The programming of traffic lights systems (TLS) in cities is a complex optimization problem. The main problem of the actual process is that this is a long, expensive and imprecise process that must be repeated regularly to reflect changes in traffic flow. The invention consists of using Vehicular's ad hoc networks (VANET) to collect traffic data in real time and transmit them to a traffic management system. VANET is currently defined by the IEEE 802.11p standard. We propose to use VANET in correlation with others techniques to control TLS. This invention will permit to program actual TLS more efficiently, manage a network in real-time and it will be possible to be used for urban planning studies, transport planning or to simulate the exit of special events (sporting, cultural, parades, etc.). It also allows programming TLS in real time with any efficient algorithm that exists or to be developed.

The programming of traffic lights systems (TLS) in cities is a complex optimization problem. The main problem of the actual process is that this is a long, expensive and imprecise process that must be repeated regularly to reflect changes in traffic flow. The invention consists of using Vehicular's ad hoc networks (VANET) to collect traffic data in real time and transmit them to a traffic management system. VANET is currently defined by the IEEE 802.11p standard. We propose to use VANET in correlation with others techniques to control TLS. This invention will permit to program actual TLS more efficiently, manage a network in real-time and it will be possible to be used for urban planning studies, transport planning or to simulate the exit of special events (sporting, cultural, parades, etc.). It also allows programming TLS in real time with any efficient algorithm that exists or to be developed.

The present disclosure provides a method for managing traffic congestion in a smart city. The method includes predicting, based on a trained traffic state prediction model, one or more target areas where the traffic congestion is likely to occur from the preset area during a next time period by processing the traffic data information during the current time period, the traffic state prediction model being a Graph Neural Network (GNN) model and a predicted result being output by at least one node of a traffic state prediction model; determining whether a traffic scheduling strategy is needed to be switched based on traffic data information in the one or more target areas during the next time period; and in response to determining that the traffic scheduling strategy is needed to be switched, switching a first traffic scheduling strategy to a second traffic scheduling strategy.

A traffic management system for controlling traffic flow in an area is provided. The system has sensors (10) positioned at respective junctions (2) in the area, forming a network of nodes (2). Software (25) processes the sensor signals to derive vehicle signatures indicative of a particular vehicle detected at the node at a particular time. This is used to track the progress of vehicles traveling across the network and derive vehicle statistics (60) as to traffic volumes (64), routes (66) and journey times (62) at various times. Artificial intelligence (AI) (80) trained on historical vehicle statistics arranged to predict traffic arriving at plural junctions at a future time based on receiving a current count of vehicles sensed at nodes in the network. Based on the prediction, a control plan for traffic lights (3) is determined to optimise traffic flow.

A traffic management system for controlling traffic flow in an area is provided. The system has sensors (10) positioned at respective junctions (2) in the area, forming a network of nodes (2). Software (25) processes the sensor signals to derive vehicle signatures indicative of a particular vehicle detected at the node at a particular time. This is used to track the progress of vehicles traveling across the network and derive vehicle statistics (60) as to traffic volumes (64), routes (66) and journey times (62) at various times. Artificial intelligence (AI) (80) trained on historical vehicle statistics arranged to predict traffic arriving at plural junctions at a future time based on receiving a current count of vehicles sensed at nodes in the network. Based on the prediction, a control plan for traffic lights (3) is determined to optimise traffic flow.

An approach is provided for providing data-driven traffic simulations for ad-hoc reconfigurations of a smart-city infrastructure. The approach involves retrieving training traffic data collected from a geographic area supported by the smart-city infrastructure. The approach also involves determining one or more configurations of the smart-city infrastructure corresponding to one or more times at which the training traffic data was collected, wherein the one or more configurations indicate respective states of one or more traffic-related actions supported by the smart-city infrastructure. The approach further involves training a predictive model to predict a traffic-related key performance indicator based on the training traffic data and the one or more configurations, wherein the predictive model is used to predict the traffic-related key performance indicator for a reconfiguration of at least one of the one or more traffic-related actions.

An approach is provided for providing data-driven traffic simulations for ad-hoc reconfigurations of a smart-city infrastructure. The approach involves retrieving training traffic data collected from a geographic area supported by the smart-city infrastructure. The approach also involves determining one or more configurations of the smart-city infrastructure corresponding to one or more times at which the training traffic data was collected, wherein the one or more configurations indicate respective states of one or more traffic-related actions supported by the smart-city infrastructure. The approach further involves training a predictive model to predict a traffic-related key performance indicator based on the training traffic data and the one or more configurations, wherein the predictive model is used to predict the traffic-related key performance indicator for a reconfiguration of at least one of the one or more traffic-related actions.

A message transmission method for a roadside equipment includes the following steps. A plurality of external sensor information is received. A road intersection sign phase information and a road map information are inputted. An object position analysis, a speed analysis, and an sign analysis in object moving direction are performed based on the external sensor information, the road intersection sign phase information, and the road map information, and a classification of dangerous objects in different groups is outputted. According to a current transmission bandwidth limitation and the classification of the dangerous objects, a dangerous object message with a higher classification of the dangerous objects is preferentially selected and transmitted within available transmission bandwidth.

A message transmission method for a roadside equipment includes the following steps. A plurality of external sensor information is received. A road intersection sign phase information and a road map information are inputted. An object position analysis, a speed analysis, and an sign analysis in object moving direction are performed based on the external sensor information, the road intersection sign phase information, and the road map information, and a classification of dangerous objects in different groups is outputted. According to a current transmission bandwidth limitation and the classification of the dangerous objects, a dangerous object message with a higher classification of the dangerous objects is preferentially selected and transmitted within available transmission bandwidth.

A controlled intersection employs video analytics to identify incoming vehicles coupled with autonomous driving capabilities in the vehicle to selectively provide intervention for collision avoidance. A camera image of an approaching vehicle is used to identify a range and speed, and to compute whether intervention is appropriate based on a detected distance and speed from the intersection. A vehicle approaching a stop signal (e.g. “red light”) at an unsafe rate of speed triggers an invocation of on-board autonomous systems in the vehicle that provide appropriate warnings and ultimately, forced braking if warnings go unheeded. A registration system maintains a local grouping of vehicles in proximity to an intersection for minimizing latency in vehicle identification for commencing intervention. In this manner, on-board vehicle collision avoidance systems collaborate with complementary traffic control logic at a controlled intersection for preventing inadvertent or intentional disregard of a red signal.