CN116853235A

CN116853235A - Collision early warning method, device, computer equipment and storage medium

Info

Publication number: CN116853235A
Application number: CN202310692998.5A
Authority: CN
Inventors: 黄德福; 黄泽坤; 杨素华; 彭兆状; 韩领涛
Original assignee: Hechuang Automotive Technology Co Ltd
Current assignee: Hechuang Automotive Technology Co Ltd
Priority date: 2023-06-12
Filing date: 2023-06-12
Publication date: 2023-10-10

Abstract

The application relates to a collision early warning method, a collision early warning device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: determining obstacle information corresponding to the target vehicle according to environment information corresponding to the environment in which the target vehicle is located; determining a collision prediction result between the target vehicle and an obstacle corresponding to the obstacle information according to the state information and the obstacle information corresponding to the target vehicle; determining predicted collision time between the target vehicle and the obstacle under the condition that the collision prediction result represents that the target vehicle collides with the obstacle; and in the case that the predicted collision time is less than or equal to the safe collision time, performing a collision early warning operation. By adopting the method, the predicted collision time between the target vehicle and the obstacle can be accurately determined based on the state information and the obstacle information of the target vehicle, and the collision early warning operation is executed based on the predicted collision time and the safe collision time, so that the accuracy of the collision early warning result is improved.

Description

Collision early warning method, device, computer equipment and storage medium

Technical Field

The present application relates to the field of automotive technology, and in particular, to a collision early warning method, apparatus, computer device, storage medium, and computer program product.

Background

With the development of unmanned technology, an active anti-collision rear-end collision technology appears, and the technology is mainly applied to an automobile safe driving system, and can be used for adopting effective preventive measures to slow down collision, improve driving safety and reduce traffic accidents when rear-end collision or collision danger occurs to the automobile.

The traditional technology adopts monocular vision to perform environment sensing and uses radar to perform target tracking.

However, the visual scheme of the traditional method is easily influenced by environmental factors, and the perception accuracy of the radar-based target tracking on the transverse target and the static target is insufficient, so that the accuracy of collision early warning results is not improved.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a collision warning method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the accuracy of collision warning results.

In a first aspect, the present application provides a collision early warning method, the method including:

determining obstacle information corresponding to a target vehicle according to environment information corresponding to the environment in which the target vehicle is located;

determining a collision prediction result between the target vehicle and an obstacle corresponding to the obstacle information according to the state information corresponding to the target vehicle and the obstacle information;

Determining a predicted collision time between the target vehicle and the obstacle in a case where the collision prediction result characterizes that the target vehicle collides with the obstacle;

executing collision early warning operation under the condition that the predicted collision time is less than or equal to the safe collision time; the safe collision time characterizes a time when no collision occurs between the target vehicle and the obstacle.

In one embodiment, the determining, according to the environmental information corresponding to the environment in which the target vehicle is located, the obstacle information corresponding to the target vehicle includes:

acquiring an environment image corresponding to the target vehicle acquired by an image acquisition device, and determining an obstacle in the environment image according to the environment image;

acquiring radar signals aiming at the obstacle, which are acquired by radio detection equipment, and determining vehicle speed information, vehicle distance information and azimuth information corresponding to the obstacle according to the radar signals; the distance information corresponding to the obstacle represents the distance between the obstacle and the target vehicle; the position information corresponding to the obstacle represents the position information of the obstacle relative to the target vehicle;

And determining the obstacle information according to the vehicle speed information corresponding to the obstacle, the vehicle distance information corresponding to the obstacle and the azimuth information corresponding to the obstacle.

In one embodiment, the determining, according to the state information corresponding to the target vehicle and the obstacle information, a collision prediction result between the target vehicle and the obstacle corresponding to the obstacle information includes:

acquiring state information corresponding to the target vehicle; the state information comprises positioning information, vehicle speed information and braking information corresponding to the target vehicle;

determining an initial motion track corresponding to the target vehicle according to the state information, and determining a real-time relative position corresponding to the obstacle according to the obstacle information;

and determining the collision prediction result according to the initial motion trail corresponding to the target vehicle and the real-time relative position corresponding to the obstacle.

In one embodiment, the method further comprises:

under the condition that the collision prediction result represents that the target vehicle collides with the obstacle, determining the predicted collision time between the target vehicle and the obstacle according to the initial motion track corresponding to the target vehicle and the real-time relative position corresponding to the obstacle;

Acquiring the safety collision time corresponding to the predicted collision time;

and executing collision early warning operation under the condition that the predicted collision time is less than or equal to the safe collision time.

In one embodiment, the acquiring the safe collision time corresponding to the predicted collision time includes:

determining relative vehicle speed information between the target vehicle and the obstacle according to the vehicle speed information corresponding to the target vehicle in the state information and the vehicle speed information corresponding to the obstacle in the obstacle information;

determining a first ratio according to the vehicle distance information corresponding to the obstacle in the obstacle information and the relative vehicle speed information; the first ratio represents the ratio between the value of the vehicle distance information corresponding to the obstacle and the value of the relative vehicle speed information;

and determining the first ratio as the safe collision time.

In one embodiment, the method further comprises:

acquiring a current braking force of the target vehicle in the case that a manual braking operation for the target vehicle is detected;

and setting the current braking force to a preset braking force threshold value under the condition that the current braking force is smaller than the preset braking force threshold value until the current speed of the target vehicle is smaller than or equal to a preset safe speed.

In a second aspect, the present application also provides a collision warning apparatus, the apparatus comprising:

the obstacle determining module is used for determining obstacle information corresponding to the target vehicle according to the environment information corresponding to the target vehicle;

the collision prediction module is used for determining a collision prediction result between the target vehicle and an obstacle corresponding to the obstacle information according to the state information corresponding to the target vehicle and the obstacle information;

a time prediction module for determining a collision time prediction result between the target vehicle and the obstacle in the case that the collision prediction result characterizes that the target vehicle collides with the obstacle;

the early warning module is used for executing collision early warning operation under the condition that the collision time prediction result is smaller than or equal to the safe collision time; the safe collision time characterizes a time when no collision occurs between the target vehicle and the obstacle.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, implements the steps of the method described above.

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method described above.

In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of the method described above.

According to the collision early warning method, the device, the computer equipment, the storage medium and the computer program product, the obstacle information corresponding to the target vehicle is determined according to the environment information corresponding to the environment where the target vehicle is located, so that the obstacle information corresponding to the obstacle possibly colliding with the target vehicle is obtained in the environment where the target vehicle is located, the collision prediction result between the target vehicle and the obstacle is determined according to the state information and the obstacle information corresponding to the target vehicle, whether each obstacle collides with the target vehicle is predicted according to the state information and the obstacle information of the target vehicle, the predicted collision time between the target vehicle and the obstacle is determined under the condition that the collision prediction result represents the collision of the target vehicle and the obstacle, the collision early warning operation is further executed under the condition that the predicted collision time is less than or equal to the safe collision time, the collision prediction result is determined based on the environment information and the environment information corresponding to the target vehicle, the collision prediction result between the target vehicle and the obstacle is determined when the collision prediction result represents the collision of the target vehicle and the obstacle, the predicted collision time between the target vehicle and the obstacle is determined, the collision time is less than or equal to the predicted collision time, and the collision early warning operation is performed on the basis of the predicted collision time between the predicted collision time and the obstacle is further improved, and the collision early warning operation is performed on the predicted on the basis of the predicted collision time.

Drawings

FIG. 1 is a diagram of an application environment of a collision warning method according to an embodiment;

FIG. 2 is a flow chart of a collision pre-warning method according to an embodiment;

FIG. 3 is a schematic diagram illustrating an implementation architecture of a collision pre-warning method according to an embodiment;

FIG. 4 is a flowchart of a collision pre-warning method according to another embodiment;

FIG. 5 is a block diagram of a collision warning apparatus according to one embodiment;

fig. 6 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The collision early warning method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the driving computer 102 communicates with the server 104 through a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The driving computer 102 determines obstacle information corresponding to the target vehicle according to the environment information corresponding to the environment in which the target vehicle is positioned; the driving computer 102 determines a collision prediction result between the target vehicle and an obstacle corresponding to the obstacle information according to the state information and the obstacle information corresponding to the target vehicle; in the case where the collision prediction result indicates that the target vehicle collides with the obstacle, the driving computer 102 determines a predicted collision time between the target vehicle and the obstacle; in the case where the predicted collision time is less than or equal to the safe collision time, the driving computer 102 performs a collision early warning operation. The driving computer can be, but not limited to, an automobile computer, a computer control module and the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.

In some embodiments, as shown in fig. 2, a collision early warning method is provided, where the method is applied to a driving computer for illustration, it can be understood that the method may also be applied to a server, and may also be applied to a system including the driving computer and the server, and implemented through interaction between the driving computer and the server. In this embodiment, the method includes the steps of:

step S202, determining obstacle information corresponding to the target vehicle according to environment information corresponding to the environment in which the target vehicle is located.

The target vehicle may refer to a vehicle that needs to perform a collision early warning operation or receive a collision early warning signal, and in practical application, the target vehicle may include a vehicle.

The environment where the target vehicle is located may refer to an environment around the target vehicle, and in practical application, the environment where the target vehicle is located may include a road.

The environmental information may refer to position information, speed information, distance information and azimuth information of each object in the environment where the target vehicle is located.

The obstacle information may be information of an obstacle that may affect the movement of the target vehicle, resulting in a change in the movement locus or movement speed of the target vehicle, or the like.

As an example, a driving computer obtains environment image information collected by a camera mounted on a target vehicle, the driving computer obtains radar signals collected by a radar mounted on the target vehicle, the driving computer performs feature extraction and visual perception on the environment image information collected by the camera mounted on the target vehicle to obtain position information of each object in the environment where the target vehicle is located, the driving computer determines speed information of each object in the environment where the target vehicle is located and distance information and azimuth information between each object and the target vehicle according to the radar signals collected by the radar mounted on the target vehicle, the driving computer determines the position information, the speed information, the distance information and the azimuth information between each object and the target vehicle in the environment where the target vehicle is located according to the position information and the speed information of each object corresponding to the environment image information and the distance information and the azimuth information between each object and the target vehicle, and in practical application, the driving computer can determine the position information, the speed information, the distance information and the azimuth information between each object and the target vehicle in the environment where the target vehicle is located as obstacle information, and the radar signals can be used as the obstacle, and the radar signals can be associated with the collected image information according to the radar signals.

Step S204, according to the state information and the obstacle information corresponding to the target vehicle, determining a collision prediction result between the target vehicle and the obstacle corresponding to the obstacle information.

The state information corresponding to the target vehicle may refer to information representing a current running or traveling state of the target vehicle, and in practical application, the state information corresponding to the target vehicle may include positioning information, speed information and braking information of the target vehicle.

The collision prediction result may refer to information indicating whether the target vehicle and the obstacle collide, and in practical application, the collision prediction result may include a forward collision prediction result and a side collision prediction result.

As an example, a driving computer determines positioning information of a target vehicle through a navigation system arranged on the target vehicle, the driving computer determines speed information and braking information (such as absolute coordinate position, speed, time information and braking acceleration information under a world coordinate system) of the target vehicle through a sensor arranged on the target vehicle, the driving computer determines state information of the target vehicle according to the positioning information, the speed information and the braking information of the target vehicle, the driving computer determines a movement track of the target vehicle when the target vehicle runs based on the speed information of the target vehicle according to the state information of the target vehicle, the driving computer determines a movement track of the target vehicle when the target vehicle runs based on the speed information corresponding to each obstacle according to the obstacle information corresponding to each obstacle, and the driving computer determines a collision prediction result between the target vehicle and each obstacle according to the movement track of the target vehicle when the target vehicle runs based on the speed information corresponding to each obstacle and the movement track of the target vehicle when the target vehicle runs based on the speed information corresponding to each obstacle.

Step S206, determining a predicted collision time between the target vehicle and the obstacle in the case where the collision prediction result indicates that the target vehicle collides with the obstacle.

The predicted collision time may be a time determined according to real-time state information of the target vehicle and real-time obstacle information of each obstacle, and in practical application, the predicted collision time may include an output result of a pre-trained relative collision time prediction model, and the real-time state information of the target vehicle and real-time obstacle information corresponding to each obstacle are input into the pre-trained relative collision time prediction model to obtain the predicted collision time between the target vehicle and the obstacle.

As an example, in the case where the collision prediction result indicates that the target vehicle collides with the obstacle, the driving computer acquires the state information of the target vehicle and the obstacle information of each obstacle in real time, and the driving computer inputs the state information of the target vehicle and the obstacle information of each obstacle into the pre-trained relative collision time prediction model to obtain the predicted collision time between the target vehicle and the obstacle.

Step S208, in the case where the predicted collision time is less than or equal to the safe collision time, a collision early warning operation is performed.

The safe collision time can represent the time when no collision occurs between the target vehicle and the obstacle, and in practical application, each obstacle has corresponding safe collision time with the target vehicle, and the target vehicle and the obstacle cannot collide outside the corresponding safe collision time.

The collision early-warning operation may be an alarm operation of a possible collision accident of the target vehicle by the pointer, and in practical application, the collision early-warning operation may include sending out a prompt tone, inducing vibration and automatically braking.

As an example, the driving computer compares the predicted collision time between the target vehicle and the obstacle with the safe collision time between the target vehicle and the obstacle, and in the case where the predicted collision time is less than or equal to the safe collision time, the driving computer performs a collision early warning operation such as: the driving computer controls the target vehicle to send out collision early warning prompt sound to remind a driver of the target vehicle to brake the vehicle, or controls the steering wheel of the target vehicle to vibrate to remind the driver of the target vehicle to brake the vehicle.

According to the collision early warning method, the obstacle information corresponding to the target vehicle is determined according to the environment information corresponding to the environment where the target vehicle is located, so that the obstacle information corresponding to the obstacle in the environment where the target vehicle is located, which is possibly collided with the target vehicle, is obtained, the collision prediction result between the target vehicle and the obstacle is determined according to the state information and the obstacle information corresponding to the target vehicle, so that whether each obstacle collides with the target vehicle is predicted according to the state information and the obstacle information of the target vehicle, the predicted collision time between the target vehicle and the obstacle is determined under the condition that the collision prediction result represents that the target vehicle collides with the obstacle, the collision early warning operation is performed under the condition that the predicted collision time is less than or equal to the safe collision time, the collision prediction result between the target vehicle and each obstacle is determined based on the environment information and the obstacle information corresponding to the environment where the target vehicle is located, the predicted collision prediction result between the target vehicle and each obstacle is determined, the predicted collision time between the target vehicle and the obstacle is determined when the collision prediction result represents that the target vehicle collides with the obstacle, the predicted collision time between the target vehicle and the obstacle is less than or equal to the safe collision time, the predicted collision time is performed, and the collision early warning operation is performed on the basis of the predicted collision time and the predicted collision time is improved, and the collision warning operation is performed timely.

In some embodiments, determining obstacle information corresponding to the target vehicle according to environment information corresponding to an environment in which the target vehicle is located includes: acquiring an environment image corresponding to a target vehicle acquired by image acquisition equipment, and determining an obstacle in the environment image according to the environment image; acquiring radar signals aiming at the obstacle, which are acquired by radio detection equipment, and determining vehicle speed information, vehicle distance information and azimuth information corresponding to the obstacle according to the radar signals; and determining the obstacle information according to the vehicle speed information corresponding to the obstacle, the vehicle distance information corresponding to the obstacle and the azimuth information corresponding to the obstacle.

The image acquisition device may be a device with an image acquisition function, which is disposed on the target vehicle, and in practical application, the image acquisition device may include a binocular 8MP integrated camera.

The environmental image may be an image of an environment where the target vehicle is located, which is acquired by the image acquisition device, and in practical application, the environmental image includes a plurality of obstacles.

The radio detection device may refer to a device for detecting radio signals, and in practical application, the radio detection device may include a millimeter wave radar.

The radar signal may refer to a radio signal collected by the radio detection device.

The vehicle speed information corresponding to the obstacle may be travel speed information corresponding to the obstacle determined according to the radar signal.

The distance information corresponding to the obstacle can represent the distance between the obstacle and the target vehicle.

The azimuth information corresponding to the obstacle can represent the position information of the obstacle relative to the target vehicle, and in practical application, the azimuth information corresponding to the obstacle can include, but is not limited to, absolute azimuth information between the target vehicle and the obstacle obtained by performing relative positioning by using information acquired by sensors such as a camera and a radar on the basis of the position information of the target vehicle acquired by the navigation positioning system.

As an example, a driving computer obtains an environment image corresponding to a target vehicle through an image acquisition device arranged on the target vehicle, the driving computer determines an obstacle in the environment image according to the environment image, the driving computer obtains a radar signal aiming at the obstacle through a radio detection device arranged on the target vehicle, the driving computer determines vehicle speed information, vehicle distance information and azimuth information corresponding to the obstacle according to the radar signal, in practical application, the driving computer determines the vehicle speed information, the vehicle distance information and the azimuth information corresponding to the obstacle by utilizing the radar signal based on a radar ranging and radar speed measuring method, and determines the obstacle information according to the vehicle speed information, the vehicle distance information and the azimuth information corresponding to the obstacle, in practical application, the millimeter wave radar can compensate the defect of insufficient image ranging precision in the process of identifying and extracting the 2D image of a camera, further, the image information (video signal) of the camera can correspondingly compensate the defect of the sensing capability of the height information of a radar sensor through feature extraction, and the image information of the camera can effectively distinguish the height information of each detected object, so that the sensing precision of the obstacle is further improved.

In the embodiment, an environment image corresponding to a target vehicle acquired by an image acquisition device is acquired, and an obstacle in the environment image is determined according to the environment image; acquiring radar signals aiming at the obstacle, which are acquired by radio detection equipment, and determining vehicle speed information, vehicle distance information and azimuth information corresponding to the obstacle according to the radar signals; according to the vehicle speed information corresponding to the obstacle, the vehicle distance information corresponding to the obstacle and the azimuth information corresponding to the obstacle, the obstacle information is determined, and the obstacle information in the environment where the target vehicle is located can be obtained through analysis based on the data acquired by the image acquisition equipment and the radio detection equipment, so that the accuracy of the obstacle information is improved, basic data is provided for collision prediction analysis, and the accuracy of collision early warning is further guaranteed.

In some embodiments, determining a collision prediction result between the target vehicle and an obstacle corresponding to the obstacle information according to the state information and the obstacle information corresponding to the target vehicle includes: acquiring state information corresponding to a target vehicle; determining an initial motion track corresponding to the target vehicle according to the state information, and determining a real-time relative position corresponding to the obstacle according to the obstacle information; and determining a collision prediction result according to the initial motion trail corresponding to the target vehicle and the real-time relative position corresponding to the obstacle.

The state information corresponding to the target vehicle may include positioning information, vehicle speed information, and braking information corresponding to the target vehicle.

The initial motion trail corresponding to the target vehicle may refer to a motion trail formed when the target vehicle runs according to the vehicle speed information in the state information of the target vehicle, and in practical application, the initial motion trail corresponding to the target vehicle includes a motion trail when the target vehicle does not collide and avoid, and when the target vehicle does not collide and avoid, the target vehicle does not change the motion states such as the vehicle speed for avoiding the obstacle.

The real-time relative position corresponding to the obstacle may refer to current relative position information of the obstacle relative to the target vehicle, and in practical application, when the obstacle is a vehicle, the real-time relative position corresponding to the obstacle may include a movement track formed when the vehicle runs according to vehicle speed information in state information of the obstacle.

As an example, a driving computer generates an initial movement track corresponding to a target vehicle by using information such as vehicle speed information, positioning information, braking information and the like in state information corresponding to a target state, generates a real-time relative position corresponding to an obstacle according to information such as vehicle speed information, azimuth information and the like in obstacle information, determines a collision prediction result between the target vehicle and the obstacle by analyzing the initial movement track corresponding to the target vehicle and the real-time relative position corresponding to the obstacle, and in practical application, the driving computer places the initial movement track corresponding to the target vehicle and the real-time relative position corresponding to the obstacle in the same coordinate system, and determines whether collision occurs between the target vehicle and the obstacle by analyzing the initial movement track corresponding to the target vehicle and the real-time relative position corresponding to the obstacle.

In this embodiment, the state information corresponding to the target vehicle is obtained; determining an initial motion track corresponding to the target vehicle according to the state information, and determining a real-time relative position corresponding to the obstacle according to the obstacle information; according to the initial motion trail corresponding to the target vehicle and the real-time relative position corresponding to the obstacle, determining a collision prediction result, determining the motion trail of the target vehicle and the motion trail of the obstacle based on the state information of the target vehicle and the obstacle information, and determining the collision prediction result based on motion trail analysis, thereby improving the accuracy of the collision prediction result.

In some embodiments, the above method further comprises: under the condition that a collision prediction result represents that a target vehicle collides with the obstacle, determining the predicted collision time between the target vehicle and the obstacle according to the initial motion track corresponding to the target vehicle and the real-time relative position corresponding to the obstacle; acquiring safety collision time corresponding to the predicted collision time; and in the case that the predicted collision time is less than or equal to the safe collision time, performing a collision early warning operation.

As an example, in the case that the collision prediction result indicates that the target vehicle collides with the obstacle, the driving computer determines the predicted collision time between the target vehicle and the obstacle according to the initial motion track corresponding to the target vehicle and the real-time relative position corresponding to the obstacle, and in practical application, the driving computer may further input the state information corresponding to the target vehicle and the obstacle information into a pre-trained relative collision time prediction model to obtain the predicted collision time between the target vehicle and the obstacle; the driving computer determines the safe collision time corresponding to the predicted collision time according to the vehicle speed information in the state information corresponding to the target vehicle, the vehicle speed information in the obstacle information and the vehicle distance information in the obstacle information, and judges whether to execute the collision prediction operation according to the magnitude relation between the predicted collision time and the safe collision time: when the predicted collision time is less than or equal to the safe collision time, the driving computer executes collision early warning operation; when the predicted collision time is longer than the safe collision time, the driving computer does not execute collision prediction operation, and the driving computer acquires the state information and the obstacle information of the target vehicle again and performs collision prediction again.

In this embodiment, under the condition that the collision prediction result indicates that the target vehicle collides with the obstacle, determining the predicted collision time between the target vehicle and the obstacle according to the initial motion track corresponding to the target vehicle and the real-time relative position corresponding to the obstacle; acquiring safety collision time corresponding to the predicted collision time; and under the condition that the predicted collision time is less than or equal to the safe collision time, performing collision early warning operation, determining the predicted collision time and the safe collision time by utilizing the motion track, and judging whether to perform the collision early warning operation or not based on the magnitude relation between the predicted collision time and the safe collision time, thereby improving the accuracy of the collision early warning.

In some embodiments, acquiring a safe collision time corresponding to the predicted collision time includes: determining relative vehicle speed information between the target vehicle and the obstacle according to the vehicle speed information corresponding to the target vehicle in the state information and the vehicle speed information corresponding to the obstacle in the obstacle information; determining a first ratio according to vehicle distance information and relative vehicle speed information corresponding to the obstacle in the obstacle information; the first ratio is determined as a safe collision time.

The relative vehicle speed information may refer to a relative movement speed between the target vehicle and the obstacle.

The first ratio may be a ratio between a value representing the vehicle distance information corresponding to the obstacle and a value representing the relative vehicle speed information.

As an example, a driving computer determines relative vehicle speed information between a target vehicle and an obstacle according to vehicle speed information corresponding to the target vehicle in the state information and vehicle speed information corresponding to the obstacle in the obstacle information, and determines a first ratio according to vehicle distance information corresponding to the obstacle in the obstacle information and the relative vehicle speed information; the first ratio is determined as a safe collision time TTC, and in practical application, the safe collision time TTC may be represented as ttc=vehicle distance/relative vehicle speed, where the vehicle distance may be a distance between the target vehicle and the obstacle, i.e. the vehicle distance information in the obstacle information, and the relative vehicle speed may be a value of the relative vehicle speed information.

In the embodiment, the relative vehicle speed information between the target vehicle and the obstacle is determined according to the vehicle speed information corresponding to the target vehicle in the state information and the vehicle speed information corresponding to the obstacle in the obstacle information; determining a first ratio according to vehicle distance information and relative vehicle speed information corresponding to the obstacle in the obstacle information; the first ratio is determined as the safe collision time, and the safe collision time can be determined based on the vehicle speed of the target vehicle and the obstacle and the distance between the target vehicle and the obstacle, so that the accuracy of the safe collision time is improved.

In some embodiments, the above method further comprises: acquiring a current braking force of the target vehicle in the case that the manual braking operation for the target vehicle is detected; and setting the current braking force as a preset braking force threshold value under the condition that the current braking force is smaller than the preset braking force threshold value until the current speed of the target vehicle is smaller than or equal to the preset safe speed.

The manual braking operation may refer to a braking operation for the target vehicle made by a driver of the target vehicle.

The current braking force may refer to a real-time braking force corresponding to the target vehicle, and in actual application, the current braking force may be obtained through a sensor disposed on the target vehicle.

The braking force threshold may be a preset threshold for judging whether the current braking force meets the requirement.

The current vehicle speed may refer to a real-time vehicle speed corresponding to the target vehicle.

The safe vehicle speed may be a vehicle speed that ensures that the target vehicle does not collide with the obstacle, and in practical application, the target vehicle does not collide with the obstacle when the target vehicle runs according to the safe vehicle speed.

As one example, when the predicted collision time between the target vehicle and the obstacle is less than or equal to the safe collision time, the driving computer controls the target vehicle to send out primary anti-collision early warning signals (such as sound, steering wheel braking, instrument icons, autonomous spot braking and the like) to warn the driver to take over, simultaneously, the brake is adjusted to a brake pre-charge state, a service computer detects an artificial braking operation (a vehicle braking operation or a vehicle steering operation made by a driver) for a target vehicle, when the traveling computer detects the manual braking operation aiming at the target vehicle, the traveling computer acquires the current braking force of the target vehicle, the traveling computer compares the current braking force with a preset braking force threshold value, under the condition that the current braking force is smaller than the preset braking force threshold value, the driving computer sets the current braking force as the preset braking force threshold value, so as to slow down the target vehicle until the current speed of the target vehicle is less than or equal to the preset safe speed, that is, in the case where the driver does not make a braking operation or a steering operation for the target vehicle (or the braking operation or the steering operation for the target vehicle made by the driver is insufficient to avoid collision of the target vehicle with an obstacle), the driving computer can apply limited autonomous braking (such as emergency braking) operation to the target vehicle according to the current speed of the target vehicle through the vehicle collision early warning system, and outputs a hazard warning signal to surrounding vehicles to avoid further collision, in practical application, the safe vehicle speed can be 0, when the safe vehicle speed is 0, the target vehicle is stationary with respect to the environment in which the target vehicle is located (e.g., the road on which the target vehicle is located).

In the present embodiment, the current braking force of the target vehicle is obtained by detecting a manual braking operation for the target vehicle; under the condition that the current braking force is smaller than a preset braking force threshold value, the current braking force is set to be the preset braking force threshold value until the current speed of the target vehicle is smaller than or equal to a preset safety speed, and the braking force of the target vehicle can be adjusted based on the current braking force of the target vehicle, so that the target vehicle is decelerated, collision between the target vehicle and an obstacle is avoided, and safety of the target vehicle is guaranteed.

As an example, as shown in fig. 3, an execution architecture diagram of a collision early warning method is provided, a driving computer acquires environmental information corresponding to an environment where a target vehicle is located through image data acquisition of a camera, the driving computer performs self-vehicle data perception through image data acquisition, feature extraction and visual perception, the driving computer acquires speed, distance and direction information of an obstacle through millimeter wave radar, thereby realizing obstacle detection, the driving computer completes vehicle positioning, matching navigation positioning data with map data and navigation information data interaction through a Global Navigation Satellite System (GNSS) and a vehicle-machine map (SDMAP), the driving computer completes road data and traffic light signal acquisition through a vehicle communication interaction technology (V2X), and each vehicle body executes information such as self-vehicle speed, gear, power, braking state and the like; in the data fusion sensing and decision-making part, the driving computer mainly performs sensing data fusion processing on data (such as image data acquired by a camera, radar signals acquired by a radar, navigation positioning data, road data, traffic lights, vehicle speed, gear, power, braking states) acquired by each sensor unit, and performs operations such as behavior prediction, task decision, scene decision, behavior decision, boundary limitation and the like, and in the planning control part, the driving computer mainly performs comprehensive judgment on the data output by the data fusion sensing and decision-making part, so as to complete operations such as track planning, execution control, driving action and the like.

As an example, as shown in fig. 4, a flow chart of a collision early warning method is provided, a driving computer continuously obtains front (rear) target information through a forward millimeter wave radar, a lateral millimeter wave radar, a forward-looking binocular camera, a round-looking camera and a rear-looking camera, the driving computer provides positioning navigation service data through a vehicle-mounted GNSS and an SDMAP, the driving computer senses road network information in advance through V2X road cooperation, the driving computer predicts states of surrounding vehicles, people, environment, obstacles and the like in advance for the vehicle, and the driving computer combines a plurality of sensor data of a power system, a braking system, a stabilizing system and the like of the vehicle to realize the acquisition of road environment and vehicle data sensing, and further identifies, extracts characteristics of and tracks the vehicle/obstacle targets in front (rear) of the vehicle and the vehicle/obstacle targets, and completes the measurement of the relative distance, azimuth and speed of the vehicle/obstacle targets; the driving computer calculates the relative speed between the target vehicle and the obstacles according to the distance, the speed, the azimuth information and the light signals of the target obstacle recognized by the millimeter wave radar and the camera, and in practical application, the relative speed required to be calculated by the driving computer comprises but is not limited to the relative speed between the target vehicle and each obstacle (right in front of or right behind) because the vehicle collision mainly occurs in the front-back direction on the current lane where the target vehicle is located; the driving computer determines the safe collision time TTC between the target vehicle and the target obstacle through a pre-trained relative collision time prediction model (the influence of other obstacles, such as the like, which are nearer to the target vehicle than the target obstacle in the motion trail of the target vehicle is not considered when the safe collision time is determined), wherein TTC=two-vehicle distance/two-vehicle relative speed, and therefore fusion and conversion of multiple sensor data are realized; judging whether the target vehicle and the target obstacle have forward collision possibility or not by the driving computer according to the GNSS navigation coordinates and the course angle of the vehicle, if the target vehicle does not have forward collision, judging that the target vehicle possibly has side collision with the target obstacle caused by the course deflection of the vehicle by the driving computer, performing track planning operation processing on the possible side collision by the driving computer, and determining the safe collision time TTC of the vehicle according to the relative driving speed between the target vehicle and the target obstacle by the driving computer; if the forward collision exists, the driving computer carries out motion trail operation processing on the possible rear-end collision or the possible front collision, and the driving computer determines the safe collision time TTC of the vehicle according to the relative driving speed between the target vehicle and the target obstacle; the driving computer calculates the predicted collision time t and the safe collision time TTC under the current condition in real time by using the relative collision time prediction model, and judges whether the predicted collision time t between the target vehicle and the target obstacle is smaller than or equal to the safe collision time TTC; when dangerous conditions (such as emergency braking of a front vehicle, obstacles and the like) occur, and the predicted collision time t between a target vehicle and the target obstacles is smaller than the safe collision time TTC, and a driving computer judges that the target vehicle possibly collides with the front vehicle/the obstacles, the driving computer sends a primary anti-collision early warning signal to a driver to prompt the driver in time, namely, a vehicle system can be utilized to warn and take over the driver through sound, steering wheel vibration, icon, autonomous spot braking and the like, and meanwhile, a brake is adjusted to a braking pre-stamping state to push a brake pad to approach a brake disc so as to provide the fastest response speed for the driver to brake; if the current predicted collision time t is greater than the safe collision time TTC, the driving computer acquires the state information and the obstacle information of the target vehicle again, and collision prediction and collision early warning are carried out again. Further, if the driving computer detects that the driver takes over to control the vehicle, the driving computer judges that the braking force of the driver is insufficient according to the driving state data fed back by the sensor, and the driving computer automatically applies the braking force to help the driver to brake (brake) to reduce the vehicle speed, avoid the occurrence of collision accidents or reduce the collision results, so as to achieve self-adaptive braking assistance; if the driver does not enter to take over the brake, the driving computer executes secondary anti-collision early warning operation, and the driving computer controls the target vehicle of the vehicle to remind the driver of collision risk through short-time primary brake; still further, when the driving computer judges that the driver does not take any braking or steering measures to avoid collision, the driving computer controls the braking to enter a state of preparing automatic emergency braking, on the premise of ensuring that the phenomenon of tire slip does not occur, and when collision danger possibly occurs, the driving computer actively transmits an oil pressure instruction to a vehicle body electronic stability system (ESP), the target vehicle cuts off or reduces the power of a Voltage Control Unit (VCU) through the coordinated work among the systems of the vehicle body, and simultaneously automatically starts a vehicle braking system, and makes limited braking or decelerating actions according to the situation to decelerate the vehicle so as to achieve the aim of slowing down the collision grade, and outputs a danger alarm signal to the vehicle behind; furthermore, the driving computer judges that the braking effect cannot avoid collision, and applies braking force to reduce the speed of the vehicle to reach the standard safe vehicle speed range so as to reduce the severity of collision or effectively reduce the damage caused by accidents; if it is judged that collision can be avoided, the driving computer applies braking force to reduce the speed of the target vehicle to 0 or keep the speed consistent with the target obstacle (such as a preceding vehicle) so as to keep running at a relatively safe distance.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a collision early-warning device for realizing the collision early-warning method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in one or more embodiments of the collision warning device provided below may refer to the limitation of the collision warning method hereinabove, and will not be repeated herein.

In one embodiment, as shown in fig. 5, there is provided a collision early warning apparatus including: an obstacle determination module 502, a collision prediction module 504, a time prediction module 506, and an early warning module 508, wherein:

the obstacle determining module 502 is configured to determine obstacle information corresponding to a target vehicle according to environmental information corresponding to the target vehicle;

a collision prediction module 504, configured to determine a collision prediction result between the target vehicle and an obstacle corresponding to the obstacle information according to the state information and the obstacle information corresponding to the target vehicle;

a time prediction module 506 for determining a collision time prediction result between the target vehicle and the obstacle in a case where the collision prediction result characterizes that the target vehicle collides with the obstacle;

the early warning module 508 is configured to perform a collision early warning operation when the collision time prediction result is less than or equal to a safe collision time; the safe collision time characterizes a time when no collision occurs between the target vehicle and the obstacle.

In an exemplary embodiment, the above-mentioned obstacle determining module 502 is specifically further configured to obtain an environmental image corresponding to the target vehicle acquired by the image acquisition device, and determine an obstacle in the environmental image according to the environmental image; acquiring radar signals aiming at the obstacle, which are acquired by radio detection equipment, and determining vehicle speed information, vehicle distance information and azimuth information corresponding to the obstacle according to the radar signals; the distance information corresponding to the obstacle represents the distance between the obstacle and the target vehicle; the position information corresponding to the obstacle represents the position information of the obstacle relative to the target vehicle; and determining the obstacle information according to the vehicle speed information corresponding to the obstacle, the vehicle distance information corresponding to the obstacle and the azimuth information corresponding to the obstacle.

In an exemplary embodiment, the collision prediction module 504 is specifically further configured to obtain state information corresponding to the target vehicle; the state information comprises positioning information, vehicle speed information and braking information corresponding to the target vehicle; determining an initial motion track corresponding to the target vehicle according to the state information, and determining a real-time relative position corresponding to the obstacle according to the obstacle information; and determining the collision prediction result according to the initial motion trail corresponding to the target vehicle and the real-time relative position corresponding to the obstacle.

In an exemplary embodiment, the collision prediction module 504 is specifically further configured to determine, when the collision prediction result indicates that the target vehicle collides with the obstacle, a predicted collision time between the target vehicle and the obstacle according to an initial motion trajectory corresponding to the target vehicle and a real-time relative position corresponding to the obstacle; acquiring the safety collision time corresponding to the predicted collision time; and executing collision early warning operation under the condition that the predicted collision time is less than or equal to the safe collision time.

In an exemplary embodiment, the collision prediction module 504 is specifically further configured to determine relative vehicle speed information between the target vehicle and the obstacle according to vehicle speed information corresponding to the target vehicle in the state information and vehicle speed information corresponding to the obstacle in the obstacle information; determining a first ratio according to the vehicle distance information corresponding to the obstacle in the obstacle information and the relative vehicle speed information; the first ratio represents the ratio between the value of the vehicle distance information corresponding to the obstacle and the value of the relative vehicle speed information; and determining the first ratio as the safe collision time.

In an exemplary embodiment, the apparatus further comprises a braking module, specifically configured to obtain a current braking force of the target vehicle in case a manual braking operation for the target vehicle is detected; and setting the current braking force to a preset braking force threshold value under the condition that the current braking force is smaller than the preset braking force threshold value until the current speed of the target vehicle is smaller than or equal to a preset safe speed.

The above-mentioned respective modules in the collision early warning apparatus may be realized in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a collision warning method. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. A collision warning method, the method comprising:

2. The method according to claim 1, wherein the determining the obstacle information corresponding to the target vehicle according to the environment information corresponding to the environment in which the target vehicle is located includes:

3. The method according to claim 1, wherein the determining a collision prediction result between the target vehicle and the obstacle corresponding to the obstacle information based on the state information corresponding to the target vehicle and the obstacle information includes:

4. A method according to claim 3, characterized in that the method further comprises:

5. The method of claim 4, wherein the obtaining the safe collision time corresponding to the predicted collision time comprises:

and determining the first ratio as the safe collision time.

6. The method according to claim 1, wherein the method further comprises:

7. A collision warning device, the device comprising:

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.