Hierarchical Robot Task and Motion Planning Framework Combining Knowledge Bases and Learning Models

This technology is a hierarchical framework that receives task and object names as input to generate task sub-goals using a learning model, converts them into robot-level task actions through object knowledge and PDDL-based graph search, and generates execution motion plans by utilizing a motion knowledge base and primitive actions.

Existing task and motion planning methods face challenges with large search spaces when performing complex, long-horizon tasks. Furthermore, limitations in symbolic task planning make it difficult to guarantee success rates in diverse, heterogeneous robot environments and restrict the generation of flexible plans.

This technology introduces a feedback loop that decomposes task goals using learning-based models and corrects infeasible plans through simulation, while ensuring feasibility via a knowledge database. It can be applied to autonomous tasks in service robots and smart factories, significantly improving the success rate of complex, long-term operations.

‍

‍

Key Features:

• Step of generating a robot task plan through a robot task planning framework that combines knowledge and learning
• Step of deriving a robot motion plan to control the robot based on the generated task plan
• Configuration that generates sub-goals from task and object names using a learning model trained on object state changes
• Configuration that constructs a task plan for the generated sub-goals using knowledge stored in an object knowledge base

Mobile platform movement device with variable turning radius via multi-joint frame rotation control

This technology is a mobile platform movement device that variably adjusts the turning radius during steering by controlling the relative rotation between frames of multiple moving parts and the multi-axis rotation of vertical and horizontal frames in a structure where multiple moving parts are connected by a connecting shaft.

Conventional Ackermann or skid steering methods are limited by fixed turning angles or suffer from efficiency issues such as steering instability and power loss when controlling individual motors for each wheel.

This technology implements a multi-joint frame structure with a first drive unit centered on the connecting shaft, a second drive unit that induces relative rotation of the rotating frame, and a third drive unit that rotates the horizontal frame, allowing the control unit to calculate and manage the turning radius. It can be applied to logistics robots and indoor/outdoor service robots, enabling flexible and stable steering even in confined spaces.

‍

‍

Key Features:

• A first moving part capable of moving along the ground and a second moving part positioned to the rear in a first direction
• A connecting shaft that links the first and second moving parts, and a first drive unit that rotates them around said shaft
• A rotating frame coupled to the body frame to allow relative rotation about a second direction axis
• Configuration of vertical and horizontal frames designed to be rotatable about both the first and second directions

End-Effector Sensing Device and Method

This technology utilizes FEM analysis to strategically place strain gauges within a Maltese cross-shaped sensor frame. It measures deformations caused by loads during object gripping to calculate 3-DOF (Fz, Tz, Tx) force/torque data. The collected signals are processed via a data acquisition board using decoupling algorithms to compensate for physical cross-talk, ensuring precise measurements.

Conventional grippers are typically limited to simple compression force measurement, making it difficult to precisely measure force and torque at the tool-tip contact surface. Furthermore, tactile sensors often suffer from slow response times, rendering them unsuitable for high-speed repetitive tasks. Additionally, attaching individual sensors to multi-fingered robotic hands leads to complex structural and control requirements.

This technology integrates a Maltese cross-shaped sensor frame with strain gauges for deformation measurement and utilizes an integrated wiring board to achieve a compact design. Analog signals acquired from the optimally placed strain gauges (via FEM analysis) are processed by a data acquisition board, which uses a decoupling matrix to separate and convert them into digital force/torque data for each axis. Applicable to robotic gripping, precision measurement, and automated equipment, this solution enhances the accuracy and response rate of force and torque measurement in robotic grippers.

‍

‍

Key Features:

• A sensor frame comprising an outer frame and internal beams that intersect within the outer frame; it is positioned on the inner surface of the end-effector, features a Maltese cross shape, and includes a protrusion at the intersection of the internal beams where the tool-tip is fastened.
• An end-effector sensing device including a wiring board that connects to the strain gauges via Teflon-wrapped wires and is integrated into the sensor frame.
• A data acquisition board that receives calibration commands and transmits them to the sensing device.
• A plurality of strain gauges that deform when the end-effector grips an object.

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of safety modules with a maximum output range of 150Nm and force-torque/joint sensor technology for dual-arm collaborative robots.

Vertical Take-Off and Landing (VTOL) Unmanned Aerial Vehicle

This technology features a structure that performs directional changes and attitude control for a tricopter-type VTOL UAV by applying a tilting mechanism to the tail propeller section. It utilizes a mechanical design where a tilting gear is engaged with a tail propeller mount, which is coupled to the center frame via bearings, allowing for rotational control via a servomotor.

Reduced energy efficiency and limited flight time of UAVs, as well as production process inefficiencies caused by the complexity of existing airframe structures.

This technology designs the tail propeller with a tiltable mount structure and uses a servomotor and tilting gear to adjust the angle of the tail propeller, enabling directional changes and stable flight attitude control. Additionally, the frame is designed using lightweight materials such as carbon fiber to optimize the airframe weight. Applicable to unmanned exploration, surveillance, and environmental monitoring, it improves energy efficiency and extends the flight time of the UAV.

‍

‍

Key Features:

• A tail propeller mount gear formed integrally with the tail propeller mount, configured to rotate around the center frame as a central axis, located below the tail propeller motor installation section where the tail propeller motor is mounted.
• A tilting gear installed to mesh with the teeth of the tail propeller mount gear, coupled to rotate the tail propeller mount gear left and right around the center frame as a central axis.
• In an unmanned aerial vehicle, a body in which the driving equipment for operating the unmanned aerial vehicle is installed.
• A tail propeller section that provides flight propulsion and is coupled to the frame section in a tiltable manner.

‍

This invention was developed with support from the Ministry of Education, Science and Technology for the development of intelligent robot convergence technology for new and renewable energy.

Shape-Adaptive Gripper Using Individual Pressure Control for Multi-Jamming Chambers

This technology is a multi-chamber gripper device and gripping method that utilizes first to third chambers with individual pressure control and a jamming phenomenon to flexibly adapt to an object's shape and secure gripping force by forming a vacuum.

Conventional suction-based grippers are effective for picking up flat objects but have limitations in stably gripping objects with three-dimensional shapes or irregular surfaces.

This technology fills internal and external jamming chambers made of flexible material with jamming particles and independently controls the internal pressure of each chamber via a pressure regulator and flow paths, allowing the gripper to change its shape to match the target object for a secure, close-contact grip. It can be applied to logistics sorting, food packaging, and handling irregular parts, enabling a single gripper to stably handle a variety of shapes.

‍

‍

Key Features:

• A gripper base with an open-bottom first space and a flexible barrier that seals the first space
• A flexible internal jamming chamber filled with jamming particles, forming a second space separated from the first space at the bottom
• An external jamming chamber that surrounds a portion of the internal jamming chamber to form a third space and is filled with jamming particles
• A pressure control unit configured to individually regulate the pressure of the first, second, and third spaces

Mobile anchor robot secured to a rope via tension-adjusting roller pressure

This technology is a mobile anchor robot that features a caterpillar-based drive unit capable of traveling along a rope. It utilizes a tension-adjusting roller connected via a linkage mechanism, with a link drive unit that controls the relative position of the roller to apply tension to the rope, thereby firmly securing the robot at a specific point.

Existing rope-traveling robots offer excellent mobility but lack the ability to remain stably stationary on a rope without swaying, and they often suffer from reduced stability when carrying heavy loads.

This technology incorporates tension-adjusting rollers at the front and rear of the drive body, using multi-jointed links to press the rollers against the rope, which maximizes friction between the caterpillar tracks and the rope. It can be applied to building exterior maintenance, high-altitude facility inspections, and industrial rope access work, providing stable, sway-free anchoring during operations.

‍

‍

Key Features:

• A drive body with caterpillar tracks for traveling along a rope, and tension-adjusting rollers positioned at the front and rear
• A pair of tension-adjusting rollers arranged to face each other across the rope to apply tension
• A linkage unit that connects the drive body to the tension-adjusting rollers and includes a first pivot axis
• A link drive unit that operates the linkage unit to change the relative positions of the tension-adjusting rollers

‍

This invention was developed with support from the Ministry of Science and ICT for the development of a robot platform capable of free movement on various types of exterior walls.

Self-Learning Based Control Method for Cleaning Robots

This technology uses a camera to identify target substances on the floor and operates a learning mode that adjusts speed and suction intensity compared to the normal mode to determine the threshold speed and suction intensity required to remove specific substances. It is an algorithm that automatically switches to an optimized calibration mode when the same substance is detected, thereby controlling cleaning efficiency.

Existing cleaning robots operate at a constant speed and suction intensity without considering the environment or the characteristics of specific substances, leading to residual debris and reduced energy efficiency.

This technology applies a control logic that extracts threshold values by sequentially performing a normal mode and a learning mode (variable speed/intensity) during the Nth cleaning cycle, and dynamically switches to a calibration mode suitable for the target substance identified by the camera during the N+1th cleaning cycle. Applicable to industrial robots and automation systems, it improves cleaning efficiency and optimizes operation by learning the optimal movement speed and suction intensity for different target materials through unsupervised learning.

‍

‍

Key Features:

• A step of operating a camera-equipped cleaning robot under normal mode conditions with a reference speed or reference suction intensity for a first set time during an Nth cleaning process.
• A step of applying learning mode conditions to the cleaning robot, which gradually vary the speed or increase the intensity compared to the normal mode conditions, and operating it for a second set time.
• A step of extracting the threshold speed or threshold suction intensity at which a target substance that was not removed during the first set time begins to be removed, and acquiring a calibration mode containing the extracted information.
• A self-learning based control method for a cleaning robot, comprising a step of switching to and operating in the calibration mode acquired during the Nth cleaning process when a target substance of the same type as the previously identified target substance is detected by the camera.

3D Irradiation Device

This technology features a structure where multiple link members and drive members are arranged along a concentric spherical trajectory centered on a target point. Multiple robotic arms rotate independently and without interference to precisely control the irradiation angle of the emission member toward the same target point.

Existing robot-based irradiation devices suffer from low aiming precision, excessive drive components that increase overall weight, difficulty in achieving a compact design, and interference issues when using multiple robotic arms.

This technology utilizes relative movement control between the cradle and the robotic arms, a concentric spherical design where the rotation axes of multiple link and drive members meet at the target point, and angle adjustment elements to control the emission member's orientation toward the target point. It can be applied to industrial robots and automation systems to improve control and directionality, reduce operating time, and enhance the precision of irradiation equipment compared to conventional technologies.

‍

‍

Key Features:

• A 3D irradiation device capable of adjusting the angle at which the emission member faces a target point.
• A control unit that manages the operation of the robotic arms or the position of the emission member.
• An emission member provided at the end of the robotic arm.
• A robotic arm that performs tasks on an object.

‍

This invention was developed with support from the Ministry of Science, ICT and Future Planning for brain mapping-based robot rehabilitation.

Cleaning robot device that switches cleaning modes based on the location of uncleaned areas

This technology is a cleaning robot device and control method that identifies uncleaned areas based on obstacle detection and environmental information, and dynamically updates and optimizes cleaning paths by switching between path, proximity, and remote modes depending on the location of those areas.

Conventional random, spiral, and zigzag methods struggle to secure efficient cleaning paths in indoor environments with many obstacles, leading to uncleaned areas, increased battery consumption, and delayed cleaning times.

This technology uses encoders, distance sensors, and contact sensors to identify obstacles and uncleaned areas. The control unit analyzes the relationship between obstacles and the location of uncleaned areas to select the appropriate cleaning mode in real time and update the path. Applicable to both residential and commercial cleaning robots, it eliminates uncleaned areas while reducing both cleaning time and battery consumption.

‍

‍

Key Features:

• A sensing unit that detects the surrounding environment using encoder, distance, and contact sensors
• A path movement step that applies movement signals for the cleaning robot to travel along its cleaning path
• A detection step that determines the presence of obstacles in the surrounding environment using the sensed information
• A configuration that updates the path by selecting between path, proximity, and remote modes based on the presence of obstacles and the location of uncleaned areas

Wedge-tip coupling inchworm-style lift device for building exteriors

This technology is a lift device that moves along the vertical panels of a building exterior using an inchworm-style mechanism. It utilizes a ball screw drive and a wedge-tip expansion/contraction system to sequentially couple and move the main body and the mobile units.

Maintenance of high-rise building exteriors currently faces challenges such as worker fall risks and labor shortages. Existing gondola systems are vulnerable to weather conditions and lack an effective means to navigate dead zones at building corners.

This technology uses a rotating ball screw to secure or release two mobile units into coupling holes via wedge-tip units, allowing the main body to ascend and descend in an inchworm motion. The L-shaped main body and guide rail mobile unit enable work even at building corners. It is designed for high-rise exterior maintenance, ensuring both precise vertical movement and large-displacement travel.

‍

‍

Key Features:

• Main body for moving the robot along the vertical panels of a building exterior
• Lifting ball screw rotatably installed on the main body to move the wedge-tip units
• Wedge-tip units that can be coupled to or released from the coupling holes of the vertical panels and move along the ball screw
• Configuration where two mobile units alternately couple and decouple to achieve inchworm-style movement

‍

This invention was developed with support from the Korea Agency for Infrastructure Technology Advancement (KAIA) for the development of an intelligent robot system for high-rise building exterior maintenance.

Mobile Robot Localization and Recovery Technology Using Area-Based Matching Error

This technology estimates a mobile robot's position by calculating matching errors based on the area deviation between range sensor scan data and environment map-based predicted data, applying these to a probability density function, and enabling rapid recovery in the event of a failure.

Existing beam models are sensitive to sensor data errors, suffer from reduced localization accuracy in real-world environments with unmapped obstacles, and experience delays in recovery when localization fails due to issues like wheel slippage.

This technology calculates matching errors using the deviation between scan range areas and predicted range areas, removes noise via a median filter, detects failures using statistical thresholds, and proposes a method for probabilistic re-estimation within a maximum motion boundary. It can be applied to indoor service robots and logistics robots, minimizing downtime by quickly recovering even if the robot loses its position.

‍

‍

Key Features:

• Acquiring scan data of the surrounding environment based on scans from a range sensor mounted on a mobile robot
• Calculating matching errors based on the deviation between the scan range area and the predicted range area derived from an environment map
• Determining whether localization has failed based on whether the matching error exceeds an error threshold
• Configured to probabilistically re-estimate the position within a maximum motion boundary upon detecting a failure

‍

This invention was developed with support from the Korea Institute for Advancement of Technology (KIAT) through the project for fostering demand-oriented global leaders in indoor/outdoor robot autonomous driving technology.

Paddle-type driving module with drag optimization via self-rotating driving legs

This technology is a driving module and a robot incorporating it, where multiple driving legs rotating around a central axis simultaneously self-rotate to control drag based on the direction of travel.

Existing paddle-structured robots suffer from reduced propulsion efficiency because the direction of drag is fixed during rotation, causing drag to act against the direction of movement.

By utilizing a gear structure between a central plate and satellite plates, this technology is designed to allow the paddle sections to self-rotate along their rotational trajectory, thereby maximizing forward drag and minimizing reverse drag. It can be applied to off-road robots, amphibious mobile platforms, and agricultural robots to achieve higher propulsion efficiency with the same power input.

‍

‍

Key Features:

• Driving legs positioned at a predetermined radius from a rotation axis of a predetermined length
• Driving legs that rotate along a trajectory centered on the rotation axis while self-rotating about their own longitudinal central axis
• A power transmission unit that connects the rotation axis to the driving legs, causing the driving legs to self-rotate as the rotation axis turns
• A central plate located in the inner region of the trajectory where the driving legs rotate, and satellite plates fixed to the upper ends of the driving legs

‍

This invention was developed with the support of the Ministry of Science and ICT for research on environment-adaptive smart wheel-based robot systems.

Variable Gripper Combining Shape-Memory Polymer 3D Printing and Heater Control

This technology is a variable gripper that uses a 3D-printed shape-memory polymer structure, an adhesive polymer layer, and a heater unit. By utilizing heat-induced glass transition to reversibly control the physical shape of the wings, it can grip and release objects.

Conventional grippers have faced challenges such as difficulty in controlling gripping and releasing performance, slow release times, and inefficiencies in manufacturing costs and time.

This technology optimizes shape recovery by controlling 3D printing process variables, such as unit layer thickness and wing edge width, and physically controls response time by combining heater temperature application with external force. It can be applied to precision component transport, micro-assembly, and medical device handling, enabling sophisticated grip control through low-cost manufacturing.

‍

‍

Key Features:

• Manufacturing a carrier unit comprising a first surface with a recessed area and an opposing second surface
• Manufacturing a variable structure including wings bonded to the side adjacent to the second surface of the carrier unit
• Manufacturing an adhesive polymer layer by providing an adhesive polymer source within the recessed area of the carrier unit
• Manufacturing a heater unit to provide temperature to the variable structure and bonding the wings at a first angle

‍

This invention was developed with support from the Ministry of Science and ICT for the development of 3D printing-based, biosignal-responsive, customized implant devices for smooth urination in patients with lower urinary tract symptoms.

Upper Limb Rehabilitation Robot Device

This technology is an upper limb rehabilitation robot that combines a multi-joint link structure, a connecting shaft, and an actuator to assist with or provide resistance to rehabilitation exercises based on the user's upper limb trajectory.

Existing upper limb rehabilitation robots have struggled to integrate various movement types—such as horizontal, inclined, and vertical—and multifunctional training modes—such as active, passive, and resistive—into a single device.

This technology features a link unit, an active actuator (motor), a passive actuator (variable damper), and a rotatable connecting support, allowing for diverse exercise modes and multi-angle rehabilitation training tailored to the user's upper limb movement trajectory. It can be applied to rehabilitation training, gait assistance, and medical/welfare services, improving both the variety of rehabilitation exercises and cost-efficiency for patients with damaged or paralyzed limbs.

‍

‍

Key Features:

• A link unit with one side coupled to a connecting shaft and the other side equipped with an upper limb connector to secure the patient's arm.
• An upper limb rehabilitation robot device where a ball plunger is installed at the junction of the third and fourth rods.
• A base frame with a laterally positioned connecting support rotatably installed on one side.
• A connecting shaft rotatably installed on one side of the connecting support.

Work tool device for electric screwdriver robots capable of verifying screw tightening force and detecting fastening errors

This technology implements mechanical decoupling in the direction perpendicular to the gripping force (Y-axis) by introducing a guide rail/protrusion structure between the electric screwdriver gripper jaws and the jaw base, and places a load cell in that direction to independently measure the reaction torque component generated during screw tightening.

Existing bolting operations using industrial robots have faced cost and reliability issues, as they often require visual inspection to verify successful fastening or the use of expensive F/T sensors.

This technology couples the second gripper jaw to the second jaw base to allow for linear movement along the Y-axis and places a load cell along that path to quantitatively measure the fastening reaction torque, thereby determining whether the fastening is complete or if an error has occurred. Applicable to logistics picking, service robots, and manufacturing automation, it improves the accuracy of screw tightening verification and eliminates the need for expensive equipment in bolting operations.

‍

‍

Key Features:

• First and second jaw bases that receive gripping force in the X and Y-axis directions from the drive unit
• A first gripper jaw integrated with the first jaw base and a second gripper jaw capable of Y-axis movement
• Gripper jaws that hold a vertically positioned electric screwdriver based on the received gripping force
• A sensor that detects the force component of the reaction torque transmitted to the second gripper jaw during screw tightening

‍

This invention was developed with support from the Ministry of Trade, Industry and Energy for the development of safety modules with a maximum output range of 150Nm and force-torque/joint sensor technology for dual-arm working robots.