A system comprises a computer having a processor and a memory, the memory storing instructions executable by the processor to obtain, while an adaptive cruise control feature of a vehicle traveling a roadway is set to operate in a standard operation mode, lighting condition data for an on-board camera of the vehicle, determine, based on the lighting condition data, whether the on-board camera is subject to a lighting-compromised condition, and responsive to a determination that the on-board camera is subject to the lighting-compromised condition, cause the adaptive cruise control feature to operate in a modified operation mode, wherein during operation in the modified operation mode, the adaptive cruise control feature operates in accordance with one or more modified operating parameters.

Described herein are methods of estimating a chance of precipitation in an area that include identifying one or more vehicles in the area and determining the likelihood of precipitation using telematics data for the one or more vehicles in the area. Also described herein are methods that include receiving telematics data from a plurality of vehicles, wherein the telematics data is associated with a location, analyzing the telematics data to identify vehicle events associated with one or more segments of road, analyzing weather information associated with the one or more segments of road, and determining a correlation between the weather information and the vehicle events.

Described herein are methods of estimating a chance of precipitation in an area that include identifying one or more vehicles in the area and determining the likelihood of precipitation using telematics data for the one or more vehicles in the area. Also described herein are methods that include receiving telematics data from a plurality of vehicles, wherein the telematics data is associated with a location, analyzing the telematics data to identify vehicle events associated with one or more segments of road, analyzing weather information associated with the one or more segments of road, and determining a correlation between the weather information and the vehicle events.

Aspects of the disclosure provide for arranging trips for autonomous vehicles. For instance, a request for a trip may be received by one or more processors of one or more server computing devices. The request may identify an initial location. A weather condition at the initial location may be identified. One or more internal vehicle state conditions and one or more priorities for pulling over may be determined based on the weather condition. A second location may be determined based on the one or more priorities and the initial location. Dispatch instructions may be provided to an autonomous vehicle, the dispatch instructions identifying the second location and the one or more internal vehicle state conditions in order to cause computing devices of the autonomous vehicle to control the autonomous vehicle to the second location and adjust internal vehicle state conditions based on the one or more internal vehicle state conditions.

Provided herein is a method for assisting a driver with driving a motor vehicle. The method includes ascertaining a permissible driving speed in a route section by evaluating environmental data describing the motor vehicle environment. The method further includes calculating a target maximum speed, which is lower than the permissible driving speed, by subtracting a predefined reduction amount from the permissible driving speed and/or by multiplying the permissible driving speed by a predefined scaling factor. The method further includes controlling at least one alert device for outputting an alert to the driver when a present driving speed of the motor vehicle exceeds the target maximum speed and/or controlling the driving speed of the motor vehicle by a longitudinally guiding driver assistance system, wherein the target maximum speed is used as a maximum speed or as a target speed.

A method for the automatic control of the longitudinal dynamics of a vehicle is provided by which vehicles traveling ahead are detected. If an upcoming traffic jam is detected, the vehicle is decelerated until a predefined distance behind the tail end of the traffic jam is reached. When the predefined distance from the traffic jam tail end has been reached, the vehicle automatically controlled in its longitudinal dynamics is able to close the remaining, predefined distance to the traffic jam tail end at a low differential velocity in comparison to the velocity of the traffic jam tail end. Using an additional rear sensor system that senses trailing vehicles, the controlled vehicle is made to close the distance to the traffic jam tail end only if a trailing vehicle was detected.

An information transmission device applied to an open moving machine driven by a driver who is exposed to an outside of the moving machine includes: a vibrator configured to vibrate a component of the moving machine, the driver in a driving posture being in contact with the component; and a controller communicably connected to an information providing device and configured to control the vibrator and a voice output device configured to output voice to the driver, the information providing device being configured to provide utterance information to the driver as information to be transmitted to the driver. The controller makes the vibrator operate when making the voice output device output the utterance information to the driver by the voice.

Systems and methods for obstacle detection are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having obstacles. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

A host vehicle including a plurality of sensors communicably coupled to the host vehicle. Additionally, the host vehicle includes processing circuitry configured to map-match a location of the host vehicle while the host vehicle is operating on a highway, receive obstruction information from the plurality of sensors, the plurality of sensors having a predetermined field of view corresponding to a host vehicle field of view, estimate a driver field of view based on the host vehicle field of view, determine whether a speed of the host vehicle is safe based on the driver field of view and the obstruction information, and modify driver operation in response to a determination that the speed of the host vehicle is not safe based on the driver field of view.

The present disclosure provides a method for identifying a confidence level of an autonomous driving system in an autonomous driving vehicle. The method includes determining hardware currently used by the autonomous driving system to realize required functions and environmental factors which affect the hardware capability of the hardware, and establishing a relationship between the hardware capability and the environmental factors; based on environmental factors on a future specific road section acquired in real time, calculating a degree to which the hardware capability will be affected on the specific road section; in consideration of acquired the environmental factors, judging an influence of the affected hardware capability on the realization of required functions of the autonomous driving system based on the acquired the environmental factors; and reflecting the influence on the realization of required functions of the autonomous driving system as a confidence level, and prompting the confidence level to a driver.