-stage passive mechanism that sequentially stores walking energy in the first and second elastic members according to the rotation angle (pitch angle) of the leg link, and reduces the burden on the wearer while increasing ankle assistance through a hybrid structure using a back-mounted motor and wires. It can be applied to rehabilitation training, gait assistance, and muscle support, reducing weight, cost, and gait unnaturalness by assisting ankle strength without relying solely on motors.

‍

‍

Key Features:

• A footplate that supports the foot and a leg link that rotates in the pitch direction relative to the footplate during walking
• First and second elastic members provided between the footplate and the leg link to store gait assistance energy
• A first link including a rotating locking pin and a second link provided with a rotation guide slot through which the rotating locking pin passes
• A structure where the rotating locking pin contacts one end of the rotation guide slot at a first pitch angle to initiate energy storage

Work robot that maintains horizontal balance by independently controlling drive units via multi-joint adjustment units

This technology is a posture stabilization mechanism that maintains the horizontal balance of the body by using the multi-joint structure of adjustment units connecting the body to multiple drive units, independently controlling the position and speed of each drive unit based on the body's tilt.

Conventional methods for posture stabilization in construction machinery are often limited to specific equipment or constrained by structures that require data from the working arm, resulting in low responsiveness and intuitiveness during automatic control.

This technology places adjustment units between the body and each drive unit to control vertical, longitudinal, and lateral positioning. When tilting occurs, it uses Closed-Loop Inverse Kinematics (CLIK) to independently control the position and speed of the drive units, correcting the body's horizontal level. It can be applied to construction and agricultural robots as well as off-road mobile platforms, enhancing operational stability by automatically maintaining a level body even on slopes.

‍

‍

Key Features:

• Multiple drive units provided for ground travel, each featuring a drive member rotatably connected to a support member
• Multiple adjustment units connecting the body to the drive units to regulate the relative position of the drive units with respect to the body
• A controller that manages the multiple drive units and adjustment units to maintain and restore the horizontal balance of the body
• Configuration that independently controls the speed differential of drive units on the tilted side and the relative distance between units

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of off-road driving systems capable of independent drive and posture control.

Impedance Control Device for Wheeled Weight Supporters Considering Dynamic Characteristics of Human Lower Limbs

This technology generates assistive driving force based on impedance control values tailored to specific walking environments (such as mud, water, or zero gravity) by measuring the user's center of gravity displacement and vertical force during gait in real time.

Conventional fixed rehabilitation aids lack mobility, making it difficult to simulate diverse walking environments and limiting the ability to perform gait training on actual ground.

This technology integrates displacement and interaction force sensors into a wheeled mobile platform and applies an optimized impedance calculation algorithm based on the user's state and mode to provide real-time assistive force for walking. Applicable to rehabilitation training, gait assistance, and medical/welfare services, it improves a patient's walking ability by providing impedance control based on their center of mass and vertical force, allowing for personalized gait training in various walking scenarios.

‍

‍

Key Features:

• A center-of-gravity extraction unit that determines the position of the user's center of gravity using a displacement measuring device mounted on the wheeled weight supporter.
• A vertical force measuring unit that measures vertical force using an interaction force measuring device mounted on the wheeled weight supporter.
• A drive unit that generates and transmits force to the wheeled weight supporter corresponding to the calculated driving force.
• A calculation unit that computes the driving force using the measured vertical force and impedance values.

‍

This invention was developed with support from the Ministry of Education's research project on ultra-high-efficiency mobility mechanisms based on natural dynamics for extreme environment exploration systems.

Device for Controlling an Active Upper Limb Exercise Assistive Device

This technology calculates the ratio of sensing values from eight 1-axis force sensors (load cells) distributed across the forearm support and handle. By comparing these values against mapped reference ranges, it identifies the user's intended movement (linear or rotational) and generates and transmits control signals to a multi-joint robot.

Conventional upper limb rehabilitation robots for feeding assistance often lack versatility, fail to account for individual user physique, and rely on expensive 6-axis force-torque sensors to detect movement intent, leading to high implementation costs and practical challenges.

This technology utilizes multiple low-cost 1-axis force sensors placed at various points on the upper limb assistive device and implements an algorithm that normalizes and estimates movement intent by combining the ratios of measurements between sensors. Applicable to robotic gripping, precision measurement, and automated equipment, it enhances daily convenience and quality of life by assisting with daily activities and rehabilitation exercises for the elderly, individuals with limited mobility, or patients with muscle weakness.

‍

‍

Key Features:

• An input unit that receives sensing values for force measured from a plurality of sensors attached to the upper limb exercise assistive device while the user's forearm is positioned on the device during movement.
• A signal generation unit that generates control signals for external force to assist the user's intended movement based on the extracted movement intent information and transmits them to the multi-joint robot connected to the upper limb exercise assistive device.
• A movement intent extraction unit that extracts the user's movement intent information using the ratio of sensing values calculated for each sensor combination.
• A calculation unit that computes the ratio of sensing values between sensors included in pre-matched combinations among the plurality of sensors.

‍

This invention was developed with support from the Ministry of Science, ICT and Future Planning for the development of an active exercise system based on human-robot collaboration technology to enhance upper limb motor function in the elderly and infirm.

Joint positioning device for easy fit adjustment

This technology relates to a joint positioning device and its operating method, allowing users to adjust the force transmission points of a wearable robot to fit their body simply by operating a knob.

Conventional wearable robots require wires or webbing to be attached to precise points on the body to ensure performance, which has historically been inconvenient due to the need to manually adjust multiple straps and fasteners.

This technology enables intuitive position adjustment through a joint device consisting of adjustment elements and a knob, reducing preparation time and improving the reproducibility of assistive performance.

‍

‍

Key Features:

• A support frame featuring multiple through-holes spaced at specific intervals along its length to serve as a reference for positioning.
• A slider frame mounted to slide along the length of the support frame for length adjustment.
• A link oriented perpendicular to the support frame, featuring a gear along the circumference of its lower outer surface.
• A knob that locks the link's rotation by engaging with the gear in fixed mode and releases it in adjustment mode.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of a wearable robot for construction workers capable of providing over 10kgf of muscle assistance with excellent wearability.

Wearable Robotic Clothing with Enhanced Comfort and Aesthetics

This technology relates to a wearable robot integrated into high-performance clothing, featuring a base layer made of functional fabric with embedded drive components.

Conventional wearable robotic clothing often suffers from poor waist belt stability and exposed power transmission components, which detract from the garment's seamless integration, aesthetics, and overall comfort.

This technology improves both comfort and appearance by integrating the waist belt and thigh sections into the base layer and housing the power transmission path within a protective cover.

‍

‍

Key Features:

• A base layer featuring a single, integrated front-and-back pattern tailored to the user's body from the waist to the knees.
• A waist belt section positioned at the top of the base layer and a thigh section positioned at the bottom.
• A power transmission unit that connects the waist belt and thigh sections to deliver assistive force from the actuator to the wearer's lower limbs.
• An upper-body garment that serves as the wearer's top, housing the actuator and battery module that generate the assistive force.

‍

This invention was developed with support from the Ministry of Science and ICT for the "New Concept Wire-Fabric Mechanism-Based Ankle Assistive Device for Improved Gait Stability and Energy Efficiency" project, and the Ministry of Trade, Industry and Energy for the "Development of a Human-Augmented Hybrid Robot Suit Capable of Safe 100m Sprints in 7 Seconds and Comfortable 12-Hour Wear" project.

Wheelchair-type gait assistance robot combining a linear guide lift and an exoskeleton

This technology is a wheelchair-type gait assistance robot that integrates a lift composed of outer and inner linear guides into a drive unit equipped with drive motors and wheels, featuring a seat upper connected to the inner linear guide and an exoskeleton worn on the user's lower body.

Existing gait assistance devices have suffered from issues such as a lack of structural stability, limited operational space, and reduced effectiveness during long-distance travel, all of which increase the burden on the user.

This technology proposes a method for stably elevating the seat upper using a linear actuator and dual linear guides, while integrating it with an exoskeleton. Applicable to lower-limb rehabilitation and long-distance mobility assistance, it allows for seamless switching between gait training and wheelchair use in a single device, ensuring both structural stability and versatility.

‍

‍

Key Features:

• A drive unit comprising a main frame, drive motors installed on the main frame, and wheels driven by the drive motors
• An outer linear guide fixed to the main frame and an inner linear guide capable of vertical movement along the outer guide
• A seat upper connected to the inner linear guide and configured to move vertically with it
• A linkage assembly connected to the outer linear guide that unfolds and folds in response to the elevation of the inner linear guide

Underwater 3D Scanning Device Using Geometric Calculation of Rotating Camera and Line Laser

This technology is an underwater scanning device that projects a line onto an object and the seafloor using a laser emitter mounted on an underwater mobile body. It extracts the 3D shape of the object by geometrically calculating the distortion and spacing differences of the line captured by a camera rotating around the body's central axis.

Existing stereo vision methods require high-performance computing resources and lighting, while sonar methods necessitate expensive positioning sensors. Furthermore, determining the relative position between robots and objects underwater has historically been difficult, leading to high costs in achieving scanning precision.

This technology proposes a method to extract the height and actual size of an object without the need for separate, expensive positioning sensors by mathematically calculating the line length per frame and the spacing differences between the seafloor and the object. It can be applied to marine structure inspection and underwater artifact surveys, enabling precise 3D measurement with a low-cost configuration.

‍

‍

Key Features:

• A body capable of underwater movement extending in a first direction, and a propulsion unit for controlling movement
• A laser emitter that projects a line laser to form a line on the object and the surrounding ground where the object is placed
• A camera provided on one end of the body in the longitudinal direction to capture the object on which the line is formed
• A configuration that extracts 3D shapes by capturing images while rotating the camera around the longitudinal central axis of the body

‍

This invention was developed with the support of the Smart Underwater Tunnel System Research Center under the Ministry of Science and ICT.

Localization Status Diagnosis for Autonomous Mobile Robots Using Machine Learning-Based Distance and Heading Error Metrics

This technology is a localization status diagnosis method that determines whether an autonomous mobile robot has successfully localized itself by calculating distance error metrics based on range sensors and heading error metrics based on odometry, then inputting these into a supervised binary classification algorithm for self-diagnosis.

Existing localization diagnosis methods have faced challenges with high dependency on specific algorithms or fluctuating sensor data reliability depending on environmental conditions, making it difficult to achieve universal and robust diagnosis.

This technology proposes a method that defines distance error metrics using the average error of highly reliable range measurements and heading error metrics based on tolerance ranges, utilizing a trained binary classification model to determine success or failure in real time. It can be applied to indoor service robots and logistics robots, significantly enhancing operational stability by enabling the robot to detect when it has lost its position and initiate recovery procedures.

‍

‍

Key Features:

• A training phase where distance error metrics, heading error metrics, and localization success status are registered as training data.
• A sensing phase where multiple distance measurements are collected via range sensors at the robot's current position.
• A calculation phase where the robot's estimated heading at its current position is derived from odometry information.
• A diagnostic configuration that applies metrics calculated from measurements to a machine learning model to determine the success of localization.

‍

This invention was developed with support from the Ministry of Science and ICT for the "Intelligent Growth Autonomous Driving System for Unmanned Vehicles Operating Safely in Congested Living Road Environments" project, and the Ministry of Agriculture, Food and Rural Affairs for the "Agricultural Production Unmanned Automation Workforce Training and Research Support" project.

Task Allocation Technology for Heterogeneous Automated Transport Systems Combining Load Constraints and Heuristic Optimization

This technology is an automated transport system and task allocation method that optimizes route and task assignment by setting vertices for multiple heterogeneous automated guided vehicles (AGVs), calculating travel costs based on vehicle-specific structural characteristics, and integrating primal-dual heuristic techniques with load constraints.

In heterogeneous AGV systems with varying structural characteristics and load capacities, there has been a challenge in maximizing overall efficiency while minimizing the computational load required for task allocation and path planning.

This technology proposes a two-stage optimization process: first, setting initial vehicle positions and task nodes as vertices to obtain a travel cost matrix for initial allocation via heuristic techniques, and second, redistributing tasks by applying constraints that compare load capacity with required loads. It can be applied to unmanned transport systems in smart factories and logistics warehouses, significantly increasing throughput in environments where heterogeneous vehicles operate together.

‍

‍

Key Features:

• Step of registering structural characteristics and load capacity for each of the multiple heterogeneous automated guided vehicles
• Step of registering multiple tasks, including pickup nodes, delivery nodes, and required loads
• Step of setting tasks and initial nodes as vertices for each vehicle and calculating travel costs between vertices
• Configuration for allocating tasks to each vehicle by reflecting primal-dual heuristics and load capacity constraints

‍

This invention was developed with the support of the National Research Foundation of Korea's Intelligent Growth Autonomous Driving System for Unmanned Vehicles operating safely in congested residential road environments.

Elevator Recognition Technology for Mobile Robots Combining Deep Learning Recognition and Point Cloud Hough Transform

This technology identifies elevators by combining point cloud data collected via RGB-D sensors with deep learning-based image recognition models. It then accurately estimates the elevator's position and boundaries by analyzing linear data extracted through Hough transforms alongside point cloud distances.

Existing location recognition methods using laser range sensors or standard cameras often suffer from low accuracy due to reflections from metallic elevator surfaces, and they typically require additional environmental modifications, such as installing artificial markers.

This technology uses a deep learning model to identify elevators and processes RGB-D sensor point cloud data through noise reduction and Hough transforms to distinguish walls from elevators, subsequently calculating boundaries and positions through geometric analysis. It can be applied to indoor delivery and disinfection robots, enabling autonomous inter-floor movement without the need for separate markers.

‍

‍

Key Features:

• A movement phase where the mobile robot travels to a recognition point near the elevator to detect it.
• A phase where an estimated elevator image is acquired at the recognition point.
• A recognition phase where a model trained on elevator and non-elevator images determines the presence of an elevator.
• A phase where the elevator's position and boundaries are estimated using point cloud data and Hough transforms.

‍

This invention was developed with support from the Ministry of Science and ICT for the development of robotic hand manipulation intelligence, which learns methods and procedures for handling various objects using tactile-capable robotic hands.

Humidity-Responsive Actuator Using Aligned Nanofiber Moisture-Responsive Layers

This technology relates to a humidity-responsive actuator that operates without external electrical energy by utilizing the expansion of a moisture-responsive layer and the asymmetric behavior of an inactive layer in response to changes in relative humidity, as well as its manufacturing method and applications in robotics.

Conventional actuators require an external power supply, leading to a high dependency on energy sources and the need for additional wiring and power units.

This technology proposes a method of stacking a moisture-responsive layer of unidirectionally aligned nanofibers formed by electrospinning with a moisture-inactive layer. By implementing a driving unit that undergoes mechanical bending and straightening due to humidity differences, it provides an actuator that operates solely on environmental energy without the need for an external power source. It can be applied to environment-responsive smart materials, self-powered sensors, and autonomous robots, offering the potential for next-generation actuators free from the constraints of batteries and wiring.

‍

‍

Key Features:

• A moisture-responsive layer containing multiple nanofibers capable of expanding and contracting based on the amount of atmospheric moisture.
• An inactive layer that is unresponsive to moisture, inducing asymmetric behavior relative to the moisture-responsive layer to create bending deformation.
• The moisture-responsive layer is configured with multiple nanofibers stacked with gaps, providing porosity and unidirectional alignment.
• An actuator where the elongation along the longitudinal direction of the nanofibers increases as relative humidity rises.

Slider-type wire actuator for underactuation with minimized friction using driven bearings

This technology is a slider-type wire actuator and a glove-type wearable robot equipped with it, which converts the rotational motion of a drive motor into the linear motion of a slider via a drive wire, and performs underactuation by distributing the tension of a driven wire through a driven pulley and driven bearing mounted on the slider.

Wire-driven underactuated robots have historically faced issues such as reduced power transmission efficiency and component wear due to friction caused by slippage between the wire and contact surfaces, as well as increased production costs due to structural complexity.

This technology proposes a method to minimize friction between the wire and the structure by equipping the slider with a driven pulley and driven bearing, ensuring that the wire only slips within the bearing. The linear drive configuration using a drive pulley and drive wire reduces mechanical volume and production costs. It can be applied to rehabilitation glove robots and industrial gripping devices, providing a practical solution that enhances durability by reducing frictional loss and component wear while lowering manufacturing costs.

‍

‍

Key Features:

• A support body, a guide member installed to extend in the longitudinal direction, and a slider that moves linearly along it
• A drive unit including a drive motor, a drive pulley, and a drive wire connecting the drive pulley and the slider
• A driven unit including a driven bearing and a driven pulley installed on the slider, and a driven wire wound around the driven pulley
• An elastic member connected to the slider and the support body to provide elastic force in the direction opposite to the slider's movement

‍

This invention was developed with support from the Human-Centered Soft Robotics Technology Research Center of the Ministry of Science and ICT.