Hyundai Motor Company

Kia Corporation

Kia Motors Corporation

Hyperconnect Inc.

Korea Advanced Institute of Science and Technology

Hyundai Rotem Company

Beom Su Kim

Dong Jin Hyun

Ju Young Yoon

Hyun Seop Lim

Ki Hyeon Bae

Sang In Park

Kyu Jung Kim

Seok Jun Seo

Seung Ju Han

Sang Il Ahn

Seung Kyu Nam

Enkhbayar Erdenee

Dong Hyun Lee

Dong Young Kim

Sung Joo Ha

Joo Won Lee

Hyo Seung Han

Hyo Joong Kim

Martin Kersner

Bu Ru Chang

Sang Bum Kim

Seok Ryung Kwon

Hyoun Taek Yong

Jin Yong Yoo

Jae Hyun Kim

Tae Jun Lee

Yeon Woo Lee

Su Hyun Lee

Se Yeon Oh

Sun Young Bae

Dong Hwa Jeong

Jae Seung Jeong

Adedoyin Olumuyiwa Aderinwale

Jun Ha Jung

Dae Je Kim

Provided is a method of transforming a landmark including: receiving an input image including a facial image of a first person and a landmark corresponding to the facial image; estimating a transformation matrix corresponding to the landmark; and calculating an expression landmark and an identity landmark corresponding to the input image by using the transformation matrix.

Method and apparatus for generating landmark

An upper arm module of a wearable muscular strength assisting apparatus is provided. The upper arm module includes a base part configured to be connected to a wearer's body, and an upper arm part having a first end thereof coupled to the base part to be rotatable about a fixed point. The upper arm part is coupled to the wearer's upper arm to apply a torque thereto. The upper arm module further includes an elastic body having a first end thereof fixedly coupled to the upper arm part and generating an elastic force by deformation. In particular, the upper arm module also includes a first link having a first end thereof rotatably coupled to the base part at a point of application, and a second link rotatably coupled to the second end of the first link at a first point.

Upper arm module of wearable muscular strength assisting apparatus and wearable muscular strength assisting apparatus including same

A training method of a conversation model according to various example embodiments of the present disclosure may include identifying a first context, identifying a first response set corresponding to the first context based on a first model, identifying a response subset selected from the first response set based on a gold response corresponding to the first context and training a second model based on the first context information and the response subset.

Method of generating conversation information using examplar-based generation model and apparatus for the same

Disclosed is a method of training a dialogue model in an electronic device, the method including selecting a first context from a first dialogue data set including at least one pair of a context and a response corresponding to the context, generating a first response corresponding to the first context through a first dialogue model, generating an augmented dialogue dataset by incorporating a pair of the first context and the first response corresponding to the first context into the first dialogue data set, and training a second dialogue model based on the augmented dialogue dataset.

Dialogue model training method and device therefor

A strength assist device includes: a base frame; a plurality of rotating bodies provided on left and right sides of the base frame, and rotatably connected to the base frame; a plurality of actuators rotatably connected to the respective rotating bodies, and forming respective restoring torques according to rotation angles with respect to the rotating bodies; and a cable connecting the rotating bodies. In particular, rotational motions of the rotating bodies with respect to the base frame are restricted against each other by a tension of the cable.

Strength assist device

Systems and techniques to generate imitative responses are illustrated. response generation method performed in an electronic apparatus of the present disclosure includes acquiring at least one piece of utterance data, acquiring a first context corresponding to the utterance data from a context candidate set, generating one or more dialogue sets including the first context and the utterance data, receiving a second context from a user, and acquiring a response corresponding to the second context using a language model based on the one or more dialogue sets.

Method of generating response using utterance and apparatus therefor

A controller includes: a head part including a display unit providing information and images and a button unit having operation buttons; and a body part joined to the head part, where the display unit includes a projection portion engaged with the body part, the body part includes a recessed portion into which the projection portion is inserted, a first uneven portion is provided on an outer circumferential surface of the projection portion, a second uneven portion having a shape corresponding to that of the first uneven portion is provided on an inner circumferential surface of the recessed portion, and at least one of the first uneven portion or the second uneven portion includes a plurality of uneven portions.

Controller, crutch and wearable robot including the same

A method of generating a reenacted image includes: extracting a landmark from each of a driver image and a target image; generating a driver feature map based on pose information and expression information of a first face shown in the driver image; generating a target feature map and a pose-normalized target feature map based on style information of a second face shown in the target image; generating a mixed feature map by using the driver feature map and the target feature map; and generating the reenacted image by using the mixed feature map and the pose-normalized target feature map.

Method and apparatus for generating reenacted image

An embodiment rehabilitation robot control apparatus includes a brainwave signal measuring device configured to measure a brainwave signal of a user, a preprocessing device configured to preprocess the measured brainwave signal, a classification device configured to classify a motor intention of the user based on the brainwave signal preprocessed by the preprocessing device, and a controller configured to reflect the motor intention of the user in real time to control an operation or a stop of a rehabilitation robot.

Rehabilitation robot control apparatus and method thereof

A strength assist device includes: a multi-link part including one or more links; a profile controller that is connected to one end portion of the multi-link part, and rotates around a central rotational axis; and an elastic force providing part that is connected to the other end portion of the multi-link part, and provides an elastic force to the multi-link part. When the profile controller rotates and one end portion of the multi-link part revolves around the central rotational axis, the elastic force applied to the multi-link part varies.

An embodiment power transmission device includes an input shaft rotatable about a first rotation axis, first and second wires wound around an outer surface of the input shaft based on a first radial direction, each having a first side fixed to the input shaft, an output shaft rotatable about a second rotation axis, the output shaft including a shaft body, wherein the first and second wires surround an outer surface of the shaft body based on a second radial direction, and first and second wire holders to which a second side of the first wire and a second side of the second wire are respectively fixed. The first wire extends in a first circumferential direction of the shaft body, and then the first wire extends in a second circumferential direction opposite to the first circumferential direction of the shaft body.

Power transmission device

A gravity compensator applied to a wearable muscular strength assisting apparatus includes a first link configured to extend parallel to a first body portion of a wearer, a second link configured to extend parallel to a second body portion and which is rotatably coupled to an end of the first link, an elastic body, which is fixed at an end thereof to the first link so as to exert an elastic force, which varies according to a length between the two ends thereof, and a connection unit, which is connected an end thereof to the other end of the elastic body and extends in a longitudinal direction of the first link and which is connected at an end thereof to the second link so as to vary a length of the elastic body by relative rotation between the first link and the second link.

Gravity compensator applied to wearable muscular strength assisting apparatus

Display screen or portion thereof with graphical user interface

Growing community of inventors

Yongin-si, South Korea

Beom Su Kim