CN111477030B

CN111477030B - Vehicle collaborative risk avoiding method, vehicle end platform, cloud end platform and storage medium

Info

Publication number: CN111477030B
Application number: CN202010288638.5A
Authority: CN
Inventors: 彭程; 陈新
Original assignee: Beijing Automotive Group Co Ltd; Beijing Automotive Research Institute Co Ltd
Current assignee: Beijing Automotive Group Co Ltd; Beijing Automotive Research Institute Co Ltd
Priority date: 2020-04-14
Filing date: 2020-04-14
Publication date: 2022-01-21
Anticipated expiration: 2040-04-14
Also published as: CN111477030A

Abstract

The embodiment of the application discloses vehicle collaborative risk avoiding method, vehicle end platform, cloud end platform and storage medium, wherein the vehicle collaborative risk avoiding method comprises the following steps: sending surrounding vehicle information, vehicle information and drive test state information to a cloud platform, so that the cloud platform judges whether the surrounding vehicles form collision risks to the target vehicle according to the surrounding vehicle information, the vehicle information and the drive test state information, and if so, generating early warning information and basic information; generating control information of the target vehicle in a second driving state at least according to the basic information, the early warning information and the finite-state machine model; and converting the running state of the target vehicle from the first running state to the second running state according to the control information. According to the method and the device, safe and correct decision and control of the vehicle in the driving process can be guaranteed through information interaction between vehicles, between the vehicles and traffic, between the vehicles and the cloud and cooperative processing of various information, so that the vehicle can safely and stably drive.

Description

Vehicle collaborative risk avoiding method, vehicle end platform, cloud end platform and storage medium

Technical Field

The application relates to the field of intelligent driving, in particular to a vehicle collaborative risk avoiding method, a vehicle end platform, a cloud end platform and a storage medium.

Background

With the continuous development of vehicle intelligence, vehicle cooperative control is increasingly important for automatically driving automobiles. The existing vehicle cooperative control is also a relatively single man-machine cooperative control, and the method has the following defects: people account for a large proportion of control and decision making, and the intelligence is poor, on the other hand, compared with people, the intelligent control system in the mode has relatively weak learning and self-adapting capabilities, further the comprehensive processing capability based on environment understanding is not perfect, the decision making capability on unknown complex working conditions is poor, further, information obtained from the intelligent control system is relatively less when people make decisions, and more comprehensive judgment and decision making cannot be made.

Disclosure of Invention

The application aims to disclose a vehicle collaborative risk avoiding method, a vehicle end platform, a cloud end platform and a storage medium, which are used for ensuring that a vehicle makes safe and correct decisions and control on the vehicle in the driving process through information interaction between vehicles, between vehicles and traffic, between vehicles and the cloud end and collaborative processing of various information, so that the vehicle can safely and stably drive.

The application discloses a vehicle collaborative risk avoiding method in a first aspect, which is applied to a vehicle end platform and comprises the following steps:

acquiring own vehicle information of a target vehicle in a first running state, peripheral vehicle information generated by the target vehicle detecting a peripheral vehicle and drive test state information sent by a road traffic system;

sending surrounding vehicle information, vehicle information and drive test state information to a cloud platform, so that the cloud platform judges whether the surrounding vehicles form collision risks to target vehicles according to the surrounding vehicle information, the vehicle information and the drive test state information, and if so, generating early warning information and basic information and sending the early warning information and the basic information to a vehicle end platform;

receiving basic information and early warning information sent by a cloud platform;

generating control information of the target vehicle in a second driving state at least according to the basic information, the early warning information and the finite-state machine model;

the travel state of the target vehicle is converted from the first travel state to the second travel state according to the control information.

The vehicle-end platform of the first aspect of the application sends the drive test state information and the information of the surrounding vehicles to the cloud-end platform by obtaining the information of the self-vehicle, the information of the surrounding vehicles and the drive test state information sent by the road traffic system, so that the early warning information and the basic information generated by the cloud-end platform according to the drive test state information, the information of the surrounding vehicles and the self-information can be obtained, and the target vehicle can be converted from the first driving state to the second driving state according to the early warning information, the basic information and the finite-state machine model, because the vehicle-end platform of the application can collect more information, the cloud-end platform can more intelligently generate the early warning information and the basic information according to more information, and when the vehicle-end platform controls the target vehicle, the vehicle-end platform can intelligently and comprehensively make control decisions based on the early warning information and the basic information, therefore compared with the prior art, the method has the advantages of better comprehensive processing capability, better decision-making capability on unknown complex working conditions, less dependence on people and the like.

As an optional implementation manner, the finite-state machine model includes at least two state nodes of an initial state node, a line patrol driving state node, an intersection passing state node, an intersection obstacle avoidance state node, a passing joint state node, a forced left state changing node, a forced right state changing node, a free left state changing node, a free right state changing node, an error state node, and a completion state node.

In this alternative embodiment, the finite-state machine model defines a transition condition between a plurality of states, so that the vehicle-end platform can more accurately transition the target vehicle from the first driving state to the second driving state according to the warning information and the basic information based on the finite-state machine model.

As an optional implementation manner, after receiving the basic information and the early warning information sent by the cloud platform, before generating control information of the target vehicle in the second driving state according to at least the basic information, the early warning information, and the finite-state machine model, the method further includes:

determining the relative position, the azimuth angle and the moving track of the surrounding vehicle according to the surrounding vehicle information and the drive test state information;

carrying out target classification on the surrounding vehicles according to the relative positions, azimuth angles and moving tracks of the surrounding vehicles and determining the target types of the surrounding vehicles;

determining a risk assessment of the nearby vehicle based on the target type of the nearby vehicle;

and generating control information of the target vehicle in a second driving state according to at least the basic information, the early warning information and the finite-state machine model, wherein the control information comprises:

and generating control information of the target vehicle in the second driving state according to the danger assessment, the basic information, the early warning information and the finite-state machine model.

In this optional embodiment, the relative position, the azimuth angle, and the moving rail of the peripheral vehicle can be determined according to the peripheral vehicle information and the drive test state information, and then the peripheral vehicle can be subjected to target classification, so that the target type of the peripheral vehicle can be preliminarily determined, and then the risk assessment is performed on the peripheral vehicle based on the target type, and then the control information of the target vehicle in the second driving state is generated according to the risk assessment, the basic information, the early warning information, and the finite state machine model.

The second aspect of the application discloses a vehicle collaborative risk avoiding method, which is applied to a cloud platform and comprises the following steps:

receiving self-vehicle information of a target vehicle in a first running state, which is sent by a vehicle-end platform, and peripheral vehicle information and drive test state information generated by the target vehicle detecting peripheral vehicles;

judging whether the peripheral vehicle forms collision risk to the target vehicle or not according to the peripheral vehicle information, the own vehicle information and the drive test state information;

when judging that the surrounding vehicles form collision risks to the target vehicle according to the surrounding vehicle information, the own vehicle information and the drive test state information, generating early warning information and basic information;

and sending the early warning information and the basic information to a vehicle-end platform so that the vehicle-end platform generates control information in a second driving state according to the early warning information, the basic information and the finite-state machine model, and converting the driving state of the target vehicle from the first driving state into the second driving state according to the control information.

The cloud platform of this application second aspect is according to the drive test state information, early warning information and the basic information that the information of peripheral vehicle and self information generated, and then can return early warning information and basic information to car end platform, so that car end platform can be according to early warning information and basic information and finite state machine model with the target vehicle from first driving state conversion to the second driving state, because the cloud platform of this application can be based on the more intelligent early warning information and the basic information that generates of the information that car end platform gathered, and then when making car end platform control the target vehicle, can be based on early warning information and basic information intelligence, make control decision comprehensively, consequently compare with prior art, the cloud platform has comprehensive processing ability more excellent, decision-making ability to unknown complicated operating mode is more excellent, to the human advantage such as less dependence.

As an optional implementation, generating the early warning information and the basic information includes:

determining early warning information according to the type of collision risk of the surrounding vehicles to the target vehicle;

screening out at least one service type from the collaborative service set according to the early warning information;

the basic information is determined according to at least one service type.

In this optional embodiment, the cloud platform can determine the early warning information according to the type of collision risk of the peripheral vehicle to the target vehicle, and then can screen out at least one service type from the cooperative service set by the early warning information, so that the basic information can be determined based on the service type.

As an alternative embodiment, the collaborative service set includes at least one of a communication access service set, a voice service set, a location service set, and a weather service set.

In this optional embodiment, the cooperative service set includes multiple service sets, so that when it is determined that the surrounding vehicle poses a collision risk to the target vehicle, the risk avoidance service can be provided more intelligently for the target vehicle.

As an optional implementation manner, the determining whether the nearby vehicle forms a collision risk with the target vehicle according to the nearby vehicle information, the own vehicle information, and the drive test state information includes:

judging whether the peripheral vehicles meet preset conditions or not according to the peripheral vehicle information, the own vehicle information and the road test state information, and if so, determining that the peripheral vehicles form collision risks to the target vehicle;

wherein the preset condition is that the target vehicle and the surrounding vehicle are simultaneously in a first early warning area and the speed of the surrounding vehicle is greater than a preset first speed threshold value,

or the target vehicle and the surrounding vehicle are simultaneously in the second early warning area and the speed of the target vehicle is greater than the preset second speed threshold,

or the target vehicle starts the steering indicating lamp, and the speed of the surrounding vehicle is greater than a preset third speed threshold in a third early warning area in the same direction with the steering indicating lamp.

In the optional embodiment, whether the peripheral vehicles meet the preset conditions or not can be judged according to the peripheral vehicle information, the own vehicle information and the road test state information, so that scene early warning danger avoidance such as intersection unclear state early warning danger avoidance, forward collision early warning danger avoidance and vehicle lane change early warning danger avoidance of the target vehicle is realized.

The third aspect of the present application discloses a car end platform, car end platform includes:

the acquisition module is used for acquiring the own vehicle information of the target vehicle in a first running state, the peripheral vehicle information generated by the target vehicle detecting the peripheral vehicle and the road test state information sent by the road traffic system;

the system comprises a first sending module, a vehicle end platform and a vehicle end platform, wherein the first sending module is used for sending surrounding vehicle information, vehicle information and drive test state information to the cloud end platform so that the cloud end platform can judge whether the surrounding vehicles form collision risks to target vehicles according to the surrounding vehicle information, the vehicle information and the drive test state information, and if yes, early warning information and basic information are generated and sent to the vehicle end platform;

the first receiving module is used for receiving basic information and early warning information sent by the cloud platform;

the first generation module is used for generating control information of the target vehicle in a second running state at least according to the basic information, the early warning information and the finite-state machine model;

and the control module is used for converting the running state of the target vehicle from the first running state to the second running state according to the control information.

The vehicle-end platform of the third aspect of the present application can obtain the vehicle information, the information of the surrounding vehicles, and the road test state information sent by the road traffic system by executing the vehicle collaborative danger avoiding method, and send the road test state information and the information of the surrounding vehicles to the cloud-end platform, so as to obtain the early warning information and the basic information generated by the cloud-end platform according to the road test state information, the information of the surrounding vehicles, and the self information, and further convert the target vehicle from the first driving state to the second driving state according to the early warning information, the basic information, and the finite-state machine model, because the vehicle-end platform of the present application can collect more information, the cloud-end platform can more intelligently generate the early warning information and the basic information according to more information, and further when the vehicle-end platform controls the target vehicle, a control decision can be made intelligently and comprehensively based on the early warning information and the basic information, therefore, compared with the prior art, the vehicle-end platform has the advantages of better comprehensive processing capability, better decision-making capability on unknown complex working conditions, less dependence on people and the like.

The application fourth aspect discloses a high in clouds platform, and high in clouds platform includes:

the second receiving module is used for receiving the self-vehicle information of the target vehicle in the first running state, which is sent by the vehicle-end platform, and the peripheral vehicle information and the road test state information which are generated by the target vehicle detecting the peripheral vehicle;

the judging module is used for judging whether the peripheral vehicle forms collision risk to the target vehicle according to the peripheral vehicle information, the own vehicle information and the drive test state information;

the second generation module is used for generating early warning information and basic information when judging that the surrounding vehicle judges that the surrounding vehicle forms collision risk to the target vehicle according to the surrounding vehicle information, the vehicle information and the drive test state information;

and the second sending module is used for sending the early warning information and the basic information to the vehicle-end platform so that the vehicle-end platform generates control information in a second driving state according to the early warning information, the basic information and the finite-state machine model, and converts the driving state of the target vehicle from the first driving state into a second driving state according to the control information.

The cloud platform in the fourth aspect of the present application, by executing the vehicle collaborative risk avoidance method, can generate the early warning information and the basic information according to the driving test state information, the information of the surrounding vehicles and the self information, and then early warning information and basic information can be returned to the vehicle-end platform, so that the vehicle-end platform can convert the target vehicle from the first running state to the second running state according to the early warning information, the basic information and the finite-state machine model, because the cloud platform can more intelligently generate early warning information and basic information based on the information collected by the vehicle-end platform, thereby leading the vehicle-end platform to intelligently and comprehensively make control decisions based on the early warning information and the basic information when controlling the target vehicle, therefore, compared with the prior art, the cloud platform has the advantages of being better in comprehensive processing capacity, better in decision-making capacity on unknown complex working conditions, less in dependence on people and the like.

A fifth aspect of the present application discloses a computer storage medium, in which a computer program is stored, and the computer program is executed by a processor to perform the vehicle collaborative risk avoiding method disclosed in the first aspect and the second aspect of the present application.

The computer storage medium of the fifth aspect of the present application can generate the early warning information and the basic information according to the road test state information, the information of the surrounding vehicles, and the early warning information and the basic information generated by the information of the surrounding vehicles, and further can convert the target vehicle from the first driving state to the second driving state according to the early warning information, the basic information, and the finite state machine model.

Drawings

In order to more clearly explain the technical solutions of the present application, the drawings needed to be used in the embodiments are briefly introduced below, and it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope of protection of the present application. Like components are numbered similarly in the various figures.

Fig. 1 is a system configuration diagram of a cooperative control system disclosed in an embodiment of the present application;

FIG. 2 is a schematic structural diagram of a finite state machine model disclosed in an embodiment of the present application;

FIG. 3 is a schematic flow chart illustrating a vehicle collaborative risk avoiding method according to an embodiment of the present application;

FIG. 4 is a schematic flow chart illustrating a further vehicle collaborative risk avoiding method according to an embodiment of the present application;

FIG. 5 is a schematic flow chart illustrating a further vehicle collaborative risk avoiding method according to an embodiment of the present application;

fig. 6 is a schematic diagram of an unknown state early warning scene at an intersection disclosed in the embodiment of the present application;

FIG. 7 is a schematic diagram of a forward collision warning scenario disclosed in an embodiment of the present application;

FIG. 8 is a schematic diagram of a vehicle lane change warning scenario disclosed in an embodiment of the present application;

FIG. 9 is a schematic structural diagram of a vehicle-end platform disclosed in an embodiment of the present application;

fig. 10 is a schematic structural diagram of a cloud platform disclosed in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments.

Before describing the embodiments of the present application in detail, a detailed description of a cooperative control system according to the present application will be given to facilitate understanding of the embodiments of the present application.

Referring to fig. 1, fig. 1 is a system structure diagram of a cooperative control system according to an embodiment of the present disclosure. As shown in fig. 1, the cooperative control system includes three subsystems, namely, an application scene library, a base platform, and an application service scene, where the base platform subsystem includes a vehicle-side platform (i.e., a vehicle-side data platform) and a cloud-side platform (i.e., a cloud-side service platform).

In the embodiment of the application, the vehicle-end platform comprises a driving layer, an interface layer, a data fusion layer, a world model layer and an application layer, wherein the driving layer is used for managing devices on a vehicle, such as devices for managing a vehicle-mounted radar, a vehicle-mounted camera and a serial/network port GPS. The interface layer is used for extracting and interfacing the equipment data acquired by the driving layer, so that data exchange can be realized among different vehicle-end platforms, the vehicle-end platforms and the cloud platform according to interface definitions. The data fusion layer is used for fusing data from multiple sources according to a fusion algorithm. And the application layer is used for providing basic application functions for application software, such as functions of providing picture rendering and the like. It should be noted that the vehicle-side platform driving layer, the interface layer, the data fusion layer, the world model layer, and the application layer are basic environments for realizing vehicle-side platform and cloud-side platform interaction and vehicle-side flat data interaction installed on other vehicles, and the basic environments can execute the vehicle collaborative risk avoiding method in the embodiment of the present application.

In the embodiment of the application, the world model layer is used for calling a world model in the application scene library, wherein the world model comprises data nodes corresponding to attributes of things existing in the real world and a management function for managing dynamic changes of the things in the real world, for example, the data nodes can be data items such as positions, states, paths, signal lamps and signs, so as to map the real attributes such as the positions and the states of the vehicles. As another example, the world model can be used to periodically clear objects (objects may refer to surrounding vehicles, pedestrians, etc.) that do not appear within a visible range for a longer period of time. On the other hand, the world model can use a data structure to spatially partition objects, for example, using a quadtree or KD-tree (k-dimensional). Through the world model, the real world objects can be further subjected to data abstraction, so that data interaction is facilitated, data can be processed conveniently according to an algorithm, and accordingly vehicle risk avoidance can be controlled accurately.

In the embodiment of the present application, the application scenario library further includes, in addition to the above-mentioned world model, a finite state machine model (i.e., a finite state machine model) and a collaborative service capability set, where the finite state machine model defines a plurality of driving states that may occur in the vehicle in a preset scenario and a transition condition between the plurality of driving states. For example, please refer to fig. 2, wherein fig. 2 is a schematic structural diagram of a finite state machine model disclosed in the embodiment of the present application. As shown in fig. 2, the finite-state machine model includes state nodes such as error state nodes, initial state nodes, intersection obstacle avoidance nodes, free right-shift nodes, free left-shift nodes, and the like, and meanwhile, the different state nodes are represented by conversion conditions C1-C37, so that the driving states and the conversion of the driving states of the vehicle under different scenes can be simulated through the finite-state machine model, and the vehicle danger avoidance can be accurately controlled.

In the embodiment of the present application, the collaborative service capability set includes a plurality of service sets, for example, a communication access service set, a voice service set, a location service set, a weather service set, and the like. It should be noted that the service set may refer to a function package or a library file composed of the function package and the like for implementing various service functions, the function package or the library file composed of the function package establishes an index relationship with a specified name and is stored in a preset database, and when a certain function needs to be used, the service set may be called by the name and then installed and executed by the execution container in the form of a plug-in. For example, when a weather service needs to be used, the set of weather services may be invoked and implemented by executing the set of weather services.

In the embodiment of the application, one service set or more than two service sets can be called according to different application scenes, so that the service capability sets can be intelligently arranged according to different requirements of intelligent driving services.

In the embodiment of the application, the application service scene comprises early warning of unknown states of crossroads, early warning of forward collision and early warning of vehicle lane change. The application service scene can be used for providing judgment conditions under a specified scene for judging whether the target vehicle and the surrounding vehicle form a collision danger or not.

Example 1

Referring to fig. 3, fig. 3 is a schematic flow chart of a vehicle collaborative risk avoiding method according to an embodiment of the present application, where the method is applied to a vehicle-end platform. As shown in fig. 3, the vehicle collaborative risk avoiding method includes S101, S102, S103, S104, and S105, wherein:

s101: the method comprises the steps of obtaining own vehicle information of a target vehicle in a first running state, peripheral vehicle information generated by the target vehicle detecting peripheral vehicles and road test state information sent by a road traffic system.

In the embodiment of the present application, the target vehicle is a vehicle to be controlled, for example, a test vehicle in an intelligent driving test process.

In the embodiment of the present application, the first traveling state of the target vehicle corresponds to one state node in the finite state machine model. In another aspect, the first driving state is associated with a current attribute of the target vehicle. For example, when the current speed of the target vehicle is 60km/h and the current acceleration is 60km/h, the target vehicle is defined as a first traveling state at this time.

In the embodiment of the present application, the nearby vehicle information may be a vehicle that can be detected by a target vehicle equipped with other sensors for detecting nearby vehicles, such as a radar and a camera. For example, the target vehicle captures an image of the vehicle within 1 meter of the target vehicle via a camera.

In the embodiment of the present application, the peripheral vehicle information may optionally include the speed, the acceleration, the position, and the size of the peripheral vehicle, it should be noted that the specific data item of the peripheral vehicle information may include other data required in the vehicle intelligent control process in addition to the speed, the acceleration, the position, and the size of the peripheral vehicle, and the specific content of the peripheral vehicle information is not limited in the implementation of the present application, and modifications to the specific content of the peripheral vehicle information (such as adding the specific content of the peripheral vehicle information and deleting the specific content of the peripheral vehicle information) made by those skilled in the art without departing from the inventive concept of the embodiment of the present application fall within the scope of the embodiment of the present application.

In the embodiment of the present application, the drive test state information may be attribute information of an object such as a signal lamp, a sign, a road bed, and the like, for example, a position and a color of the signal lamp, and a position and an icon of the sign. Preferably, the drive test state information may be acquired by the road traffic system and sent to the vehicle-end platform, wherein the vehicle-end platform may send a data pull request carrying the authentication information to the road traffic system, and then the drive test state information is returned to the vehicle-end platform after the authentication information is successfully verified by the road traffic system.

S102: and sending the peripheral vehicle information, the vehicle information and the drive test state information to the cloud platform, so that the cloud platform judges whether the peripheral vehicle forms collision risk to the target vehicle according to the peripheral vehicle information, the vehicle information and the drive test state information, and if so, generating early warning information and basic information and sending the early warning information and the basic information to the vehicle-side platform.

In the embodiment of the application, the early warning information comprises the early warning type and the early warning grade, so that the vehicle-end platform can execute different danger avoiding actions according to the early warning type and the early warning grade, namely, the target vehicle is converted into a corresponding second driving state from a first driving state.

In this application embodiment, the basic information can include the decision information that is used for controlling the target vehicle, so, the vehicle end platform confirms whether to give the control right of vehicle to the high in the clouds platform according to basic information, and then can realize when the high in the clouds platform judges that the target vehicle is in emergency for the high in the clouds platform can directly control the target vehicle.

For example, when the target vehicle is 1 meter away from the surrounding vehicle, the cloud platform can directly control the target vehicle through the basic information.

S103: and receiving basic information and early warning information sent by the cloud platform.

And S104, generating control information of the target vehicle in the second running state at least according to the basic information, the early warning information and the finite-state machine model.

In the embodiment of the present application, the second driving state corresponds to one state node in the finite state machine model.

And S105, converting the running state of the target vehicle from the first running state to the second running state according to the control information.

In the embodiment of the application, optionally, the vehicle-end platform may input control information to the device for controlling the speed of the target vehicle to realize the conversion between the first driving state and the second driving state, and may also display the control information to a driver, so that the driving state of the target vehicle is changed by the driver.

For example, when it is determined that the surrounding vehicle forms a collision risk with the target vehicle, the vehicle-end platform may generate the warning image according to the warning information and the basic information, where a display duration of the warning image may be 3S or 4S, and is not limited by comparing the present application.

It can be seen that, the vehicle-end platform of the embodiment of the present application sends the drive test state information and the information of the surrounding vehicles to the cloud-end platform by obtaining the vehicle information, the information of the surrounding vehicles, and the drive test state information sent by the road traffic system, so as to obtain the early warning information and the basic information generated by the cloud-end platform according to the drive test state information, the information of the surrounding vehicles, and the self information, so as to convert the target vehicle from the first driving state to the second driving state according to the early warning information, the basic information, and the finite-state machine model, because the vehicle-end platform of the present application can collect more information, the cloud-end platform can more intelligently generate the early warning information and the basic information according to more information, and when the vehicle-end platform controls the target vehicle, the vehicle-end platform can intelligently and comprehensively make control decisions based on the early warning information and the basic information, compared with the prior art, the method has the advantages of better comprehensive processing capability, better decision-making capability on unknown complex working conditions, less dependence on people and the like.

As an optional implementation manner, the finite-state machine model may include an initial state node and a completed state node, and may also include multiple state nodes such as an initial state node, a completed state node, a line patrol driving state node, an intersection passing state node, an intersection obstacle avoidance state node, a passing joint state node, a forced left state switching node, a forced right state switching node, a free left state switching node, a free right state switching node, an error state node, and a completed state node.

Example two

Referring to fig. 4, fig. 4 is a schematic flow chart of a vehicle collaborative risk avoiding method according to an embodiment of the present application, where the method is applied to a vehicle-end platform. As shown in fig. 4, the vehicle collaborative risk avoiding method includes S201, S202, S203, S204, S205, S206, S207, S208, wherein:

s201: the method comprises the steps of obtaining own vehicle information of a target vehicle in a first running state, peripheral vehicle information generated by the target vehicle detecting peripheral vehicles and road test state information sent by a road traffic system.

S202: and sending the peripheral vehicle information, the vehicle information and the drive test state information to the cloud platform, so that the cloud platform judges whether the peripheral vehicle forms collision risk to the target vehicle according to the peripheral vehicle information, the vehicle information and the drive test state information, and if so, generating early warning information and basic information and sending the early warning information and the basic information to the vehicle-side platform.

S203: and receiving basic information and early warning information sent by the cloud platform.

S204: and determining the relative position, the azimuth angle and the moving track of the surrounding vehicle according to the surrounding vehicle information and the drive test state information.

S205: carrying out target classification on the surrounding vehicles according to the relative positions, azimuth angles and moving tracks of the surrounding vehicles and determining the target types of the surrounding vehicles;

s206: a risk assessment of the nearby vehicle is determined based on the target type of the nearby vehicle.

And S207, generating control information of the target vehicle in the second running state according to the danger assessment, the basic information, the early warning information and the finite-state machine model.

And S208, converting the running state of the target vehicle from the first running state to the second running state according to the control information.

In the embodiment of the present application, the control information in the second driving state is generated based on the transition condition between the two states in the finite-state machine model, for example, assuming that when the speed of the first driving state of the target vehicle is 60km/h, the second driving state is obstacle avoidance at the intersection, and the transition condition for the transition from the first driving state to the second driving state is the warning level of 2 and the warning type is the intersection collision, the control information generated by the vehicle-end platform is "speed of 0 km/h", thereby transitioning the target vehicle from the first driving state to the second driving state according to the control information "speed of 0 km/h".

In this application embodiment, the vehicle end platform judges whether the peripheral vehicle constitutes danger according to the relative position, the azimuth angle and the movement track of the peripheral vehicle, so, just can be before the high in the clouds platform returns early warning information and basic information, the danger of dynamic detection peripheral vehicle to control the target vehicle more intelligently. For example, before the cloud platform returns the early warning information and the basic information, the peripheral vehicle drives away from the target vehicle, and at the moment, the vehicle-end platform judges that the peripheral vehicle does not form a collision risk by analyzing the relative position, the azimuth angle and the moving track of the peripheral vehicle, so that the vehicle-end platform does not change the driving state of the target vehicle.

Therefore, according to the method and the device for controlling the risk avoidance of the target vehicle, the relative position, the azimuth angle and the moving rail of the peripheral vehicle can be determined according to the information of the peripheral vehicle and the state information of the drive test, the target classification of the peripheral vehicle can be further performed, the target type of the peripheral vehicle can be preliminarily judged, the risk assessment of the peripheral vehicle can be further performed on the basis of the target type, the control information of the target vehicle in the second driving state is further generated according to the risk assessment, the basic information, the early warning information and the finite state machine model, and the risk avoidance control of the target vehicle can be further intelligently performed.

It should be noted that, regarding the detailed descriptions of S201, S202, S203, and S208, reference may be made to the detailed descriptions of S101, S102, S103, and S105 in the first embodiment of the present application, which are not described herein again.

EXAMPLE III

Referring to fig. 5, fig. 5 is a schematic flow chart of a vehicle collaborative risk avoiding method according to an embodiment of the present application, where the method is applied to a cloud platform. As shown in fig. 5, the vehicle collaborative risk avoiding method includes S301, S302, S303, and S304, wherein:

s301: and receiving the own vehicle information of the target vehicle in the first running state, which is sent by the vehicle-end platform, and the peripheral vehicle information and the drive test state information generated by the target vehicle detecting the peripheral vehicle.

S302: and judging whether the peripheral vehicle forms collision risk to the target vehicle according to the peripheral vehicle information, the own vehicle information and the drive test state information.

S303: and when judging that the surrounding vehicles form collision risks to the target vehicle according to the surrounding vehicle information, the own vehicle information and the drive test state information, generating early warning information and basic information.

S304: and sending the early warning information and the basic information to a vehicle-end platform so that the vehicle-end platform generates control information in a second driving state according to the early warning information, the basic information and the finite-state machine model, and converting the driving state of the target vehicle from the first driving state into the second driving state according to the control information.

Therefore, the cloud platform of the embodiment of the application can intelligently generate the early warning information and the basic information based on the information collected by the vehicle-end platform, and further can intelligently make a control decision based on the early warning information and the basic information when the vehicle-end platform controls the target vehicle, so that the cloud platform has the advantages of being better in comprehensive processing capacity, better in decision making capacity on unknown complex working conditions, less in dependence on people and the like.

As an alternative embodiment, S303: when judging that the surrounding vehicle forms collision risk to the target vehicle according to the surrounding vehicle information, the own vehicle information and the drive test state information, generating early warning information and basic information, comprising the following steps:

the basic information is determined according to at least one service type.

In this optional embodiment, the early warning information includes an early warning type and an early warning level, so that the vehicle-end platform can execute different risk avoidance actions according to the early warning type and the early warning level, that is, the target vehicle is converted from the first driving state to the corresponding second driving state.

In this alternative embodiment, the basic information may include information for guiding the target vehicle to avoid danger, such as navigation voice information.

For example, assuming that the target vehicle includes a driver, when it is determined that the target vehicle is at risk of collision, navigation voice information may be produced to guide the driver to avoid the collision.

In this optional implementation, optionally, the basic information may further include decision information for controlling the target vehicle, so that the vehicle-side platform determines whether to give the control right of the vehicle to the cloud-side platform according to the basic information, and further, when the cloud-side platform determines that the target vehicle is in an emergency, the cloud-side platform may directly control the target vehicle.

Therefore, in the optional embodiment, the cloud platform can determine the early warning information according to the type of collision risk of the peripheral vehicle to the target vehicle, and then can screen out at least one service type from the cooperative service set by the early warning information, so that the basic information can be determined based on the service type.

As an optional implementation manner, S302, determining whether the nearby vehicle constitutes a collision risk to the target vehicle according to the nearby vehicle information, the own vehicle information, and the drive test state information includes the substeps of:

and judging whether the peripheral vehicle meets a preset condition or not according to the peripheral vehicle information, the own vehicle information and the drive test state information, and if so, determining that the peripheral vehicle forms a collision risk to the target vehicle. Optionally, the preset condition is that the target vehicle and the peripheral vehicle are simultaneously located in the first early warning area, and the speed of the peripheral vehicle is greater than a preset first speed threshold, and the preset condition is suitable for early warning of collision risks at intersections such as intersections of ordinary roads and highways in cities and suburbs, entrances of roundabouts, and entrances of highways.

For example, please refer to fig. 6, fig. 6 is a schematic diagram of an early warning scene of an unknown state at an intersection. As shown in fig. 6, HV indicates that the target vehicle, and RV-1 and RV-2 represent the surrounding vehicles, and at this time, the target vehicle and the surrounding vehicles are in the first early warning region, that is, the target vehicle and the surrounding vehicles travel to the intersection at the same time, and further, when the surrounding vehicles are greater than the preset first speed threshold, it is determined that the surrounding vehicles constitute a collision risk for the target vehicle.

In this optional implementation, the preset first speed threshold may be determined according to the current speed of the target vehicle, the speed of the peripheral vehicle, the distance between the target vehicle and the intersection center, and the distance between the peripheral vehicle and the intersection center. For example, if the current speed of the target vehicle is 30km/h, the distance to the intersection center is 50m, the distance of the neighboring vehicle to the intersection center is 50m, and the distance of the target vehicle to the intersection center is 50m, the first speed threshold is preset to be 30km/h, that is, when the target vehicle passes through the intersection, the neighboring vehicle also passes through the intersection, and at this time, the neighboring vehicle poses a collision risk to the target vehicle.

In this optional embodiment, further optionally, the early warning level may be determined according to the current speed of the target vehicle and the distance from the intersection center.

Illustratively, when the speed of the target vehicle is 0-20 km/h and the distance from the intersection center is 6m, or the speed of the target vehicle is 20-50 km/h and the distance from the intersection center is 25m, or the speed of the target vehicle is 50-80 km/h and the distance from the intersection center is 50m, or the speed of the target vehicle is 80-100 km/h and the distance from the intersection center is 70m, the early warning grade is determined as grade 1, and the early warning grade is determined as 2 in other cases.

It should be noted that the first warning area may be a circular area with an intersection center as an origin and a range of R, where the value of R may be 30m or 50m, and this is not limited in this embodiment of the present application.

In this optional embodiment, further optionally, the preset condition is that the target vehicle and the nearby vehicle are simultaneously in the second early warning region and the speed of the target vehicle is greater than the preset second speed threshold.

In this alternative embodiment, please refer to fig. 7, and fig. 7 is a schematic diagram of a forward collision warning scenario. As shown in fig. 7, the second warning area may be a front lane in the same driving direction as the target vehicle, and may be a rectangular range having a specified length and width from the head of the target vehicle, where the specified length and width may be 10m, and the embodiment of the present application is not limited thereto.

In this alternative embodiment, still further alternatively, the preset second speed threshold may be determined according to the current speed of the nearby vehicle. For example, assuming that the nearby vehicle is 100m ahead of the target vehicle at a speed of 60km/m, it is determined that the nearby vehicle constitutes a collision risk to the target vehicle if the target vehicle is greater than a preset second speed threshold of 60 km/m.

In this alternative embodiment, it may be determined according to the current speed of the target vehicle and the distance between the target vehicle and the nearby vehicle.

Illustratively, the early warning level is determined to be level 1 when the speed of the target vehicle is 40-60 km/h and the distance to the nearby vehicle is 25m, or the speed of the target vehicle is 60-80 km/h and the distance to the nearby vehicle is 50m, or the speed of the target vehicle is 80-100 km/h and the distance to the nearby vehicle is 70m, or the speed of the target vehicle is >100km/h and the distance to the nearby vehicle is 70m, and the early warning level is determined to be 2 in other cases.

In this optional embodiment, further optionally, the preset condition is that the target vehicle turns on a turn signal lamp, and the vehicle speed of the surrounding vehicle is greater than a preset third speed threshold in a third early warning region in the same direction as the turn signal lamp.

In this alternative embodiment, a rectangular range having a predetermined length and width calculated from the vehicle body transverse central axis of the target vehicle is used as the third warning region in a lane that is the same as the traveling direction of the target vehicle and is adjacent to the lane in which the target vehicle is located. For example, please refer to fig. 8, fig. 8 is a schematic diagram of a lane-change warning scenario of a vehicle. As shown in fig. 8, assuming that the target vehicle turns on the left turn signal, a line WW extending to the left from the lateral central axis of the vehicle body of the target vehicle and a line WL extending from the rear end of the target vehicle form a third warning region.

In this alternative embodiment, the line WL may have a value range of 20m and the line WW may have a value range of 3.5 m. Further preferably, the preset third speed threshold value can be determined according to a speed range of 36 km/h-108 km.

In this optional embodiment, further optionally, the preset condition is that the target vehicle turns on a turn signal lamp, and is in a third early warning area in the same direction as the turn signal lamp, and there is a surrounding vehicle entering the third early warning area within a preset time interval.

For example, when the target vehicle turns on the left turn indicator, the left turn indicator is turned on for timing, and if it is detected within 5S that the surrounding vehicle enters the third early warning area, it is determined that the surrounding vehicle forms a collision risk for the target vehicle.

Therefore, according to the optional implementation mode, whether the peripheral vehicles meet the preset conditions or not can be judged according to the peripheral vehicle information, the own vehicle information and the road test state information, and scene early warning danger avoidance such as intersection unclear state early warning danger avoidance, forward collision early warning danger avoidance and vehicle lane change early warning danger avoidance of the target vehicle is achieved.

Example four

Referring to fig. 9, fig. 9 is a schematic structural diagram of a vehicle end platform disclosed in the embodiment of the present application. As shown in fig. 9, the vehicle-end platform includes an obtaining module 401, a first sending module 402, a first receiving module 403, a first generating module 404, and a control module 405, where:

the acquiring module 401 is configured to acquire own vehicle information of the target vehicle in a first driving state, and peripheral vehicle information generated by the target vehicle detecting a peripheral vehicle and drive test state information sent by a road traffic system.

In the embodiment of the present application, the nearby vehicle information may be a vehicle that can be detected by a target vehicle equipped with other sensors for detecting nearby vehicles, such as a radar and a camera. For example, the target vehicle captures an image of the vehicle within 1 meter of the target vehicle via a camera. Alternatively, the peripheral vehicle information may include speed, acceleration, position, and size of the peripheral vehicle, it should be noted that the specific data item of the peripheral vehicle information may include other data required in the vehicle intelligent control process in addition to the speed, acceleration, position, and size of the peripheral vehicle, and the specific content of the peripheral vehicle information is not limited in the present application, and modifications to the specific content of the peripheral vehicle information (such as adding the specific content of the peripheral vehicle information and deleting the specific content of the peripheral vehicle information) made by those skilled in the art without departing from the inventive concept of the embodiment of the present application fall within the scope of the embodiment of the present application.

The first sending module 402 is configured to send the peripheral vehicle information, the vehicle information, and the drive test state information to the cloud platform, so that the cloud platform determines whether the peripheral vehicle forms a collision risk to the target vehicle according to the peripheral vehicle information, the vehicle information, and the drive test state information, and if so, sends the early warning information and the basic information to the vehicle-end platform.

The first receiving module 403 is configured to receive basic information and early warning information sent by the cloud platform.

A first generating module 404, configured to generate control information in a second driving state of the target vehicle according to at least the basic information, the warning information, and the finite-state machine model.

A control module 405 for converting the driving state of the target vehicle from the first driving state to the second driving state according to the control information.

It can be seen that, the vehicle-end platform of the embodiment of the present application, by executing the vehicle collaborative risk avoidance method, can obtain the vehicle information, the information of the surrounding vehicles, and the road test state information sent by the road traffic system, and send the road test state information and the information of the surrounding vehicles to the cloud-end platform, and further can obtain the early warning information and the basic information generated by the cloud-end platform according to the road test state information, the information of the surrounding vehicles, and the self information, and further can convert the target vehicle from the first driving state to the second driving state according to the early warning information, the basic information, and the finite state machine model, because the vehicle-end platform of the present application can collect more information, and further the cloud-end platform can be more intelligent according to more information, and further when the vehicle-end platform controls the target vehicle, the vehicle-end platform can make intelligent and comprehensive control decisions based on the early warning information and the basic information, therefore compared with the prior art, the method has the advantages of better comprehensive processing capability, better decision-making capability on unknown complex working conditions, less dependence on people and the like.

As an optional implementation manner, the vehicle-end platform further includes a first determining module, a classifying module, and a second determining module, where:

the first determining module is used for determining the relative position, the azimuth angle and the moving track of the surrounding vehicle according to the surrounding vehicle information and the drive test state information;

the classification module is used for classifying the targets of the surrounding vehicles according to the relative positions, the azimuth angles and the moving tracks of the surrounding vehicles and determining the target types of the surrounding vehicles;

the second determination module determines a risk assessment of the nearby vehicle based on the target type of the nearby vehicle.

Further optionally, the specific way for the first generating module 404 to generate the control information in the second driving state of the target vehicle according to at least the basic information, the early warning information and the finite-state machine model is as follows:

In the present alternative embodiment, the control information in the second running state is generated based on the transition condition between the two states in the finite-state machine model, for example, assuming that when the speed of the target vehicle in the first running state is 60km/h, the second running state is intersection obstacle avoidance, and the transition condition for the transition of the first running state to the second running state is the warning level of 2 and the warning type is intersection collision, the control information generated by the vehicle-end platform is "speed 0 km/h", thereby transitioning the target vehicle from the first running state to the second running state according to the control information "speed 0 km/h".

In this optional implementation mode, the vehicle-end platform judges whether the surrounding vehicle constitutes danger according to the relative position, the azimuth angle and the movement track of the surrounding vehicle, and thus, before the cloud-end platform returns the early warning information and the basic information, the danger of the surrounding vehicle is dynamically detected, so that the target vehicle is controlled more intelligently. For example, before the cloud platform returns the early warning information and the basic information, the peripheral vehicle drives away from the target vehicle, and at the moment, the vehicle-end platform judges that the peripheral vehicle does not form a collision risk by analyzing the relative position, the azimuth angle and the moving track of the peripheral vehicle, so that the vehicle-end platform does not change the driving state of the target vehicle.

Therefore, the optional implementation method can determine the relative position, the azimuth angle and the moving track of the peripheral vehicle according to the peripheral vehicle information and the road test state information, further can classify the target of the peripheral vehicle, can preliminarily judge the target type of the peripheral vehicle, further can evaluate the danger of the peripheral vehicle based on the target type, further generates the control information of the target vehicle in the second driving state according to the danger evaluation, the basic information, the early warning information and the finite state machine model, and further realizes more intelligent danger avoidance control of the target vehicle.

EXAMPLE five

Referring to fig. 10, fig. 10 is a schematic structural diagram of a cloud platform disclosed in the embodiment of the present application. As shown in fig. 10, the cloud platform includes a second receiving module 501, a determining module 502, a second generating module 503, and a second sending module 504, where:

the second receiving module 501 is configured to receive the own vehicle information of the target vehicle in the first driving state, which is sent by the vehicle-end platform, and the peripheral vehicle information and the drive test state information generated by the target vehicle detecting the peripheral vehicle.

The determining module 502 is configured to determine whether the neighboring vehicle forms a collision risk with the target vehicle according to the neighboring vehicle information, the own vehicle information, and the drive test state information.

And a second generating module 503, configured to generate the early warning information and the basic information when it is determined that the neighboring vehicle determines that the neighboring vehicle constitutes a collision risk with the target vehicle according to the neighboring vehicle information, the own vehicle information, and the drive test state information.

The second sending module 504 is configured to send the warning information and the basic information to the vehicle-end platform, so that the vehicle-end platform generates control information in a second driving state according to the warning information, the basic information and the finite-state machine model, and converts the driving state of the target vehicle from the first driving state to the second driving state according to the control information.

Therefore, the cloud platform of the embodiment of the application can generate the early warning information and the basic information according to the road test state information, the information of the surrounding vehicles and the self information by executing the vehicle collaborative risk avoiding method, and then early warning information and basic information can be returned to the vehicle-end platform, so that the vehicle-end platform can convert the target vehicle from the first running state to the second running state according to the early warning information, the basic information and the finite-state machine model, because the cloud platform can be more intelligent based on the information collected by the vehicle-end platform, when the vehicle-end platform controls the target vehicle, the cloud platform can intelligently and comprehensively make control decisions based on the early warning information and the basic information, therefore, compared with the prior art, the cloud platform has the advantages of being better in comprehensive processing capacity, better in decision-making capacity on unknown complex working conditions, less in dependence on people and the like.

As an optional implementation manner, the second generating module 503 executes a specific manner that:

the basic information is determined according to at least one service type.

As an alternative embodiment, the specific way for the determining module 502 to determine whether the neighboring vehicle forms a collision risk with the target vehicle according to the neighboring vehicle information, the own vehicle information, and the drive test state information is as follows:

and judging whether the peripheral vehicle meets a preset condition or not according to the peripheral vehicle information, the own vehicle information and the drive test state information, and if so, determining that the peripheral vehicle forms a collision risk to the target vehicle. Optionally, the preset condition is that the target vehicle and the nearby vehicle are simultaneously in the first early warning area and the speed of the nearby vehicle is greater than the preset first speed threshold.

EXAMPLE six

The embodiment of the application discloses a computer storage medium, wherein a computer program is stored in the computer storage medium, and the computer program is executed by a processor to execute the vehicle collaborative risk avoiding method disclosed in the first embodiment, the second embodiment and the third embodiment of the application.

The computer storage medium of the embodiment of the application can generate the early warning information and the basic information according to the road test state information, the information of the surrounding vehicles and the self information by executing the vehicle collaborative danger avoiding method, and further can convert the target vehicle from the first driving state to the second driving state according to the early warning information, the basic information and the finite state machine model.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, each functional module or unit in each embodiment of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a smart phone, a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: u disk, mobile hard disk and read-only memory

A Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other media capable of storing program codes.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application.

Claims

1. A vehicle collaborative risk avoiding method is applied to a vehicle-end platform and comprises the following steps:

sending the peripheral vehicle information, the vehicle information and the drive test state information to a cloud platform, so that the cloud platform judges whether the peripheral vehicle forms a collision risk to the target vehicle according to the peripheral vehicle information, the vehicle information and the drive test state information, if so, generating early warning information and basic information and sending the early warning information and the basic information to the vehicle-end platform;

receiving the basic information and the early warning information sent by the cloud platform;

generating control information of the target vehicle in a second driving state at least according to the basic information, the early warning information and a finite-state machine model, wherein the finite-state machine model defines a conversion condition among a plurality of states;

and converting the running state of the target vehicle from the first running state to a second running state according to the control information.

2. The method of claim 1, wherein the finite state machine model comprises at least two state nodes of an initial state node, a line patrol driving state node, an intersection passing state node, an intersection obstacle avoidance state node, a passing joint state node, a forced left change state node, a forced right change state node, a free left change state node, a free right change state node, an error state node, and a completion state node.

3. The method of claim 1, wherein after the receiving the base information and the early warning information sent by the cloud platform, and before the generating control information for the target vehicle in the second driving state according to at least the base information and the early warning information and a finite state machine model, the method further comprises:

carrying out target classification on the surrounding vehicles according to the relative positions, the azimuth angles and the moving tracks of the surrounding vehicles and determining the target types of the surrounding vehicles;

and generating control information in a second driving state of the target vehicle according to at least the basic information, the early warning information and a finite-state machine model, wherein the control information comprises:

and generating control information of the target vehicle in a second driving state according to the danger assessment, the basic information, the early warning information and the finite-state machine model.

4. A vehicle collaborative risk avoiding method is applied to a cloud platform and comprises the following steps:

when judging that the surrounding vehicle forms a collision risk to the target vehicle according to the surrounding vehicle information, the own vehicle information and the drive test state information, generating early warning information and basic information;

and sending the early warning information and the basic information to the vehicle-end platform so that the vehicle-end platform generates control information in a second driving state according to the early warning information, the basic information and a finite-state machine model, and converts the driving state of the target vehicle from the first driving state to a second driving state according to the control information, wherein the finite-state machine model defines a conversion condition among a plurality of states.

5. The method of claim 4, wherein generating early warning information and basic information comprises:

determining the early warning information according to the type of collision risk of the surrounding vehicle to the target vehicle;

determining the basic information according to the at least one service type.

6. The method of claim 5, wherein the collaborative service set comprises at least one of a communication access service set, a voice service set, a location service set, a weather service set.

7. The method according to claim 4, wherein the determining whether the nearby vehicle constitutes a collision risk to the target vehicle based on the nearby vehicle information, the own vehicle information, and the drive test state information includes:

judging whether the surrounding vehicles meet preset conditions or not according to the surrounding vehicle information, the own vehicle information and the road test state information, and if so, determining that the surrounding vehicles form collision risks to the target vehicle;

wherein the preset condition is that the target vehicle and the nearby vehicle are simultaneously in a first early warning area and the speed of the nearby vehicle is greater than a preset first speed threshold value,

or the target vehicle and the surrounding vehicle are simultaneously in a second early warning area and the speed of the target vehicle is greater than a preset second speed threshold,

or the target vehicle starts a steering indicator light, and the speed of the surrounding vehicle is greater than a preset third speed threshold value in a third early warning area in the same direction as the steering indicator light.

8. A vehicle end platform, comprising:

the system comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring the own vehicle information of a target vehicle in a first running state, the peripheral vehicle information generated by the target vehicle detecting the peripheral vehicle and the road test state information sent by a road traffic system;

the first sending module is used for sending the surrounding vehicle information, the self-vehicle information and the drive test state information to a cloud platform so that the cloud platform can judge whether the surrounding vehicle forms collision risk to the target vehicle according to the surrounding vehicle information, the self-vehicle information and the drive test state information, and if yes, early warning information and basic information are generated and sent to the vehicle-end platform;

the first receiving module is used for receiving the basic information and the early warning information sent by the cloud platform;

a first generating module, configured to generate control information of the target vehicle in a second driving state according to at least the basic information, the warning information, and a finite state machine model, where the finite state machine model defines a transition condition between multiple states;

and the control module is used for converting the running state of the target vehicle from the first running state to a second running state according to the control information.

9. A cloud platform, the cloud platform comprising:

the second receiving module is used for receiving the own vehicle information of the target vehicle in the first running state, which is sent by the vehicle-end platform, and the peripheral vehicle information and the road test state information which are generated by the target vehicle for detecting the peripheral vehicle;

the judging module is used for judging whether the peripheral vehicle forms collision risks to the target vehicle according to the peripheral vehicle information, the own vehicle information and the drive test state information;

the second generation module is used for generating early warning information and basic information when judging that the surrounding vehicle judges that the surrounding vehicle forms a collision risk to the target vehicle according to the surrounding vehicle information, the own vehicle information and the drive test state information;

the second sending module is used for sending the early warning information and the basic information to the vehicle-end platform, so that the vehicle-end platform generates control information in a second driving state according to the early warning information, the basic information and a finite-state machine model, and converts the driving state of the target vehicle from the first driving state to a second driving state according to the control information, wherein the finite-state machine model defines conversion conditions among multiple states.

10. A computer storage medium, characterized in that the computer storage medium stores a computer program, which is executed by a processor to perform the vehicle collaborative risk avoiding method according to claims 1-7.