This technology describes a mechanism for generating an AI model that leverages Visual Grounding technology to extract object category, position, and attribute information from images. This information is then converted into natural language instructions to plan and control a robot's manipulation trajectory.
Existing robot control methods required operators to manually input object coordinates and task details. This resulted in limitations such as the need for fixed object positions and low operational efficiency when generating commands for multiple objects.
This technology proposes a method for generating a training dataset and subsequently training an AI model. This is achieved using a first framework (GVCCI) which comprises: a visual feature extraction module that recognizes objects and extracts features from images; a module that generates context-appropriate natural language instructions; a model that infers targets and positions via a visual grounding model; and a manipulation module that plans the trajectory of a robot arm.
This technology was developed with support from the Institute of Information & Communications Technology Planning & Evaluation (IITP) through a self-directed AI research project focused on solving novel problems.
This technology extracts individual components of robots and obstacles, then predicts collision distances in parallel through pairwise batch operations. It trains a collision distance prediction model based on geometric feature vectors and relative transformation matrices. The minimum value among the predicted pairwise distances is calculated as the global collision distance, which can then be utilized for real-time motion planning.
Previously, high computational complexity led to performance degradation when calculating minimum distances, a crucial step for conventional motion planning algorithms in high-degree-of-freedom robot systems. Furthermore, data-driven learning methods suffered from low flexibility to environmental changes and frequent retraining requirements, limiting their versatility.
This technology proposes a model that learns by extracting relative transformation values and point cloud-based shape feature vectors between robot components and obstacles. By processing these inputs in batches and performing parallel computations, it enhances operational efficiency and provides flexibility to adapt to environmental changes without needing to retrain for specific shape elements.
This technology was developed with support from the Institute of Information & Communications Technology Planning & Evaluation (IITP) through its goal-oriented AI generation and inference research project.
This technology converts RGB and depth information from images captured by a mobile robot into embedding data via an encoder module. This data is then mapped with the robot's position information to construct grid-based spatial map data. Subsequently, a decoder module generates rendered images from this map, and by learning the differences from the original captured images through a loss function, optimizes the neural network-based map generation model.
Existing grid-based map generation methods suffer from decreased map accuracy due to the accumulation of robot localization errors. They also require significant memory for storing visual information and have slow data processing speeds, making them difficult to apply in real-world robot operating environments.
This technology introduces a deep neural network encoder-decoder architecture to embed features of captured images into a grid. Through efficient position-information-based data recording and rendering processes, it is an excellent technology that can improve real-time environmental perception and localization accuracy.
This technology was developed with support from the Institute of Information & Communications Technology Planning & Evaluation (IITP) (SW Star Lab) research project 'Robot Learning: Efficient, Safe, and Socially Friendly Machine Learning'.
This technology pertains to an identity sharing system, specifically a distributed ledger technology-based user identity sharing system for virtual asset services. It enables the reception of counterparty identity information when virtual assets are sent and received using distributed ledger technology.
This user identity sharing system, which leverages a distributed ledger technology security platform for virtual asset services, prevents the forgery and alteration of user identity information. It also facilitates the sharing of user identity information among virtual asset service providers, other blockchain and distributed ledger technology platforms, and existing IT systems.
Furthermore, this technology enables compliance with anti-money laundering obligations related to virtual assets through the identity verification and storage of virtual asset senders and recipients. It also ensures adherence to the Financial Action Task Force (FATF) guidelines (Guidance for a Risk-Based Approach to Virtual Assets and Virtual Asset Service Providers) and personal information protection laws and regulations in each country.
[Standard Patent Details]
Domestic and international standards related to patent technology: TTA Telecommunications Technology Association Standard TTAK.KO-12.0374
This technology relates to an identity verification system, specifically a peer-to-peer, non-face-to-face system utilizing wireless communication. It operates by registering only the information necessary for verification on an on/off-chain—without storing personal data—and then verifying certificates using individual public keys on personal devices to generate integrated certificates.
The advantage of this technology is that the peer-to-peer, non-face-to-face identity verification system, which uses wireless communication, allows for the exchange of electronically signed confirmations. These can be verified against public keys registered on the on/off-chain, enabling the secure, non-face-to-face exchange of verified certificates.
Furthermore, because it can generate certificates that confirm event participation, organizers of workshops, conferences, exhibitions, or meetings can quickly and accurately verify the attendance of numerous participants at the venue simultaneously.
[Standard Patent Details]
Domestic and international standards related to the patented technology: International Standard ITU-T X.2310 (03/2026), TTA Information and Communication Association Standard TTAK.KO-12.0397
This invention relates to a smart farm crop monitoring method and system using drones. Specifically, it involves utilizing drones flying within a farm area to monitor the growth and pest/disease status of crops, and subsequently manage their conditions.
Traditionally, various chemicals must be preemptively sprayed on crops to prevent pests and diseases, or additional growth-promoting activities must be carried out. However, these activities lead to excessive human involvement and can also degrade crop quality. Therefore, we propose a smart farm crop monitoring method that utilizes drones to manage optimal crop growth.
This technology enables optimal crop growth management by utilizing drone-mounted sensors for target tracking. It identifies the growth status of crops by location and can preemptively analyze the occurrence of pests and diseases.
This invention relates to a forest fire monitoring device and system utilizing drones. Specifically, it is a technology that operates as a 360-degree rotatable CCTV, tracks the progression of forest fires when they occur, and can wirelessly transmit real-time fire images of the forest fire.
Existing fixed CCTVs have limitations in the initial response to forest fire suppression. Drones, with their limited flight time of up to 40 minutes, are also impractical for monitoring the vast areas of forests prone to fires. Therefore, this forest fire monitoring device utilizing drones proposes a method that involves a 360-degree rotating wireless charging pad and charging a battery equipped to receive wireless power supplied from this pad.
The forest fire monitoring system based on this technology effectively monitors fires across vast forest areas by utilizing multiple drone hangars and drones, thereby aiding in the early detection and suppression of forest fires.
This technology pertains to sensor-integrated actuator haptic devices and their manufacturing method. Specifically, it is a haptic device technology that integrates both sensors and actuators on a single plane.
Existing technologies faced limitations in conventional haptic feedback devices, such as cost, complexity, and durability, which necessitated integrating sensors and actuators into a single unit. This technology addresses these issues by proposing a configuration that includes sensors and actuators, comprising a lower electrode, an ionic elastomer layer, and an upper electrode, all arranged on the same plane.
Consequently, this technology can enhance the efficiency and cost-effectiveness of haptic feedback devices by integrating sensors and actuators into a single unit. It offers significant value for applications in electronics, healthcare, pharmaceuticals, and advanced materials.
This technology relates to digital door locks and their control methods. Specifically, it is a digital door lock technology that combines password and facial authentication with an intrusion prevention mode.
In existing technologies, there was a need to address the problem of potential security risks arising from administrators being unable to monitor real-time situations detected by digital door locks. To address this, the present technology proposes a configuration that includes a digital door lock equipped with a door lock communication unit, a sensing unit, a capturing unit, and a door lock controller.
Accordingly, this technology can enhance security by enabling administrators to recognize situations occurring around the digital door lock and take necessary actions. It has application value in the fields of household goods, real estate, and software.
This technology relates to a location tracking system and method. Specifically, it is an AP signal and pedestrian-based location tracking technology that switches between indoor and outdoor modes.
Existing technologies were specialized for either indoor or outdoor environments, which meant conventional location tracking methods had limitations in that they could not track locations without distinguishing between indoor and outdoor. To overcome this, the present technology proposes a configuration that includes a location tracking system. This system comprises a server that receives signals from a user's nearby APs and measures AP signal strength, and a mobile terminal that transmits information about the measured signal strength and receives AP signal strength information.
Accordingly, this technology can improve the accuracy of location tracking by seamlessly transitioning between indoor and outdoor location tracking modes based on the user's location. It has practical value in the fields of IT, internet, smartphones, and software.
The present invention relates to a hair styling device that allows for easy, convenient, and diverse creation of hair wave styles at home or in salons.
Conventional hair irons, with their flat (straight) plate structure, make it very inconvenient to create hair waves (curls) as users must manually wrap and twist hair around a high-heat device. Moreover, because these clamp-type hair irons apply direct heat to the hair from above and below using a pressing method, there is a risk of severe hair damage if the usage time is not properly controlled. To address these issues, we propose a solution that incorporates an elastic hair styling device body and hair-securing protrusions on the body.
The present invention allows for easy, convenient, and diverse creation of hair wave styles even at home. Moreover, when styling hair, after wrapping it around the device body, the hair can be securely fixed using only the integrated hair-fixing mechanism, eliminating the need for separate components. This also offers the advantage of easy and convenient disassembly of the hair styling device after the desired hair wave is achieved.
This technology relates to unmanned aerial vehicle control systems and methods. Specifically, it is a technology that automatically controls unmanned aerial vehicles by switching between GPS and video analysis.
Existing technologies faced the challenge of controlling unmanned aerial vehicles without a dedicated pilot, particularly in areas with weak GPS reception, while also needing to automatically track users and avoid obstacles in the flight path. To overcome this, the present technology proposes a configuration comprising a mobile terminal that controls the UAV's flight using GPS location information, and a camera-equipped UAV that analyzes images to control flight based on user movement.
Accordingly, this technology improves the control of unmanned aerial vehicles by automatically tracking users and avoiding obstacles in the flight path, thereby enhancing user experience and safety in various applications. It offers significant value for use in the aerospace, robotics, and automation fields.
This technology relates to a composition for the prevention and treatment of diabetic complications, containing as active ingredients an alcohol extract of the whole plant, flowers, roots, or stems and leaves of Erigeron annuus, as well as ethyl acetate and butanol fractions obtained through systematic fractionation.
Diabetic complications are triggered by the formation of advanced glycation end-products and the abnormal activity of aldose reductase, yet there has been a lack of natural product-based compositions that effectively inhibit these processes.
This technology utilizes Erigeron annuus extract and its fractions to inhibit the formation of advanced glycation end-products and the activity of aldose reductase, making it applicable for use in therapeutic agents and health functional foods for the prevention and improvement of diabetic complications.
This patent is owned by IPBank. Upon purchase, you may receive support through commercialization programs, recommendations for technology transfer and commercialization funding guarantees, and additional points during the evaluation for priority procurement of excellent inventions.
This technology relates to a digital door lock remote control system and method using a mobile device. Specifically, it is a digital door lock remote control technology utilizing mobile device authentication.
Existing technologies needed to address the security and convenience issues of digital door locks by providing a system that distinguishes between regular and temporary users and enhances security and convenience for both types of users. To address this, the present technology proposes a configuration that includes a mobile device, a digital door lock, and a management server for communication and authentication processes.
Accordingly, this technology can enhance both security and convenience for regular and temporary users of digital door lock systems. It has practical application value in the household goods, real estate, and software sectors.
This technology relates to an apparatus and method for distinguishing stationary and moving objects using radar spectrum. Specifically, it is a technology that identifies stationary and moving objects through radar spectrum block analysis.
Existing technologies faced the challenge of accurately determining whether an object detected by radar was stationary or moving, especially when a vehicle was in motion. To address this, the present technology proposes a configuration that includes a receiver for radar spectrum analysis, a partition section, a binarization processing unit, a coordinate acquisition part, an operation unit, a controller, and an estimation unit.
Accordingly, this technology can improve the accuracy of object discrimination by considering vehicle speed and radar spectrum analysis. It has value for application in the automotive, mobility, and electronic device sectors.
