Intelligent muscle strength and gait assistance robot with joint actuators mounted directly on the exoskeleton

This technology is an intelligent muscle strength and gait assistance robot that integrates an exoskeleton worn on the user's lower body with a caster walker as a gait aid via an arm, and minimizes power transmission distance by installing actuators directly on the hip and knee joints.

Conventional gait aids suffer from low mechanical efficiency and complex structures due to the long power transmission distance between the actuator and the joint, as well as risks of detachment and structural instability caused by the separation of the arm and the exoskeleton.

This technology proposes a method of positioning the joint actuators on the exoskeleton rather than the arm and integrating the arm and exoskeleton into a single unit. It can be applied to lower limb rehabilitation and muscle strengthening training, maximizing power transmission efficiency, simplifying control, and ensuring structural stability.

‍

‍

Key Features:

• Exoskeleton equipped with a pair of frames and hip and knee joints that rotate the frames
• Configuration where waist, thigh, and calf braces are fastened to the frame
• Caster walker unit that is mobile and equipped with handles to provide stable gait assistance to the user
• A pair of arms integrally coupled to the frame, with both ends fastened to the exoskeleton and the caster walker, respectively

Parallel Gripper Performing Ground-Contact Scooping via a Mechanical Compliance Mechanism

This technology is a parallel gripper that performs a scooping motion upon ground contact without complex control by combining a first drive mechanism that induces passive vertical movement at the contact point with a second drive mechanism that induces passive rotation.

Conventional rigid grippers struggle to adapt to various shapes, soft fin-ray grippers lack gripping precision and force, and existing finger mechanisms often fail to interact with the surrounding environment upon ground contact, hindering the gripping process.

This technology proposes a method where a joint section based on a Mecha-Hartz mechanism induces vertical movement and compliance at the contact point, while a link unit and pressure section implement rotation and scooping. It can be applied to logistics picking, disinfection robots, and picking up objects from the floor, allowing for the stable retrieval of thin objects on the ground without the need for additional sensors or control.

‍

‍

Key Features:

• A pair of chucks equipped with contact sections that interact with the ground while contacting the target object
• A first drive mechanism that passively moves the contact section in a vertical direction when it makes contact with the ground
• A second drive mechanism that passively rotates the contact section when it makes contact with the ground
• A parallel drive module that moves the pair of chucks horizontally to grip the target object

‍

This invention was developed with support from the Ministry of Science and ICT for the development of task design and control algorithms for intelligent autonomous disinfection robots.

Extrinsic Parameter Calibration for Multiple 3D LiDAR Sensors Using Plane Extraction and Variance Minimization

This technology is an optimization-based calibration method designed to calibrate extrinsic parameters—the relative positions between multiple 3D LiDAR sensors. It extracts planar information from measured point clouds, calculates initial values through similarity analysis between reference and corresponding planes, and minimizes the variance of measured points.

Existing methods using artificial markers require additional environmental setup and costs. Point cloud registration-based techniques often fail when there is a significant difference in the field of view between sensors, while methods relying on trajectory data are prone to estimation errors.

This technology sequentially performs data collection, plane extraction, corresponding plane detection, and the calculation of initial and final extrinsic parameters, calibrating based on planes that satisfy mathematical conditions such as planarity and normal direction variance. It can be applied to autonomous vehicles and multi-sensor robots, providing an economical solution for immediate on-site sensor alignment without the need for specialized calibration equipment.

‍

‍

Key Features:

• Data collection phase where point clouds are gathered by each 3D LiDAR sensor
• Plane extraction phase where multiple target planes are identified from the point clouds
• Detection phase where one target plane is set as the reference plane to identify corresponding planes from other sensors
• Calculation phase for extrinsic parameters through similarity analysis between corresponding planes and minimization of measured point variance

‍

This invention was developed with support from the Ministry of Science and ICT and the Ministry of Agriculture, Food and Rural Affairs for the training and research of personnel in unmanned agricultural production automation.

Wearable Gait Assistance Robot Control Technology Utilizing Residual Muscle Strength via EMG Analysis

This technology is a control device and method for a wearable gait assistance robot that measures a user's muscle activity signals using EMG sensors, quantifies muscle strength through signal analysis, and controls the level of assistance by subtracting the user's residual muscle strength from the total power required for robot operation, thereby encouraging active muscle engagement.

Existing gait assistance robots focus on supporting patients with complete paralysis. When used by patients with partial muscle strength, these robots often lead to total reliance, resulting in muscle atrophy or risks of injury due to a lack of synchronization between the user's muscle movements and the robot's assistance.

This technology analyzes current muscle strength based on EMG signals and calculates the necessary assistance by subtracting the user's strength from the total required power, while setting the driving power at a predetermined lower ratio to encourage voluntary muscle participation. It can be used for stroke rehabilitation and gait training for the elderly, preventing robot dependency and enabling active rehabilitation that enhances residual muscle strength.

‍

‍

Key Features:

• A biosignal sensing unit that detects biosignals from a user wearing a wearable gait assistance robot
• A signal analysis unit that quantitatively analyzes the user's current muscle strength based on the EMG signals detected by the biosignal sensing unit
• A robot drive control unit that regulates the robot's operating power based on the analyzed muscle strength of the user
• A configuration that determines the level of assistance by subtracting the user's muscle strength from the power required for the intended movement

Brain-Machine Interface Wearable Robot Control Technology Combining Tactile Stimulation Induction and Motion Artifact Removal

This technology collects brain signals generated by applying distinct tactile stimuli to both of the user's feet to induce motor imagery. It removes motion artifacts generated during robot movement using reference signals and independent component analysis, then calculates walking intent, speed, and stride length through a brain signal classifier to control the wearable robot.

Existing brain-machine interface technologies face challenges in intuitively distinguishing between right and left foot movement intentions during rehabilitation for patients with lower-limb paralysis, and the motion artifacts generated during robot operation distort brain signals, leading to lower accuracy in intent recognition.

This technology proposes a method that induces EEG patterns by applying tactile stimuli of different frequencies to the left and right feet, removes motion artifacts in real-time by using the robot's inertial sensor values as reference signals, and distinguishes walking intent through a multi-classifier ensemble. It can be used for the rehabilitation and gait reconstruction of patients with lower-limb paralysis, enabling intuitive robot control that accurately reflects the user's intent.

‍

‍

Key Features:

• A step of presenting different tactile stimuli to the left and right feet of a user wearing a wearable robot
• A step of acquiring brain signals manifested by motor imagery and tactile stimulation, as well as reference signals for movement
• A step of determining the movement intent corresponding to the brain signals based on the brain signals and a brain signal classifier
• A step of transmitting the classifier's output and movement intent to a control command receiver to control the wearable robot

‍

This invention was developed with support from the Ministry of Science and ICT under the project "Development of Non-invasive BCI Integrated Brain-Cognitive Computing SW Platform Technology for Controlling Real-life Devices and AR/VR Devices with Thoughts" (BCI-General/Sub-project 1) and "Development of BCI-based Brain-Cognitive Computing Technology for Recognizing Human Intent Using Deep Learning" (BCI-Sub-project 2).

Wearable Upper Limb Rehabilitation Device Combining a Wire-Driven Glove and Anchor Member

This technology is a wearable upper limb rehabilitation device that implements rotational movement of a glove through wire winding and unwinding, and secures a comfortable fit by tightening and loosening the arm support using a wire-driven mechanism.

Conventional upper limb rehabilitation devices are bulky and heavy due to their frame and stand configurations, and are limited to use in fixed locations, which reduces accessibility for patient rehabilitation training.

This technology proposes a method where a fixing member is placed on a glove worn on the user's hand, support is adjusted via a tightening motor and wire within an anchor member that wraps around the forearm, and a length-adjustment motor controls a rotation wire to induce vertical rotational movement of the wrist joint. This enables a lightweight, wearable structure that allows for rehabilitation training anywhere. It can be used for upper limb rehabilitation in stroke patients and for home-based self-training, significantly improving rehabilitation accessibility and the patient's quality of life by removing location constraints through its lightweight, wearable design.

‍

‍

Key Features:

• A glove worn on the user's hand, featuring a fixing member provided on the upper side that covers the back of the hand.
• An anchor member comprising a lower support that wraps around the outer circumference of the forearm, a plurality of locking parts, a tightening wire, and a tightening motor.
• A rotation wire with one end attached to the fixing member on the glove and the other end extending past the lower support of the anchor member.
• A length-adjustment motor that moves the glove vertically by winding or unwinding the rotation wire to adjust its length.

‍

This invention was developed with support from the Human-Centered Soft Robotics Research Center of the Ministry of Science and ICT.

Mobile robot device for playing hide-and-seek based on video and distance recognition

This technology is a mobile robot device that performs hide-and-seek scenarios between a robot and a user based on video information from a camera and spatial information from a distance sensor. It features control technology that tracks the user via video during "seeker" mode and plans a path to a concealable location using surrounding obstacle information during "hider" mode.

Existing robot toys with simple combat functions fail to encourage physical activity in users and lack diversity in play, particularly in terms of emotional exchange and interaction between the user and the robot.

This technology proposes a method where a motion controller manages the drive unit based on "seeker" and "hider" modes, utilizing a camera for user recognition and light level detection, and a distance sensor for environmental awareness. It enables emotional interaction with the user by displaying facial expressions on a screen and providing audio feedback through a speaker. It can be applied to educational toys, children's play robots, and emotionally responsive service robots, offering a new direction for the robot toy market by encouraging both physical activity and emotional engagement.

‍

‍

Key Features:

• An image processing unit that processes camera footage to generate display images, and an image display unit that outputs them
• A distance sensor that measures the distance to surrounding objects and a drive unit that moves the mobile robot device
• A motion control unit that manages the drive unit to perform hide-and-seek based on the captured video and measured distances
• Detects the user via captured video during "seeker" mode and controls the drive unit based on distance values during "hider" mode

Minimally invasive surgical robot system with remote endoscopic control via head movement

This technology is a minimally invasive surgical robot system that remotely controls the 3D position and orientation of an endoscope by sensing the pitching, yawing, and rolling movements of a surgical headset, while preventing physical collisions by calculating the centerline distance between the endoscope and the robotic arm.

Existing systems often require surgeons to control robotic arms and endoscopes using both hands or foot pedals, which disrupts the surgical workflow, demands high operational proficiency, causes user fatigue from constant focus on large monitors, and reduces spatial efficiency.

This technology proposes a method that transmits headset orientation data based on the user's head movements to a control unit, which then automatically executes the endoscope's vertical/horizontal rotation and forward/backward movement, while providing 2D and 3D surgical views through the headset's display. By controlling distance thresholds between the robotic arm and the endoscope to avoid interference, it enhances both surgical continuity and safety. Applicable to a wide range of minimally invasive procedures, including laparoscopic and robotic surgeries, it offers a solution that reduces the surgeon's operational burden and fatigue while simultaneously improving surgical flow and safety.

‍

‍

Key Features:

• An endoscope inserted through an incision to capture real-time images of the surgical site, and a drive unit that moves it.
• A headset worn on the user's head that detects head movements to generate orientation data and displays 2D or 3D images.
• A control unit that sends drive control signals to the drive unit based on the orientation data generated by the headset and transmits endoscopic image data to the headset.
• A configuration where an orientation sensor detects the pitching, yawing, rolling, and angular velocity of the user's head to generate orientation data for endoscopic control.

‍

This invention was developed with support from the Ministry of Science and ICT for research on the development of next-generation surgical robot systems through collision avoidance for surgical robot arms.

Finger Prosthesis Mechanism with Underactuated Drive and Elastic Elements for Shape-Adaptive Grasping

This technology is a finger prosthesis device utilizing an underactuated mechanism. It transmits rotational force from the first axis to the second body via an elastic element. When the rotation of a specific link is restricted, the deformation of the elastic element allows the third body to rotate independently, enabling an adaptive grasp that conforms to the shape of an object.

Conventional robotic prostheses require multiple actuators to mimic the movement of individual finger joints, leading to complex structures. These designs struggle to provide flexible grasping capabilities that adapt to object shapes and often lack user comfort.

This technology achieves multiple degrees of freedom with fewer actuators through an interlocking structure between the first and second bodies that incorporates elastic elements. It also features a rolling contact mechanism using wires and pulleys at the terminal device to ensure stable torque transmission through tension control. Applicable to prosthetics, rehabilitation aids, and wearable robots, it allows for flexible adaptation to object shapes with fewer actuators while enhancing wearer comfort.

‍

‍

Key Features:

• A first body comprising a first axis with one end of a transmission link connected to the other side, and a second axis coupled to the first axis and the other end of the transmission link.
• A second body comprising a first link that rotates in conjunction with the first axis through a member housing, and a second link connected to the second axis that pivots in conjunction.
• A robotic mechanism in which the third body rotates independently of the second body according to the pivoting of the second link connected to the second axis.
• A third body provided at one end of the second body that rotates according to the pivoting of the second link.

‍

This invention was developed with support from the Ministry of Science and ICT for the development of biomimetic bionic arm mechanisms.

Prosthetic hand module with multi-degree-of-freedom bending and adaptive grasping using elastic members and wires

This technology is a prosthetic hand mechanism that achieves independent bending/extension and adaptive grasping of multi-degree-of-freedom links by distributing the motor's rotational force to each joint frame through elastic members and wires within a transmission frame.

Conventional prosthetic hands suffer from non-independent finger joint movement, making adaptive motion to object shapes impossible and hindering the implementation of natural movements such as finger abduction and adduction.

By placing an elastic member between the motor's rotation axis and the wire tension adjustment plate, this technology enables independent rotation and adaptive grasping of individual links through elastic deformation upon contact with an object. It can be applied to prosthetic hands, rehabilitation aids, and wearable robots to achieve natural grasping tailored to object shapes through independent finger actuation.

‍

‍

Key Features:

• A mounting section that houses the battery and the motor powered by it to provide power to the prosthetic hand
• A transmission frame including a rotation axis that rotates according to the motor's torque and a first wire tension adjustment plate to which the 1-1 and 1-2 wires are fixed
• A first link including a first joint frame connected to wires that rotate according to the tension of the 1-1 and 1-2 wires
• A third link including a third joint frame connected to 3-1 and 3-2 wires whose tension is adjusted according to the rotation of the rotation axis

‍

This invention was developed with support from the Ministry of Science and ICT for the development of biomimetic bionic arm mechanisms.

Catheter-Mounted Microrobot

This technology provides a microrobot mechanism for precise steering and drilling within blood vessels, utilizing a magnetic microrobot that generates rotational torque via an external magnetic field, along with a connector and ball bearing structure that attaches it to a catheter.

Conventional catheter-based vascular procedures lack a dedicated drive unit, making precise steering difficult, while high-speed rotational drilling poses a high risk of damaging the inner vessel walls.

This technology features a detachable connector and ball bearing at the catheter tip, combined with a magnetic microrobot containing an internal magnet, allowing for precise rotation and drilling control at low speeds through external magnetic field manipulation. Applicable to surgical robots, interventional systems, and medical automation, it improves operational speed control and enables safer surgical procedures in complex blood vessels.

‍

‍

Key Features:

• A connector featuring one side that attaches to the catheter end and another side that houses the ball bearing.
• A magnetic microrobot that includes a magnet and ball bearing assembly area, performing drilling operations via an external magnetic field.
• A cylindrical magnet inserted inside the connector to enhance the steering of the magnetic microrobot.
• A rolling bearing containing a specific number of balls, determined by the magnetic field strength and magnetic settings.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of a micro-medical robot system for treating chronic total occlusion in myocardial infarction.

Robot Driving Test System Simulating Collapse Scenarios

This technology uses multiple sensors to detect a robot driving on a track, calculates its position and speed in real time, and controls the timing of a drop module to simulate collisions between the robot and falling objects or to replicate post-fall avoidance scenarios, thereby quantitatively evaluating the robot's performance.

It is difficult to replicate actual collapse scenarios at disaster sites, and there is a lack of automated systems capable of accurately predicting the timing of falling objects to objectively and quantitatively evaluate a robot's collision or avoidance performance.

This technology calculates the robot's position and speed using sensor modules installed at entry, passage, and exit points. It precisely controls the drop module by calculating the time difference for the drop based on the weight and height of the falling object, while simultaneously automating the recording intervals of camera modules based on sensor detection to efficiently capture experimental data. Applicable to logistics transport, service robots, and autonomous driving platforms, it provides a more realistic and objective testing system capable of simulating collisions or avoidance scenarios in collapse disasters, thereby improving the performance evaluation of disaster response robots.

‍

‍

Key Features:

• A control module that calculates the time the robot reaches a set point using the robot's position or speed obtained from sensor module detection data, and transmits a control signal generated based on that arrival time to the drop module.
• A second sensor module installed at a second point located between the first point and the set point, at a first distance from the first point.
• A third sensor module installed at a third point, which is the exit point of the track located at a second distance from the set point.
• A plurality of sensor modules installed along multiple sections of the track to detect the robot as it drives along the track.

‍

This invention was developed with support from the Ministry of Public Safety and Security for the development of technology to establish field performance evaluation environments for special equipment and robots used in fire suppression, search, and rescue, taking into account grading, modularization, and standardization.

Hybrid Twisted String Actuator with Auxiliary Drive

This technology relates to a twisted string actuator for hybrid operation, which drives robot joints by combining a twisted string drive unit with an auxiliary drive unit.

Conventional twisted string actuators suffer from asymmetric contraction and relaxation, leading to complex control and performance limitations due to the trade-off between force and speed.

By placing an auxiliary drive unit in parallel, this technology minimizes interference and compensates for the trade-off relationship, thereby improving the control performance and response speed of robot joints.

‍

‍

Key Features:

• A twisted string drive unit where a pair of string twisting units rotate in opposite directions to create string tension.
• A joint member and cam pulley that receive power from the twisted string drive unit to control bidirectional movement.
• An auxiliary drive unit connected to the output shaft of the joint member to directly control the bidirectional movement of the output shaft.
• A load cell that slides on a linear guide to detect the torque generated by the twisted string drive unit.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of core technologies for compact, lightweight, high-performance, and highly durable safe drive modules based on string twisting, utilizing string surface reinforcement, variable radius pulleys, and hybrid drive control, as well as the Ministry of Trade, Industry and Energy's Engineering Graduate School Support Program (Plant Engineering field).

Muscle-assistive device with variable stiffness using electrostatic static friction

This technology relates to a variable-stiffness muscle-assistive device and its control method using electrostatic static friction, which adjusts interlayer friction through voltage application to vary stiffness in real time.

Existing layer jamming actuators were difficult to apply in scenarios requiring high bending or torsional stiffness due to their structural characteristics, and they faced limitations in response speed and stiffness range.

By applying voltage to a multi-layered stack to generate electrostatic static friction and controlling stiffness accordingly, this technology improves both effectiveness and response speed in wearable robots and exoskeleton suits.

‍

‍

Key Features:

• A multi-layered stack worn on the human skeleton and joints to assist muscle strength, featuring overlapping sections at the joint connections.
• Layers are coupled to allow relative sliding and rotation, with each layer comprising an electrode layer and a dielectric layer.
• Electrode and dielectric layers configured to induce electrostatic force by applying an electric field between the layers in relative motion.
• A configuration that varies stiffness by using electrostatic force to induce static friction, thereby preventing relative motion between the layers.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy’s project for a human-augmentation hybrid robot suit capable of a safe 7-second 100m dash and 12-hour comfortable wear, and the Ministry of Education’s project for high-speed hand motion control using a variable-stiffness exo-glove.

Wheelchair-integrated lower limb exercise and rehabilitation device combining a four-bar linkage lift and an exoskeleton

This technology is a wheelchair-integrated lower limb exercise and rehabilitation device that combines a driving unit equipped with a drive motor and wheels, a lift unit that moves in a quadrant path via a four-bar linkage, and an exoskeleton worn on the user's lower body.

Existing wheelchair-based exercise and rehabilitation systems have been limited by safety issues during lifting, inefficient mechanisms, and restricted control over weight-bearing support.

This technology proposes a configuration where the main lift linkage and the lift frame work together to move stably along a quadrant path. It can be applied to lower limb rehabilitation for people with disabilities and the elderly, safely assisting with standing and sitting while providing the mobility of a wheelchair to significantly improve the user's quality of life.

‍

‍

Key Features:

• A driving unit comprising a frame, a drive motor, left and right wheels driven by the drive motor, and a main lift motor
• A main lift linkage rotatably coupled to the frame in a four-bar linkage configuration and powered by the main lift motor
• A lift frame rotatably coupled to the main lift linkage, designed to ascend or descend along a quadrant path
• A linkage configuration that unfolds when the lift frame ascends and folds when it descends