The described aspects and implementations enable vehicle light classification in autonomous vehicle (AV) applications. In one implementation, disclosed is a method and a system to perform the method that includes, obtaining, by a processing device, first image data characterizing a driving environment of an autonomous vehicle (AV). The processing device may identify, based on the image data, a vehicle within the driving environment. The processing device may process the image data using one or more trained machine-learning models (MLMs) to determine a state of one or more lights of the vehicle and cause an update to a driving path of the AV based on the determined state of the lights.

An abnormality notification system includes: a vehicle that travels regularly on a predetermined travel route; a communication device configured to be able to communicate with a sensor mounted on the vehicle and an outside, the sensor being a sensor that acquires road data obtained by imaging or measuring a road along the travel route; and a control device. The control device is configured to determine whether an abnormality has occurred on the road along the travel route based on a different part when the road data acquired by the sensor is compared with reference road data obtained by imaging or measuring the road along the travel route in the past, and transmit predetermined abnormality occurrence information to an external client via the communication device when the control device determines that an abnormality has occurred on the road along the travel route.

An autonomous vehicle includes audio sensors configured to detect audio in an environment around the autonomous vehicle and to generate audio signals based on the detected audio. A processor in the autonomous vehicle receives the audio signals and compares a time domain or frequency domain representation of the audio signals to a corresponding representation of a known emergency vehicle siren. The comparison causes the processor to output a first determination indicating whether the audio signals are indicative of an emergency vehicle siren. The processor also applies a trained neural network to the audio signals that causes the processor to output a second determination indicating whether the audio signals are indicative of the emergency vehicle siren. If the first determination or the second determination indicates presence of an emergency vehicle siren in the environment around the autonomous vehicle, the autonomous vehicle is caused to perform an action.

A vehicular parking system includes vehicle-to-vehicle (V2V) communication system disposed at a first vehicle. The vehicular parking system, as the first vehicle navigates a parking facility in search of an available parking space, receives a parking space availability communication via the V2V communication system. The parking space availability communication originates from a second vehicle that is also navigating the parking facility. The parking space availability communication indicates multiple available parking spaces within the parking facility and the multiple available parking spaces are determined by the second vehicle as the second vehicle navigates the parking facility and passes available parking spaces. The vehicular parking system, responsive to receiving the parking space availability communication, reserves one of the multiple available parking spaces of the parking space availability communication for the first vehicle.

A system comprises a computer having a processor and a memory, the memory storing instructions executable by the processor to determine, as a vehicle travels along a roadway while an adaptive cruise control feature of the vehicle is active, that the roadway is a non-controlled-access roadway, detect a presence of traffic congestion impeding travel of the vehicle along the non-controlled-access roadway, responsive to detecting the presence of the traffic congestion, generate a prompt for driver input indicating whether the adaptive cruise control feature is to enter an extended auto-resume (XAR) mode, and cause the adaptive cruise control feature to enter the XAR mode based on driver input indicating that the adaptive cruise control feature is to enter the XAR mode.

A driving assistance apparatus assists a driver of a vehicle by performing a deceleration control to decelerate the vehicle when the vehicle makes a right turn or a left turn at an intersection. The driving assistance apparatus is configured to make a magnitude of a deceleration of a vehicle while performing a deceleration control of when a left-or-right-turn-condition is not satisfied smaller than a magnitude of a deceleration of the vehicle while performing the deceleration control of when the left-or-right-turn-condition is satisfied, in a case where a distance between the vehicle and the intersection is equal to or shorter than a distance threshold and the vehicle is predicted to change a moving direction to a particular direction, the left-or-right-turn-condition being a condition that is satisfied when the vehicle is permitted to change the moving direction to the particular direction in/from a traveling lane in which the vehicle is running.

A rearwardly directed movement of a first vehicle that has a driving assistance system that can be controlled, the driving assistance system having at least one sensor and a control device, in which threshold values for triggering a warning intervention and/or braking intervention in respect of the interval in relation to at least one further road user are set, and additionally being connected to or having a camera, by which activated travel-direction indicators of a further road user are recognized, which travel-direction indicators are included in the calculation of a probable trajectory of the further road user, and a probability of a collision is calculated, according to which the threshold values are lowered or raised.

A method, apparatus and computer program product are provided for automatically identify wrong-way driven vehicles in real-time on a roadway. Methods may include: receiving an image from at least one image sensor captured at a location; processing the image using a computer vision model to detect features within the image; identifying, using the computer vision model, a wrong-way driven vehicle in the image; incrementing a confidence value for detection of the wrong-way driven vehicle; and generating an alert indicating the presence of the wrong-way driven vehicle at the location in response to the confidence value satisfying a predetermined value.

A vehicular forward viewing image capture system includes an accessory module configured for attachment at an in-cabin side of a windshield of a vehicle, whereby a CMOS image sensor views through the windshield forward of the vehicle. With the accessory module attached at the in-cabin side of the windshield, and while the vehicle is traveling along a road, captured image data is processed to determine movement of an object of interest viewed by the image sensor. Multiple frames of captured image data are processed in determining movement of the object of interest. The accessory module includes an electrical connector for electrically connecting to a vehicle wiring system of the vehicle. Image data captured by the image sensor may be processed for an automatic headlamp control system of the equipped vehicle. The vehicular forward viewing image capture system may compensate for misalignment of the image sensor.

The present disclosure relates to a vehicle control apparatus disposed in a vehicle and a control method of the vehicle. A vehicle control apparatus according to one embodiment of the present disclosure is a vehicle control apparatus disposed in a vehicle, and comprises: a camera for capturing an image of an object which approaches the vehicle; a seat driving unit for driving a seat disposed in the vehicle; and a processor for sensing information related to the object on the basis of the image captured through the camera and controlling the seat driving unit such that the seat is disposed at a predetermined position, on the basis of the sensed information related to the object.