This technology is a compliant control system that operates a target robot in parallel with a corresponding virtual model. It identifies differences between the two state signals as operational errors and limits the compensation range based on the magnitude of disturbances and the robot's sliding speed, thereby suppressing excessive driving torque.
Conventional industrial robots often misinterpret external collisions or disturbances during operation as simple tracking errors, leading the control system to apply excessive torque, which can result in equipment damage or safety accidents.
This technology utilizes an operational error observer to calculate the state difference between the physical robot and the virtual model, and a compensation output unit to separately output virtual and actual compensation signals, enabling the robot to adapt to external forces. It can be applied to precision assembly and human-robot collaboration environments, ensuring safety for both the robot and the operator during collisions without the need for additional force sensors.
This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of a universal multi-mode robot teaching device for high-difficulty assembly tasks requiring 0.1mm precision in position, velocity, and contact force teaching.
This technology features a soft finger unit and gripper that selectively implements shape-adaptive grasping and vacuum suction grasping through a single pneumatic control. It utilizes a soft body made of stretchable material with internal pneumatic channels and an opening/closing module that operates under positive and negative pressure.
Existing soft grippers suffer from low payload capacity and difficulty in grasping specific shapes, such as thin sheets. This has historically necessitated the inefficient addition of separate suction-type grippers to overcome these limitations.
This technology introduces a check-valve-based opening/closing module at the tip of the soft body. It performs shape-adaptive grasping by expanding the bending chamber under positive pressure and enables suction grasping by opening the module to deliver vacuum pressure under negative pressure. This allows a single gripper to perform both grasping methods. It significantly improves facility efficiency by handling various object shapes in fields such as food packaging, logistics picking, and electronic component handling without the need for gripper changes.
This invention was developed with support from the Ministry of Trade, Industry and Energy for recognition technology and grippers capable of multi-product random piece picking.
This technology is an underactuated robot gripper that utilizes a single motor and a magnetic-based non-contact power transmission mechanism. It drives multiple fingers with a single actuator and performs adaptive grasping tailored to an object's shape through a complex kinematic structure incorporating worm gears and magnetic gears.
Conventional robot hands have been difficult to apply to service robots due to complex control requirements and high costs, while simple industrial grippers have limitations in flexibly grasping objects of various shapes.
This technology proposes a method that transmits motor power to the output shaft of each finger via a set of magnetic and worm gears, utilizing torsion springs and multi-stage link structures to allow finger joints to bend according to the object's shape upon contact. This enables adaptive grasping with only a single actuator. It can be applied to service robots, logistics picking, and daily assistance robots, significantly reducing the production cost of robot hands while maintaining high grasping performance.
This invention was developed with support from the Ministry of Trade, Industry and Energy for recognition technology and grippers capable of high-mix random piece picking.
This technology is a tactile sensing system that uses thermoelectric elements and temperature sensors attached to a robot gripper's fingertips to acquire time-series data on thermal conductivity changes during object contact, which is then processed by a 1D-CNN deep learning model to identify and classify objects.
Existing robot recognition systems based on pressure or force sensors often struggle with limited classification accuracy, as they fail to provide sufficient information regarding the unique physical properties of an object's texture or material.
This technology proposes a method where the thermoelectric element heats the fingertip above room temperature before contact; the temperature sensor then measures the temperature changes caused by the object's thermal conductivity, and the deep learning model classifies the data. This allows for precise object recognition that incorporates material properties. It can be applied to logistics sorting, recycling, and service robot object handling, providing a new means of perception that can distinguish objects that are difficult to identify using visual information alone.
This invention was developed with support from the Ministry of Science and ICT for the development of electro-hydraulic actuator-based soft robot modules.
This technology is an elbow rehabilitation device that measures the stiffness of a patient's elbow joint and performs rehabilitation training by controlling the speed of the drive motor based on torque values.
Conventional rehabilitation robots struggle with precise operational control based on a patient's stiffness and lack adequate response to sudden spasms, posing a risk of injury to the patient.
This technology uses a torque sensor to measure the load applied to the elbow and its instantaneous changes in real-time, while a rehabilitation control unit variably adjusts the motor's rotation angle and speed according to the patient's condition. Applicable to rehabilitation training, gait assistance, and medical/welfare services, it provides a robot capable of adjusting treatment based on the patient's condition and mobility, thereby improving the effectiveness of rehabilitation therapy for stroke patients with elbow stiffness.
This invention was developed with support from the Ministry of Science, ICT and Future Planning for brain mapping-based robot rehabilitation.
This technology corrects sensor and control errors that occur during autonomous robot localization and mapping. It generates a noise-minimized map by inputting real-time robot-view maps and global maps into a style transfer learning model, which is then used to calibrate the robot's position.
Existing autonomous robots often suffer from degraded localization performance in real-world operation due to discrepancies between simulated and actual environments, as well as errors in odometry sensors and motor control.
This technology utilizes an operation control program to generate robot-view and global maps. By applying a style transfer learning model between ground-truth image sets and real-world image sets, it produces transformed map data to calibrate the navigation agent's position estimates, enabling precise localization and mapping in real-world environments. Since it bridges the gap between simulation and reality using only a learning model—without the need for additional sensors—it significantly reduces development costs and trial-and-error during the commercialization of logistics and service robots.
This invention was developed with support from the Ministry of Science and ICT for learning to establish mid-to-long-term task plans for service robots through hierarchical understanding of 3D information.
This technology utilizes 1-axis force sensors placed on each link connecting the top and bottom plates of a Stewart platform structure to calculate multi-axis force/torque data, enabling collaborative driving and internal force control among multiple mobile robots.
Conventional single mobile robots are limited in payload capacity and size, making them inefficient for transporting large or irregularly shaped objects and creating an economic burden by requiring the acquisition of separate, larger robots.
This technology configures multiple mobile robots in a master-slave structure and calculates the 1-axis force sensor data (summed force and torque values) from each robot's Stewart platform links in real-time. It then adjusts and controls the driving speed of individual robots using force control and force-velocity algorithms. Applicable to logistics, service robots, and autonomous driving platforms, it enhances the efficiency of object transport, particularly in e-commerce and warehouse management, by reducing unnecessary costs and resource usage.
This invention was developed with support from the Ministry of Science, ICT and Future Planning for research on neural robot technology based on physical and cognitive interaction.
This technology is a multi-user Human-Swarm Interaction (HSI) control system that tracks user hand gestures in virtual reality (VR/AR/MR) environments to simulate swarm robot movement paths, formations, and control commands in real-time, applying them to actual robotic systems.
Existing 2D interface-based swarm control has limitations in 3D spatial manipulation and fails to support complex formation control or simultaneous multi-user operation beyond individual robot control.
This technology integrates head-mounted displays with hand-tracking systems to visualize robot swarms in a 3D virtual space. It enables intuitive control through hand gestures such as pinch-to-zoom for viewpoint manipulation, automatic scaling, waypoint setting, virtual wall creation for herding, and swarm shaping, allowing multiple users to control swarm robots simultaneously. By significantly reducing the operational complexity in fields requiring the simultaneous deployment of multiple robots—such as logistics warehouses, disaster response, and defense surveillance—it provides a practical solution to lower the barriers to the commercialization of swarm robotics.
This invention was developed with support from the Ministry of Science and ICT’s Human-Centered Soft Robot Technology Research Center and the Ministry of Science and ICT’s project for developing 3D collaborative teleoperation technology for unstructured tasks in harsh environments.
This technology is an upper limb rehabilitation device featuring a modular structure designed to support a patient's upper arm, forearm, and hand for rehabilitation exercises. Each module can be selectively attached or detached using a dovetail mechanism, and the kinematic structure allows for independent operation and control of the elbow, wrist, and fingers.
Conventional integrated upper limb rehabilitation robots require all components to be assembled regardless of the specific area needing rehabilitation, resulting in large installation footprints, high costs, difficulty in switching between left and right arm configurations, and low user convenience.
This technology utilizes a base frame and a modular design with a dovetail attachment system for the upper arm support, forearm exercise unit, and hand rehabilitation unit. This allows for selective assembly based on the specific rehabilitation area, easy switching between left and right arm use, and adjustable length mechanisms. Applicable to rehabilitation training, gait assistance, and medical/welfare services, it improves installation efficiency and utility by allowing hardware to be selected based on the specific body part requiring rehabilitation.
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 multifunctional soft robot mechanism based on a variable-stiffness structure that applies origami and kirigami principles. It uses motors and cable tension to control the folding, unfolding, and rotation of the structure, enabling both locomotion and shape transformation through two mobile parts.
Existing soft robots have limitations, such as low stiffness, which makes them vulnerable to external forces, and monotonous deformation methods that restrict them to single-function tasks.
Based on the Miura-ori pattern, this technology features a variable structure composed of sub-bases and sub-heads. By adjusting cable tension via motors and pulleys embedded in the first and second mobile parts, the robot can precisely control its bending, contraction, and stiffness. This allows a single robot to perform various locomotion and transformation tasks. It offers new possibilities beyond the stiffness limitations of conventional soft robots and can be widely applied in environments requiring shape changes, such as navigating narrow spaces, entering disaster sites, and logistics automation.
This invention was developed with support from the Metamorphic Mechanical Systems Research Group of the Ministry of Science and ICT.
This technology consists of a brokerage server, a customer device, and a driver device. It facilitates a reverse auction-based designated driver service where customers input trip details such as origin and destination, and drivers bid their desired rates, allowing the customer to select their preferred driver.
Existing designated driver services often lack transparency in the selection process, as customers cannot choose their own drivers, making it difficult to build trust regarding pricing and service quality, while also creating potential for misuse or disputes.
By presenting driver information and bid amounts to the customer and displaying real-time availability, this technology allows customers to select the most suitable driver based on various factors. It can be applied to O2O mobility platforms, including designated driver services, to enhance service transparency and user convenience.
This technology provides a mechanical mechanism for a gripper module mounted on the end of a multi-jointed robot arm to attach or detach a rod-type coupling aid on a device module, or to grip workpieces such as bolts, using a coupling interface and gripping groove formed on two fingertips.
Previously, manual tool changes were required for every task, resulting in low efficiency, while the use of tool changers led to excessive downtime during changeovers.
This technology features a mechanical interface structure designed with a concave coupling section on the inner side of the fingertips and a gripping groove crossing it. By inserting the protruding rod-type coupling aid of a device module into the coupling section, the module is secured, while the gripping groove allows for the handling of objects like bolts. Applicable to manufacturing automation, assembly processes, and service robots, it increases task transition efficiency by enabling device tool changes without the need for a tool changer.
This invention was developed with support from the Grand ICT Research Center funded by the Ministry of Science and ICT.
This technology is a high-degree-of-freedom (DOF) robot hand design that features multiple motor sets within the palm module, combining wire and gear drive systems to enable finger flexion/extension and abduction/adduction.
Conventional tendon-driven robot hands often require the drive unit to be mounted on the forearm due to the bulk of the motors and controllers, which limits their practical application and increases the overall system size.
This technology integrates the drive module within the palm, utilizing a bearing array to control wire paths for each finger joint and a stopper member to limit motor rotation, thereby achieving independent multi-DOF control. Additionally, the palm and finger modules are designed to be detachable, enhancing maintenance convenience. Suitable for humanoids, manufacturing automation, and service robots, this design enables multi-DOF movement and easy maintenance entirely within the palm, eliminating the need for forearm-mounted drives.
This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of robot task control technology capable of grasping and manipulating various objects in daily life environments and utilizing tools based on multimodal perception.
This technology is a manual tool changer mechanism for replacing robot end-effectors. When an operator moves the shaft using a handle, the shaft bracket, link, and hook bracket work in tandem to lock the guide pins of the lower mechanical plate.
Conventional technologies faced challenges such as manufacturing and setup difficulties due to complex structures, reduced coupling accuracy caused by bending deformation of the Z-axis reference plane, and the risk of tool detachment in air-driven systems if the air circuit fails.
This technology adopts a simplified mechanical linkage structure consisting of a shaft bracket, link, and hook bracket. It incorporates a PCB module for electrical signal connection and implements a mechanical locking device operated by a handle, ensuring robust tool coupling and safety during detachment. Applicable to industrial robots and automation systems, it enhances manufacturing process efficiency, maximizes installation space utilization, and optimizes robot utility in small-scale production.
This technology is an automatic tool changer mechanism that converts the linear motion of a servomotor into the rotational motion of a link and hook bracket to physically engage and secure guide pins between a robot hand and a tool.
Conventional air cylinder-based clamping methods pose a risk of tool detachment if the air supply is cut off, and they suffer from structural complexity due to multiple reference surfaces, as well as reduced coupling precision caused by bending deformation over long-term use.
This technology utilizes a drive mechanism consisting of a servomotor, rod, rod bracket, link, and hook bracket to lock the tool by engaging the stepped portion of the hook bracket with the cutout of the guide pin. It achieves structural simplification and protection from external environments through electrical signal connection via a PCB and the strategic placement of components within the housing. Applicable to industrial robots and automation systems, it enhances tool change efficiency and maximizes space utilization in small-scale production environments.
