Flexible Walking Robot Foot with Tensegrity-Based Shock Absorption

This technology is a robotic foot device based on a tensegrity structure. Multiple frames (forefoot, hindfoot, and ankle) are not physically joined directly but are held together by tension members (cables) to maintain tension and enable flexible walking movements.

Conventional rigid-body robotic feet have limited shock absorption due to their structure. Furthermore, because motors must be mounted directly onto the joint rotation axes, these systems are heavy and complex, making it difficult to achieve a wide range of motion.

This technology connects the forefoot, hindfoot, and ankle frames with cables (tension members), allowing for the adjustment of tension across the entire structure. This enables lightweight, flexible shock absorption and multi-directional rotation (dorsiflexion, plantarflexion, pronation/supination). By allowing the joint drive motors to be placed outside the ankle structure, the overall system weight is reduced. It can be applied to walking robots, disaster response robots, and off-road mobility platforms, providing shock absorption and flexible movement similar to a human foot.

‍

‍

Key Features:

• Hindfoot section comprising a right hindfoot frame that intersects with the right forefoot frame, and a hindfoot connector between the left hindfoot frame and the right hindfoot frame
• First ankle section comprising a left ankle frame, an intermediate frame installed on the side of the left ankle frame, and a right ankle frame installed on the side of the intermediate frame opposite the left ankle frame
• Forefoot section comprising a left forefoot frame, a right forefoot frame, and a rear fixing bar connecting the left and right forefoot frames
• Tension member providing tensile force to at least one of the forefoot section, hindfoot section, first ankle section, or second ankle section

‍

This invention was developed with support from the Ministry of Science and ICT for a tensegrity robot system using pneumatic and tendon hybrid actuation.

Sewer Pipe Repair Robot Controlled via User Behavioral Data

This technology is a sewer pipe repair system mechanism that extracts 6-DOF motion data for repair tasks based on the user's biological signals (EMG, joint movement, etc.) and external force information to generate autonomous operation manuals, which are then used to control the manipulator.

The challenges include labor shortages due to the hazardous nature of sewer environments, as well as increased operator fatigue, reliance on individual skill levels, and the potential for safety accidents when using remote control systems.

This technology consists of a control module that uses a guide module to digitize user control actions and biological signals to generate autonomous operation manuals, and a mobile platform that actively maintains the manipulator's level through tilt measurement and cylinder control. It can be applied to robotic gripping, precision measurement, and automated equipment, improving the accuracy and efficiency of sewer repair work, enhancing user safety, and overcoming obstacles in the robot's path.

‍

‍

Key Features:

• A guide module that measures the biological signals of the user operating the guide member
• A work platform including a repair module for chipping or removing debris from the inner walls of sewer pipes and a manipulator to control it
• A mobile platform that moves along the sewer pipe and controls the manipulator to maintain a level position relative to the ground
• A control module that generates autonomous operation manuals from measured biological signals and controls the work platform

‍

This invention was developed with support from the Ministry of Science, ICT and Future Planning for the development of a reinforced concrete chipping robot system for the maintenance of covered structures.

Sewer Pipe Repair Device

This technology is a gate-type structure designed for the repair and inspection of sewer pipe inner walls. It features a mobile platform integrated with a frame consisting of horizontal and vertical components, allowing for autonomous movement. A mobile unit equipped with repair and inspection modules travels along rails installed on the frame to perform tasks.

Repairing aging concrete in sewer pipes poses significant safety risks to workers, including suffocation, electric shock, and falls. Furthermore, the need for automation is increasing due to a shortage of skilled labor and declining labor productivity.

This technology features a mobile platform for navigating the sewer floor, a rail structure capable of adjusting to the pipe's cross-sectional shape for omnidirectional repair and inspection, a depth control unit for enhanced efficiency, and sensor-based algorithms for leveling and distance control. Applicable to logistics, service robots, and autonomous platforms, it replaces manual labor with robotics for sewer pipe maintenance, significantly improving both operational efficiency and safety.

‍

‍

Key Features:

• A frame assembly comprising a horizontal frame facing the ceiling of the sewer pipe and a pair of vertical frames coupled to both ends of the horizontal frame, extending downward to face the side walls of the sewer pipe.
• A mobile rail assembly that mirrors the shape of the frame assembly, positioned at a distance from it, partially connected to the frame, and featuring rails formed along its longitudinal direction.
• An inspection module coupled to the mobile unit that monitors the quality of the repair work or the condition of the sewer pipe's inner wall.
• A repair module coupled to the mobile unit that performs repairs on the ceiling and walls of the pipe.

‍

This invention was developed with support from the Ministry of Science, ICT and Future Planning for the development of a reinforced concrete chipping robot system for the maintenance of covered structures.

Brush assembly and pipe cleaning robot equipped with the same

This technology secures the adhesion of a brush assembly by combining link members, which feature variable bending angles via a hinge structure to match the inner wall profile of a pipe, with leaf spring-based elastic members attached to the sides of the link members to prevent twisting and provide restorative force.

When cleaning pipes with varying diameters or bends, conventional fixed-brush structures suffer from reduced adhesion to the inner wall, leading to low cleaning efficiency and difficulty in removing debris.

This technology allows the link members to bend and deform according to the pipe's inner wall environment, while using elastic members (leaf springs) to prevent twisting at the hinge and ensure natural restoration to the original state. Furthermore, by connecting multiple link members with hinge axes and connecting components, it enables omnidirectional pipe cleaning. Applicable to industrial robots and automated systems, it improves cleaning efficiency and effectiveness in deep, narrow transport lines where high levels of toxic gas residue are likely.

‍

‍

Key Features:

• A connecting member that links the common hinge axis of at least two first link members with the common hinge axis of at least two second link members
• At least two second link members spaced apart from each other in a second direction different from a first direction
• An elastic member mounted on the side of the link member that deforms according to the bending angle of the link member
• At least two first link members spaced apart from each other in a first direction

‍

This invention was developed with support from the Ministry of Science, ICT and Future Planning for the development of core human-centric wellness technologies.

Shaft-based endovascular intervention robot with integrated drive components using a multi-part setup jig

This technology integrates multiple drive components, which align and operate intervention wires and catheters, into a single module using a multi-part setup jig for streamlined assembly and alignment.

Previously, assembling endovascular intervention robots involved individually mounting and aligning each drive component onto a base, leading to cumbersome processes, delays, and misalignment issues.

This technology introduces a multi-part setup jig that coaxially aligns and secures multiple drive components as a single unit, allowing the entire set to be mounted onto the base at once. Applicable to endovascular interventions, robotic surgery, and medical automation, it significantly reduces alignment time and enhances assembly efficiency.

‍

‍

Key Features:

• Features a shaft-based multi-part setup jig including a jig body that couples to each of the multiple drive component fasteners, where the drive component fastener includes a jig base that connects to the base part.
• Multiple drive component fasteners that secure multiple drive components as a single unit.
• An endovascular intervention robot featuring a shaft-based multi-part setup jig that includes a fastener with latch grooves provided on both sides of the outer circumference facing the width direction.
• A multi-part setup jig that coaxially aligns multiple drive components and secures them as a single, integrated module.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the AI algorithm-based endovascular intervention robot system project aimed at reducing radiation exposure and achieving 0.5 mm procedural accuracy.

Rail robot traveling on a single rail using drive wheels and pivoting rail guide units

This technology features a rail robot structure that includes drive wheels and multiple rail guide units, enabling travel on a single rail via a rail guide path. It is characterized by a mechanical mechanism that performs pivoting and guide control of the rail guide units to adapt to curvatures and inclines.

Conventional dual-rail systems have faced issues such as high installation costs, the difficulty of designing complex curved rails, and increased system costs due to the need for complex control algorithms to prevent derailment during travel on curved sections.

This technology utilizes drive wheels and rail guide units arranged in opposition within the main body's mounting space in an isolated structure to enable travel on a single rail. By securely gripping the rail through side guide units, lower guide units, and support units (first and second), the guide units are configured to respond fluidly when traveling on curved and inclined rails. Applicable to smart factories, logistics transport, and automated facility inspection, it reduces installation costs compared to dual-rail systems while improving performance on curved and inclined sections.

‍

‍

Key Features:

• An isolation unit that separates multiple mounting spaces from each other, is positioned between the multiple rail guide units, and features a bulkhead shape
• At least one of the multiple rail guide units is a first side guide unit that guides the rail from one side of the rail
• Multiple rail guide units mounted in the multiple mounting spaces, exposed to the rail guide path, and configured to guide the rail
• A second side guide unit that guides the rail from the side opposite to the first side of the rail

Brain Training Simulation System Based on Imitation Learning

This technology acquires non-invasive brain signals (such as EEG and NIRS), performs preprocessing and AI-based machine learning to continuously decode a patient's movement intentions, links these to the operation modes and difficulty levels of rehabilitation equipment (such as treadmills), and induces neuroplasticity through visual avatar content and neurofeedback.

Conventional bottom-up rehabilitation training struggles to encourage active patient participation, and technologies focused on single-motion recognition cannot change training modes continuously, failing to provide the sensory-motor virtuous cycle required for chronic or paralyzed patients.

This technology implements a continuous movement intention recognition algorithm based on brain signals (applying wavelet transforms and AI models), a control unit for the speed and intensity of rehabilitation equipment using state transition diagrams (S1–S5), and an evaluation system that monitors the user's training status to provide feedback on appropriate training protocols and store them in a database. It can be applied to rehabilitation training, gait assistance, and medical/welfare services, improving rehabilitation by clearly recognizing the user's operational intent using brain signals and operating the rehabilitation training accordingly.

‍

‍

Key Features:

• A user intention expression unit that operates the rehabilitation equipment and presents rehabilitation training content based on the user's movement intention recognized by the user movement intention decoding unit.
• A user movement intention decoding unit that recognizes the user's movement intention based on brain signal data processed by the brain signal acquisition and processing unit.
• A brain signal acquisition and processing unit that acquires and processes the user's brain signals using non-invasive brain activation measurement methods.
• A brain training simulation system based on imitation learning, characterized by providing neurofeedback to induce brain activity by presenting training speed visually or audibly through a monitor, which serves as a user monitoring device, in text or voice format.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of biosignal interface technology with over 90% gait intention detection accuracy for various gait rehabilitation of stroke patients, and application technology for overground gait rehabilitation robots.

Mobile Robot for Underground Structure Maintenance

This technology is a robot control system that calculates the distance and orientation error relative to the inner walls of underground structures using the rotation angles of rollers mounted around a radar module on a manipulator. Based on this data, it performs real-time adjustments to the manipulator's orientation and working distance to execute autonomous scanning and maintenance tasks.

Maintenance of underground structures has traditionally relied on manual operation, posing high safety risks. Furthermore, an aging workforce and a general avoidance of such labor-intensive jobs have led to decreased productivity and imbalances in labor supply.

This technology utilizes a manipulator equipped with a radar module, multiple rollers, and angle sensors to acquire physical contact data. It employs mathematical models to calculate orientation errors and distance correction values, while sensor-based obstacle avoidance and autonomous path planning allow it to process environmental data and operate independently. Applicable to robotic gripping, precision measurement, and automated equipment, this system removes workers from hazardous environments and enables robots to perform maintenance autonomously, thereby enhancing both efficiency and safety.

‍

‍

Key Features:

• A distance measurement unit that calculates the distance between the manipulator and the target surface of the underground structure using the rotation angles of multiple rollers installed around a radar module mounted on an arm-type manipulator.
• An orientation correction unit that adjusts the manipulator's position to ensure the radar module remains parallel to the target surface of the underground structure.
• A control unit that analyzes scan results to determine if there is any water infiltration in the target area and transmits the findings to a management server.
• A mobile platform unit that adjusts its speed and direction of travel under the control of the control unit.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the commercialization of wall-penetrating radar-based box-type sewer pipe exterior water infiltration detection robots.

Detachable Modular Universal Gripper Device

This technology separates the gripping unit from the electronic control module and utilizes a spring pin and conductive plate contact structure between modules to ensure versatility in robot server interfacing and control signal connectivity.

Conventional grippers have fixed specifications and functions, making it difficult to adapt to diverse working environments or different robot arm communication protocols, and they suffer from inefficiencies requiring the replacement of the entire unit during maintenance.

This technology features a design where the jaw module and drive module are detachable within the housing, and the electronic module that communicates with external robot servers is implemented as a separate, detachable structure. In particular, the use of spring pins and conductive plates allows for automatic electrical connection upon mechanical coupling, enhancing the convenience of module replacement. Applicable to logistics picking, service robots, and manufacturing automation, it improves adaptability to various working environments and maximizes operational flexibility by defining the gripper's configuration through individual modules.

‍

‍

Key Features:

• A detachable modular universal gripper device where the conductive plate is a metal plate capable of conducting electricity that contacts the spring pins in a 1:1 ratio.
• The electronic module includes a robot server interface unit for inputting and outputting first signals to and from external devices.
• A drive module control unit for inputting and outputting power or second signals to the drive module.
• A power transmission unit that transfers the rotational force of the motor unit to the driving force of the jaw module.

Robotic Gripper with Vision-Tactile Sensor Capturing Tensegrity Matrix Deformation

This technology is a vision-tactile sensor utilizing a tensegrity structure. It acquires physical information about an object by visually capturing the deformation of a matrix plane—composed of multiple contact points connected by tension members—in response to external pressure. A mirror and camera inside the sensor record the geometric changes of the plane, which are then analyzed by a processor to determine the object's gripping state and shape.

Conventional grippers rely heavily on external cameras, requiring additional space and struggling to accurately recognize complex shapes. They also have limitations in real-time detection of subtle contact information or anomalies during the gripping process.

This technology implements a tensegrity-based vision-tactile sensor mounted on the joints of a gripper finger. An internal camera captures the deformation of the matrix-arranged contact points upon contact with an object, and a processor calculates the position, posture, and orientation of these points to recognize the object and adjust finger movement. Applicable to logistics picking, precision assembly, and service robots, it enhances 3D shape estimation accuracy by providing real-time contact information at the moment of grasping.

‍

‍

Key Features:

• Vision-tactile sensor comprising a main housing with a bottom opening and a tensegrity plane installed within the opening
• Multiple contact points arranged in a matrix structure forming the tensegrity plane to detect object contact
• Tension members connecting at least two of the multiple contact points to form the tensegrity structure
• Tensegrity plane that changes shape as the position, posture, and orientation of the contact points shift upon contact with an object

‍

This invention was developed with support from the 2022 Regional Industry-Linked University Open-Lab Promotion Program funded by the Ministry of Science and ICT.

Robot gripper with surface-adaptive capability using vacuum suction modules and wire tension control

This technology is a robot gripper mechanism that connects vacuum suction modules via a chain-structured linkage arm and adapts to the surface shape of an object by adjusting the arm's configuration through a wire tension control unit.

In environments such as logistics terminals where the shape, material, and volume of objects are not standardized, fixed-form grippers have struggled to provide stable grasping.

This technology features a structure that varies the gripper's shape to fit an object's surface by controlling the curvature of the arm using multiple gripping modules, chain-structured connecting links, wires, winding rollers, and sliding tension-adjusting pulleys. It can be applied to logistics picking, service robots, and manufacturing automation, allowing for the stable grasping of various objects with different specifications without the need for gripper changes.

‍

‍

Key Features:

• A first upper wire guide member provided in a tube structure, coupled to the top of one of the plurality of first connecting links and having a hole penetrating in the front-to-back direction
• A surface-adaptive robot gripper including a first lower wire guide member provided in a tube structure with a hole penetrating in the front-to-back direction.
• A first adaptive gripping module positioned in front of the main gripping module, designed to suction and grasp objects using negative pressure
• The first connecting arm consists of a plurality of first connecting links connected in a chain structure

‍

This invention was developed with support from the Ministry of Science and ICT for the development of core robot work intelligence technologies to improve labor environments.

Curling Robot

This technology is a feedback control mechanism for wheeled robots with independently driven left and right wheels. It calculates real-time angular velocity and the rate of change in distance from a side guide using gyro and distance sensors, adjusting the wheel rotation differential to calibrate straight-line driving performance.

For robots that throw curling stones, straight-line driving performance prior to release directly impacts the outcome. Existing technologies lack the control techniques necessary to precisely correct the driving direction in real-time when disturbances occur, making precision throws difficult.

This technology measures real-time angular velocity and the rate of change in distance from the guide during operation, correcting the robot's path by rotating it in the opposite direction whenever these values deviate from zero. Furthermore, it applies an interpolation control algorithm that maintains a straight path by rotating the robot and then counter-rotating it in a second direction once the rotation angle and distance change rate reach zero. Applicable to logistics transport, service robots, and autonomous driving platforms, this technology enhances the forward driving performance of curling robots by controlling forward movement through various sensors.

‍

‍

Key Features:

• Configuration including wheels and sensors positioned on the left and right sides of the curling robot
• Processor that drives the wheels and performs real-time feedback control based on input straight-line speed and angular velocity
• Control configuration that calculates the rate of change in distance by measuring the distance between the robot and the guide in real-time
• Control method that rotates the robot by driving the left and right wheels in opposite directions to bring the distance change rate to zero

‍

This invention was developed with support for the development of AI robot technology capable of collecting game strategies and executing game performance, funded by the Ministry of Science, ICT and Future Planning.

Tactile Detection Device and Method

This technology is a device and method that uses a multi-array tactile sensor to scan the surface of a medium through tapping and rubbing motions, mapping multi-channel time-series signals with positional coordinates to classify the physical properties (hardness, roughness) of single or complex media.

Existing technologies are designed primarily to distinguish tactile sensations over fixed durations or to identify single media, which limits their ability to recognize tactile inputs occurring at arbitrary times or to perceive specific spatial information for objects composed of complex media.

This technology receives real-time n*m data from a multi-array tactile sensor, performs first and second actions—tapping (for hardness measurement) and rubbing (for roughness measurement)—and maps the acquired positional information and tactile signals to spatially distinguish and classify multiple media regions. Applicable to robotic grasping, precision measurement, and automated equipment, it improves the classification of tactile input signals by accounting for spatial information and categorizing the tactile properties of multiple media.

‍

‍

Key Features:

• A tactile input receiver that scans the surface of a medium using a multi-array tactile sensor composed of n*m sensors (where n and m are arbitrary natural numbers) to receive the positional coordinates of the n*m sensors and their corresponding tactile input signals in real time.
• A tactile signal detector that determines a tactile input exists when the value of the tactile input signal exceeds a preset threshold and detects the specific location on the medium's surface where the input occurred.
• A tactile classifier that, upon determining the existence of a tactile input, categorizes and outputs the input based on pre-learned thresholds for each medium.
• A tactile detection device characterized by outputting the regions of each medium such that they are spatially distinguished.

‍

This invention was developed with support from Samsung Electronics for the development of cognitive tactile sensors.

Sewer Pipe Repair Robot

This technology is a robot system for sewer pipe repair that features a modular design, separating the autonomous and remotely controlled mobile platform from the towed work platform.

Conventional drum-type chipping tools are difficult to assemble and install inside sewer pipes, and they face limitations in terms of work efficiency and cost-effectiveness.

This technology utilizes a crane-type work platform equipped with a pneumatic rock drill, separated from the mobile platform, and performs chipping operations through crawler-based movement and precision control. It can be applied to logistics, service robots, and autonomous driving platforms, thereby improving work productivity, addressing labor supply imbalances, and enhancing cost-efficiency in sewer pipe repair operations.

‍

‍

Key Features:

• A control unit that is electrically connected to the mobile platform, work platform, and chipping tool, and controls these components based on preset control signals and control signals generated from detection signals sensed during operation.
• A work platform provided on the upper side of the towing base, which rotates selectively to direct one end toward the target work area, either autonomously or via operator control, based on preset work path information.
• A servo cylinder coupled at its center to the top of the rotation support via a coupling shaft, which rotates on a horizontal axis relative to the coupling shaft and selectively extends or retracts the length of one end.
• A chipping tool provided at one end of the work platform that performs chipping on the target work area, either autonomously or via operator control, based on preset work path information.

‍

This invention was developed with the support of the Ministry of Science and ICT for the commercialization of reinforced concrete chipping robots for the automation of box-type sewer pipe maintenance.

Variable Axis Joint Device with Self-Alignment via Tensegrity Strings and Leg-Roller Sliding

This technology features a joint assembly composed of multiple independently rotatable frames, connected by a tensegrity-structured string system and a leg-roller-based sliding mechanism to achieve self-aligning joint movement with a variable axis of rotation.

Conventional rigid-body joints have fixed axes of rotation, making it difficult to replicate the complex combination of rotation and sliding found in human joints. They also suffer from issues such as user discomfort due to a lack of flexibility under external impact, mechanical wear from friction, and weight burdens during prolonged wear.

This technology maintains force equilibrium through the sliding movement of connecting legs and the tensegrity structure of the string members. This ensures rotational flexibility in yaw, roll, and pitch directions while minimizing friction and wear through a non-contact frame structure. It is ideal for wearable robots, rehabilitation aids, and exoskeleton systems, as it naturally mimics human joint movement and reduces the burden on the wearer.

‍

‍

Key Features:

• Upper and lower mounts that are attached to adjacent body parts around the joint and spaced apart from each other
• A joint assembly that connects the upper and lower mounts and includes a plurality of sequentially arranged frames
• First through fourth string members configured to connect adjacent frames to form a tensegrity structure
• A string connection unit including a first point where the first and second string members are connected, and a second point where the third and fourth string members are connected

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of a 50Nm/kg high-torque-to-weight ratio low-voltage drive module series for wearable robots.