Collision early warning method, vehicle-mounted terminal, and storage medium

Abstract

The embodiment of the present disclosure provides a collision early warning method, an in-vehicle terminal, and a storage medium, which belong to the field of smart cars. The method includes the steps of: acquiring a map message MAP, status information of a host vehicle, and basic safety messages BSM of multiple distant vehicles; judging whether the host vehicle is about to enter an intersection based on the MAP and the status information; if the host vehicle is about to enter an intersection, selecting a target distant vehicle that has a collision risk with the host vehicle in the intersection from among the multiple distant vehicles based on the MAP, the status information, and the BSM of each distant vehicle; and outputting collision early warning information when it is predicted that the host vehicle will collide with one of the target distant vehicles during the process from when the host vehicle enters the intersection to when the host vehicle leaves the intersection. The present disclosure significantly improves the accuracy of vehicle collision risk detection and early warning.

Description

[Technical field]

[0001] This disclosure is based on and claims priority to Chinese patent application CN202210334288.0, filed on March 31, 2022, entitled "Collision early warning method, on-board terminal, and storage medium," the disclosure of which is incorporated herein by reference in its entirety.

[0002] The present disclosure relates to the technical field of smart cars, and in particular to a collision early warning method, an in-vehicle terminal, and a storage medium. [Background technology]

[0003] With the popularity of vehicles and the development of vehicle Internet technology, the application and algorithms of vehicle to X (V2X) wireless communication technology are attracting more and more attention. The most important application function is the early warning function of vehicles, that is, using V2X technology to warn drivers of potential dangers in advance and reduce traffic accidents.

[0004] For example, intersections are prone to traffic accidents due to complex road conditions and frequent lane changes. Existing V2X technology performs collision detection for vehicles entering an intersection, and if there is a collision risk, it promptly warns the driver, so that the driver can make driving decisions in advance and avoid traffic accidents. Currently, the collision risk is calculated for each vehicle at the intersection, which results in too much calculation and wastes resources. In addition, existing risk early warnings are not accurate enough. When a vehicle is away from the intersection, repeated advance warnings will interfere with the driver's driving. When a vehicle approaches an intersection, the risk early warning will be delayed, and the driver will not be able to change his driving strategy or apply the brakes in time. Therefore, how to accurately issue a collision early warning to vehicles passing through an intersection is currently an issue that needs to be resolved as soon as possible. Summary of the Invention [Problem to be solved by the invention]

[0005] An embodiment of the present disclosure provides an early collision warning method, an in-vehicle terminal, and a storage medium for issuing an accurate early collision warning to a vehicle passing through an intersection. [Means for solving the problem]

[0006] According to a first aspect, an embodiment of the present disclosure provides a collision early warning method, comprising: obtaining a map message MAP, status information of the host vehicle, and basic safety messages BSM of a plurality of distant vehicles; determining whether the vehicle is about to enter an intersection based on the MAP and the state information; When the host vehicle is about to enter an intersection, selecting a target distant vehicle that has a collision risk with the host vehicle in the intersection from among the multiple distant vehicles based on the MAP, the state information, and a BSM for each distant vehicle; and a step of outputting collision early warning information when it is predicted that the host vehicle will collide with one of the target distant vehicles during the process from when the host vehicle enters the intersection to when the host vehicle exits the intersection.

[0007] According to a second aspect, an embodiment of the present disclosure includes: The present invention further provides an in-vehicle terminal including a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for connecting and communicating between the processor and the memory, the computer program, when executed by the processor, realizing any step of the early collision warning method according to the specification of the present disclosure.

[0008] According to a third aspect, an embodiment of the present disclosure includes: A computer-readable storage medium for storage, comprising: There is further provided a storage medium having stored thereon one or more programs that, when executed by one or more processors, implement the steps of the early collision warning method according to the present disclosure. [Brief description of the drawings]

[0009] [Figure 1] 1 is a flow diagram of an early collision warning method according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a schematic flow diagram of the sub-steps of the early collision warning method of FIG. 1; [Diagram 3] FIG. 2 is a schematic diagram of an example scenario of an early collision warning method according to an embodiment of the present disclosure. [Figure 4] FIG. 2 is a schematic diagram of another scenario of the collision early warning method according to an embodiment of the present disclosure; [Diagram 5] FIG. 2 is a schematic diagram of another scenario of the collision early warning method according to an embodiment of the present disclosure; [Figure 6] FIG. 2 is a schematic diagram of another scenario of the collision early warning method according to an embodiment of the present disclosure; [Figure 7] FIG. 2 is a schematic block diagram of a configuration of an in-vehicle terminal according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the technical solutions in the embodiments of the present disclosure will be clearly and completely described with reference to the drawings in the embodiments of the present disclosure, but it is clear that the described embodiments are only a part of the embodiments of the present disclosure, and are not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative labor belong to the protection scope of the present disclosure.

[0011] The flowcharts illustrated in the drawings are merely illustrative and do not necessarily include all contents and operations / steps, and do not necessarily need to be performed in the order described. For example, some operations / steps may be separated, combined, or partially combined, and the actual execution order may be changed according to actual circumstances.

[0012] The terms used in the specification of the present disclosure are for the purpose of describing particular embodiments and are not intended to be limiting of the present disclosure. As used in this specification and the appended claims, the singular forms "a," "one," and "the" are intended to include the plural forms unless the context clearly dictates otherwise.

[0013] The embodiments of the present disclosure provide a collision early warning method, an on-board terminal, and a storage medium. In particular, the collision early warning method can be applied to an on-board terminal, which is a device based on vehicle to X (V2X) wireless communication technology, for example, an on-board unit (OBU).

[0014] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the drawings. The following examples and features in the examples may be combined with each other unless they are inconsistent.

[0015] Please refer to FIG. 1, which is a flow diagram of an early collision warning method according to an embodiment of the present disclosure.

[0016] As shown in FIG. 1, this early collision warning method includes steps S101 to S104.

[0017] Step S101: A map message MAP, status information of the host vehicle, and basic safety messages BSM of a plurality of distant vehicles are obtained.

[0018] Here, the map message (MAP) is broadcast by the roadside unit (RSU) to transmit map information of a local area to vehicles, and the MAP includes local area intersection messages, section messages, lane messages, connection relationships between roads, etc. The status information of the host vehicle (HV) is the basic driving status information of the host vehicle, and this status information includes information such as longitude and latitude, speed, yaw angle, and acceleration. As for the basic safety message (BSM) of the remote vehicle (RV), this BSM includes the speed, steering, brake, double flash, and position information of the remote vehicle.

[0019] In one embodiment, by acquiring a map message broadcast by the roadside unit, the MAP at the position of the vehicle and the BSM of distant vehicles within a preset area of ​​the vehicle can be acquired. This BSM is each BSM broadcast by each distant vehicle. The vehicle receives the BSM broadcast by each distant vehicle, and the status information of the vehicle is acquired from a control device of the vehicle, which may be set according to the actual situation, but is not particularly limited in this embodiment, and may be, for example, a central control system of the vehicle. This preset area may be set according to the actual situation, but is not particularly limited in this embodiment, and may be set within 500 m from the position of the vehicle. The roadside unit or the cloud may receive radar or sensor data, create a BSM based on the data, and broadcast the BSM to allow the vehicle to acquire the broadcasted BSM.

[0020] Step S102: Based on the MAP and the state information, it is determined whether the host vehicle is about to enter an intersection.

[0021] This intersection may be a three-way intersection, a crossroads intersection, a five-way intersection, or other type of intersection, and is not particularly limited in this embodiment. However, in this embodiment, a crossroads intersection is used as an example for ease of explanation.

[0022] In one embodiment, the state information includes the yaw angle of the vehicle, which is the angle between the driving direction of the vehicle and the true north direction, and the MAP includes the angle between each road in the area where the vehicle is located and the road in the true north direction. The angle difference between the yaw angle of the vehicle and the road angle of each road is determined, the angle difference between the vehicle and each road is obtained, and the road corresponding to the minimum angle difference is determined as the driving road of the vehicle. Based on the position information of the vehicle and the MAP, it is determined whether or not there is an intersection within a preset distance on the driving road of the vehicle, and if it is determined that there is an intersection within the preset distance on the driving road of the vehicle, it is determined that the vehicle is about to enter the intersection. Here, this preset distance may be set according to time, but is not particularly limited in this embodiment. This preset distance may be set to, for example, 150 m. By determining the driving road of the vehicle and determining whether or not there is an intersection within a preset distance on this driving road, it is possible to accurately determine whether or not the vehicle will enter the intersection.

[0023] As an example, the yaw angle of the host vehicle is 100°, the area in which the host vehicle is located includes roads 1, 2, 3, and 4, the angle between road 1 and the true north direction is 95°, the angle between road 2 and the true north direction is 185°, the angle between road 3 and the true north direction is 275°, and the angle between road 4 and the true north direction is 5°. As can be seen from this, the angle between the host vehicle and road 1 is 5°, the angle between the host vehicle and road 2 is 95°, the angle between the host vehicle and road 3 is 185°, and the angle between the host vehicle and road 4 is 95°. Since the angle between the host vehicle and road 1 is the smallest, road 1 is the road on which the host vehicle is traveling. It is determined whether or not there is an intersection on road 1 within 150 m of the traveling direction of the host vehicle, and if there is an intersection on road 1 within 150 m of the traveling direction of the host vehicle, it is determined that the host vehicle is about to enter the intersection.

[0024] In one embodiment, the step of determining whether the vehicle is about to enter an intersection includes the steps of acquiring the vertical distance between the vehicle and each lane in the road, obtaining the lane distance from the vehicle to each lane, determining the lane corresponding to the minimum lane distance as the lane in which the vehicle is traveling, determining whether the lane in which the vehicle is traveling is within a preset distance based on the position information of the vehicle and the MAP, and determining that the vehicle is about to enter the intersection if the lane in which the lane in which the vehicle is traveling is within a preset distance. Here, the vertical distance between the vehicle and each lane in the road means the distance between the center point of the vehicle and the center line of the lane. Note that, if the road on which the vehicle is traveling has one lane, the road on which the vehicle is traveling is the lane on which the vehicle is located. The lane on which the vehicle is traveling can also be determined by the above method. By determining the vertical distance between the vehicle and each lane, the lane on which the vehicle is traveling can be accurately known.

[0025] As an example, a road includes lanes 1, 2, and 3, and the vertical distance between the host vehicle and lane 1 is 3.1 m, the vertical distance between the host vehicle and lane 2 is 0.1 m, and the vertical distance between the host vehicle and lane 3 is 2.9 m. The vertical distance between the host vehicle and lane 2, 0.1 m, is the smallest of the distances between the host vehicle and each lane. That is, the host vehicle is traveling in lane 2, and based on the position information of the host vehicle and the MAP, it is determined whether or not there is an intersection within a distance of 150 m in lane 2, and if it is determined that there is an intersection within a distance of 150 m in lane 2, it is determined that the host vehicle is about to enter the intersection.

[0026] In one embodiment, Global Positioning System (GPS) data on the vehicle's travel is acquired, and based on this data and a map, it is determined whether or not there is an intersection within a preset distance in the direction in which the vehicle is traveling. If it is determined that there is an intersection within a preset distance in the direction in which the vehicle is traveling, it is determined that the vehicle is about to enter the intersection.

[0027] Step S103: When the host vehicle is about to enter an intersection, a target distant vehicle that has a collision risk with the host vehicle within the intersection is selected from the multiple distant vehicles based on the MAP, the status information, and the BSM for each distant vehicle.

[0028] Here, the target distant vehicle is a distant vehicle that has a high risk of colliding with the host vehicle in the intersection.

[0029] In one embodiment, as shown in FIG. 2, step S103 includes sub-steps S1031 to S1032.

[0030] Sub-step S1031: Based on the MAP, the state information, and the BSM of each of the distant vehicles, distant vehicle candidates that have a collision risk with the host vehicle within the intersection are selected from among a plurality of distant vehicles.

[0031] A distant vehicle candidate is a distant vehicle that has an intersection between the travel path of the distant vehicle and the travel path of the host vehicle.

[0032] In one embodiment, based on the MAP, the state information, and the BSM for each distant vehicle, a plurality of distant vehicles are grouped to obtain a plurality of distant vehicle groups, a collision detection model for the intersection is obtained, a collision detection condition corresponding to each of the distant vehicle groups is obtained from the collision detection model, and each distant vehicle of the distant vehicle group is selected according to the collision detection condition corresponding to each of the distant vehicle groups to obtain one or more distant vehicle candidates that have a collision risk with the host vehicle in the intersection. Here, this collision detection model is set in advance based on a collision simulation, and this collision simulation may be set according to the actual situation, but is not particularly limited in this embodiment. By grouping the distant vehicles, the efficiency of collision detection can be improved, and by selecting each distant vehicle group according to the collision detection condition, the accuracy of selecting distant vehicle candidates can be improved.

[0033] In one embodiment, a method for grouping a plurality of distant vehicles based on the MAP, the state information, and the BSM for each distant vehicle to obtain a plurality of distant vehicle groups may be as follows: The state information includes the yaw angle of the host vehicle, and the BSM of the distant vehicle includes the yaw angle of the distant vehicle. The number of distant vehicle groups is determined based on the MAP, a first yaw angle difference between the yaw angle of the host vehicle and the yaw angle of each distant vehicle is determined, and distant vehicles corresponding to a first yaw angle difference that is equal to or greater than a first preset difference and equal to or less than a second preset difference are aggregated into a first distant vehicle group. A first deviation angle between a connecting line between the host vehicle and the distant vehicle and a true north direction is determined, and distant vehicles that have not been aggregated are aggregated into a second distant vehicle group and a third distant vehicle group based on the first deviation angle and the yaw angle of the host vehicle. Here, the first preset difference and the second preset difference may be set according to an actual situation, and are not particularly limited thereto in this embodiment.

[0034] In one embodiment, the method of consolidating the unconsolidated distant vehicles into the second distant vehicle group and the third distant vehicle group based on the first deviation angle and the yaw angle of the host vehicle may be as follows: determine the difference between the first deviation angle and the yaw angle of the host vehicle, obtain the second yaw angle difference, consolidate the distant vehicles corresponding to the second yaw angle difference that is greater than the third preset difference and smaller than the fourth preset difference into the second distant vehicle group, and consolidate the distant vehicles corresponding to the second yaw angle difference that is greater than the fifth preset difference and smaller than the sixth preset difference into the third distant vehicle group. Here, the third preset difference, the fourth preset difference, the fifth preset difference, and the sixth preset difference may be set according to the actual situation, and are not particularly limited thereto in this embodiment.

[0035] As an example, as shown in FIG. 3, a method of selecting each distant vehicle of the distant vehicle group according to a collision detection condition corresponding to each distant vehicle group to obtain one or more distant vehicle candidates having a collision risk with the host vehicle in the intersection may be as follows: The distant vehicle groups include a first distant vehicle group, a second distant vehicle group, and a third distant vehicle group, where the first distant vehicle group includes a distant vehicle 1, the second distant vehicle group includes a distant vehicle 2, and the third distant vehicle group includes a distant vehicle 3. When the host vehicle A turns right, the distant vehicles 1, 2, and 3 are selected according to the collision detection condition, and the distant vehicle candidates having a collision risk with the host vehicle in the intersection include the distant vehicles 2 and 3. When the host vehicle A travels straight, the distant vehicles 1, 2, and 3 are selected according to the collision detection condition, and the distant vehicle candidates having a collision risk with the host vehicle in the intersection include the distant vehicles 1, 2, and 3. When the host vehicle A turns left, distant vehicle 1, distant vehicle 2, and distant vehicle 3 are selected according to the collision detection conditions, and candidate distant vehicles that are at risk of collision with the host vehicle at the intersection include distant vehicle 1, distant vehicle 2, and distant vehicle 3.

[0036] As an example, a method for selecting each distant vehicle of the distant vehicle group according to a collision detection condition corresponding to each distant vehicle group to obtain one or more distant vehicle candidates having a collision risk with the host vehicle in the intersection may be as follows: The distant vehicle groups include a first distant vehicle group, a second distant vehicle group, and a third distant vehicle group, the first distant vehicle group includes a distant vehicle 1, the second distant vehicle group includes a distant vehicle 2, and the third distant vehicle group includes a distant vehicle 3. As shown in FIG. 3, when the host vehicle A turns right, according to the collision detection conditions corresponding to the distant vehicles in the collision detection model, the distant vehicle 1 includes going straight, turning left, and turning right, the distant vehicle 2 includes going straight, turning left, and turning right, the distant vehicle 3 includes going straight, turning left, and turning right, the distant vehicle 2 has a collision intersection with the host vehicle A when turning left, and the distant vehicle 3 has a collision intersection with the host vehicle A when going straight, and when the host vehicle A turns right, the distant vehicle candidates include the distant vehicle 2 and the distant vehicle 3. Here, the black circle mark in the figure indicates the collision point between the host vehicle and the distant vehicle.

[0037] As shown in FIG. 4, when the host vehicle A is traveling straight, the distant vehicle 1 includes traveling straight, turning left, and turning right, the distant vehicle 2 includes traveling straight, turning left, and turning right, the distant vehicle 3 includes traveling straight, turning left, and turning right, and the distant vehicle 1 has an intersection with the host vehicle A in all cases of turning right, traveling straight, and turning left, the distant vehicle 2 has an intersection with the host vehicle A in the case of turning left and traveling straight, and the distant vehicle 3 has an intersection with the host vehicle A in the case of traveling straight and turning left. When the host vehicle A is traveling straight, the distant vehicle candidates include the distant vehicle 1, the distant vehicle 2, and the distant vehicle 3. Here, the black circle mark point in the figure indicates the collision point between the host vehicle and the distant vehicle.

[0038] As shown in FIG. 5, when the host vehicle A turns left, the distant vehicle 1 includes going straight, turning left, and turning right, the distant vehicle 2 includes going straight, turning left, and turning right, the distant vehicle 3 includes going straight, turning left, and turning right, the distant vehicle 1 has an intersection with the host vehicle A in both cases of going straight and turning left, the distant vehicle 2 has an intersection with the host vehicle A in both cases of turning left, going straight, and turning right, and the distant vehicle 3 has an intersection with the host vehicle A in both cases of turning left and going straight. When the host vehicle A turns left, the distant vehicle candidates include the distant vehicle 1, the distant vehicle 2, and the distant vehicle 3. Here, the black circle mark point in the figure indicates the collision point between the host vehicle and the distant vehicle.

[0039] Sub-step S1032: Based on the MAP, the state information, and the BSM for each of the distant vehicle candidates, a target distant vehicle that has a collision risk with the host vehicle within the intersection is selected from the multiple distant vehicle candidates.

[0040] In one embodiment, a collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection is determined based on the MAP, the state information, and the BSM for each distant vehicle candidate, and a target distant vehicle that has a collision risk with the host vehicle is determined from among the multiple distant vehicle candidates based on the collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection. By determining the collision risk point between the host vehicle and the distant vehicle candidate and determining the target distant vehicle that has a collision risk with the host vehicle based on the risk point, the accuracy of risk early warning is improved.

[0041] In one embodiment, a method for determining a collision risk point between the host vehicle and each of the distant vehicle candidates in an intersection based on a MAP, state information, and a BSM for each distant vehicle candidate may be as follows: Based on the MAP and state information, a lane in which the host vehicle is located is determined from among a plurality of lanes of the intersection, based on the MAP and a BSM for each distant vehicle candidate, a lane in which each of the distant vehicle candidates is located is determined from among a plurality of lanes of the intersection, based on the MAP, steering information of the lane in which the host vehicle is located and steering information of the lane in which each of the distant vehicle candidates is located is determined, and based on the steering information of the lane in which the host vehicle is located and steering information of the lane in which each of the distant vehicle candidates is located, a collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection is determined. By determining the lane of the host vehicle and the lane of the distant vehicle candidate, a collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection can be accurately determined based on the steering information of the lane in which the host vehicle is located and the steering information of the lane in which the distant vehicle is located.

[0042] In one embodiment, a method for determining a collision risk point between the host vehicle and each of the distant vehicle candidates in an intersection based on steering information of the lane in which the host vehicle is located and steering information of the lane in which each of the distant vehicle candidates is located may be as follows: Based on the steering information of the lane in which the host vehicle is located and the steering information of the lane in which the distant vehicle candidate is located, an intersection between the lane in which the host vehicle is located and the lane in which the distant vehicle is located is determined as a collision risk point between the host vehicle and each of the distant vehicles in the intersection.

[0043] In one embodiment, a method for determining a target distant vehicle having a collision risk with the host vehicle from among a plurality of distant vehicle candidates based on the collision risk points between the host vehicle and each of the distant vehicle candidates in an intersection may be as follows. For each collision risk point, a first collision time at which the host vehicle reaches the collision risk point and a second collision time at which the distant vehicle candidate corresponding to the collision risk point reaches the collision risk point are determined, and if the difference between the first collision time and the second collision time is equal to or less than a preset threshold, the distant vehicle candidate corresponding to the collision risk point is determined as the target distant vehicle. Here, the preset threshold may be set according to the actual situation, but is not particularly limited in this embodiment. The preset threshold may be set to, for example, 0.2 seconds. The time at which the host vehicle and the distant vehicle candidate reach the collision risk point are determined, and if the time difference at which the host vehicle and the distant vehicle candidate reach the collision risk point is equal to or less than a preset threshold, it is determined that there is a possibility that the host vehicle and the distant vehicle candidate will collide, and the distant vehicle candidate is determined as the target distant vehicle.

[0044] JPEG2025508116000002.jpg55170

[0045] In one embodiment, the method for determining the distance that the host vehicle will reach the collision risk point based on the MAP and the position of the host vehicle may be as follows: Based on the MAP, determine a first distance between the host vehicle and the stop line position of the intersection, and a second distance between the stop line position and the collision risk point, and add the first distance and the second distance to obtain the distance that the host vehicle will reach the collision risk point. Here, the stop line position is the stop line of the traffic light where the lane in which the host vehicle is located meets the intersection. By dividing the distance between the host vehicle and the collision risk point into two calculations, the calculation accuracy of the distance that the host vehicle will reach the collision risk point can be improved.

[0046] As an example, the first collision time when the host vehicle reaches the collision risk point is 10.2 seconds, the second collision time when the distant vehicle candidate reaches the collision risk point is 10 seconds, the difference between the first collision time of 10.2 seconds and the second collision time of 10 seconds is 0.2 seconds, the preset threshold is 0.5 seconds, and the difference between the first collision time of 10.2 seconds and the second collision time of 10 seconds, which is 0.2 seconds, is less than 0.5 seconds, so the distant vehicle candidate is determined to be the target distant vehicle.

[0047] Step S104: If it is predicted that the host vehicle will collide with one of the target distant vehicles during the process from when the host vehicle enters the intersection to when the host vehicle exits the intersection, output early collision warning information.

[0048] The early warning information may be set according to the actual situation, and is not particularly limited in this embodiment, but may be, for example, a collision sound or a hint sound to alert the driver to slow down and drive slowly.

[0049] In one embodiment, after the host vehicle enters the intersection, a first travel trajectory of the host vehicle within the intersection and a second travel trajectory of the target distant vehicle within the intersection are generated, and whether or not the host vehicle will collide with the target distant vehicle is predicted based on the first travel trajectory and the second travel trajectory. If it is predicted that the host vehicle will collide with the target distant vehicle, early warning information is output. Since the travel trajectories are generated and it is possible to accurately determine whether or not the host vehicle will collide with the target distant vehicle based on the travel trajectory, the accuracy of the collision early warning is greatly improved.

[0050] In one embodiment, after the host vehicle enters the intersection, a method for generating a first driving trajectory of the host vehicle in the intersection may be as follows: A preset linear fitting rule is obtained, and based on the preset linear fitting rule, the speed, acceleration, and angular velocity of the host vehicle at the next time point are predicted from the speed, acceleration, and angular velocity of the host vehicle at the previous time point, and a first driving trajectory is generated from the speed, acceleration, and angular velocity at each time point. Here, the preset linear fitting rule is a pre-trained linear fitting, and the linear fitting rule may be set according to the actual situation, but is not particularly limited in this embodiment. Based on the linear fitting rule and the speed, acceleration, and angular velocity at each time point, the first driving trajectory of the host vehicle in the intersection can be accurately generated.

[0051] In addition, the second travel path of the target distant vehicle within the intersection may refer to the first travel path of the host vehicle within the intersection, so a description of this will be omitted.

[0052] In one embodiment, a method for predicting whether or not a collision will occur between the host vehicle and a distant target vehicle based on a first travel trajectory and each of the second travel trajectories may be as follows: A first rectangular parameter of the host vehicle on the first travel trajectory is determined, and a second rectangular parameter of the distant target vehicle on the second travel trajectory is determined. If it is determined that there is an overlapping portion between the vector projection of the first rectangular parameter and the vector projection of the second rectangular parameter, it is determined that a collision will occur between the host vehicle and the distant target vehicle.

[0053] JPEG2025508116000003.jpg120170

[0054] In the collision early warning method in the above embodiment, the map message MAP, the status information of the host vehicle, and the basic safety messages BSM of multiple distant vehicles are obtained, and then, based on the MAP and the status information, it is determined whether the host vehicle is about to enter an intersection. If the host vehicle is about to enter an intersection, based on the MAP, the status information, and the BSM of each distant vehicle, a target distant vehicle that has a collision risk with the host vehicle in the intersection is selected from the multiple distant vehicles, and if it is predicted that the host vehicle will collide with one target distant vehicle during the process from when the host vehicle enters the intersection to when the host vehicle leaves the intersection, collision early warning information is output. By selecting a distant vehicle that has a collision risk from the multiple distant vehicles when the host vehicle is about to enter an intersection, the use of calculation power for the collision risk can be reduced and the detection efficiency can be improved, and by predicting whether the host vehicle will collide with the target distant vehicle, the accuracy of collision risk detection can be improved.

[0055] Referring to FIG. 7, FIG. 7 is a schematic structural block diagram of an in-vehicle terminal according to an embodiment of the present disclosure.

[0056] 7, the in-vehicle terminal 200 includes a processor 201, a memory 202, and a V2X protocol module 203, and the processor 201, the memory 202, and the V2X protocol module 203 are connected via a bus 204 such as an I2C (Inter-integrated Circuit) bus. The V2X protocol module 203 is for processing data of the V2X protocol.

[0057] Specifically, the processor 201 is for providing calculation and control capabilities that support the operation of the entire in-vehicle terminal. The processor 201 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, the general-purpose processor may be a microprocessor, any conventional processor, etc.

[0058] Specifically, the memory 202 may be a flash chip, a read-only memory (ROM), a magnetic disk, an optical disk, a USB memory, a removable hard disk, and the like.

[0059] As will be understood by those skilled in the art, the configuration shown in FIG. 7 is merely a block diagram showing a portion of the configuration relating to an embodiment of the present disclosure, and does not limit the vehicle-mounted terminal to which the embodiment of the present disclosure can be applied; a specific vehicle-mounted terminal may have more or fewer components than those shown in the figure, may combine some of the components, or may have a different component arrangement.

[0060] The processor executes a computer program stored in the memory, and by executing the computer program, realizes any of the early collision warning methods according to the embodiments of the present disclosure.

[0061] In one embodiment, the processor executes a computer program stored in the memory, and by executing the computer program, achieves the following steps:

[0062] It obtains map messages MAP, status information of the vehicle itself, and basic safety messages BSM of multiple distant vehicles. Based on the MAP and the state information, it is determined whether the host vehicle is about to enter an intersection. When the vehicle is about to enter an intersection, a target distant vehicle that has a risk of collision with the vehicle within the intersection is selected from the multiple distant vehicles based on the MAP, the status information, and the BSM for each distant vehicle. When it is predicted that the host vehicle will collide with one of the target distant vehicles during the process from when the host vehicle enters the intersection to when the host vehicle exits the intersection, early collision warning information is output.

[0063] In one embodiment, when the processor realizes the step of selecting a target distant vehicle that has a collision risk with the host vehicle in the intersection from among the multiple distant vehicles based on the MAP, the state information, and the BSM for each distant vehicle, the processor: selecting, from among the plurality of distant vehicles, a distant vehicle candidate that has a collision risk with the host vehicle at the intersection based on the MAP, the state information, and a BSM for each distant vehicle; This is used to realize a step of selecting a target distant vehicle that has a collision risk with the host vehicle within the intersection from among the multiple distant vehicle candidates based on the MAP, the status information, and the BSM for each distant vehicle candidate.

[0064] In one embodiment, when the processor realizes the step of selecting a distant vehicle candidate that has a collision risk with the host vehicle in the intersection from among the plurality of distant vehicles based on the MAP, the processor grouping the plurality of distant vehicles based on the MAP, the state information, and the BSM for each distant vehicle to obtain a plurality of distant vehicle groups; obtaining a collision detection model for the intersection, and obtaining a collision detection condition corresponding to each of the distant vehicle groups from the collision detection model; This is used to realize a step of selecting each distant vehicle in the distant vehicle group according to a collision detection condition corresponding to each of the distant vehicle groups, and obtaining one or more candidate distant vehicles that have a collision risk with the host vehicle within the intersection.

[0065] In one embodiment, when the processor realizes the step of selecting a target distant vehicle that has a collision risk with the host vehicle in the intersection from among the multiple distant vehicle candidates based on the MAP, the state information, and the BSM for each of the distant vehicle candidates, the processor: determining a collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection based on the MAP, the state information, and a BSM for each of the distant vehicle candidates; This is used to realize a step of determining a target distant vehicle that has a collision risk with the own vehicle from among a plurality of distant vehicle candidates based on the collision risk points between the own vehicle and each of the distant vehicle candidates within the intersection.

[0066] In one embodiment, when the processor realizes the step of determining a collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection based on the MAP, the state information, and the BSM for each of the distant vehicle candidates, the processor: determining a lane in which the host vehicle is located from among a plurality of lanes at the intersection based on the MAP and state information; determining a lane in which each of the distant vehicle candidates is located from among a plurality of lanes of the intersection based on the MAP and the BSM for each of the distant vehicle candidates; determining steering information of a lane in which the host vehicle is located and steering information of a lane in which each of the distant vehicle candidates is located based on the MAP; This is used to realize a step of determining collision risk points between the host vehicle and each of the distant vehicle candidates within the intersection based on steering information of the lane in which the host vehicle is located and steering information of the lanes in which each of the distant vehicle candidates is located.

[0067] In one embodiment, when the processor realizes a step of determining a target distant vehicle that has a collision risk with the host vehicle from among the multiple distant vehicle candidates based on a collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection, the processor determining, for each of the collision risk points, a first collision time at which the host vehicle reaches the collision risk point, and a second collision time at which the distant vehicle candidate corresponding to the collision risk point reaches the collision risk point; When the difference between the first collision time and the second collision time is less than or equal to a predetermined threshold, the distant vehicle candidate corresponding to the collision risk point is determined as a target distant vehicle.

[0068] In one embodiment, the processor further comprises: generating a first travel path of the host vehicle within the intersection and a second travel path of the target distant vehicle within the intersection after the host vehicle enters the intersection; and predicting whether or not the host vehicle and the target distant vehicle will collide based on the first travel path and each of the second travel paths.

[0069] In one embodiment, when the processor realizes the step of predicting whether or not the host vehicle and the target distant vehicle will collide based on the first travel path and each of the second travel paths, determining a first rectangle parameter of the host vehicle on the first travel path and determining a second rectangle parameter of the target distant vehicle on the second travel path; This is used to realize a step of determining that a collision will occur between the host vehicle and the target distant vehicle if it is determined that there is an overlapping portion between the vector projection of the first rectangle parameter and the vector projection of the second rectangle parameter.

[0070] In addition, as can be understood by those skilled in the art, for the specific operating procedures of the above-mentioned vehicle-mounted terminal, for the convenience of explanation and for the sake of concise explanation, reference can be made to the corresponding procedures in the embodiment of the above-mentioned collision early warning method, so that the explanation is omitted here.

[0071] An embodiment of the present disclosure is a computer readable storage medium, comprising: There is further provided a storage medium having stored thereon one or more programs that, when executed by one or more processors, implement the steps of the early collision warning method according to the present disclosure.

[0072] Here, the storage medium may be an internal storage unit of the in-vehicle terminal according to the embodiment, for example, a hard disk or memory of the in-vehicle terminal, or an external storage device of the in-vehicle terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD), or a Flash Card.

[0073] All or part of the steps in the methods, systems, functional modules or units of the apparatus disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware embodiments, the division of the functional modules or units described above does not necessarily correspond to the division of physical components. For example, one physical component may have multiple functions, or one function or step may be performed cooperatively by multiple physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processor, digital signal processor, microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (e.g., computer readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cartridges, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer. Additionally, those skilled in the art will recognize that communication media typically include computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism and may include any information delivery media.

[0074] The term "and / or" as used in the specification of this disclosure and in the appended claims means and includes any and all possible combinations of one or more of the associated listed items. It is noted that the terms "comprise," "include," or any other variation thereof herein are intended to encompass a non-exclusive inclusion such that a process, method, article, or system that includes a set of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article, or system. Unless further limited, an element defined by the phrase "comprises..." does not exclude the presence of other identical elements in the process, method, article, or system that includes the element.

[0075] The numbers of the above examples of the present disclosure are for illustrative purposes only and do not represent the superiority or inferiority of the examples. The above are only specific embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Those skilled in the art can easily think of various equivalent modifications or replacements within the technical scope of the present disclosure, and all of these modifications or replacements should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be in accordance with the scope of the claims.

Claims

1. obtaining a map message MAP, status information of the host vehicle, and basic safety messages BSM of a plurality of distant vehicles; determining whether the vehicle is about to enter an intersection based on the MAP and the state information; When the host vehicle is about to enter an intersection, selecting a target distant vehicle that has a collision risk with the host vehicle in the intersection from among the multiple distant vehicles based on the MAP, the state information, and a BSM for each distant vehicle; and a step of outputting collision early warning information when it is predicted that the host vehicle will collide with one of the target distant vehicles during the process from when the host vehicle enters the intersection to when the host vehicle exits the intersection.

2. The step of selecting a target distant vehicle that has a collision risk with the host vehicle within the intersection from among the plurality of distant vehicles based on the MAP, the state information, and the BSM for each distant vehicle, includes: selecting, from among the plurality of distant vehicles, a distant vehicle candidate that has a collision risk with the host vehicle within the intersection based on the MAP, the state information, and a BSM for each distant vehicle; The collision early warning method of claim 1, further comprising a step of selecting a target distant vehicle that has a collision risk with the host vehicle within the intersection from among the plurality of distant vehicle candidates based on the MAP, the status information, and the BSM for each distant vehicle candidate.

3. The step of selecting a distant vehicle candidate that has a collision risk with the host vehicle at the intersection from among the plurality of distant vehicles based on the MAP includes: grouping the plurality of distant vehicles based on the MAP, the status information, and a BSM for each distant vehicle to obtain a plurality of distant vehicle groups; obtaining a collision detection model for the intersection, and obtaining a collision detection condition corresponding to each of the distant vehicle groups from the collision detection model; The collision early warning method of claim 2, further comprising a step of selecting each distant vehicle in the distant vehicle group according to a collision detection condition corresponding to each distant vehicle group to obtain one or more candidate distant vehicles that are at risk of collision with the host vehicle within the intersection.

4. The step of selecting a target distant vehicle that has a collision risk with the host vehicle within the intersection from among the plurality of distant vehicle candidates based on the MAP, the state information, and a BSM for each distant vehicle candidate, includes: determining a collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection based on the MAP, the state information, and a BSM for each of the distant vehicle candidates; The collision early warning method of claim 2, further comprising a step of determining a target distant vehicle that has a collision risk with the subject vehicle from among the plurality of distant vehicle candidates based on a collision risk point between the subject vehicle and each of the distant vehicle candidates within the intersection.

5. The step of determining a collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection based on the MAP, the state information, and a BSM for each of the distant vehicle candidates includes: determining a lane in which the vehicle is located from among a plurality of lanes at the intersection based on the MAP and state information; determining a lane in which each of the distant vehicle candidates is located from among a plurality of lanes at the intersection based on the MAP and a BSM for each of the distant vehicle candidates; determining steering information of a lane in which the host vehicle is located and steering information of a lane in which each of the distant vehicle candidates is located based on the MAP; The collision early warning method of claim 4, further comprising a step of determining a collision risk point between the subject vehicle and each of the distant vehicle candidates within the intersection based on steering information of the lane in which the subject vehicle is located and steering information of the lane in which each of the distant vehicle candidates is located.

6. The step of determining a target distant vehicle having a collision risk with the host vehicle from among a plurality of distant vehicle candidates based on a collision risk point between the host vehicle and each of the distant vehicle candidates in the intersection includes: determining, for each of the collision risk points, a first collision time at which the host vehicle reaches the collision risk point, and a second collision time at which the distant vehicle candidate corresponding to the collision risk point reaches the collision risk point; The collision early warning method of claim 4, further comprising a step of determining the distant vehicle candidate corresponding to the collision risk point as a target distant vehicle when the difference between the first collision time and the second collision time is less than or equal to a predetermined threshold.

7. generating a first travel path of the host vehicle within the intersection and a second travel path of the target distant vehicle within the intersection after the host vehicle enters the intersection; The collision early warning method according to any one of claims 1 to 6, further comprising a step of predicting whether or not the subject vehicle will collide with the target distant vehicle based on the first driving trajectory and each of the second driving trajectories.

8. The step of predicting whether or not the host vehicle and the target distant vehicle will collide based on the first travel path and each of the second travel paths includes: determining a first rectangular parameter of the host vehicle on the first travel path and determining a second rectangular parameter of the target distant vehicle on the second travel path; The early collision warning method according to claim 7, further comprising a step of determining that a collision will occur between the host vehicle and the target distant vehicle when it is determined that there is an overlapping portion between the vector projection of the first rectangular parameter and the vector projection of the second rectangular parameter.

9. An in-vehicle terminal comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus realizing connection and communication between the processor and the memory, wherein the computer program, when executed by the processor, realizes the steps of the early collision warning method described in any one of claims 1 to 8.

10. A computer-readable storage medium for storage, comprising: A storage medium storing one or more programs which, when executed by one or more processors, implement the steps of the collision early warning method according to any one of claims 1 to 8.

Images