Abstract: An apparatus for providing tire information is provided. The apparatus includes a detector that detects driving information as a vehicle is being driven and a controller that calculates a relative speed of a tire of the vehicle and a resonance frequency of the tire based on the driving information. The controller then compares the calculated relative speed and the calculated resonance frequency with a previously learned determination reference value to determine whether the tire is deflated.

Abstract: An embodiment system for controlling switching to a manual driving mode of an autonomous vehicle includes a steering controller configured to determine whether a steering angle is changed according to operation of a steering wheel by a driver, a braking controller configured to apply braking torque to a braking device of each wheel, a motor controller configured to apply individual regenerative braking torque and driving torque to each wheel, and an autonomous driving controller configured to determine a control torque for maintaining straight-ahead driving and to issue an instruction using a feedforward control scheme when a steering angle change signal according to the operation of the steering wheel by the driver is received from the steering controller in a transition section in which an autonomous driving mode is switched to the manual driving mode during high-speed straight-ahead driving of the autonomous vehicle.

Abstract: When there is a request of a driver for transition to manual driving mode while the autonomous vehicle is driving in autonomous driving mode, the autonomous vehicle is set to a safe state by performing control operations of maintaining a vehicle speed previously designated by the driver, maintaining safe distances between vehicles, and changing the driving land and the driving route. The driver is provided with a warning signal notifying that safe transition to the manual driving mode is possible. Accordingly, the driving mode of the autonomous vehicle is transited to the manual mode in a state in which the safety of the autonomous vehicle is obtained.

Abstract: A method of controlling switching to a manual driving mode of an autonomous vehicle, enables switching to the manual driving mode to be safely performed without interfering with a nearby vehicle in a safe lane or a safe place according to a surrounding driving environment by allowing a driver to select between switching to the manual driving mode while driving or switching to the manual driving mode after stopping to switch to the manual driving mode while the autonomous vehicle is driven in an autonomous driving mode.

Abstract: A method for controlling a driving mode transition of an autonomous driving vehicle may safely perform a lane change to avoid a collision accident with the other vehicle and prevent an injury to a joint, etc., while minimizing a sense of heterogeneity of a driver according to minimization of rotational steering of a steering wheel by determining whether the other vehicle in a next lane suddenly cuts in in an autonomous driving controller while the autonomous driving vehicle is driving in a manual driving mode and determining a safety distance from a rear vehicle to minimize rotational steering of the steering wheel held by the driver and at the same time perform partial braking control by autonomous driving mode transition control using an autonomous driving controller.

Abstract: A method of controlling switching to a manual driving mode of an autonomous vehicle allowing stable transition to the manual driving mode and prevention of collision accidents includes performing motor drive control of a motor controller and braking control of a braking controller according to a command of an autonomous driving controller in a complex manner, when there is a risk of a collision accident caused by a difference between a target yaw rate of the autonomous vehicle and an actual yaw rate of the autonomous vehicle in a transition section from an autonomous driving mode to a manual driving mode during turning of the autonomous vehicle.

Abstract: A control method for monitoring and responding to hacking into a vehicle, which may monitor whether hacking is performed by cross-checking preset check values for each ID with each other in a state where a plurality of controllers mounted in an autonomous vehicle is connected like a blockchain, and response-control the vehicle in a safe state upon determining that a specific controller is hacked as a result of monitoring.

Abstract: A method of emergency braking of a vehicle includes: displaying a brake button in a vehicle; determining pre-touch information on a distance before the brake button is touched by a user; determining post-touch information on a distance after the brake button is touched; and performing any one of a first brake control in which general braking is performed according to the degree of the pressing of the brake button and braking force is added from a first time point after the brake button is pressed, a second brake control in which the general braking is performed and braking force is added from a second time point that is after the first time point, and a third brake control in which the general braking is performed according to the pre-touch information and the post-touch information.

Abstract: Disclosed are a method and apparatus for energy-aware deep neural network compression. A network pruning method for deep neural network compression includes measuring importance scores of a network unit by using an energy-based criterion with respect to a deep learning model, and performing network pruning of the deep learning model based on the importance scores.

Abstract: In a braking control method of responding to sensor failure for autonomous vehicles, when a braking-related sensor, such as a G sensor or a braking hydraulic sensor, has failed while driving of an autonomous vehicle, the host vehicle requests a nearby another autonomous vehicle determine a deceleration of the host vehicle and transmit deceleration information to the host vehicle. The host vehicle accurately determines a braking hydraulic pressure based on the deceleration information received from the aid vehicle and apply the accurate braking hydraulic pressure to a braking device. In the present manner, even in the case in which it is difficult to convert the vehicle to manual driving, the host vehicle is able to drive to a destination or a safe place.

Abstract: A system for controlling an autonomous vehicle is capable of predicting and eliminating a possibility of motion sickness before and during travelling of the autonomous vehicle. The system includes: a first control unit which compares a first vehicle motion sickness index that is determined by a travelling simulation with a first threshold set including passenger information before travelling and controls a boarding location of a passenger before travelling; and a second control unit which computes a passenger motion sickness index from passenger state information and vehicle state information detected during travelling, compares a second threshold indicating the degree of sensitivity to motion sickness according to passenger information during travelling with the passenger motion sickness index, and controls the autonomous vehicle so as to reduce or eliminate a generation of a motion sickness causing frequency.

Abstract: Disclosed is an automatic lightweight method and apparatus for information flow-based neural network compression model that may preserve a performance. An automatic lightweight method for a neural network model may include receiving a first model, generating a second model by injecting trainable bottleneck parameters into the first model, training the bottleneck parameters of the second model using training data, determining an optimal threshold for the trained bottleneck parameters, and pruning the second model based on the trained bottleneck parameters and the determined optimal threshold.

Abstract: A braking control system and method for an autonomous vehicle, may transmit information on surrounding vehicles monitored by autonomous traveling-related sensors of each vehicle while the autonomous vehicles are traveling to the cloud, and transmit a braking induction signal to a specific vehicle when the cloud determines that a distance with a leading vehicle of the specific vehicle has reached a reference distance or less at which braking is required so that the specific vehicle may be braked, checking occurrence of an error or a failure of autonomous traveling-related sensors of a specific vehicle, and easily preventing the safety accidents such as collision with the leading vehicle.

Abstract: A system and method for inducing vehicles to yield right of way determines whether a common vehicle is an emergency vehicle through a cloud, which transmits and receives requests and response signals between vehicles, when the common vehicle transmits a request signal showing that the common vehicle is an emergency vehicle, and informs surrounding vehicles that there is an emergency vehicle in a driving path and simultaneously provides a yielding driving guide signal, which includes a driving direction for yielding driving, a lane change direction of the emergency vehicle, whether to accelerate and decelerate, etc., to the surrounding vehicles so that yielding driving may be easily performed for specific vehicles with an emergency patient other than emergency vehicles such as an ambulance and a fire truck.

Abstract: A method of controlling a vehicle when the vehicle passes over a speed bump, may include: dividing sections of the road into a first section within a first time period before the front wheel of the vehicle collides with the speed bump, a second section while the front wheel collides with the speed bump, a third section within a second time period before the rear wheel collides with the speed bump, and a fourth section while the rear wheel collides with the speed bump; and controlling and distributing at least one of suspension damping force, driving power and braking force to the front wheel and the rear wheel for each of the first section, the second section, the third section and the fourth section to reduce the amount of impact to be applied when the vehicle collides with the speed bump and to reduce a vertical motion of the vehicle that occurs while the vehicle goes over the speed bump.

Abstract: A method of moving an autonomous vehicle to a safe zone after an accident is provided. The method includes: setting a threshold which is a criterion for determining a failure of a chassis system; determining whether a failure occurs by using the threshold; determining a control mode of twin clutches or a braking system; designating avoidance speed level in accordance with whether a following vehicle approaches; and setting a target trajectory to a safe zone and then generating braking torque on left and right wheels or controlling distribution of driving torque through the twin clutches in order to move the autonomous vehicle at the avoidance speed along the target trajectory.

Abstract: A control method for distribution of braking force of an autonomous vehicle may include a vertical load determination step in which a controller is configured to recognize an object existing in an interior of the vehicle and recognizes data of at least one among a position in the vehicle, a size, volume, density, weight, and center of gravity of the corresponding object, and determines a vertical load applied to each wheel of the vehicle according to the recognized data, wherein the controller transmits data of the determined vertical load of each wheel to a brake controller electrically connected to the controller, and the brake controller 40 determines an amount of the distribution of the braking force for each wheel of the vehicle according to the received data of the vertical load and drives a brake actuator electrically connected to the brake controller according to the determined amount of the distribution of the braking force.

Abstract: According to the embodiments of the present invention, the drive feel suitable to given conditions is provided to a driver by generating friction when a steering shaft is rotated to enhance the drive feel of the driver, limiting the maximum steering angle, restoring the steering wheel automatically, and controlling friction on the steering shaft in accordance with the steering angle, vehicle speed and road conditions.

Abstract: According to the embodiments of the present invention, the drive feel suitable to given conditions is provided to a driver by generating friction when a steering shaft is rotated to enhance the drive feel of the driver, limiting the maximum steering angle, restoring the steering wheel automatically, and controlling friction on the steering shaft in accordance with the steering angle, vehicle speed and road conditions.

Abstract: Disclosed are a method and apparatus for energy-aware deep neural network compression. A network pruning method for deep neural network compression includes measuring importance scores of a network unit by using an energy-based criterion with respect to a deep learning model, and performing network pruning of the deep learning model based on the importance scores.