Stradvision, Inc.

Hyundai Motor Company

Kia Motors Corporation

Kia Corporation

Samsung Electronics Co., Ltd.

Stadvision, Inc.

DongSoo Shin

Hongmo Je

Wooju Ryu

Yongjoong Kim

Hojin Cho

Woonhyun Nam

Taewoong Jang

SukHoon Boo

Donghun Yeo

Myungchul Sung

Kyungjoong Jeong

Kye-Hyeon Kim

Hak-Kyoung Kim

Hyungsoo Lee

Myeong-Chun Lee

Jeong-Eom Lee

Seona Kim

Donghee Seok

HeeJin Ro

Ga Hee Kim

Kye Yoon Kim

Jung Mi Park

Sihyun Joo

Hwan Mook Kim

Miyeon Park

Sung Un Kim

Minkyung Lee

Jung Park

Jihyun Ahn

Joonho Ok

Miji Park

Jongil Jeong

Jinsoo Jang

Eunsil Gim

Jina Choe

Sukhoon Boo

An electronic device is provided. The electronic device includes a sensor module, a communication module, a display, a memory, and at least one processor configured to identify a plurality of states based on at least one of information obtained through the sensor module, information received from an external electronic device through the communication module, or information associated with a function of the electronic device, identify priorities of the plurality of states, identify a first state among the plurality of states based on the identified priorities, identify whether there is a second state mergeable with the first state, and control the display to display, a first character object corresponding to the first state or a third character object corresponding to merge of the first state and the second state, based on whether there is the second state mergeable with the first state.

Electronic device and method for displaying character object based on priority of multiple states in electronic device

It is an aspect of the present disclosure to provide a dialogue system capable of providing an extended function to the user by registering a new vocabulary that matches the user's preference and by changing the pre-stored conversation pattern.

Dialogue system and dialogue processing method

A dialog processing system may include a communication device configured to receive information sent from the outside and circumstantial information; a storage configured to store a rule and a dialog template related the rule; a rule determiner configured to compare a condition of the rule and the information to generate a determined rule; a situation determiner configured to determine to express the determined rule based on the determined rule and circumstantial information collected from the outside; and a result processor configured to generate text to be expressed based on the determined rule and the dialog template and output the text according to a signal sent from the situation determiner.

Dialog processing system, vehicle having the same, dialog processing method

A method for learning a recurrent neural network to check an autonomous driving safety to be used for switching a driving mode of an autonomous vehicle is provided. The method includes steps of: a learning device (a) if training images corresponding to a front and a rear cameras of the autonomous vehicle are acquired, inputting each pair of the training images into corresponding CNNs, to concatenate the training images and generate feature maps for training, (b) inputting the feature maps for training into long short-term memory models corresponding to sequences of a forward RNN, and into those corresponding to the sequences of a backward RNN, to generate updated feature maps for training and inputting feature vectors for training into an attention layer, to generate an autonomous-driving mode value for training, and (c) allowing a loss layer to calculate losses and to learn the long short-term memory models.

Learning method and learning device of recurrent neural network for autonomous driving safety check for changing driving mode between autonomous driving mode and manual driving mode, and testing method and testing device using them

A learning method for acquiring at least one personalized reward function, used for performing a Reinforcement Learning (RL) algorithm, corresponding to a personalized optimal policy for a subject driver is provided. And the method includes steps of: (a) a learning device performing a process of instructing an adjustment reward network to generate first adjustment rewards, by referring to the information on actual actions and actual circumstance vectors in driving trajectories, a process of instructing a common reward module to generate first common rewards by referring to the actual actions and the actual circumstance vectors, and a process of instructing an estimation network to generate actual prospective values by referring to the actual circumstance vectors; and (b) the learning device instructing a first loss layer to generate an adjustment reward and to perform backpropagation to learn parameters of the adjustment reward network.

Learning method and learning device for supporting reinforcement learning by using human driving data as training data to thereby perform personalized path planning

A dialogue system and a vehicle having the same is provided. The dialogue system may recognize the user's speech, which is transmitted from the speech input device, as a text, derive user labeling context information after verifying an entity of the text, store the user labeling context information in the type to share an entity ontology with other user, and generate a dialogue response to perform an action corresponding when a user performs a free utterance or a designated entity utterance.

Dialogue system and vehicle using the same

A learning method for performing a seamless parameter switch by using a location-specific algorithm selection for an optimized autonomous driving is provided. And the method includes steps of: (a) a learning device instructing a K-th convolutional layer to apply a convolution operation to K-th training images, to thereby generate K-th feature maps; (b) the learning device instructing a K-th output layer to apply a K-th output operation to the K-th feature maps, to thereby generate K-th estimated autonomous driving source information; (c) the learning device instructing a K-th loss layer to generate a K-th loss by using the K-th estimated autonomous driving source information and its corresponding GT, and then to perform backpropagation by using the K-th loss, to thereby learn K-th parameters of the K-th CNN; and (d) the learning device storing the K-th CNN in a database after tagging K-th location information to the K-th CNN.

Location-specific algorithm selection for optimized autonomous driving

A learning method for transforming a virtual video on a virtual world to a more real-looking video is provided. And the method includes steps of: (a) a learning device instructing a generating CNN to apply a convolutional operation to an N-th virtual training image, N-th meta data and (N-K)-th reference information to generate an N-th feature map; (b) the learning device instructing the generating CNN to apply a deconvolutional operation to the N-th feature map to generate an N-th transformed image; (c) the learning device instructing a discriminating CNN to apply a discriminating CNN operation to the N-th transformed image to generate a category score vector; (d) the learning device instructing the generating CNN to generate a generating CNN loss by referring to the category score vector and its corresponding GT, and to perform backpropagation by referring to the generating CNN loss to learn parameters of the generating CNN.

Learning method and learning device for generating training data from virtual data on virtual world by using generative adversarial network, to thereby reduce annotation cost required in training processes of neural network for autonomous driving, and a testing method and a testing device using the same

A dialogue system is provided to assist a user while minimizing distraction and achieve safe driving by adjusting a level of a dialogue service based on a dialogue with the user in a vehicle driving environment and multiple kinds of information including vehicle state information, driving environment information, and user information, and a vehicle having the dialogue system and a dialogue service processing method is provided.

Dialogue system, vehicle having the same and dialogue service processing method

A method for delivering a steering intention of an autonomous driving module to a steering apparatus more accurately by using a reference map is provided. And the method includes steps of: (a) a computing device, if a subject intended steering signal inputted by the autonomous driving module at a current timing is acquired, instructing a signal adjustment module to select, by referring to the reference map, specific reference steering guide values corresponding to the subject intended steering signal; (b) the computing device (i) adjusting the subject intended steering signal by referring to the specific reference steering guide values, in order to generate a subject adjusted steering signal, and (ii) transmitting the subject adjusted steering signal to the steering apparatus, to thereby support the steering apparatus to rotate the subject vehicle by a specific steering angle corresponding to the subject intended steering signal.

Method and device for delivering steering intention of autonomous driving module or driver to steering apparatus of subject vehicle more accurately

A dialogue system includes: an input processor extracting an action corresponding to a user's utterance; a storage storing information value of context information comprising at least one of vehicle state information related to a vehicle state, and driving environment information related to the driving environment of the vehicle; a dialogue managing processor acquiring a parameter value of a condition determination parameter used to determine whether the action corresponding to the user's utterance is executable, from the storage, the dialogue managing processor determining an action to be executed based on the parameter value of the condition determination parameter, the dialogue managing processor acquiring a parameter value of action parameter used to execute the determined action, from the storage; and a result processor generating a response to execute the determined action by using the acquired parameter value of action parameter.

Dialogue system, vehicle having the same and dialogue processing method

A dialogue system, a vehicle and a method for controlling the vehicle is disclosed. The method for controlling the vehicle includes: acquiring an utterance and a speech pattern by recognizing a speech when a speech of a plurality of speakers is input through a speech input device; classifying dialogue contents for each speaker based on the acquired utterance and speech pattern; acquiring a relationship between the speakers based on the acquired utterance; understanding an intention and a context for each speaker based on the acquired relationship between the speakers and the acquired dialogue content for each speaker determining an action corresponding to the acquired relationship and the acquired intention and context for each speaker, and outputting an utterance corresponding to the determined action; generating a control command corresponding to the determined action; and controlling a load based on the generated control command.

Dialogue system, vehicle and method for controlling the vehicle

A learning method for generating integrated object detection information by integrating first object detection information and second object detection information is provided. And the method includes steps of: (a) a learning device instructing a concatenating network to generate one or more pair feature vectors; (b) the learning device instructing a determining network to apply FC operations to the pair feature vectors, to thereby generate (i) determination vectors and (ii) box regression vectors; (c) the learning device instructing a loss unit to generate an integrated loss by referring to the determination vectors, the box regression vectors and their corresponding GTs, and performing backpropagation processes by using the integrated loss, to thereby learn at least part of parameters included in the DNN.

Learning method and learning device for integrating object detection information acquired through V2V communication from other autonomous vehicle with object detection information generated by present autonomous vehicle, and testing method and testing device using the same

A method for signaling a driving intention of an autonomous vehicle is provided. The method includes steps of: a driving intention signaling device (a) detecting a pedestrian ahead of the autonomous vehicle using surroundings video images, and determining whether the pedestrian crosses a roadway using a virtual crosswalk; (b) if the pedestrian crosses the roadway, estimating a crosswalking trajectory, corresponding to an expected path of the pedestrian, by referring to a moving trajectory of the pedestrian, setting a driving plan of the autonomous vehicle referring to driving information and the crosswalking trajectory, and allowing the autonomous vehicle to self-drive by the driving plan; and (c) determining whether the pedestrian pays attention to the autonomous vehicle by referring to gaze patterns and, if not, allowing delivery of the driving intention to the pedestrian and/or a nearby driver, via an external display and/or an external speaker.

Method and device for signaling present driving intention of autonomous vehicle to humans by using various V2X-enabled application

Growing community of inventors

Suwon-si, South Korea

DongSoo Shin