Intelligent networked automobile system

Abstract

The invention provides an intelligent networked automobile system. The system comprises an information acquisition module, an information processing module and a control module, wherein the information acquisition module is used for acquiring driving information and environment information of a vehicle; the path planning module is used for constructing a traffic prediction model, predicting traffic jam conditions of all driving routes in future time periods and planning an optimal driving path for the vehicle; the intelligent early warning module is used for predicting driving intentions of other surrounding vehicles and early warning a driver in advance based on the predicted driving intentions; the traffic risk prediction module is used for predicting the traffic accident risk probability of the optimal driving path planned by the path planning module in the future time period; and the man-machine interaction module is used for displaying the vehicle driving information, the environment information, the optimal driving path and the predicted traffic information, early warning information and traffic risk prediction information of the optimal driving path. The traffic safety and the passing efficiency are effectively improved, and the occurrence rate of traffic accidents is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent connected vehicles, and in particular to an intelligent connected vehicle system. Background Art

[0002] With the rapid development of the automotive industry and the continuous advancement of intelligent transportation technology, intelligent connected vehicles have gradually become an important development direction of the automotive industry. However, the existing intelligent connected vehicle systems have many shortcomings, such as incomplete information collection, and the inability to effectively integrate the vehicle's own status information, surrounding environment information, and traffic network information to predict future traffic congestion on the vehicle's driving path, the driving intentions of surrounding vehicles, and traffic risks on the driving section. Its decision-making and control are not intelligent enough, and it is difficult to make the best decision in complex traffic scenarios, which requires further optimization. Summary of the Invention

[0003] In view of this, an object of the present invention is to provide an intelligent connected vehicle system that solves or at least partially solves the above-mentioned problems existing in the prior art.

[0004] To achieve the above objectives, the present invention provides an intelligent connected vehicle system, comprising: Information collection module: used to collect vehicle driving information and environmental information. The vehicle driving information includes vehicle speed and vehicle turning speed. The environmental information includes road signs, information about other vehicles and pedestrians around the vehicle, and their relative speed and distance to the vehicle. Route planning module: This module is used to obtain dynamic data on the vehicle's current location and destination, combined with real-time traffic information and weather conditions, to build a traffic prediction model. The model is used to obtain all driving routes from the vehicle's current location to the destination, predict traffic congestion conditions for all driving routes in the future, and plan the optimal driving route for the vehicle based on the prediction results. Intelligent warning module: This module analyzes the information collected by the information collection module to obtain the speed of other vehicles around the vehicle and the distance between other vehicles around the vehicle and the road traffic markings. It combines this information with the speed of other vehicles around the vehicle to predict the driving intentions of other vehicles around the vehicle and provides early warning to the driver based on the predicted driving intentions. Traffic risk prediction module: used to predict the probability of traffic accident risks in the future period of the optimal driving route planned by the route planning module; Human-computer interaction module: used to display vehicle driving information, environmental information, optimal driving path and its predicted traffic information, warning information, traffic risk prediction information to the driver based on the information collection module, path planning module, intelligent warning module and traffic risk prediction module, and receive the driver's voice input commands.

[0005] Furthermore, the information collection module includes: The information acquisition module is used to obtain the vehicle's driving speed and steering speed by installing a vehicle speed sensor, an acceleration sensor, and a steering wheel angle sensor on the vehicle; The information collection module is used to set up multiple cameras, millimeter-wave radars and laser radars on the vehicle. The multiple cameras are distributed in the front, back, left and right of the vehicle to collect road signs, surrounding vehicles and pedestrian information around the vehicle. The millimeter-wave radars and laser radars are used to detect the distance and relative speed to surrounding vehicles and pedestrians.

[0006] Furthermore, the path planning module specifically includes the following steps: S21, obtaining the current location of the vehicle and the destination of this vehicle, as well as dynamic data of traffic information and weather conditions for the current time period; S22. Build a traffic prediction model, obtain all routes from the current location of the vehicle to the current destination, obtain historical traffic data and historical weather data for all routes, analyze the number of traffic jams in the historical traffic data for different routes, and the time characteristics corresponding to the number of traffic jams, and convert the data and the historical weather data into high-dimensional data, and use the high-dimensional data to train the traffic prediction model; S23. A dynamic graph convolution recursive unit and a traffic weight unit are respectively provided in the traffic prediction model. The dynamic graph convolution recursive module simulates the traffic conditions of the driving route based on the high-dimensional data. The traffic weight unit is used to generate a traffic weight value based on the traffic information of the current time period in combination with the high-dimensional data. The influence of historical traffic data and historical weather data on the prediction of the future time period is adjusted according to the traffic weight value. S24. Based on the degree of influence in step S23, the dynamic data of traffic information and weather conditions in the current period in step S21 is input into the traffic prediction model, and the high-dimensional data corresponding to the conditions is matched by the traffic prediction model, and the matched high-dimensional data is divided into a non-hidden time series and a hidden time series; S25. Introducing a gated recurrent unit and an attention mechanism into the traffic prediction model to track the traffic dynamics of hidden time series according to their temporal characteristics, and introducing a dynamic spatiotemporal graph convolutional network layer into the traffic prediction model to extract the spatiotemporal dependencies between non-hidden time series; S26. Combine the processing results of the non-hidden time series and the hidden time series with the dynamic data of traffic information and weather conditions in the current period to predict traffic congestion conditions on all routes to the destination of this vehicle, and plan the optimal driving route for this vehicle based on the prediction results.

[0007] Furthermore, the intelligent early warning module specifically includes the following steps: S31. Analyze the driving information and environmental information collected by the information collection module to obtain the distances and positions of other vehicles around the vehicle and the vehicle itself, and determine the dynamic driving speeds of the surrounding vehicles based on the distances and positions of the other vehicles around the vehicle and their relative speeds to the vehicle itself, where the dynamic driving speeds of the surrounding vehicles include the lateral speed and acceleration, and the longitudinal speed and acceleration of the vehicles; S32. Obtain the distances between other vehicles around the vehicle and the road traffic markings, as well as the relative speeds and distances of other vehicles to the vehicles around them. Combine these with the distances between other vehicles around the vehicle and the road traffic markings and their dynamic driving speeds to predict the driving intentions of other vehicles around the vehicle, as expressed as follows:

[0008] in, is the driving intention of the predicted vehicle, is the predicted vehicle lateral velocity, is the predicted vehicle longitudinal velocity, is the predicted vehicle lateral acceleration, is the predicted vehicle longitudinal acceleration, is the distance between the predicted vehicle and the road traffic markings, is the relative speed and distance between the predicted vehicle and surrounding vehicles.

[0009] Furthermore, the traffic risk prediction module specifically includes the following steps: S41. Obtaining a road environment of the optimal driving path based on the optimal driving path obtained by the path planning module, wherein the road environment includes blind spots, intersections, and other driving intersections on the optimal driving path; S42, based on the road section environment of the optimal driving path, obtaining traffic accident information of the road section environment of the optimal driving path in a previous time period; S43. Real-time traffic information of the optimal driving route is obtained, and the information is combined with the road environment of the optimal driving route and traffic accident information of the road environment in previous time periods to predict the traffic accident risk probability of the optimal driving route in the future time period, which is expressed as follows:

[0010] in, For The traffic accident risk probability of the optimal driving path during this period, Calculate the probability of traffic accident risk. For Whether there are any traffic participants who may pose a risk on the optimal driving route during this period, For Whether there are any traffic participants on the optimal driving path during this time period.

[0011] Furthermore, the human-computer interaction module includes: The human-computer interaction module displays the optimal driving route and its predicted traffic information, warning information, and traffic risk prediction information to the driver through a head-up display or an on-board display screen; The human-computer interaction module detects through the information collection module that there are pedestrians crossing the road ahead and issues a warning to the driver through sound and light; The human-computer interaction module is used to receive the driver's voice input instructions, set a new navigation destination, and send the new navigation destination to the path planning module and traffic risk prediction module to replan the optimal driving path for the driver and predict the traffic risks of the optimal driving path.

[0012] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes an intelligent connected vehicle system, which uses an information collection module to collect vehicle speed, turning speed, road signs, and information about other surrounding vehicles and pedestrians. It uses a path planning module to predict traffic congestion conditions in future time periods for all driving routes and plan the optimal driving route. It uses an intelligent early warning module to predict the driving intentions of other surrounding vehicles. It uses a traffic risk prediction module to predict traffic risks in the vehicle's driving section. It uses a human-computer interaction module to display various types of vehicle driving information, effectively improving traffic safety and traffic efficiency and reducing the incidence of traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only preferred embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 A schematic diagram of the structure of an intelligent connected vehicle system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0015] The principles and features of the present invention are described below with reference to the accompanying drawings. The enumerated embodiments are only used to explain the present invention and are not used to limit the scope of the present invention.

[0016] Reference Figure 1 , this embodiment provides an intelligent connected vehicle system, including: Information collection module: used to collect vehicle driving information and environmental information. The vehicle driving information includes vehicle speed and vehicle turning speed. The environmental information includes road signs, information about other vehicles and pedestrians around the vehicle, and their relative speed and distance to the vehicle. For example, the module can remind the driver of the driving status based on the content of the road signs. For example, if the road sign of the road section indicates that the speed should not exceed 45 km / h, the driver will be reminded to drive the vehicle at a speed not exceeding the marked speed. Specifically, it includes: The information acquisition module is used to obtain the vehicle's driving speed and steering speed by installing a vehicle speed sensor, an acceleration sensor, and a steering wheel angle sensor on the vehicle; The information collection module is used to set up multiple cameras, millimeter-wave radars and laser radars on the vehicle. The multiple cameras are distributed in the front, back, left and right of the vehicle to collect road signs, surrounding vehicles and pedestrian information around the vehicle. The millimeter-wave radars and laser radars are used to detect the distance and relative speed to surrounding vehicles and pedestrians.

[0017] Route planning module: This module is used to obtain dynamic data on the vehicle's current location and destination, combined with real-time traffic information and weather conditions, to build a traffic prediction model. The traffic prediction model is used to obtain all driving routes from the vehicle's current location to the destination, and to predict traffic congestion conditions for all driving routes in the future. Based on the prediction results, the module plans the optimal driving route for the vehicle. The specific steps include: S21. Obtain the current location of the vehicle and the destination of the vehicle, and obtain dynamic data of traffic information and weather conditions for the current period from the traffic management center server and the meteorological center respectively; S22. Build a traffic prediction model, obtain all routes from the current location of the vehicle to the current destination, obtain historical traffic data and historical weather data for all routes, analyze the number of traffic jams in the historical traffic data for different routes, and the time characteristics corresponding to the number of traffic jams, and convert the data and the historical weather data into high-dimensional data, and use the high-dimensional data to train the traffic prediction model; S23. A dynamic graph convolution recursive unit and a traffic weight unit are respectively provided in the traffic prediction model. The dynamic graph convolution recursive module simulates the traffic conditions of the driving route based on the high-dimensional data. The traffic weight unit is used to generate a traffic weight value based on the traffic information of the current time period in combination with the high-dimensional data. The influence of historical traffic data and historical weather data on the prediction of the future time period is adjusted according to the traffic weight value. S24. Based on the degree of influence in step S23, the dynamic data of traffic information and weather conditions in the current period in step S21 is input into the traffic prediction model, and the high-dimensional data corresponding to the conditions is matched by the traffic prediction model, and the matched high-dimensional data is divided into a non-hidden time series and a hidden time series; S25. Introducing a gated recurrent unit and an attention mechanism into the traffic prediction model to track the traffic dynamics of hidden time series according to their temporal characteristics, and introducing a dynamic spatiotemporal graph convolutional network layer into the traffic prediction model to extract the spatiotemporal dependencies between non-hidden time series; S26. Combine the processing results of the non-hidden time series and the hidden time series with the dynamic data of traffic information and weather conditions in the current period to predict traffic congestion conditions on all routes to the destination of this vehicle, and plan the optimal driving route for this vehicle based on the prediction results.

[0018] Intelligent warning module: It is used to analyze the information collected by the information collection module, obtain the driving speed of other vehicles around the vehicle, and obtain the distance between other vehicles around the vehicle and the road traffic markings. It combines this with the driving speed of other vehicles around the vehicle to predict the driving intention of other vehicles around the vehicle. Based on the predicted driving intention, it provides early warning to the driver. Specifically, it includes the following steps: S31. Analyze the driving information and environmental information collected by the information collection module to obtain the distances and positions of other vehicles around the vehicle and the vehicle itself, and determine the dynamic driving speeds of the surrounding vehicles based on the distances and positions of the other vehicles around the vehicle and their relative speeds to the vehicle itself, where the dynamic driving speeds of the surrounding vehicles include the lateral speed and acceleration, and the longitudinal speed and acceleration of the vehicles; S32. Obtain the distances between other vehicles around the vehicle and the road traffic markings, as well as the relative speeds and distances of other vehicles to the vehicles around them. Combine these with the distances between other vehicles around the vehicle and the road traffic markings and their dynamic driving speeds to predict the driving intentions of other vehicles around the vehicle, as expressed as follows:

[0019] in, is the driving intention of the predicted vehicle, is the predicted vehicle lateral velocity, is the predicted vehicle longitudinal velocity, is the predicted vehicle lateral acceleration, is the predicted vehicle longitudinal acceleration, is the distance between the predicted vehicle and the road traffic markings, is the relative speed and distance between the predicted vehicle and surrounding vehicles.

[0020] Traffic risk prediction module: This module is used to predict the probability of traffic accidents in the future based on the optimal driving route planned by the route planning module. It specifically includes the following steps: S41. Obtaining a road environment of the optimal driving path based on the optimal driving path obtained by the path planning module, wherein the road environment includes blind spots, intersections, and other driving intersections on the optimal driving path; S42, based on the road section environment of the optimal driving path, obtaining traffic accident information of the road section environment of the optimal driving path in a previous time period; S43. Real-time traffic information of the optimal driving route is obtained, and the information is combined with the road environment of the optimal driving route and traffic accident information of the road environment in previous time periods to predict the traffic accident risk probability of the optimal driving route in the future time period. The real-time traffic information of the optimal driving route is used to determine whether there are traffic participants in the future time period, and the traffic participants that pose a risk, as shown below:

[0021] in, For The traffic accident risk probability of the optimal driving path during this period, Calculate the probability of traffic accident risk. For Whether there are any traffic participants who may pose a risk on the optimal driving route during this period, For Whether there are any traffic participants on the optimal driving path during this time period.

[0022] Human-computer interaction module: used to display vehicle driving information, environmental information, optimal driving path and predicted traffic information, warning information, traffic risk prediction information to the driver based on the information collection module, path planning module, intelligent warning module and traffic risk prediction module, and receive the driver's voice input instructions, including: The human-computer interaction module displays the optimal driving route and its predicted traffic information, warning information, traffic risk prediction information, current traffic information and estimated time of arrival at the destination to the driver through a head-up display or an in-vehicle display screen; The human-computer interaction module detects through the information collection module that a pedestrian is suddenly crossing the road ahead and issues a warning to the driver through sound and light; The human-computer interaction module is used to receive the driver's voice input instructions, set a new navigation destination, and send the new navigation destination to the path planning module and the traffic risk prediction module to re-plan the optimal driving path for the driver and predict the traffic risk of the optimal driving path. The human-computer interaction module receives the re-planned route from the path planning module and displays the navigation route of the new optimal driving path on the head-up display or the vehicle display.

[0023] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent connected vehicle system, characterized in that: The system comprises: Information collection module: used to collect vehicle driving information and environmental information. The vehicle driving information includes vehicle speed and vehicle turning speed. The environmental information includes road signs, information about other vehicles and pedestrians around the vehicle, and their relative speed and distance to the vehicle. Route planning module: This module is used to obtain dynamic data on the vehicle's current location and destination, combined with real-time traffic information and weather conditions, to build a traffic prediction model. The model is used to obtain all driving routes from the vehicle's current location to the destination, predict traffic congestion conditions for all driving routes in the future, and plan the optimal driving route for the vehicle based on the prediction results. Intelligent warning module: This module analyzes the information collected by the information collection module to obtain the speed of other vehicles around the vehicle and the distance between other vehicles around the vehicle and the road traffic markings. It combines this information with the speed of other vehicles around the vehicle to predict the driving intentions of other vehicles around the vehicle and provides early warning to the driver based on the predicted driving intentions. Traffic risk prediction module: used to predict the probability of traffic accident risks in the future period of the optimal driving route planned by the route planning module; Human-computer interaction module: used to display vehicle driving information, environmental information, optimal driving path and its predicted traffic information, warning information, traffic risk prediction information to the driver based on the information collection module, path planning module, intelligent warning module and traffic risk prediction module, and receive the driver's voice input commands.

2. The intelligent connected vehicle system according to claim 1, characterized in that: The information collection module includes: The information acquisition module is used to obtain the vehicle's driving speed and steering speed by installing a vehicle speed sensor, an acceleration sensor, and a steering wheel angle sensor on the vehicle; The information collection module is used to set up multiple cameras, millimeter-wave radars and laser radars on the vehicle. The multiple cameras are distributed in the front, back, left and right of the vehicle to collect road signs, surrounding vehicles and pedestrian information around the vehicle. The millimeter-wave radars and laser radars are used to detect the distance and relative speed to surrounding vehicles and pedestrians.

3. The intelligent connected vehicle system according to claim 1, characterized in that: The path planning module specifically includes the following steps: S21, obtaining the current location of the vehicle and the destination of this vehicle, as well as dynamic data of traffic information and weather conditions for the current time period; S22. Build a traffic prediction model, obtain all routes from the current location of the vehicle to the current destination, obtain historical traffic data and historical weather data for all routes, analyze the number of traffic jams in the historical traffic data for different routes, and the time characteristics corresponding to the number of traffic jams, and convert the data and the historical weather data into high-dimensional data, and use the high-dimensional data to train the traffic prediction model; S23. A dynamic graph convolution recursive unit and a traffic weight unit are respectively provided in the traffic prediction model. The dynamic graph convolution recursive module simulates the traffic conditions of the driving route based on the high-dimensional data. The traffic weight unit is used to generate a traffic weight value based on the traffic information of the current time period in combination with the high-dimensional data. The influence of historical traffic data and historical weather data on the prediction of the future time period is adjusted according to the traffic weight value. S24. Based on the degree of influence in step S23, the dynamic data of traffic information and weather conditions in the current period in step S21 is input into the traffic prediction model, and the high-dimensional data corresponding to the conditions is matched by the traffic prediction model, and the matched high-dimensional data is divided into a non-hidden time series and a hidden time series; S25. Introducing a gated recurrent unit and an attention mechanism into the traffic prediction model to track the traffic dynamics of hidden time series according to their temporal characteristics, and introducing a dynamic spatiotemporal graph convolutional network layer into the traffic prediction model to extract the spatiotemporal dependencies between non-hidden time series; S26. Combine the processing results of the non-hidden time series and the hidden time series with the dynamic data of traffic information and weather conditions in the current period to predict traffic congestion conditions on all routes to the destination of this vehicle, and plan the optimal driving route for this vehicle based on the prediction results.

4. The intelligent connected vehicle system according to claim 1, characterized in that: The intelligent early warning module specifically includes the following steps: S31. Analyze the driving information and environmental information collected by the information collection module to obtain the distances and positions of other vehicles around the vehicle and the vehicle itself, and determine the dynamic driving speeds of the surrounding vehicles based on the distances and positions of the other vehicles around the vehicle and their relative speeds to the vehicle itself, where the dynamic driving speeds of the surrounding vehicles include the lateral speed and acceleration, and the longitudinal speed and acceleration of the vehicles. S32. Obtain the distances between other vehicles around the vehicle and the road traffic markings, as well as the relative speeds and distances of other vehicles to their surrounding vehicles. Combine these with the distances between other vehicles around the vehicle and the road traffic markings and their dynamic driving speeds to predict the driving intentions of other vehicles around the vehicle, as expressed as follows: in, is the driving intention of the predicted vehicle, is the predicted vehicle lateral velocity, is the predicted vehicle longitudinal velocity, is the predicted vehicle lateral acceleration, is the predicted vehicle longitudinal acceleration, is the distance between the predicted vehicle and the road traffic markings, is the relative speed and distance between the predicted vehicle and surrounding vehicles.

5. The intelligent connected vehicle system according to claim 1, characterized in that: The traffic risk prediction module specifically includes the following steps: S41. Obtaining a road environment of the optimal driving path based on the optimal driving path obtained by the path planning module, wherein the road environment includes blind spots, intersections, and other driving intersections on the optimal driving path; S42, based on the road section environment of the optimal driving path, obtaining traffic accident information of the road section environment of the optimal driving path in a previous time period; S43. Real-time traffic information of the optimal driving route is obtained, and the information is combined with the road environment of the optimal driving route and traffic accident information of the road environment in previous time periods to predict the traffic accident risk probability of the optimal driving route in the future time period, which is expressed as follows: in, For The traffic accident risk probability of the optimal driving path during this period, Calculate the probability of traffic accident risk. For Whether there are any traffic participants who may pose a risk on the optimal driving route during this period, For Whether there are any traffic participants on the optimal driving path during this time period.

6. The intelligent connected vehicle system according to claim 1, characterized in that: The human-computer interaction module includes: The human-computer interaction module displays the optimal driving route and its predicted traffic information, warning information, and traffic risk prediction information to the driver through a head-up display or an on-board display screen; The human-computer interaction module detects through the information collection module that there are pedestrians crossing the road ahead and issues a warning to the driver through sound and light; The human-computer interaction module is used to receive the driver's voice input instructions, set a new navigation destination, and send the new navigation destination to the path planning module and traffic risk prediction module to replan the optimal driving path for the driver and predict the traffic risks of the optimal driving path.

Images