This technology is a passive dynamic gripper for aerial vehicles that automatically closes its claws to grasp an object by transferring the impact energy generated upon collision through a linkage structure and tendon mechanism.
Existing aerial vehicles, such as drones, have struggled to efficiently utilize the impact energy generated when interacting with objects without static approach, and have faced difficulties in immediately stabilizing their posture after grasping.
This technology proposes a mechanism that converts impact energy into claw-actuating force via tendons, and uses a tendon locking module—an electro-adhesive clutch—to rapidly maintain the claw's state. This allows for rapid object grasping during flight without the need for additional actuators. It can be applied to drone delivery, aerial retrieval operations, and securing supplies in disaster zones. Since grasping is achieved solely through impact without requiring additional drive power, it significantly reduces the payload and power burden on the aerial vehicle.
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 micro-gripper mechanism that connects an optical fiber to a gripper made of shape memory alloy, driving and deforming the gripper through Joule heating generated by light transmitted from a light source.
Conventional micro-grippers suffer from complex driving structures that make manufacturing difficult, as well as structural inconveniences requiring separate power supplies and high power consumption.
This technology proposes a structure that can be operated without separate electrical wiring by delivering heating energy to the gripper via light irradiation through an optical fiber. By using a Nitinol shape memory alloy gripper processed with a focused ion beam and a photocurable polymer adhesive, both miniaturization and precision manipulation are achieved. It offers a wireless-driven gripper for ultra-precision tasks such as semiconductor processing, bio-sample manipulation, and micro-assembly, opening new possibilities for micro-scale automation.
This invention was developed with support from the Ministry of Science and ICT for the nanoscale 3D printing system.
This technology is a shock-absorbing and vibration-damping neck device designed to stabilize sensor data for legged mobile robots. It features a linkage-based shock absorber and a tunable mass damper mounted on a sensor platform, which adjusts the absorption frequency in real-time by controlling the position of a linear stepping motor based on the robot's gait frequency.
Legged mobile robots often experience periodic shocks and vibrations during locomotion that resonate with the sensor platform, causing motion blur and reducing the accuracy of visual and inertial navigation. Conventional passive vibration-damping devices have struggled to adapt to changes in a robot's walking speed.
This technology utilizes a multi-joint linkage structure with hydraulic dampers and springs to absorb primary shocks. It further incorporates a tunable mass damper that adjusts the distance of the mass body via a torsion spring and linear stepping motor control. By actively varying the vibration-damping frequency to match the robot's gait, it ensures clear sensor data. This technology fundamentally enhances the perception performance of quadrupedal and patrol/inspection robots, serving as a critical component for reliable autonomous navigation in legged robots.
This technology features a robot joint structure based on tensegrity principles. Multiple bodies (first through third) are connected by a series of string members without direct contact, enabling 3-DOF (pitch, yaw, roll) rotation and flexibility against external forces.
Conventional rigid-body robot joints are prone to damage from external impacts, struggle to achieve flexibility along the axis of rotation through control methods alone, and suffer from friction and wear due to contact between rigid parts, as well as increased weight that makes long-term wear uncomfortable.
This technology implements a tensegrity structure by arranging three bodies in a non-contact configuration and utilizing string members in square pyramid, rhombus, and octahedron patterns. The first through third bodies are made of elastic materials, and bearings are installed at the rotation axis anchor points to prevent friction and wear. By separating the drive unit externally, the weight of the joint is significantly reduced. This design is ideal for robotic shoulders, collaborative robots, and wearable robots, providing flexible response to external impacts while minimizing joint weight.
This invention was developed with support from the Ministry of Science and ICT for the Tensegrity Robot System using Pneumatic and Tendon Hybrid Actuation.
This technology performs a pinch-grip motion with the fingertips by transmitting rotational torque from the drive unit through a four-bar linkage and connecting links. By adjusting the link length ratios of the four-bar mechanism, it controls the force vector direction applied to the fingertips, allowing the robot gripper to adapt to external environmental constraints, such as a table surface.
Conventional grippers often fail to account for collisions between the fingertips and environmental obstacles, such as tables, during pinch-gripping, which limits their ability to stably grasp small objects.
This technology configures the length ratios of the four-bar linkage (input, output, intermediate, and frame links) so that the force vector applied to the fingertips acts in a direction that lifts or lowers the object. Additionally, it incorporates a parallelogram linkage to maintain the fingertip angle and utilizes an elastic member and stopper between the output link and the frame link to ensure adaptive grasping. Suitable for logistics picking, precision assembly, and service robots, it enables stable grasping of small objects without colliding with surrounding constraints like tables.
This invention was developed with support from the Ministry of Science and ICT for the development of biomimetic bionic arm mechanisms.
This technology features a robotic arm that concentrates both the upper and lower arm actuators at the shoulder base. It utilizes a 4-bar linkage assembly, consisting of a transmission link and two link units, to transfer the rotational force of the lower arm actuator to the elbow axis, allowing for independent or synchronized control of the upper and lower arm.
Conventional technology typically places actuators directly on the elbow joint, which leads to reduced control responsiveness as the end-effector load increases and complicates wiring design.
By centralizing the actuators at the base and transmitting physical power through a linkage assembly, this technology reduces the end-effector load and improves control responsiveness. It can be applied to wearable upper-limb assistive robots, rehabilitation training equipment, and collaborative robotic arms, enabling precise joint control while minimizing the burden on the user through a lightweight end-effector structure.
This technology is a monitoring method that determines in real-time whether a human-robot collaboration state is safe within a specific frequency band by passing multi-degree-of-freedom force signals through low-pass and high-pass filters and comparing the Euclidean norm values of each output signal.
Existing DFT-based frequency analysis techniques require large amounts of sampling data to achieve low frequency resolution, making it impossible to recognize collaboration states quickly within 0.5 seconds, which can lead to safety issues such as skin plastic deformation during collisions.
Instead of DFT, this technology separates frequency components using a 2nd-order IIR Butterworth filter and calculates the collaboration state value through median calculation using the ratio between filter outputs, derivative filter smoothing, and saturation processing. It can be applied to the safety control of collaborative robots and wearable robots, dramatically increasing operator safety through immediate risk detection within 0.5 seconds.
This technology relates to a variable driving assembly for military robots, specifically a driving device capable of mechanically switching between standard road driving mode and rough terrain driving mode.
Military robots previously required a choice between wheel and tracked systems depending on the mission environment; however, relying on a single method imposed significant operational limitations, as it could not simultaneously satisfy the requirements for high-speed driving on paved roads and traversing rough terrain.
This technology implements two driving modes on a single platform by modifying the wheel configuration through variable links and a variable driving force supply unit. This significantly enhances adaptability to diverse driving conditions.
This technology relates to a biomimetic lightweight wearable suit and its design method, featuring an assistive suit that optimizes force transmission paths by mimicking human anatomical structures and physical properties.
Conventional exoskeleton devices are often heavy and bulky, making them uncomfortable for daily use, while their rigid frames restrict joint movement and reduce overall comfort.
By aligning force transmission patterns and anchor points with human muscle and tendon structures, this technology achieves a lightweight, flexible design that enhances walking and mobility efficiency. It is applicable to various assistive devices, including ankle exoskeletons.
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 12 hours of comfortable wear; the Ministry of Agriculture, Food and Rural Affairs for the development of a deep-learning-integrated smart wearable suit to assist forest workers with muscle strength, injury prevention, and work efficiency; and for the development of soft wearable robot suits to assist the gait of the elderly and Parkinson's patients.
This technology is a system that calculates the current electrical phase difference between rotors in a coaxial magnetic gear drive module equipped with a motor and multiple rotors, and controls the motor to a target torque by adjusting the rotation angle of one of the rotors to converge on a target phase difference.
Conventional reduction mechanisms suffer from wear due to mechanical contact, leading to high maintenance costs, while existing non-contact power transmission mechanisms have limitations in terms of torque control performance and stability.
This technology proposes a method that linearizes the non-linearity of magnetic gears by combining a disturbance observer with a non-contact power transmission structure that utilizes the magnet arrangement of inner and outer rotors. It can be applied to small robots and collaborative robot drive systems, enabling precise torque control while reducing maintenance costs through wear-free, sealed power transmission.
This invention was developed with support from the Ministry of Science and ICT for research on the design and control of non-contact active small continuous variable transmission mechanism modules for ideal robot operation.
본 기술은 모바일 로봇 하단의 전·후·좌·우 4면에 매립 배치된 광시야각 라이다 센서로부터 깊이 영상을 획득하고, 센서별 캘리브레이션 파라미터를 이용해 단일 World 좌표계로 정합하여 사각지대 없는 통합 3D 포인트 클라우드를 생성하는 감지 시스템입니다.
기존 로봇 상단 탑재형 라이다는 고가이면서 부피가 크고, 센서 사각지대로 인해 로봇 하부와 구동부 근처의 장애물을 감지하지 못해 별도의 보조 센서가 필수적이라는 비효율이 있었습니다.
본 기술은 4면에 매립된 라이다로 수평 전방향 서라운드 뷰와 수직 30도 이상의 화각을 확보하고 회전변환 행렬과 원점 좌표를 이용해 개별 센서 데이터를 병합하는 방식을 제안합니다. 라스트 마일 배송 로봇과 실내 서비스 로봇에 적용될 수 있어 보조 센서 없이 음영 지역을 제거하여 주행 안전성과 원가 경쟁력을 동시에 확보합니다.
본 발명은 과학기술정보통신부의 광시야 고해상도 라이다 기반 라스트 마일 자율주행 로봇 플랫폼 지원을 통해 개발되었습니다.
This technology is a reinforcement learning-based gait control method that enables robots to quickly resume adaptive walking when hardware failures, such as leg damage, occur. It achieves this by distilling knowledge from an agent trained in a normal state and utilizing it as a refined joint trajectory space through an encoder-decoder neural network.
Existing gait control technologies can adapt to terrain or environmental changes, but they face inefficiencies when hardware failures occur, often leading to a loss of control or requiring the agent to be retrained from scratch.
This technology proposes a method that uses a conditional variational autoencoder to set the joint trajectory space as the action space, narrowing the search space during failures based on knowledge learned in a normal state. It generates anchor points and paths based on conditional vectors to derive optimal joint trajectories in real time. This ensures robust autonomy, allowing robots to autonomously reconfigure their gait even when legs are damaged, making it ideal for environments where mission interruption is critical, such as disaster site exploration, defense, and industrial patrolling.
This invention was developed with support from the Artificial Intelligence Graduate School Program (Korea University) funded by the Ministry of Science and ICT.
This technology is an AR-based robot arm control system that detects objects in real-time from video captured via an AR device and calculates their 3D coordinates using ray casting and mesh generation to precisely control the target position of a robot arm.
Conventional controller or eye-tracking methods are difficult for individuals with physical disabilities, such as quadriplegia, to operate directly. Furthermore, these methods present inconveniences and collision risks, as users must simultaneously monitor the screen and the robot arm's position.
This technology proposes a method where an AR device recognizes the user's gaze to select a specific object, calculates the relative distance and 3D coordinates between the object and the robot arm, and enables the robot arm to automatically move and perform grasping tasks, ensuring intuitive and safe operation. It can be utilized for rehabilitation assistance, support for daily living for people with disabilities, and remote operations, significantly improving the independence and quality of life for users with physical limitations.
This invention was developed with support from the Ministry of Science and ICT for the "Development of Customized Brain-Robot Interface for the Physically Disabled with Improved Accuracy, Speed, and Convenience" and the "Development of Non-invasive BCI Integrated Brain-Cognitive Computing SW Platform Technology for Controlling Real-life Appliances and AR/VR Devices via Thought" (BCI-General/Sub-project 1) projects.
This technology is an AI-based approximate path planning device and method that identifies substitute objects or approximate spaces when a target object is not detected by utilizing distances in an embedding vector space, and re-plans the robot's destination and movement path accordingly.
Previously, if a target object commanded by a user was not detected in the surrounding environment, it was impossible to set an endpoint, causing the robot's path planning to be interrupted and the movement task to fail.
This technology proposes a method that uses an embedding algorithm to extract a substitute object with an embedding value closest to the target object, or identifies an approximate space where the target object is highly likely to exist, and generates a path to that point. This allows tasks to continue without interruption even when recognition fails. It is applied to home service robots and indoor delivery robots to ensure autonomy that flexibly responds to the uncertainties of real-world environments.
This invention was developed with support from the Artificial Intelligence Graduate School Program (Korea University) funded by the Ministry of Science and ICT.
This technology is a multifunctional soft robot mechanism that combines four pneumatically driven modules with two snap-through joint sections, allowing the robot to change and maintain its geometric shape using only a single pneumatic control.
Conventional pneumatic network soft robots require continuous air supply to maintain their shape and demand complex inputs, which increases the overall volume and weight of the device.
This technology introduces bistable shell-structured snap joints that use snap-through and snap-back behaviors triggered by critical pressure to lock the robot's physical shape. This enables the implementation of a soft robot capable of dynamic mode switching, such as aligning the four drive modules in a line or deploying them horizontally depending on the control mode. Because it can switch between various movement modes with a single pneumatic input, it offers exceptional competitiveness in environments requiring multifunctionality with limited resources, such as exploration and disaster response robotics.
This invention was developed with support from the Metamorphic Mechanical Systems Research Group of the Ministry of Science and ICT.
