A vehicle collision warning method and system

Abstract

The application provides a vehicle collision warning method and system, and relates to the technical field of vehicles.In the method, the motion state of the ego vehicle is obtained first, wherein the motion state of the ego vehicle includes straight motion, constant-curvature motion, variable-curvature motion and static state; when the motion state of the ego vehicle is constant-curvature motion or variable-curvature motion, the running track of the ego vehicle is predicted according to the time, arc length and turning angle of the constant-curvature motion or variable-curvature motion of the ego vehicle, wherein the running track includes predicted position coordinates and a motion direction; the running track of a target vehicle is further predicted; and finally, vehicle collision warning is performed according to the running track of the ego vehicle and the running track of the target vehicle.In this way, the running track of the ego vehicle can be accurately predicted according to the time, arc length and turning angle of the constant-curvature motion or variable-curvature motion of the ego vehicle, and vehicle collision warning can be accurately performed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a vehicle collision warning method and system. BACKGROUND

[0002] With the development of technology, the coverage requirement of active safety function for urban road scene is higher and higher. For the scene of vehicle driving along the lane, the active safety obstacle avoidance function is mature. For intersection scene, especially in the scene of self-vehicle left turn or right turn, the active safety obstacle avoidance function is limited by the prediction accuracy of self-vehicle trajectory and target trajectory, and there is a problem that the collision risk cannot be accurately identified.

[0003] In summary, how to accurately perform vehicle collision warning is a problem that those skilled in the art need to solve. SUMMARY

[0004] Therefore, the present application provides a vehicle collision warning method and system, which aims to accurately perform vehicle collision warning.

[0005] In a first aspect, the present application provides a vehicle collision warning method, comprising:

[0006] obtaining a self-vehicle motion state, the self-vehicle motion state comprising straight motion, constant-curvature motion, variable-curvature motion and static state;

[0007] when the self-vehicle motion state is constant-curvature motion or variable-curvature motion, predicting a self-vehicle running trajectory according to the time, arc length and turning angle of the self-vehicle constant-curvature motion or variable-curvature motion, the running trajectory comprising a predicted position coordinate and a motion direction;

[0008] predicting a target vehicle running trajectory;

[0009] performing vehicle collision warning according to the self-vehicle running trajectory and the target vehicle running trajectory.

[0010] Optionally, the step of predicting the self-vehicle running trajectory according to the time, arc length and turning angle of the self-vehicle constant-curvature motion or variable-curvature motion comprises:

[0011] taking the time point when the self-vehicle motion state is determined as constant-curvature motion or variable-curvature motion as the starting point of timing, and calculating the time, arc length and turning angle of the self-vehicle constant-curvature motion or variable-curvature motion;

[0012] obtaining a self-vehicle speed direction at the starting point of timing;

[0013] establishing a Cartesian coordinate system by taking the projection of the center of the rear axle of the self-vehicle on the ground at the starting point of timing as the origin of the Cartesian coordinate system, taking the self-vehicle speed direction at the starting point of timing as the positive direction of the x-axis, and taking the left side direction of the self-vehicle as the positive direction of the y-axis;

[0014] predicting a running track of the ego vehicle according to the time, arc length and turning angle of the constant-curvature motion or variable-curvature motion of the ego vehicle and the Cartesian coordinate system.

[0015] Optionally, after the time, arc length and turning angle of the constant-curvature motion or variable-curvature motion of the ego vehicle are calculated, the method further comprises:

[0016] judging whether the motion state of the ego vehicle is switched, and performing anti-shake processing during the judging of the motion state switching of the ego vehicle;

[0017] if yes, obtaining the time of the motion state switching of the ego vehicle, and processing the timing and arc length of the curve motion of the ego vehicle according to the time of the motion state switching of the ego vehicle.

[0018] Optionally, the predicting of the running track of the target vehicle comprises:

[0019] obtaining a motion state of the target vehicle;

[0020] when the motion state of the target vehicle is a straight-line motion, determining that the target vehicle is in uniform motion, calculating a predicted position coordinate and speed of the target vehicle in the current Frenet coordinate system of the ego vehicle according to the speed of the straight-line motion of the target vehicle, and converting the predicted position coordinate and speed of the target vehicle into the Cartesian coordinate system of the ego vehicle to predict the running track of the target vehicle.

[0021] when the motion state of the target vehicle is a constant-curvature motion or variable-curvature motion, predicting the running track of the target vehicle according to the time, arc length and turning angle of the constant-curvature motion or variable-curvature motion of the target vehicle.

[0022] Optionally, the vehicle collision warning according to the running track of the ego vehicle and the running track of the target vehicle comprises:

[0023] performing collision risk assessment according to the relationship between the predicted position coordinate of the ego vehicle and the predicted position coordinate of the target vehicle, and the relationship between the motion direction of the ego vehicle and the motion direction of the target vehicle;

[0024] performing vehicle collision warning according to the assessment result.

[0025] Optionally, the method further comprises:

[0026] obtaining historical track data of the ego vehicle, the historical track data of the ego vehicle comprising actual position coordinates of the ego vehicle after a certain time;

[0027] obtaining a coordinate difference value by comparing the predicted position coordinates of the ego vehicle at the certain time and the actual position coordinates of the ego vehicle after the certain time;

[0028] evaluating the accuracy of the track prediction of the ego vehicle according to the coordinate difference value.

[0029] displaying a vehicle collision warning system abnormality when the accuracy is lower than a preset threshold.

[0030] In a second aspect, the present application provides a vehicle collision warning system, comprising:

[0031] a first acquisition module configured to acquire a host vehicle motion state, the host vehicle motion state comprising linear motion, constant-curvature motion, variable-curvature motion, and static state;

[0032] a first prediction module configured to predict a host vehicle running track according to a time, an arc length, and a turning angle of constant-curvature motion or variable-curvature motion of the host vehicle when the host vehicle motion state is constant-curvature motion or variable-curvature motion, the running track comprising a predicted position coordinate and a motion direction;

[0033] a second prediction module configured to predict a target vehicle running track;

[0034] a warning module configured to perform vehicle collision warning according to the host vehicle running track and the target vehicle running track.

[0035] Optionally, the first prediction module comprises:

[0036] a calculation unit configured to calculate the time, the arc length, and the turning angle of constant-curvature motion or variable-curvature motion of the host vehicle with a timing start point being when the host vehicle motion state is determined to be constant-curvature motion or variable-curvature motion;

[0037] a first acquisition unit configured to acquire a host vehicle speed direction at the timing start point;

[0038] a building unit configured to build a Cartesian coordinate system with a projection of a host vehicle rear axle center on the ground at the timing start point as an origin, with a host vehicle speed direction at the timing start point as a positive direction of an x-axis, and with a left side direction of the host vehicle as a positive direction of a y-axis;

[0039] a first prediction unit configured to predict the host vehicle running track according to the time, the arc length, and the turning angle of constant-curvature motion or variable-curvature motion of the host vehicle and the Cartesian coordinate system.

[0040] Optionally, the first prediction module further comprises:

[0041] a first processing unit configured to determine whether the host vehicle motion state is switched, and to perform anti-shake processing during the determination of the host vehicle motion state switching;

[0042] a second processing unit configured to, if yes, acquire a host vehicle motion state switching time, and to process the timing and the arc length of the curve motion of the host vehicle according to the host vehicle motion state switching time.

[0043] Optionally, the second prediction module comprises:

[0044] a second acquisition unit, configured to acquire a target vehicle motion state;

[0045] a second prediction unit, configured to, when the target vehicle motion state is linear motion, determine that the target vehicle is moving at a constant speed, calculate a target vehicle predicted position coordinate and a speed in a current Frenet coordinate system of the ego vehicle according to a speed of the linear motion of the target vehicle, and convert the target vehicle predicted position coordinate and the speed to a Cartesian coordinate system of the ego vehicle to predict a target vehicle running track;

[0046] a third prediction unit, configured to, when the target vehicle motion state is constant-curvature motion or variable-curvature motion, predict the target vehicle running track according to a time, an arc length and a turning angle of the constant-curvature motion or the variable-curvature motion of the target vehicle.

[0047] Optionally, the early warning module comprises:

[0048] an evaluation unit, configured to perform collision risk evaluation according to a relationship between the ego vehicle predicted position coordinate and the target vehicle predicted position coordinate, and a relationship between a motion direction of the ego vehicle and a motion direction of the target vehicle;

[0049] a warning unit, configured to perform vehicle collision early warning according to the evaluation result.

[0050] Optionally, the system further comprises:

[0051] a second acquisition module, configured to acquire ego vehicle historical trajectory data, the ego vehicle historical trajectory data comprising an actual ego vehicle position coordinate after a certain time;

[0052] a comparison module, configured to obtain a coordinate difference value by comparing the ego vehicle position coordinate at the prediction time and the actual ego vehicle position coordinate after the certain time;

[0053] an accuracy evaluation module, configured to evaluate the accuracy of the ego vehicle trajectory prediction according to the coordinate difference value;

[0054] an abnormality display module, configured to display vehicle collision early warning system abnormality when the accuracy is lower than a preset threshold.

[0055] In a third aspect, the present application provides a computer device, comprising a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes to make the device execute the vehicle collision early warning method of any one of the preceding first aspect.

[0056] In a fourth aspect, the present application provides a computer storage medium, wherein the computer storage medium stores codes, and when the codes are executed, a device executing the codes implements the vehicle collision warning method according to any one of the first aspect.

[0057] The present application provides a vehicle collision warning method. In the execution of the method, the self-vehicle motion state is acquired first, wherein the self-vehicle motion state includes linear motion, constant-curvature motion, variable-curvature motion and static state. When the self-vehicle motion state is constant-curvature motion or variable-curvature motion, the self-vehicle motion trajectory is predicted according to the time, arc length and turning angle of the self-vehicle constant-curvature motion or variable-curvature motion, wherein the motion trajectory includes predicted position coordinates and motion direction. Then, the target vehicle motion trajectory is predicted. Finally, the vehicle collision warning is performed according to the self-vehicle motion trajectory and the target vehicle motion trajectory. In this way, the self-vehicle motion trajectory can be accurately predicted according to the time, arc length and turning angle of the self-vehicle constant-curvature motion or variable-curvature motion, and the vehicle collision warning can be accurately performed. BRIEF DESCRIPTION OF DRAWINGS

[0058] To make the technical solutions in the embodiments or the prior art clearer, the accompanying drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative effort based on these drawings.

[0059] Figure 1 A flow chart of a vehicle collision warning method provided by the embodiments of the present application;

[0060] Figure 2 A schematic diagram of a vehicle collision warning situation provided by the embodiments of the present application;

[0061] Figure 3 A schematic diagram of another vehicle collision warning situation provided by the embodiments of the present application;

[0062] Figure 4 A structural diagram of a vehicle collision warning system provided by the embodiments of the present application;

[0063] Figure 5 A structural schematic diagram of a computer device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. The vehicle collision warning method and system provided by the present application are used in the technical field of vehicles. The above examples do not limit the application field of the method and system provided by the present application.

[0065] With technological advancements, the coverage requirements for active safety features in urban road scenarios are becoming increasingly stringent. For scenarios where vehicles travel along their lanes, active safety obstacle avoidance features are relatively mature. However, for intersection scenarios, especially when vehicles are turning left or right, active safety obstacle avoidance features are limited by the accuracy of predicting the vehicle's trajectory and the target's trajectory, resulting in a failure to accurately identify collision risks.

[0066] The inventors, through research, proposed the technical solution of this application. When executing the method, the vehicle's motion state is first acquired, including linear motion, constant curvature motion, variable curvature motion, and stationary motion. When the vehicle's motion state is constant curvature motion or variable curvature motion, the vehicle's trajectory is predicted based on the time, arc length, and turning angle of the constant curvature motion or variable curvature motion. The trajectory includes predicted position coordinates and direction of motion. Then, the trajectory of the target vehicle is predicted. Finally, a vehicle collision warning is issued based on both the vehicle's trajectory and the target vehicle's trajectory. Thus, by accurately predicting the vehicle's trajectory based on the time, arc length, and turning angle of the constant curvature motion or variable curvature motion, accurate vehicle collision warnings can be provided.

[0067] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application. It should be noted that, for ease of description, only the parts related to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features in the embodiments of the present application can be combined with each other.

[0068] See Figure 1 , Figure 1 A flowchart of a vehicle collision warning method provided in this application embodiment includes:

[0069] S101: Obtain the vehicle's motion status.

[0070] Based on the vehicle's curvature and rate of change of curvature, its motion state can be classified as: linear motion, constant curvature motion, variable curvature motion, and stationary. Therefore, the vehicle's motion state can be obtained, which includes: linear motion, constant curvature motion, variable curvature motion, and stationary.

[0071] S102: When the vehicle's motion state is constant curvature motion or variable curvature motion, predict the vehicle's trajectory based on the time, arc length, and turning angle of the constant curvature motion or variable curvature motion.

[0072] When the vehicle's motion state is constant curvature motion or variable curvature motion, the timing starting point is determined when the vehicle's motion state is determined to be constant curvature motion or variable curvature motion. The time, arc length, and turning angle of the vehicle's constant curvature motion or variable curvature motion are calculated. Then, the vehicle's velocity direction at the timing starting point is obtained. The projection of the vehicle's rear axle center on the ground at the timing starting point is used as the origin of the Cartesian coordinate system. The vehicle's velocity direction at the timing starting point is used as the positive x-axis, and the left side direction of the vehicle is used as the positive y-axis. This Cartesian coordinate system is used for vehicle position prediction. Based on the time, arc length, and turning angle of the vehicle's constant curvature motion or variable curvature motion, and the Cartesian coordinate system, the vehicle's trajectory is predicted. The trajectory includes the predicted position coordinates and the direction of motion.

[0073] Furthermore, after calculating the time, arc length, and turning angle of the vehicle's constant curvature motion or variable curvature motion, it can be determined whether the vehicle's motion state has switched. Anti-shake processing is performed during the process of determining the vehicle's motion state switching. If so, the time of the vehicle's motion state switching is obtained, and the timing and arc length of the vehicle's curved motion are processed based on the time of the vehicle's motion state switching. The processed data is used to predict the vehicle's trajectory, which can improve the accuracy of the vehicle's trajectory prediction. If not, no data processing is performed.

[0074] The specific calculation method is as follows:

[0075] When the vehicle is in the variable curvature motion phase, the theoretical basis for trajectory prediction is the spiral equation, which states that the curvature of the trajectory is proportional to the arc length. According to the spiral equation, the proportionality coefficient A between the arc length S and the curvature K is a constant. The x and y coordinates of the vehicle's trajectory need to be integrated with respect to the arc length.

[0076]

[0077]

[0078]

[0079] Considering engineering applications, the approximate value of the integral is calculated using a periodic accumulation method as the predicted value of the vehicle's horizontal and vertical coordinates.

[0080] Taking the moment when the vehicle's state satisfies the variable curvature motion as the starting point for timing, t clothiod =0, at this point, the arc length, rotation angle, and x and y coordinates are initialized to 0: S N =0,α N =0,x N =0,y N =0; Sampling is performed according to the algorithm's running period dT:

[0081] t clothiod =tclothiodK +dT

[0082] S N =S NK +V ego ·dT

[0083]

[0084]

[0085]

[0086] Among them, t clothiodK ,S Nk ,x Nk ,y Nk The timing, arc length, and x and y coordinates sampled in the previous cycle are initialized to 0; V ego Let A be the vehicle speed, and let A be the current curvature S. N With the current curvature K N The ratio:

[0087]

[0088] Assuming the vehicle undergoes uniform acceleration during the variable curvature motion phase within the predicted time, the change in arc length ds during the predicted period dt is:

[0089]

[0090] The prediction arc length S of the vehicle in each prediction cycle (dt) pred Predicted curvature K pred Predicting the turning angle α pred :

[0091] S pred =S predK +ds

[0092]

[0093]

[0094] Among them, S predK The predicted curvature of the previous prediction period is given by the initial value of the current curvature S. N The predicted lateral and longitudinal coordinates of the vehicle (x pred ,y pred ):

[0095]

[0096]

[0097] Among them, (x predK,y predK (x) represents the predicted coordinates of the previous prediction period, with its initial value being the current coordinate (x). N ,y N );

[0098] If there is a constant curvature motion phase during the variable curvature process and it reaches a certain time threshold, the position is calculated as if the vehicle is performing uniform circular motion:

[0099] Taking the moment when the vehicle's state satisfies constant curvature motion as the starting point for timing, t CR =0; At this point, the arc length of the constant curvature motion is initialized to 0, while the rotation angle and horizontal and vertical coordinates remain at their current values: S CR =0; the predicted curvature K of the vehicle when it is in the constant curvature stage. pred Keep the current value, K pred =K N Predicting the turning angle α pred :

[0100] S CR =S CRK +V ego ·dt

[0101]

[0102] Among them, S CRK ,α CR_predk The predicted curvature arc length and rotation angle for the previous prediction cycle are initialized to 0; the predicted lateral and longitudinal coordinates (x, y, y) of the vehicle are also calculated. pred ,y pred ):

[0103]

[0104]

[0105] x pred =x predK +dx CR ·cos(α CR_predk )-dy CR ·sin(α CR_predk )

[0106] y pred =y predK +dx CR ·sin(α CR_predk )+dy CR ·cos(α CR_predk )

[0107] Among them, (x predK ,y predK (x) represents the predicted coordinates of the previous prediction period, with its initial value being the current coordinate (x). N,y N ).

[0108] S103: Predict the trajectory of the target vehicle.

[0109] The target vehicle's motion state is determined based on its historical trajectory and velocity direction. Since the perceived input attributes such as position and velocity are based on the historical vehicle's Frenet coordinate system, it is necessary to convert the historical trajectory points to the current vehicle's Frenet coordinate system. When the target vehicle's motion state is constant curvature motion or variable curvature motion, the target vehicle's trajectory is predicted based on the time, arc length, and turning angle of the constant curvature or variable curvature motion.

[0110] The specific calculation method is as follows:

[0111] If the target vehicle is moving in a straight line, assuming it moves at a constant speed within the prediction time, first calculate the target's predicted coordinates in the vehicle's current Frenet coordinate system, and then transform the predicted coordinates to the vehicle's Cartesian coordinate system. If the target vehicle is moving with constant or variable curvature, first transform the target coordinates to the vehicle's Cartesian coordinate system, and then calculate the target's predicted position.

[0112] The method for transforming the target vehicle's position coordinates is as follows:

[0113] x obj_trans =(x obj -y obj ·tan(α egoN )·cos(α egoN ))+x egoN

[0114]

[0115] Among them, (x obj y obj (x) represents the target vehicle's coordinates in the current Frenet coordinate system of the current vehicle, (x) objtrans y objtrans (x) represents the target vehicle's position coordinates in the Cartesian coordinate system. egoN y egoN ), α egoN The coordinates of the vehicle's current position and rotation angle in Cartesian coordinates;

[0116] The curvature K of the target vehicle obj for:

[0117]

[0118] Where, ω obj Let Vx be the yaw rate of the target vehicle. absobj Let S be the longitudinal absolute velocity of the target vehicle; and S be the current arc length of the target vehicle.obj And predicted arc length S obj_pred for:

[0119]

[0120]

[0121] Where, ax obj S represents the longitudinal acceleration of the target vehicle. objK Let dT be the arc length of the target vehicle's motion in the previous sampling period, initially set to 0; S obj_predK Let dt be the arc length of the target vehicle's motion in the previous prediction period, with the initial value being the current arc length S of the target vehicle. obj ;

[0122] The subsequent calculations for calculating and predicting the variable curvature motion position of the target vehicle are the same as those for calculating and predicting the variable curvature motion position of the self-vehicle in S102, and will not be repeated here.

[0123] S104: Based on the trajectory of the self-driving vehicle and the trajectory of the target vehicle, a vehicle collision warning is issued.

[0124] Based on the relationship between the predicted position coordinates of the self-vehicle and the predicted position coordinates of the target vehicle, as well as the relationship between the direction of movement of the self-vehicle and the direction of movement of the target vehicle, a collision risk assessment is conducted, and a vehicle collision warning is issued based on the assessment results.

[0125] like Figure 2 As shown, Figure 2 This diagram illustrates a vehicle collision warning scenario. During the prediction time, the lateral and longitudinal distance differences between the vehicle and the target vehicle are calculated in each sampling period. A collision risk is considered present when the lateral and longitudinal distance differences are within a certain range, the speed directions are inconsistent, and the target vehicle is close to the vehicle. The lateral and longitudinal distance difference thresholds are related to the vehicle's lateral and longitudinal projections in a Cartesian coordinate system with the origin of the vehicle's curvature motion as the origin. For example, considering the size of the target vehicle, if its predicted area intersects with the predicted position of the vehicle or the projected area of ​​the vehicle on the side of the target vehicle's motion direction, a collision risk is considered present.

[0126] like Figure 3 As shown in the diagram, another vehicle collision warning scenario provided in this application embodiment considers the width of the target. A collision warning is required when the difference between the predicted position coordinates of the target and the vehicle at any time within the prediction time meets the following conditions:

[0127]

[0128] Among them, (x egopred ,y egopred ), (x obj_pred ,y obj_predLen represents the predicted coordinates of the rear axle center of the vehicle and the front center of the target vehicle in the vehicle's Cartesian coordinate system. ego Len obj Wdt represents the lengths of both the target vehicle and the vehicle itself. ego Wdt obj dstR represents the width of both the target vehicle and the vehicle itself. ego This is the distance from the rear axle to the rear of the vehicle. The predicted turning angle of the vehicle is the angle between the predicted driving direction of the vehicle and the X-axis of the vehicle's Cartesian coordinate system.

[0129] In addition, historical trajectory data of the vehicle is acquired, including the actual coordinates of the vehicle's position after a certain period of time. By comparing the vehicle's position coordinates at the predicted time with the actual vehicle position coordinates after a certain period of time, the coordinate difference is obtained. The accuracy of the vehicle trajectory prediction is evaluated based on the coordinate difference. When the accuracy is lower than a preset threshold, an anomaly is displayed in the vehicle collision warning system. Specifically, since the historical trajectory data of the vehicle is relatively accurate, the accuracy of the vehicle trajectory prediction can be evaluated by comparing the coordinate difference between the vehicle's position at the predicted time and the actual vehicle position after a certain period of time. The horizontal and vertical differences can be evaluated separately using RMSE, with an expected value range of 0.2 to 0.5. When the evaluation result does not meet the expected range, an anomaly is displayed in the vehicle collision warning system, thereby ensuring the accuracy of the vehicle collision warning.

[0130] In the embodiments provided in this application, the vehicle's motion state is first acquired, including linear motion, constant curvature motion, variable curvature motion, and stationary motion. When the vehicle's motion state is constant curvature motion or variable curvature motion, the vehicle's trajectory is predicted based on the time, arc length, and turning angle of the constant curvature motion or variable curvature motion. The trajectory includes predicted position coordinates and direction of motion. Then, the trajectory of a target vehicle is predicted. Finally, a vehicle collision warning is issued based on the vehicle's trajectory and the target vehicle's trajectory. Thus, by accurately predicting the vehicle's trajectory based on the time, arc length, and turning angle of the constant curvature motion or variable curvature motion, an accurate vehicle collision warning can be issued.

[0131] This application provides some specific implementations of a vehicle collision warning method. Based on this, this application also provides a corresponding system. The system provided by this application will be described below from the perspective of functional modularity.

[0132] See Figure 4 The diagram shows the structure of a vehicle collision system 400, which includes:

[0133] The first acquisition module 410 is used to acquire the motion state of the vehicle, which includes linear motion, constant curvature motion, variable curvature motion, and stationary motion.

[0134] The first prediction module 420 is used to predict the trajectory of the vehicle when the vehicle's motion state is constant curvature motion or variable curvature motion, based on the time, arc length and turning angle of the constant curvature motion or variable curvature motion. The trajectory includes the predicted position coordinates and the direction of motion.

[0135] The second prediction module 430 is used to predict the trajectory of the target vehicle.

[0136] The early warning module 440 is used to provide vehicle collision warning based on the trajectory of the self-driving vehicle and the trajectory of the target vehicle.

[0137] Optionally, the first prediction module 420 includes:

[0138] The calculation unit is used to calculate the time, arc length, and turning angle of the vehicle's constant curvature motion or variable curvature motion, starting from the time point when the vehicle's motion state is determined to be constant curvature motion or variable curvature motion.

[0139] The first acquisition unit is used to acquire the vehicle speed direction at the timing start point;

[0140] The unit is used to establish a Cartesian coordinate system by taking the projection of the center of the rear axle of the vehicle at the starting point of the timing onto the ground as the origin of the Cartesian coordinate system, taking the vehicle's velocity direction at the starting point of the timing as the positive x-axis, and the direction from the left side of the vehicle as the positive y-axis.

[0141] The first prediction unit is used to predict the trajectory of the vehicle based on the time, arc length, and turning angle of the vehicle's constant curvature motion or variable curvature motion, and the Cartesian coordinate system.

[0142] Optionally, the first prediction module 420 further includes:

[0143] The first processing unit is used to determine whether the vehicle's motion state has changed, and to perform anti-shake processing during the process of determining the change of the vehicle's motion state.

[0144] The second processing unit is used to obtain the time of the vehicle's motion state switching if the condition is met, and to process the timing and arc length of the vehicle's curved motion based on the time of the vehicle's motion state switching.

[0145] Optionally, the second prediction module 430 includes:

[0146] The second acquisition unit is used to acquire the motion state of the target vehicle;

[0147] The second prediction unit is used to determine that the target vehicle is moving at a constant speed when the target vehicle is moving in a straight line, calculate the predicted position coordinates and speed of the target vehicle in the current Frenet coordinate system of the vehicle based on the speed of the target vehicle's straight line movement, and convert the predicted position coordinates and speed of the target vehicle to the vehicle's Cartesian coordinate system to predict the trajectory of the target vehicle.

[0148] The third prediction unit is used to predict the trajectory of the target vehicle based on the time, arc length, and turning angle of the target vehicle's motion state of constant curvature motion or variable curvature motion.

[0149] Optionally, the early warning module 440 includes:

[0150] The assessment unit is used to assess collision risk based on the relationship between the predicted position coordinates of the self-vehicle and the predicted position coordinates of the target vehicle, as well as the relationship between the direction of movement of the self-vehicle and the direction of movement of the target vehicle.

[0151] The warning unit is used to provide vehicle collision warnings based on the assessment results.

[0152] Optionally, the system further includes:

[0153] The second acquisition module is used to acquire the vehicle's historical trajectory data, which includes the actual vehicle position coordinates after a certain period of time.

[0154] The comparison module is used to obtain the coordinate difference by comparing the vehicle's position coordinates at the predicted time with the actual vehicle position coordinates after a certain time.

[0155] An accuracy evaluation module is used to evaluate the accuracy of the vehicle trajectory prediction based on the coordinate difference.

[0156] An anomaly display module is used to display an anomaly in the vehicle collision warning system when the accuracy is lower than a preset threshold.

[0157] This application also provides corresponding devices and computer storage media for implementing the solutions provided in this application.

[0158] The device includes a memory and a processor. The memory stores instructions or code, and the processor executes the instructions or code to cause the device to perform the method described in any embodiment of this application.

[0159] like Figure 5As shown, the computer device 01 is represented in the form of a general-purpose computing device. The components of the computer device 01 may include, but are not limited to: one or more processors or processing units 03, system memory 08, and bus 04 connecting different system components (including system memory 08 and processing unit 03).

[0160] Bus 04 represents one or more of several bus architectures, including memory buses or memory controllers, peripheral buses, graphics acceleration ports, processors, or local buses using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0161] Computer device 01 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 01, including volatile and non-volatile media, removable and non-removable media.

[0162] System memory 08 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 09 and / or cache memory 10. Computer device 01 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 11 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 5 Not shown; usually referred to as a "hard drive"). Although Figure 5 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 04 via one or more data media interfaces. Memory 08 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0163] A program / utility 12 having a set (at least one) of program modules 13 may be stored in, for example, memory 08. Such program modules 13 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 13 typically perform the functions and / or methods described in the embodiments of the present invention.

[0164] Computer device 01 can also communicate with one or more external devices 02 (e.g., keyboard, pointing device, display 07, etc.), and with one or more devices that enable a user to interact with the computer device 01, and / or with any device that enables the computer device 01 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 06. Furthermore, computer device 01 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) through network adapter 05. Figure 5 As shown, network adapter 05 communicates with other modules of computer device 01 via bus 04. It should be understood that, although... Figure 5 As not shown in the diagram, it can be used in conjunction with computer device 01 with other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0165] The processor unit 03 executes various functional applications and data processing by running programs stored in the system memory 08, such as implementing a method for determining the standard name of an inspection item provided in an embodiment of this application.

[0166] The terms "first" and "second" mentioned in the embodiments of this application are merely for name identification and do not represent a sequential order. It should be understood that the terms "system," "device," "unit," and "module" used in this application are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other words can achieve the same purpose, they can be replaced by other expressions.

[0167] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the methods of the above embodiments can be implemented by means of software plus a general-purpose hardware platform. Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as a read-only memory (ROM) / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network communication device such as a router) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0168] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0169] The above description is merely an exemplary implementation of this application and is not intended to limit the scope of protection of this application.

Claims

1. A vehicle collision warning method, characterized in that, include: The vehicle's motion state is obtained, including linear motion, constant curvature motion, variable curvature motion, and stationary motion. Taking the moment when the vehicle's motion state is determined to be constant curvature motion or variable curvature motion as the starting point of timing, the time, arc length, and turning angle of the vehicle's constant curvature motion or variable curvature motion are calculated. Obtain the vehicle's speed and direction at the starting point of the timing; The Cartesian coordinate system is established by taking the projection of the rear axle center of the vehicle at the starting point of the timing onto the ground as the origin of the Cartesian coordinate system, taking the vehicle's velocity direction at the starting point of the timing as the positive x-axis, and the direction from the left side of the vehicle as the positive y-axis. Based on the time, arc length, and turning angle of the vehicle's constant curvature motion or variable curvature motion, and the Cartesian coordinate system, the vehicle's trajectory is predicted; the trajectory includes the predicted position coordinates and direction of motion. Predict the trajectory of the target vehicle; Based on the trajectory of the autonomous vehicle and the trajectory of the target vehicle, a vehicle collision warning is issued.

2. The method according to claim 1, characterized in that, After calculating the time, arc length, and rotation angle of the self-propelled vehicle's constant curvature motion or variable curvature motion, the method further includes: Determine whether the vehicle's motion state has changed, and perform anti-shake processing during the process of determining the change in the vehicle's motion state; If so, the time of the vehicle's motion state transition is obtained, and the timing and arc length of the vehicle's curved motion are processed based on the time of the vehicle's motion state transition.

3. The method according to claim 1, characterized in that, The predicted trajectory of the target vehicle includes: Obtain the motion status of the target vehicle; When the target vehicle is in a straight line motion, it is determined that the target vehicle is moving at a constant speed. Based on the speed of the target vehicle's straight line motion, the predicted position coordinates and speed of the target vehicle are calculated in the current Frenet coordinate system of the vehicle. The predicted position coordinates and speed of the target vehicle are then transformed to the Cartesian coordinate system of the vehicle to predict the trajectory of the target vehicle. When the target vehicle is in a constant curvature motion or a variable curvature motion, the trajectory of the target vehicle is predicted based on the time, arc length, and turning angle of the constant curvature motion or the variable curvature motion.

4. The method according to claim 1, characterized in that, The method of providing vehicle collision warning based on the vehicle's trajectory and the target vehicle's trajectory includes: Collision risk assessment is conducted based on the relationship between the predicted position coordinates of the self-vehicle and the predicted position coordinates of the target vehicle, as well as the relationship between the direction of movement of the self-vehicle and the direction of movement of the target vehicle. Vehicle collision warnings are issued based on the assessment results.

5. The method according to claim 1, characterized in that, The method further includes: Acquire historical trajectory data of the vehicle, which includes the actual location coordinates of the vehicle after a certain period of time; The coordinate difference is obtained by comparing the vehicle's position coordinates at the predicted time with the actual vehicle position coordinates after a certain time. The accuracy of the vehicle trajectory prediction is evaluated based on the coordinate difference. When the accuracy is lower than a preset threshold, the vehicle collision warning system is displayed as abnormal.

6. A vehicle collision warning system, characterized in that, include: The first acquisition module is used to acquire the motion state of the vehicle, which includes linear motion, constant curvature motion, variable curvature motion, and stationary motion. The first prediction module is used to predict the trajectory of the vehicle when the vehicle's motion state is constant curvature motion or variable curvature motion, based on the time, arc length and turning angle of the constant curvature motion or variable curvature motion. The trajectory includes the predicted position coordinates and the direction of motion. The first prediction module includes: The calculation unit is used to calculate the time, arc length, and turning angle of the vehicle's constant curvature motion or variable curvature motion, starting from the time point when the vehicle's motion state is determined to be constant curvature motion or variable curvature motion. The first acquisition unit is used to acquire the vehicle speed direction at the timing start point; The unit is used to establish a Cartesian coordinate system by taking the projection of the center of the rear axle of the vehicle at the starting point of the timing onto the ground as the origin of the Cartesian coordinate system, taking the vehicle's velocity direction at the starting point of the timing as the positive x-axis, and the direction from the left side of the vehicle as the positive y-axis. The first prediction unit is used to predict the trajectory of the vehicle based on the time, arc length, and turning angle of the vehicle's constant curvature motion or variable curvature motion, and the Cartesian coordinate system. The second prediction module is used to predict the trajectory of the target vehicle; The early warning module is used to provide vehicle collision warnings based on the trajectory of the self-driving vehicle and the trajectory of the target vehicle.

7. A computer device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the vehicle collision warning method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a terminal device, cause the terminal device to perform the vehicle collision warning method as described in any one of claims 1-5.

Images