A method for operating at least one automated vehicle, including the steps: detecting road users by sensors with the aid of the at least one automated vehicle and/or with the aid of sensor systems in an infrastructure; ascertaining predicted traffic routes for the road users with the aid of a computing device based on defined criteria; transmitting control data corresponding to the predicted traffic route to the automated vehicle; and operating the automated vehicle according to the control data.

Disclosed are techniques for wireless communication. In an aspect, a vehicle communications system of a vehicle comprises a vehicle controller with a wireless communications interface capable of providing wireless coverage in a plurality of vehicle regions, and a set of relay devices that are each communicatively coupled to the vehicle controller and are each capable of providing wireless coverage in at least one of the plurality of vehicle regions. In a further aspect, the vehicle controller transitions between first and second modes of communication based in part upon a traffic condition.

Mobile wireless terminals, such as vehicles in traffic, can determine the relative positions of other vehicles with improved precision by arranging to acquire GNSS (global navigational satellite system) signals simultaneously, and then analyzing the various data sets differentially. Simultaneous acquisition can cancel many important errors such as motional errors of the vehicles, atmospheric distortions, and satellite timebase errors. Differential analysis to determine the relative positions of vehicles (as opposed to their overall geographical coordinates) can reduce errors related to satellite ephemeris and velocity, as well as roundoff errors. Localization with a precision of less than 1 meter can greatly improve collision avoidance while discriminating near-miss scenarios from imminent collisions, according to some embodiments. Messaging examples, in 5G and 6G, to manage the simultaneous acquisition and differential analysis, are provided in examples. Many other aspects are disclosed.

System for automatically recognising anomalous situations along roads travelled by motor-vehicles for intelligent motor-vehicle driving speed control along roads.

The motor-vehicles are configured to transmit data allowing anomalous situations to be recognised along roads travelled by the motor-vehicles.

The system comprises data processing resources configured to:

receive and process data transmitted by the motor-vehicles to recognise anomalous situations along the roads travelled by the motor-vehicles based on a recognition algorithm,

when anomalous situations are recognised along roads travelled by the motor-vehicles, generate associated alert events and compute reference driving speeds along the roads recognised to be affected by anomalous situations, and

transmit data representative of the alert events and of the reference driving speeds along the roads recognised to be affected by anomalous situations.

The motor-vehicles are further configured to:

receive data representative of alert events and reference driving speeds, and

use the received data to implement one or both of the following actions: inform the drivers of motor-vehicles, through automotive user interfaces of motor-vehicles of the anomalous situations recognised along roads travelled by motor-vehicles, and cause current driving speeds of the motor-vehicles to be adjusted to the reference driving speeds along roads recognised to be affected by anomalous situations.

The present disclosure provides a method and system for selecting an optimal edge computing node in an Internet of vehicle (IoV) environment. The method includes: acquiring and analyzing properties of computing tasks of a vehicle in the IoV environment; acquiring and analyzing properties of different edge computing nodes; computing matching degrees between the properties of the computing tasks and the properties of the nodes; analyzing computing demands of different tasks, and assigning weights to different types of matching degrees; and selecting a node having an optimal sum for products of the matching degrees and the weights as an optimal edge computing node to compute each of the computing tasks of the vehicle.

A system includes a sensor network comprising at least two optical fibers coupled to a pavement. Each optical fiber includes one or more optical sensors installed a predetermined distance from one or more adjacent optical fibers. The one or more optical sensors are configured to produce a wavelength shift signal. A processor is configured to determine one or both of one or more attributes of one or more objects travelling on the pavement and a traffic condition of the pavement based on the wavelength shift signal. A transmitter is configured to transmit the one or more attributes to a predetermined location.

At least one nearby vehicle may be extracted from a vehicle vicinity image collected by a sensor equipped in the target vehicle. Lane recognition information representing which one position a position of the extracted nearby vehicle corresponds to with respect to the target vehicle, and/or vehicle position information representing a relative distance from the target vehicle to the nearby vehicle may be identified. An attention degree of the nearby vehicle may be calculated based on a speed of the nearby vehicle calculated from the relative distance and a vehicle speed of the target vehicle, the vehicle position information of the nearby vehicle, the relative distance of the nearby vehicle, the speed of the target vehicle, or any combination thereof. An alarm for the nearby vehicle may be displayed on a screen according to the calculated attention.

An approach is provided for accessing traffic impact caused by individual driving behaviors. For example, the approach involves receiving, by one or more processors, sensor data collected from one or more sensors of a vehicle traveling on a road network. The approach also involves processing, by the processors, the sensor data to determine one or more driving behaviors associated with the vehicle. The approach further involves computing, by the processors, a traffic impact index based on the one or more driving behaviors and at least one contextual parameter associated with the vehicle, the road network, a driver of the vehicle, or a combination thereof. The traffic impact index represents an estimated impact of the vehicle on a traffic flow within at least a portion of the road network. The approach further involves providing, by the processors, the traffic impact index as an output.

Disclosed are a method, device, and system to control stopping of a mobility device. In particular, the method includes: receiving a stop change request of a route mobility device from a user device; determining whether the stop change request satisfies a change condition; determining a change stop of the route mobility device based on the stop change request when the change condition is satisfied; and transmitting a change stop message to the route mobility device and at least one of the user device or a mobility device used by a user.

A method for visualizing and analyzing contributions of various input features for traffic safety status prediction is provided. The method includes initializing a deep belief network (DBN) with input features; performing unsupervised learning/training by observing changes of weights of the input features during the unsupervised learning/training; when the unsupervised learning/training process is complete, performing supervised learning/training process by generating a reconstructed input layer based on results of each hidden layer; and continually running the supervised learning/training and generating a weight diagram based on both visualization and numerical analysis that calculates contributions of the input features. The input features may include one or more of annual average daily commercial traffic (AADCT), median width, left shoulder width, right shoulder width, curve deflection, and exposure for traffic safety status prediction.