This technology describes an unpowered gait assistance mechanism that utilizes an elastic body to convert changes in distance between the device and the user, occurring during the user's gait, into a compensatory force.
Existing robotic gait assist devices that use external power sources had problems with temporal and spatial constraints, as well as reduced rehabilitation training effectiveness due to passive joint movements.
This technology, therefore, proposes a method that utilizes an elastic body, a link unit, and an action point conversion unit, all integrated into the weight support section, to convert the user's trunk movement force into gait assistance force and deliver it to the lower limbs in sync with the gait cycle.
This technology was developed through the support of the Pan-Government Medical Device R&D Project Group's research project on the development and usability evaluation of an indoor mobile gait rehabilitation device capable of weight support and lower limb muscle assistance.
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 involves doping Mg, Ti, and Zr into a Na-Ni-Mn-Fe-based layered cathode active material to achieve a composite crystal structure where P2 and O3 phases coexist, thereby mitigating lattice deformation during charging and discharging and improving ion mobility.
Conventional transition metal-based layered cathode materials (Na-Ni-Mn-Fe system) have high discharge capacity, but they suffer from a rapid decrease in capacity retention due to structural instability during repeated charge/discharge cycles.
Accordingly, this technology proposes the design of a cathode active material with a composition of Na a Ni b Mn c Fe d Mg e Ti f Zr gO h (e.g., 0.70≤a≤0.80). Specifically, through Mg, Ti, and Zr doping, it expands the c-axis lattice within the crystal structure, thereby enhancing sodium ion diffusion performance and suppressing irreversible phase transitions, which significantly contributes to securing electrochemical cycle life and reversibility.
This technology was developed with support from the National Research Foundation of Korea's research project on 'Development of 4V-class aqueous lithium-ion batteries through AI-based novel lithium salt discovery'.
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'.
