Abstract: An intra prediction method and a device using the intra prediction method are provided. The intra prediction method includes the steps of: deriving a current prediction mode as a prediction mode of a current block; constructing neighboring samples of the current block with available reference samples; filtering the available reference samples; and generating predicted samples of the current block on the basis of the filtered available reference samples. The filtering step includes performing the filtering using the available reference sample located in the prediction direction of the current prediction mode and a predetermined number of available reference samples neighboring to the prediction direction of the current prediction mode.

Abstract: The present invention includes obtaining block type identification information on a partition of the current macroblock when the current macroblock is intra-mixed specifying a bock type of the current macroblock based on the block type identification information, obtaining an intra prediction mode of the current macroblock according to the block type of the partition of the current macroblock, and predicting the current macroblock using the intra prediction mode and a pixel value of a neighboring block.

Abstract: Disclosed are an apparatus for distributing power of an electric vehicle and a method thereof capable of optimally improving the energy consumption efficiency of the electric vehicle by predicting a vehicle speed for a predetermined time using a learned vehicle speed prediction model, determining wheel power based on the vehicle speed, and distributing the wheel power to a front wheel drive motor and a rear wheel drive motor. The apparatus includes a storage that stores a vehicle speed prediction model in which learning is completed, and a controller that predicts a vehicle speed for a preset time using the vehicle speed prediction model, determines wheel power based on the vehicle speed, and distributes the wheel power to a front wheel drive motor and a rear wheel drive motor.

Abstract: A system for modeling energy consumption efficiency of an electric vehicle and a method thereof are disclosed. The system includes a communication device that communicates with a plurality of electric vehicles and includes a controller that receives learning data from the plurality of electric vehicles, learns an energy consumption efficiency model based on the received learning data, and transmits the energy consumption efficiency model in which the learning is completed to the plurality of electric vehicles.

Abstract: Disclosed are a system for modeling energy consumption efficiency of an electric vehicle and a method thereof. The system includes: a communication device that communicates with a plurality of electric vehicles, and a controller that receives a parameter set of an energy consumption efficiency model from the plurality of electric vehicles. The controller determines an average of received parameter sets as an optimal parameter set, and transmits the determined optimal parameter set to the plurality of electric vehicles.

Abstract: An apparatus and method are provided for controlling a powertrain of an autonomous vehicle. The apparatus includes an autonomous driving controller that controls autonomous driving of the vehicle and a transmission controller that determines whether the vehicle satisfies a pulse and glide (P&G) driving condition during the autonomous driving. The transmission controller alternately performs pulse driving and coasting in conjunction with the autonomous driving controller when the vehicle satisfies the P&G driving condition. The transmission controller causes a transmission to remain in a neutral state during the coasting.

Abstract: Disclosed are a multi-agent-based reinforcement learning system and method therefor. The multi-agent-based reinforcement learning system includes: a slave agent configured to: store a data set collected in each state of a first environment in a first buffer, store a data set received from a master agent in the first buffer, and learn a Q-function based on the data set stored in the first buffer; and the master agent configured to store a data set collected in each state of a second environment in a second buffer; transmit the data set to the slave agent; update a Q-function matched with the slave agent among a plurality of Q-functions; and perform reinforcement learning based on the data set stored in the second buffer.

Abstract: A system for controlling a vehicle battery includes a vehicle which includes a motor that provides a driving force or generates power through regenerative braking and a battery that provides power to the motor and calculates a battery usage according to use of the battery, and a portable terminal which obtains location information of a user, generates a battery charge/discharge guide based on the location information of the user and the battery usage received from the vehicle, and transmits the battery charge/discharge guide to the vehicle, thus minimizing anxiety and inconvenience to users when charging and discharging an electric vehicle, and also minimizing the maintenance cost of the electric vehicle.

Abstract: An apparatus and a method for controlling a transmission of a vehicle include an agent that determines a gear stage of the vehicle based on driving information of the vehicle, shape information of a road, and/or operation information of a driver, and include a controller that performs a reward with respect to the determination of the agent and controls the transmission of the vehicle based on the gear stage determined by the agent.

Abstract: A system and a method for controlling shifting stage of a hybrid vehicle may include a speed detecting device that detects a vehicle speed, an automatic transmission that changes a shifting stage of the vehicle, and a shift controller connected to the speed detecting device and the automatic transmission. The shift controller is configured to determine a start of shift control based on a travel environment and a travel state of the vehicle, compares the vehicle speed with a target vehicle speed when the start of the shift control is determined, and performs the shift control based on a state of charge of a battery of the vehicle and a regenerative braking amount of the vehicle when the shift controller concludes that the vehicle speed exceeds the target vehicle speed.

Abstract: A vehicle curation system includes: a vehicle that obtains driving information of a driver, a server that obtains the driving information from the vehicle and stores the driving information for each driver and specification information of a new vehicle, and a curation device that receives driving information corresponding to driver information from the server when the driver information is input. In particular, the curation device determines driver driving tendencies and a vehicle character based on the specification information of the new vehicle, and further determines a curation target vehicle based on a similarity between the driver driving tendencies and the vehicle character.

Abstract: A device for controlling an electric oil pump (EOP), which is configured to supply a hydraulic pressure to a vehicle, includes a controller that controls driving of the EOP based on lighting information of a traffic light corresponding to a travel direction of the vehicle in a state in which an engine of the vehicle is stopped as an Idle Stop and Go (ISG) system of the vehicle is operated.

Abstract: An apparatus of controlling a pulley of a continuously variable transmission and a method therefore is provided. The apparatus includes a non-transitory storage configured for storing a deep learning model, learning of which is completed and a controller that predicts a vehicle speed and an accelerator position sensor (APS) value for each future time point based on the deep learning model and controls the pulley of the continuously variable transmission based on a pulley ratio for each future time point, the pulley ratio corresponding to the predicted vehicle speed and the predicted APS value, thus preventing a reverse control phenomenon of the pulley ratio and increasing a tension of the belt in the continuously variable transmission.

Abstract: A shift control device and a shift control method for a vehicle may include a storage to store a table having a target speed corresponding to a speed of the vehicle at a starting point of a coasting operation of the vehicle and a speed profile corresponding to each of gearshifting stages of the vehicle with respect to each downhill slope, and a controller to control gearshifting of the vehicle traveling in the coasting operation on a downhill road, according to the table and the speed profile, to control the speed of the vehicle, according to a driver intent of accelerating the vehicle and a driver intent of traveling the vehicle at a constant speed.

Abstract: An apparatus of controlling a pulley of a continuously variable transmission and a method therefore is provided. The apparatus includes a non-transitory storage configured for storing a deep learning model, learning of which is completed and a controller that predicts a vehicle speed and an accelerator position sensor (APS) value for each future time point based on the deep learning model and controls the pulley of the continuously variable transmission based on a pulley ratio for each future time point, the pulley ratio corresponding to the predicted vehicle speed and the predicted APS value, thus preventing a reverse control phenomenon of the pulley ratio and increasing a tension of the belt in the continuously variable transmission.

Abstract: An apparatus and a method for controlling a transmission of a vehicle include an agent that determines a gear stage of the vehicle based on driving information of the vehicle, shape information of a road, and/or operation information of a driver, and include a controller that performs a reward with respect to the determination of the agent and controls the transmission of the vehicle based on the gear stage determined by the agent.

Abstract: An apparatus configured for controlling shift of a vehicle and a method therefore are provided. The apparatus include a storage storing a deep learning model, learning of which is completed; and a controller that predicts a vehicle speed and an accelerator position sensor (APS) value for each future time point according to the deep learning model, predicts a gear stage for each future time point using the predicted vehicle speed and the predicted APS value, and controls the shift of the vehicle based on the gear stage for each future time point, thus preventing a busy shift phenomenon and preventing an acceleration delay phenomenon.

Abstract: A vehicular driving control system and a method for operating the same are provided, may include an information provider to provide information on a front road of a vehicle, a transmission controller to control gear shifting by predicting a condition on the front road based on the information on the front road, and a diagnosing device to diagnose a failure status by verifying matching with the information on the front road, and to restrict a predictive gear-shifting controlling operation of the transmission controller, according to a result of the diagnosing.

Abstract: Disclosed are a device and a method for controlling a driving mode of a vehicle. The device includes a sensor for collecting information about an access road to a controlled-access highway, and a controller which determines a switching point on the access road at which the driving mode of the vehicle is switched to a sport mode, based on the information about the access road to the controlled-access highway, and switches the driving mode of the vehicle to the sport mode when the vehicle reaches the switching point on the access road. Thus, the vehicle accesses the controlled-access highway naturally without interfering with flow of other vehicles.

Abstract: An apparatus for controlling shifting of a vehicle and a method therefor are provided, where the apparatus includes a storage storing a power map in which a demand power corresponding to a vehicle speed and an accelerator position sensor (APS) value is recorded and storing an energy consumption map of a power source for each gear stage. The apparatus includes a controller that detects a current demand power based on the power map, generates a power graph representing the detected demand power as the number of revolution and a torque of the power source for each gear stage, and matches the generated power graph with the energy consumption map of the power source to control a shift to a gear stage which consumes minimum energy.