This technology utilizes a magnetic gear to split rotational force from a single power source, enabling a gripper to perform both part gripping and fastening without the need for a separate electric screwdriver. Its non-contact torque transmission prevents excessive gripping force.
Existing solutions often require expensive tool changers to switch between grippers and electric screwdrivers. Furthermore, using separate power sources leads to energy waste, reduced control efficiency, and the risk of damaging components.
This technology features an integrated design that transmits motor torque to a magnetic gear composed of primary and secondary rotating magnets, simultaneously driving the gripping mechanism and rotating the fastening tool holder. It ensures stable fastening through a lead screw-based anti-backdrive gripping mechanism. Suitable for electronics assembly and automated production lines, it significantly reduces cycle times and equipment costs by eliminating the need for tool changers.
This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of intelligent robot technology capable of recognizing and assembling objects in real-world environments based on given work plans.
This technology is a gait assistance system that calculates the predicted stiffness of the ankle joint by analyzing the wearer's lower limb electromyography (EMG) signals using LSTM or CNN-based machine learning algorithms, and controls the ankle joint angle by integrating data from foot contact sensors.
Existing stiffness prediction methods using muscle models or mathematical linearization formulas have suffered from low accuracy, as they fail to fully account for the non-linear characteristics and time-varying states of muscles.
This technology proposes a method that trains machine learning algorithms based on EMG and stiffness data from multiple pedestrians to predict real-time stiffness, while utilizing combined data from toe and heel contact sensors to calculate target angles. It can be applied to rehabilitation therapy and gait assistance for the elderly, providing natural gait support by adapting in real-time to changes in the wearer's muscle condition.
This invention was developed with support from the Ministry of Culture, Sports and Tourism's project for hybrid smart clothing and monitoring systems for enhanced athletic performance, and the Ministry of Science, ICT and Future Planning's Human-Centered Soft Robot Technology Research Center.
This technology is a tidying system that controls an articulated robot to match the arrangement of multiple target objects in an unstructured environment to a target image. It uses an image segmenter to process current and target images, then sequentially applies deep reinforcement learning-based task sequencing and motion estimation models.
Existing cleaning robots are limited to simple suction tasks, and tidying objects in unstructured environments has historically been inefficient and inflexible, requiring operators to manually pre-define sequences and locations.
This technology proposes a method for planning final robot motions by combining AI-based image segmentation, deep reinforcement learning-based task sequencing and motion estimation, 3D point cloud processing, and generative adversarial networks. This allows the robot to autonomously establish tidying plans without pre-defined instructions. It can be applied to home service robots and automated retail display systems, significantly expanding the range of household and service tasks that robots can perform.
This technology is a vision-based collaborative simultaneous localization and mapping (SLAM) system. To identify rendezvous situations between multiple platforms and fuse individual SLAM maps, it uses an optimization algorithm at a ground station to compare and calculate the movement of non-static features extracted from each platform, along with the similarity of pose and map information between platforms, to perform inter-platform matching.
Existing collaborative SLAM systems have faced significant limitations in sensor configuration and operation, as they often require visual markers for platform identification or demand precise distance information.
This technology proposes a method that tracks and manages non-static features—which are typically discarded in images collected by monocular cameras—without the need for separate markers. By formulating the detection of inter-platform rendezvous as an optimization problem, it enables the fusion of individual maps and pose data at a ground station, allowing for collaborative mapping among multiple robots with a simple sensor setup. It can be applied to multi-drone exploration, collaborative mapping in disaster zones, and indoor autonomous navigation. Since it is implemented using only a monocular camera without markers or expensive sensors, it significantly reduces system construction costs.
This invention was developed with support from the multi-ministry project for the development of autonomous driving assistance robots for foldable wheelchairs.
This technology is a multi-object gripping gripper featuring a storage unit composed of multiple polymer belts and bristle elements. By combining finger members, link members, slider members, and a tendon-driven mechanism, it performs flexible multi-object gripping and sequential storage operations.
Conventional multi-object gripping grippers have limited utility in environments where object arrangement is inconsistent due to their fixed gripper structure, and they lack the capability for simultaneous multi-object gripping and storage of unaligned items.
This technology proposes a method that integrates a drive unit—consisting of finger members, finger connecting members, sliders, and links—with an internal storage unit containing polymer belts and bristle elements. It controls the gripper's rotational and translational motion using gripping and transmission tendons, allowing it to grip individual objects and stack them sequentially into the internal storage. This significantly improves operational efficiency in fields requiring continuous processing of multiple objects, such as logistics sorting, agricultural harvesting, and waste sorting, thereby maximizing productivity in automated lines.
This invention was developed with support from the Ministry of Trade, Industry and Energy's project for developing collaborative assistive robot arms using foldable hybrid-driven soft robot technology, and the Ministry of Science and ICT's Human-Centered Soft Robot Technology Research Center.
This technology is a deployable robotic arm that utilizes multiple panels wound around a hub. By applying sliding and folding mechanisms, it minimizes volume through a rolling method during storage and achieves high structural rigidity upon deployment by forming a folded structure via shape-forming and shape-maintaining devices.
Conventional deployable robotic arms have faced technical limitations where storage efficiency and structural rigidity are in conflict due to link joint play, weakened strength at folding lines, and thickness constraints inherent in rolling structures.
This technology proposes a method where panels with sliding and folding structures are stored by winding them around a hub. Upon deployment, a shape-forming device guides the panels into a folded structure, while a shape-maintaining device—equipped with a spacing adjustment mechanism and a wire winder—ensures structural rigidity in the deployed state. This allows for both high storage efficiency and high rigidity. It serves as an innovative solution to the fundamental limitations of existing robotic arms in fields requiring both portability and strength, such as space structures, disaster site exploration equipment, and mobile service robots.
This technology is a joint mechanism based on a tensegrity structure that maintains a non-contact state between a first body and a second body, providing rotation and flexibility through wire integration. It utilizes the equilibrium of wire forces to perform rotational movement without physical contact between bodies and controls stiffness and range of motion by adjusting wire tension during external impacts.
Conventional rigid-body joints have faced issues such as the transmission of external shocks, a lack of rotational flexibility due to control limitations, and reduced durability caused by physical friction and wear between bodies.
This technology places a spacer between the first and second bodies and utilizes wire members (first, second, and third connecting wires) to implement a tensegrity structure. A drive motor pulls the wires to induce rolling motion along a virtual circumference, while the inclined design of the frame physically limits the range of motion. Applicable to collaborative robots, wearable robots, and precision manipulators, it enhances rotational performance and longevity by eliminating friction and wear between bodies.
This invention was developed with support from the Ministry of Science and ICT for the development of biomimetic bionic arm mechanisms.
This technology is a biomimetic joint mechanism that performs bending motions using tendon tension and returns to its initial position using the resilience of a string set. It is designed to allow joint rotation without bearings by connecting multiple bodies with strings at set intervals.
Existing robot joints suffer from mechanical wear, discomfort due to heavy components, a lack of biomimetic structure, limited shock absorption, and increased control complexity.
This technology constructs joints by connecting bodies with tendons and multiple strings, eliminating direct contact between the bodies. Bending is controlled via tendon tension, while the tensile elasticity of the strings provides natural restoration. By asymmetrically adjusting the tension of certain strings, the range of motion during rotation can be variably limited to enhance gripping force. Applicable to wearable robots, prosthetic hands, and collaborative robots, it enables bearing-free joint operation while improving durability and wearer comfort.
This invention was developed with support from the Ministry of Science and ICT for the development of biomimetic bionic arm mechanisms.
This technology is a mechanical manipulation device that induces finger rehabilitation exercises for patients by converting rotational force from a drive source into a link structure (main link and thumb link).
Conventional technologies faced challenges such as high manufacturing costs due to complex structures, as well as difficulties in selectively operating the thumb and four fingers and achieving precise movement.
This technology implements hand rehabilitation exercises with a minimal connection structure by controlling the movement of the link structure through a single motor, a power transmission shaft, and a selective gear coupling method that includes a four-finger motion control unit and a thumb motion control unit. It can be applied to rehabilitation training, gait assistance, and medical/welfare services, improving the simplicity and cost-efficiency of hand rehabilitation robots by reducing structural complexity and manufacturing costs.
This invention was developed with support from the Ministry of Science, ICT and Future Planning for brain mapping-based robot rehabilitation.
This technology is a robotic structure that performs selective rehabilitation exercises by transmitting rotational force generated from a drive unit to a finger-seating unit via a link structure and a control unit.
Conventional hand rehabilitation robots struggle to control the selective movement of the thumb and the other four fingers, and their complex structures lead to high manufacturing costs.
Based on a single motor and a power transmission shaft, this technology features separate movement control units for the four fingers and the thumb, allowing for selective power transmission to perform finger rehabilitation exercises. Applicable to rehabilitation training, gait assistance, and medical/welfare services, it uses a single motor to simultaneously improve the selective rehabilitation of both the fingers and the thumb.
This invention was developed with support from the Ministry of Science, ICT and Future Planning for brain mapping-based robot rehabilitation.
This technology relates to an elastic unit capable of adjusting elastic force and elastic curves, and its operating method. It involves a technology that varies the stiffness characteristics themselves through a plurality of elastic control modules.
Conventional elastic members have fixed stiffness, requiring parts to be replaced whenever the intended use changes. Furthermore, adjusting the elastic curve—the displacement-load curve—in addition to the magnitude of the elastic force, has been even more difficult.
This technology simultaneously adjusts elastic force and elastic curves by combining elastic and inelastic bands and controlling the position of the fixing unit. It can be applied to various products, such as passive wearable robots and training equipment.
This invention was developed with support from the Ministry of Science and ICT for the development of machine learning and extended reality for high-speed mutual adaptation between users and wearable robots; the Korea Forest Service for the development of deep learning-integrated smart wearable suits for forest worker muscle assistance, injury prevention, and work efficiency improvement; and the Ministry of Trade, Industry and Energy for the development of human-augmentation hybrid robot suits capable of safe 7-second 100m sprints and comfortable 12-hour wear.
This technology relates to a gas supply system and operating method for driving pneumatic actuators, utilizing the vaporization of liquid nitrogen to supply high-pressure gas to wearable pneumatic actuators.
Existing pneumatic drive systems for wearable robots required compressors and large-capacity tanks, resulting in heavy weight, bulky volume, complex structures, and high manufacturing costs.
By incorporating a liquefied gas chamber and a vaporized gas discharge line, and utilizing waste heat to accelerate vaporization, this technology achieves lightweight, high-output pneumatic actuation while preventing actuator damage to enhance efficiency and safety.
This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of a human-augmentation hybrid robot suit capable of a 100m sprint in 7 seconds and comfortable 12-hour wear.
This technology features a gait assistance robot where the upper and lower leg units are connected by a knee joint unit, and the footplate is connected via an ankle joint unit. It utilizes intent-sensing sensors installed on the lower leg unit to instantly detect the wearer's gait intent based on muscle movement.
Existing gait assistance devices have struggled to accurately and quickly identify a user's gait intent. Furthermore, they often suffer from high noise levels, significant power consumption, and joint stiffness, making them ineffective for supporting patients in the early stages of rehabilitation.
This technology proposes a method that provides immediate assistance by combining intent-sensing sensors, which directly detect muscle movement, with a non-powered propulsion module. It can be applied to the rehabilitation of patients with central nervous system disorders, such as stroke, supporting natural gait tailored to the patient's intent while minimizing noise and power consumption.
This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of a machine learning-based lower limb rehabilitation robot system customized for stroke and Parkinson's patients.
This technology is a control method for scanning the 3D shape of an object by moving an underwater robot, equipped with a camera and a laser projector that emits a line laser at an angle, vertically between the minimum height required for object imaging and the maximum height for laser alignment, while simultaneously rotating it.
Existing stereo vision methods require high-performance computing and lighting, while sonar methods rely on expensive sensors, increasing manufacturing costs. Furthermore, these methods face challenges in achieving precise height control and resolution optimization for high-resolution 3D scanning.
This technology proposes a method of acquiring data with higher resolution toward the outer edges of an object by maintaining a constant tilt of the line laser while controlling rotation continuously or intermittently as the height descends. It can be applied to marine structure inspection and underwater terrain surveying, enabling high-resolution 3D scanning using only low-cost equipment.
This invention was developed with support from the Smart Underwater Tunnel System Research Center of the Ministry of Science and ICT.
This technology is a torque measurement system that precisely estimates joint torque by modeling and compensating for mechanical eccentricity errors within the reducer in a dual-encoder system—using both input and output encoders—and calculating the torsion angle from the angular deviation that occurs under load.
Existing robot joint torque measurement methods have faced structural limitations, such as the high cost of dedicated force/torque sensors, reduced joint stiffness in strain-gauge-based systems, and the low accuracy and difficulty of modeling reducer friction in current-based methods.
This technology proposes a method that models and stores mechanical eccentricity errors under no-load conditions using functions such as polynomials or Fourier series. During operation, it subtracts the compensation function value from the angular deviation to derive the pure torsion angle, which is then multiplied by the joint stiffness to calculate torque. It serves as an innovative solution for collaborative robots and precision assembly equipment, enabling precise force control without the need for expensive torque sensors.
This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of deep reinforcement learning-based collaborative technology capable of intelligently responding to unstructured work environments, such as assembly tasks.
