A vehicle control apparatus includes a recognition unit configured to recognize a surrounding situation of a host vehicle, a driving control unit configured to control at least one of acceleration and deceleration and steering of the host vehicle based on a recognition result of the recognition unit and to perform driving control of the host vehicle, and a driving request unit configured to execute a driving change request or a driving operation request based on the surrounding situation during execution of the driving control. The driving request unit is configured to output a first request and a second request different from the first request. The driving request unit comprises a first mode in which the first request is output, and the second request is output when the first request is not satisfied, and a second mode in which the second request is output without outputting the first request.

A vehicle arithmetic system includes a single information processing circuitry. performs control of vehicle external environment estimation circuitry configured to receive outputs from sensors that obtain information of a vehicle external environment, and estimate the vehicle external environment including a road and an obstacle; a route generation circuitry configured to generate a traveling route of the vehicle which avoids the obstacle estimated on the road estimated, based on an output from the vehicle external environment estimation unit; and a target motion determination circuitry configured to determine a target motion of the vehicle so that the vehicle travels along the traveling route generated by the route generation circuitry.

Techniques for generating trajectories and drivable areas for navigating a vehicle in an environment are discussed herein. The techniques can include receiving a reference trajectory representing an initial trajectory for a vehicle, such as an autonomous vehicle, to traverse the environment. Portions of the reference trajectory can be identified as corresponding to actions to navigate around a double-parked vehicle or to change lanes, for example. In some cases, a portion of the reference trajectory can be identified based on a proximity to an object in the environment. A weight can be associated with the portions of the reference trajectory, and the techniques can include evaluating a reference cost function at points of the reference trajectory based on the associated weights to generate a target trajectory. Further, the techniques can include controlling the autonomous vehicle to traverse the environment based at least in part on the target trajectory.

A system for avoiding blind spot using accident history information, includes an image sensor configured to provide image information by acquiring a surrounding image of a host vehicle, and a vehicle controller. The vehicle controller is configured to detect, through the image sensor, an adjacent vehicle traveling adjacent to the host vehicle and a license plate of the adjacent vehicle; determine a dangerous level of the blind spot of the adjacent vehicle, based on accident history information of the adjacent vehicle and driver tendency information of a driver of the adjacent vehicle obtained by inquiring about the license plate of the adjacent vehicle, after determining a blind spot range of the adjacent vehicle; and generate a path in which the host vehicle deviates from the blind spot or avoids the blind spot to reduce the dangerous level of the blind spot, based on a traveling situation of the host vehicle.

The present disclosure provides a collision avoidance apparatus including: a first detector configured to detect another vehicle information including a longitudinal velocity and a lateral velocity of another vehicle, and distance information including a longitudinal distance and a lateral distance from another vehicle; a second detector configured to detect subject vehicle information including a velocity and a yaw rate of the subject vehicle; a calculator configured to determine whether steering avoidance is executable, on the basis of the another vehicle information, the subject vehicle information, and the distance information, and when steering avoidance is executable, calculate steering avoidance information on steering avoidance of the subject vehicle; and a control unit configured to control the subject vehicle to travel according to the steering avoidance information. Therefore, it is possible to prevent execution of steering avoidance in a case where steering avoidance is not needed or is inexecutable, and safer steering avoidance can be performed.

A vehicle control device, which reduces intervention in automatic parking by a driver, includes a processor and a memory, that control the vehicle to a target parking position. The vehicle control device includes an obstacle detection unit detecting a position of an obstacle around the vehicle, a travelable region setting unit that determines a region where the vehicle may travel based on the position of the obstacle, and sets the target parking position within the travelable region, a route generation unit that calculates a travel route to the target parking position within the travelable region, and an automatic parking execution unit that causes the vehicle to automatically travel toward the target parking position. When a driver intervenes during the automatic traveling, the route generation unit stores vehicle state information at the time of the intervention, and resets the travelable region based on the driver operation intervention information.

A processor-implemented method of performing an operation using a complex-valued attention network includes: extracting a complex-valued attention weight from complex-valued input data; and determining complex-valued attention data by applying the extracted complex-valued attention weight to the complex-valued input data.

Techniques to generate driving scenarios for autonomous vehicles characterize a path in a driving scenario according to metrics such as narrowness and effort. Nodes of the path are assigned a time for action to avoid collision from the node. The generated scenarios may be simulated in a computer.

A trajectory for a vehicle can be generated using a lateral offset bias. The vehicle, such as an autonomous vehicle (AV), may be directed to follow reference trajectory for through an environment. The AV may determine a segment associated with the reference trajectory based on curvatures of the reference trajectory, determine a lateral offset bias associated with the segment based at least in part on, for example, one or more of a speed or acceleration of the vehicle, and determine a candidate trajectory for the autonomous vehicle based at least in part on the lateral offset bias. The candidate trajectory may then be used to control the autonomous vehicle.

A vehicle control method for controlling a vehicle includes: (A) detecting a rainfall condition or a non-rainfall condition using a first sensor mounted on the vehicle; (B) determining whether the vehicle is passing under an upper structure covering the vehicle using a second sensor mounted on the vehicle; (C) determining that the rainfall condition is continuing even when a transition from the rainfall condition to the non-rainfall condition is detected in a case where the vehicle passes under the upper structure; and (D) controlling the vehicle based on whether a weather condition is the rainfall condition or the non-rainfall condition.