A driver assistance system of a vehicle can adjust a warning time-point for a hands-off detector configured to detect that a hand of a driver is off of a steering wheel. To this end, the driver assistance system can include an image acquisition device configured to acquire image data of an area outside of the vehicle, a sensor configured to acquire behavior data of the vehicle, a hands-off detector configured to detect that a hand of the driver is off of the steering wheel, and a controller. The controller is configured to determine a driving situation of the vehicle based on the image data and behavior data, and to determine a warning time-point for the hands-off detector based on the driving situation. The controller can further control a warning device to output a warning message for the hands-off at the determined warning time-point.

In a vehicle control system (1, 101), a control unit (15) is configured to execute a stop process by which the vehicle is parked in a prescribed stop position located within a permitted distance when it is detected that the control unit or the driver has become incapable of properly maintaining a traveling state of the vehicle, and, in executing the stop process, the control unit computes an agreement between an object (X) contained in the map information based on an estimated position of the vehicle and an object (Y) on the road detected by an external environment recognition device (6), the permitted distance being smaller when the agreement is below a prescribed agreement threshold than when the agreement is equal to or above the agreement threshold.

The present disclosure provides a vehicle control apparatus and a vehicle control method comprising a radar for receiving radar signals transmitted from outside the vehicle and reflected from objects around the vehicle and processing the received radar signals to obtain detection data for the objects, and a controller for determining a stationary object among the objects based on the detection data, extracting feature points, determining whether the stationary object is a guardrail based on the extracted feature points, and determining a false target among the objects based on the guardrail. According to the present disclosure, it is possible to prevent the unrecognition or misrecognition of the control targets due to the guardrail.

An autonomous vehicle is described, wherein the autonomous vehicle is configured to estimate a change in direction of a vehicle that is on a roadway and is proximate to the autonomous vehicle. The autonomous vehicle has a mechanical system, one or more sensors that generate one or more sensor signals, and a computing system in communication with the mechanical system and the one or more sensors. The autonomous vehicle is configured to detect an imminent lane change by another vehicle based on at least one of a computed angle between a wheel of the other vehicle and a longitudinal direction of travel of the other vehicle, a degree of misalignment between the wheel of the other vehicle and a body of the other vehicle, and/or an eccentricity of the wheel of the other vehicle. The mechanical system of the autonomous vehicle is controlled by the computing system based upon the detected imminent lane change.

A system for reconstructing a vehicular crash (i) receives sensor data of a vehicular crash from at least one mobile device associated with a user; (ii) generates a scenario model of the vehicular crash based upon the received sensor data; (iii) transmits the scenario model to a user computer device associated with the user; (iv) receives a confirmation of the scenario model from the user computer device; (v) stores the scenario model; and (vi) may generate at least one insurance claim form based upon the scenario model. As a result, the speed and accuracy of the claim processing is increased. The system may also utilize vehicle occupant positional data, and internal and external sensor data to detect potential imminent vehicle collisions, take corrective actions, automatically engage autonomous or semi-autonomous vehicle features, and/or generate virtual reconstructions of the vehicle collision.

A driver assistance system of a vehicle can adjust a warning time-point for a hands-off detector configured to detect that a hand of a driver is off of a steering wheel. To this end, the driver assistance system can include an image acquisition device configured to acquire image data of an area outside of the vehicle, a sensor configured to acquire behavior data of the vehicle, a hands-off detector configured to detect that a hand of the driver is off of the steering wheel, and a controller. The controller is configured to determine a driving situation of the vehicle based on the image data and behavior data, and to determine a warning time-point for the hands-off detector based on the driving situation. The controller can further control a warning device to output a warning message for the hands-off at the determined warning time-point.

Provided is a method and apparatus for operating an autonomous driving controller, the method including generating route information for the vehicle based on a rule, transitioning from an autonomous driving mode to an autonomous driving disable mode, in response to the driving route information not being generated for an amount of time greater than or equal to a threshold, tracking at least one neighboring vehicle based on data sensed by a sensor, and generating temporary driving route information based on a movement of the at least one neighboring vehicle.

Example embodiments relate to techniques for adjusting vehicle behavior based on ambient ground relative wind estimations. An onboard computing system may receive wind data from one or multiple wind sensors positioned onboard a vehicle. The wind data can indicate a direction and a speed of wind propagating in the vehicle's environment. The computing system can also receive navigation data that represents a direction and a speed of the vehicle and then estimate an ambient ground relative wind speed based on the navigation data and the wind data. The computing system can adjust the behavior of the vehicle based on the ambient ground relative wind speed. For instance, the computing system may compare the speed of the ambient ground relative wind to a predefined behavior threshold curve and adjust the behavior of the vehicle based on the comparison.

A method of representation learning for object detection from unlabeled point cloud sequences is described. The method includes detecting moving object traces from temporally-ordered, unlabeled point cloud sequences. The method also includes extracting a set of moving objects based on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method further includes classifying the set of moving objects extracted from on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method also includes estimating 3D bounding boxes for the set of moving objects based on the classifying of the set of moving objects.

The subject technology is related to autonomous vehicles (AV) and, in particular, to calibrating multiple sensors of an AV in an undefined training area. An example method includes instructing the AV to pilot itself in an undefined training area subject to at least one constraint, wherein the AV is instructed to pilot itself along a path until the AV has overlapped at least a portion of the path, and at a location at which the AV has overlapped at least the portion of the path, determining that first returns from a previous LIDAR scan overlaps with second returns from a subsequent LIDAR scan taken when the AV has overlapped at least the portion of the path. Initially, the AV does not include a location reference to identify locations of objects in the undefined training area and a plurality of sensors of the AV are uncalibrated with respect to each other.