An automated driving system includes an object detection system. A neural network image encoder generates image embeddings associated with an image including an object. A neural network text encoder generates concept embeddings associated with each of a plurality of concepts. Each of the plurality of concepts is associated with one of at least two object classes. A confidence score module generates a confidence score for each of the plurality of concepts based on the image embeddings and the concept embeddings associated with the concept. An object class prediction module generates a predicted object class of the object based on an association between a set of concepts of the plurality of concepts having at least two of the highest values of the generated confidence scores and the one of the at least two object classes associated with a majority of the set of concepts.

A system for determining a type of a road upon which a vehicle is traveling includes a processor and a memory in communication with the processor. The memory has a road type determination module having has instructions that cause the processor to determine, using sensor data having information about at least one of a vehicle and a road upon which the vehicle is traveling, that the vehicle previously traveled on a ramp leading to a limited access highway. The road type determination module also has instructions that cause the processor to determine, using the sensor data, that the road is a limited access highway when the vehicle is traveling at or below a first predetermined speed for a first predetermined amount of time sufficiently immediately after determining that the vehicle was traveling on a ramp, and the vehicle is behind one or more preceding slow-moving vehicles.

Provided is a vehicle headlight device which can improve overlooking of pedestrians by a drive, even under adverse conditions such as nighttime or rain at night. A vehicle headlight device includes: a photoirradiator which irradiates light on a light distribution region outside of a travel roadway in an irradiation pattern in which a bright region and a dark region are alternately repeated; a detector which detects presence of a pedestrian in the light distribution region; and a controller which controls the photoirradiator based on a detection result of the detector. In this embodiment, the detector generates a detection output in which a pedestrian accuracy which is an extent to which a detection target is likely a pedestrian is a second pedestrian accuracy lower than a first pedestrian accuracy which is a degree activating a pedestrian protection brake, and the controller illuminates the photoirradiator in response to the detection output.

The present invention relates to an apparatus and method of controlling a vehicle. The present disclosure relates to a vehicle control apparatus and a control method therefor. Particularly, the vehicle control apparatus according to the present disclosure comprises: an operation performance unit for recognizing a first moving target on the basis of detection information detected by a sensor and performing a collision avoidance control operation; an identity determination unit for, when the first moving target is not recognized, recognizing a second moving target on the basis of the detection information after the first moving target is not recognized and determining whether or not the first moving target and the second moving target are identical to each other; and a control unit for, when the identity between the first moving target and the second moving target is recognized, controlling the vehicle on the basis of the collision avoidance control operation.

A control system of the autonomous vehicle may generate multiple possible behavior control movements based on the driving goal and the assessment of the vehicle environment. In doing so, the method and system selects one of the best behavior control, among the multiple possible movements, and the selection is based on the quantitative grading of its driving behavior.

A vehicular camera includes a lens barrel having a lens, a front camera housing having an aperture therethrough, and an imager printed circuit board (imager PCB) having an imager. The imager PCB is attached at the front camera housing with the imager aligned with the aperture. An attaching portion of the lens barrel is positioned at least partially in the aperture of the front camera housing with a gap between the attaching portion and the front camera housing that circumscribes the attaching portion. With the attaching portion positioned at least partially in the aperture, a filler material is disposed at least partially within the gap. After the lens is aligned relative to the imager, the filler material is heated to melt and flow into the gap, whereby the melted filler material hardens upon cooling to secure the lens barrel relative to the front camera housing and the imager PCB.

A vehicle acquires position information of the obstacle, identifies a collision point that may collide with the obstacle based on the acquired position information of the obstacle, controls one of steering and braking based on the position information of the identified collision point, and when controlling the steering, acquires a collision avoidance margin distance value corresponding to the position information of the identified collision point, predicts the collision position based on the position information of the obstacle and the information detected by the velocity detector, acquires a distance value between the predicted collision position and the current position, acquires a lateral movement distance value based on the acquired distance value and a preset turning radius of the vehicle, acquires a steering angle based on the acquired lateral movement distance value and the acquired collision avoidance margin distance value and controls steering based on the acquired steering angle.

Aspects of the present disclosure describe systems, methods, and devices for automated vehicular control based on glare detected by an optical system of a vehicle. In some aspects, automated control includes controlling the operation of the vehicle itself, a vehicle subsystem, or a vehicle component based on a level of glare detected. According to some examples, controlling the operation of a vehicle includes instructing an automatically or manually operated vehicle to traverse a selected route based on levels of glare detected or expected along potentials routes to a destination. According to other examples, controlling operation of a vehicle subsystem or a vehicle component includes triggering automated responses by the subsystem or the component based on a level of glare detected or expected. In some additional aspects, glare data is shared between individual vehicles and with a remote data processing system for further analysis and action.

This document describes a pedestrian alert system that can draw a driver's attention to a pedestrian on or near a roadway. The described pedestrian alert system can help prevent collisions with pedestrians and other objects in poor visibility environments or when drivers may be distracted. For example, a system can determine a presence of an object in or near a travel path of a host vehicle. The system can also determine the object's position relative to the host vehicle and control a light bar to provide an indication of the object. The indication can have specific characteristics to indicate the object's position relative to the host vehicle. In this way, the described pedestrian alert system can utilize sensors to focus a driver's attention on an object before a potential crash occurs and reduce the number of traffic-related deaths.

Systems and methods for controlling autonomous vehicle are provided. A method can include obtaining, by a computing system, data indicative of a plurality of objects in a surrounding environment of the autonomous vehicle. The method can further include determining, by the computing system, one or more clusters of the objects based at least in part on the data indicative of the plurality of objects. The method can further include determining, by the computing system, whether to enter an operation mode having one or more limited operational capabilities based at least in part on one or more properties of the one or more clusters. In response to determining that the operation mode is to be entered by the autonomous vehicle, the method can include controlling, by the computing system, the operation of the autonomous vehicle based at least in part on the one or more limited operational capabilities.