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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
This invention was developed with the support of the Smart Underwater Tunnel System Research Center under the Ministry of Science and ICT.
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.
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.
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.
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.
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.
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.
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.
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.
This invention was developed with support from the Human-Centered Soft Robotics Technology Research Center of the Ministry of Science and ICT.
This technology is a monolithic joint mechanism that uses 3D printing to output multiple bodies in a separated state, which are then deformed to make contact through external force, maintaining contact and performing rolling motion through the interaction between the connecting parts and guide parts.
When joint parts that come into contact are printed as a single piece using 3D printing, they fuse together, preventing movement. Conversely, printing them separately requires a manual assembly process, which introduces assembly gaps and makes precision control difficult.
This technology proposes a method where multiple bodies are printed as a single piece in a first state, separated by a rolling surface, and then transition to a second state where the bodies come into contact as the connecting part is tensioned by external force, following an arc-shaped guide. This enables the implementation of joints capable of precise rolling motion without any assembly process. It can be applied across various 3D printing-based manufacturing fields, such as medical devices, small robots, and custom mechanical parts, significantly reducing production time and costs by eliminating the need for assembly.
This invention was developed with support from the Ministry of Science and ICT for the development of biomimetic bionic hand mechanisms.
This technology features a mechanism where plug and wire grippers are spaced apart on the first and second gripper bodies of a robot gripper, sliding along a rail to simultaneously grip and press both the plug and its connected wire.
Conventional parallel jaw grippers suffer from limited gripping surface area for electrical connectors, poor compatibility due to connector size variations, and risks of movement path restrictions or connection damage caused by exposed wires.
This technology separates the plug and wire gripping sections and uses first and second pressure plates to secure the plug. By setting the hardness of the plug gripping surface lower than that of the wire gripping surface, it enhances gripping stability and achieves variable-width gripping through sliding rail actuation. It can be applied to manufacturing assembly, electrical automation, and industrial robotics, increasing assembly process efficiency by simultaneously gripping connectors and wires of varying specifications.
This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of process technology, grippers, and assembly techniques for small, precision component assembly in mobile IT products.
