Stradvision, Inc.

Stadvision, Inc.

Stradivision, Inc.

Myungchul Sung

Hongmo Je

Wooju Ryu

Yongjoong Kim

Hojin Cho

Taewoong Jang

SukHoon Boo

Donghun Yeo

Kyungjoong Jeong

Woonhyun Nam

Kye-Hyeon Kim

Hak-Kyoung Kim

Insu Kim

Hyungsoo Lee

Myeong-Chun Lee

DongSoo Shin

Dongsoo Shin

Woonhyu Nam

A method for learning parameters of a CNN using a 1&#xd7;K convolution operation or a K&#xd7;1 convolution operation is provided to be used for hardware optimization which satisfies KPI. The method includes steps of: a learning device (a) instructing a reshaping layer to two-dimensionally concatenate features in each group comprised of corresponding K channels of a training image or its processed feature map, to thereby generate a reshaped feature map, and instructing a subsequent convolutional layer to apply the 1&#xd7;K or the K&#xd7;1 convolution operation to the reshaped feature map, to thereby generate an adjusted feature map; and (b) instructing an output layer to refer to features on the adjusted feature map or its processed feature map, and instructing a loss layer to calculate losses by referring to an output from the output layer and its corresponding GT.

Learning method and learning device for CNN using 1xK or Kx1 convolution to be used for hardware optimization, and testing method and testing device using the same

A method for on-device continual learning of a neural network which analyzes input data is provided to be used for smartphones, drones, vessels, or a military purpose. The method includes steps of: a learning device, (a) sampling new data to have a preset first volume, instructing an original data generator network, which has been learned, to repeat outputting synthetic previous data corresponding to a k-dimension random vector and previous data having been used for learning the original data generator network, such that the synthetic previous data has a second volume, and generating a batch for a current-learning; and (b) instructing the neural network to generate output information corresponding to the batch. The method can be performed by generative adversarial networks (GANs), online learning, and the like. Also, the present disclosure has effects of saving resources such as storage, preventing catastrophic forgetting, and securing privacy.

Method and device for on-device continual learning of a neural network which analyzes input data, and method and device for testing the neural network to be used for smartphones, drones, vessels, or military purpose

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 method for generating a lane departure warning (LDW) alarm by referring to information on a driving situation is provided to be used for ADAS, V2X or driver safety which are required to satisfy level 4 and level 5 of autonomous vehicles. The method includes steps of: a computing device instructing a LDW system (i) to collect information on the driving situation including information on whether a specific spot corresponding to a side mirror on a side of a lane, into which the driver desires to change, belongs to a virtual viewing frustum of the driver and (ii) to generate risk information on lane change by referring to the information on the driving situation; and instructing the LDW system to generate the LDW alarm by referring to the risk information. Thus, the LDW alarm can be provided to neighboring autonomous vehicles of level 4 and level 5.

Method and device for learning generating lane departure warning (LDW) alarm by referring to information on driving situation to be used for ADAS, V2X or driver safety required to satisfy level 4 and level 5 of autonomous vehicles

A method for achieving better performance in autonomous driving while saving computing power, by using confidence scores representing a credibility of an object detection which is generated in parallel with an object detection process is provided. And the method includes steps of: (a) a computing device acquiring at least one circumstance image on surroundings of a subject vehicle, through at least one image sensor installed on the subject vehicle; (b) the computing device instructing a convolutional neural network (CNN) to apply at least one CNN operation to the circumstance image, thereby to generate initial object information and initial confidence information on the circumstance image; and (c) the computing device generating final object information on the circumstance image by referring to the initial object information and the initial confidence information with a support of a Reinforcement learning (RL) reinforcement learning (RL) agent, and through V2X communications with at least part of surrounding objects.

Method and device for attention-driven resource allocation by using reinforcement learning and V2X communication to thereby achieve safety of autonomous driving

A learning method of a CNN (Convolutional Neural Network) for monitoring one or more blind spots of a monitoring vehicle is provided. The learning method includes steps of: a learning device, if training data corresponding to output from a detector on the monitoring vehicle is inputted, instructing a cue information extracting layer to uses class information and location information on a monitored vehicle included in the training data, thereby outputting cue information on the monitored vehicle; instructing an FC layer for monitoring the blind spots to perform neural network operations by using the cue information, thereby outputting a result of determining whether the monitored vehicle is located on one of the blind spots; and instructing a loss layer to generate loss values by referring to the result and its corresponding GT, thereby learning parameters of the FC layer for monitoring the blind spots by backpropagating the loss values.

Learning method and testing method for monitoring blind spot of vehicle, and learning device and testing device using the same

A learning method for calculating collision probability, to be used for determining whether it is appropriate or not to switch driving modes of a vehicle capable of an autonomous driving, by analyzing a recent driving route of a driver is provided. And the method includes steps of: (a) a learning device, on condition that a status vector and a trajectory vector are acquired, performing processes of (i) instructing a status network to generate a status feature map and (ii) instructing a trajectory network to generate a trajectory feature map; (b) the learning device instructing a safety network to calculate a predicted collision probability representing a predicted probability of an accident occurrence; and (c) the learning device instructing a loss layer to generate a loss by referring to the predicted collision probability and a GT collision probability, which have been acquired beforehand, to learn at least part of parameters.

Learning method and learning device for determining whether to switch mode of vehicle from manual driving mode to autonomous driving mode by performing trajectory-based behavior analysis on recent driving route

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 method for planning an autonomous driving by using a V2X communication and an image processing under a road circumstance where both vehicles capable of the V2X communication and vehicles incapable of the V2X communication exist is provided. And the method includes steps of: (a) a computing device, corresponding to a subject autonomous vehicle, instructing a planning module to acquire recognition information on surrounding vehicles including (i) first vehicles capable of a V2X communication and (ii) second vehicles incapable of the V2X communication; (b) the computing device instructing the planning module to select an interfering vehicle among the surrounding vehicles; and (c) the computing device instructing the planning module to generate a potential interference prediction model, and to modify current optimized route information in order to evade a potential interfering action, to thereby generate updated optimized route information of the subject autonomous vehicle.

Method and device for short-term path planning of autonomous driving through information fusion by using V2X communication and image processing

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 method for providing an autonomous driving service platform for autonomous vehicles by using a competitive computing and information fusion is provided. And the method includes steps of: (a) a service server acquiring individual sensor data and individual driving data through sensors installed on at least part of the autonomous vehicles including a subject vehicle; (b) the service server performing (i) a process of acquiring autonomous driving source information for the subject vehicle by inputting specific sensor data of specific autonomous vehicles among the autonomous vehicles and subject sensor data of the subject vehicle to data processing servers and (ii) a process of acquiring circumstance-specific performance information on the data processing servers from a circumstance-specific performance DB; and (c) the service server transmitting the autonomous driving source information and the circumstance-specific performance information to the subject vehicle, to thereby instruct the subject vehicle to perform the autonomous driving.

Method for providing autonomous driving service platform to be used for supporting autonomous driving of vehicles by using competitive computing and information fusion, and server using the same

A learning method for providing a functional safety by warning a driver about a potential dangerous situation by using an explainable AI which verifies detection processes of a neural network for an autonomous driving is provided. And the learning method includes steps of: (a) a learning device for verification, if at least one training image for verification is acquired, instructing a property extraction module to apply extraction operation to the training image for verification to extract property information on characteristics of the training image for verification to thereby generate a quality vector; (b) the learning device for verification instructing the neural network for verification to apply first neural network operations to the quality vector, to thereby generate predicted safety information; and (c) the learning device for verification instructing a loss module to generate a loss, and perform a backpropagation by using the loss, to thereby learn parameters included in the neural network for verification.

Learning method and learning device for providing functional safety by warning driver about potential dangerous situation by using explainable AI which verifies detection processes of autonomous driving network, and testing method and testing device using the same

A learning method for detecting driving events occurring during driving, to thereby detect driving scenarios including at least part of the driving events is provided. The method includes: (a) in response to a specific enumerated event vector including each of pieces of information on each of specific driving events as its specific components in a specific order being acquired, a learning device instructing a recurrent neural network (RNN) to apply RNN operations to the specific components of the specific enumerated event vector, to thereby detect a specific predicted driving scenario including the specific driving events; (b) the learning device instructing a loss module to generate an RNN loss by referring to the specific predicted driving scenario and a specific ground-truth (GT) driving scenario and to perform a backpropagation through time (BPTT) by using the RNN loss, to thereby learn at least part of the parameters of the RNN.

Growing community of inventors

Gyeongsangbuk-do, South Korea

Myungchul Sung