Driving collision avoidance early warning method based on differential game and processing device

Abstract

The invention provides a driving collision avoidance early warning method based on differential game and a processing device, and belongs to the technical field of vehicle collision early warning, and the method comprises the steps: collecting vehicle trajectory parameters, processing the collected vehicle trajectory parameters, obtaining vehicle prediction trajectory parameters, and carrying out collision risk detection on a vehicle. Obtaining the probability of occurrence of the vehicle collision risk; obtaining the safety early warning distance of the conflicting vehicle, judging the relationship between the safety early warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line of the intersection, and determining the collision risk of the conflicting vehicle according to the probability of occurrence of the vehicle collision risk and the relationship between the safety early warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line of the intersection. Judging whether an early warning game process is triggered or not; if the early warning game process is triggered, the differential game method is adopted for collision avoidance early warning conflicting vehicles, appropriate early warning decision making is carried out, collision avoidance early warning is carried out based on the differential game, and uncontrolled intersection vehicle collision early warning in a complex scene is more accurate and reliable.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle collision warning, and specifically to a driving collision avoidance warning method and processing device based on differential game. Background Art

[0002] Uncontrolled intersections are one of the more dangerous areas in road traffic. Since there are no facilities such as traffic lights to guide and control vehicle movement, the incidence of traffic accidents is relatively high. According to traffic safety accident statistics, traffic accidents at uncontrolled intersections account for a large proportion of total traffic accidents.

[0003] Specifically, the proportion of traffic accidents at uncontrolled intersections to total traffic accidents varies with region and time, but in general, in many cities and regions, the proportion of traffic accidents at uncontrolled intersections is above 20%. According to statistics from the National Transportation Administration, the traffic accident rate at intersections was 30% in 2022 and 32% in 2021. As one of the important places for road traffic accidents, intersections need to strengthen traffic management and technical means to improve traffic safety.

[0004] In order to solve the problem of vehicle collisions at intersections, some researchers have proposed a collision time-based warning algorithm, but the collision time in the algorithm is affected by many factors, resulting in unreliable collision time prediction; some researchers have proposed a warning method based on vehicle speed, but this method does not take road conditions and traffic flow into consideration, and may not be able to accurately assess the risk of collision under complex road conditions; therefore, there is currently a lack of collision warning for intersections with multiple following vehicles behind the conflicting vehicle in complex scenarios. Therefore, how to overcome the above-mentioned technical problems and defects has become a key issue that needs to be addressed. Summary of the invention

[0005] In order to overcome the current lack of collision warning for intersections with multiple following vehicles behind a conflicting vehicle in complex scenarios, the present application provides a driving collision avoidance warning method and processing device based on differential game, which adopts the following technical solutions:

[0006] In the first aspect, the present application provides a vehicle collision avoidance warning method based on differential game, comprising:

[0007] Step S1, collecting vehicle trajectory parameters, wherein the vehicle trajectory parameters include vehicle position coordinate parameters and vehicle speed parameters;

[0008] Step S2, processing the collected vehicle trajectory parameters to obtain vehicle predicted trajectory parameters;

[0009] Step S3, based on the obtained vehicle prediction trajectory parameters, performing collision risk detection on the vehicle to obtain the probability of vehicle collision risk occurrence;

[0010] Step S4, obtaining the safety warning distance of the conflicting vehicle, and determining the relationship between the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection;

[0011] Step S5, judging whether to trigger the early warning game process according to the relationship between the probability of vehicle collision risk and the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection;

[0012] Step S6: If the early warning game process is triggered, the differential game method is used for the conflicting vehicles facing the collision avoidance warning to make appropriate early warning decisions.

[0013] Furthermore, the collecting of vehicle trajectory parameters in step S1 includes:

[0014] The vehicle trajectory parameters are acquired according to the vehicle trajectory parameters obtained by various sensors equipped on the vehicle, so as to realize the collection of vehicle trajectory parameters.

[0015] Furthermore, the step S2 of processing the collected vehicle trajectory parameters to obtain the vehicle predicted trajectory parameters includes:

[0016] (1) Construct the vehicle trajectory state equation based on the vehicle trajectory parameters;

[0017] (2) Based on the Kalman filter algorithm, a prediction equation for vehicle trajectory parameters is constructed;

[0018] (3) Obtain the observed values ​​of vehicle trajectory parameters and construct the vehicle observation trajectory state equation;

[0019] (4) Based on the Kalman filter algorithm, construct the update equation of vehicle trajectory parameters;

[0020] Furthermore, the step S3 of performing collision risk detection on the vehicle based on the obtained predicted trajectory parameters of the vehicle to obtain the probability of occurrence of the vehicle collision risk includes:

[0021] If the main vehicle HV and the remote vehicle RV drive straight into the intersection and arrive at the collision area one after another within a certain period of time, a collision accident may occur; conversely, if the remote vehicle RV has left the collision area boundary when the main vehicle HV arrives at the collision area boundary, or the remote vehicle RV has not reached the collision area boundary when the main vehicle HV leaves the collision area boundary, the two vehicles will not collide;

[0022] When the main vehicle HV reaches the boundary of the collision area, the remote vehicle RV has already left the boundary of the collision area, which is a random event A; when the main vehicle HV leaves the boundary of the collision area, the remote vehicle RV has not reached the boundary of the collision area, which is a random event B; then random events A and B are independent and mutually exclusive;

[0023] Let the collision at the intersection be a random event C, then the probability of the random event C occurring P(C) is:

[0024] P(C)=1-P(A∪B)=1-P(A)-P(B)

[0025] The probability P(A) of random event A is obtained by querying the probability table, and the probability P(B) of random event B is obtained by the same method. The probability P(C) of collision random event C can be obtained.

[0026] Furthermore, the step S3 of performing collision risk detection on the vehicle based on the obtained vehicle predicted trajectory parameters to obtain the probability of vehicle collision risk occurrence also includes:

[0027] If the probability of random event C occurring P(C)>0.05, it is determined that there is a collision risk between the main vehicle HV and the remote vehicle RV, and it is necessary to decide whether to trigger the early warning game process based on the current position information of the vehicle; if the probability of random event C occurring P(C)≤0.05, the driver still drives the vehicle in a natural driving state.

[0028] Furthermore, the step S5 determines whether to trigger the warning game process according to the relationship between the probability of vehicle collision risk and the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection, including:

[0029] Take the safety warning distance as the upper limit of the distance that triggers the warning game, and record the safety warning distance as D W , let the distance between the conflicting vehicle and the stop line of the intersection be D, if and only if D and P(C) simultaneously satisfy the following formula:

[0030]

[0031] The conflicting vehicles trigger the early warning game process.

[0032] Furthermore, the conflicting vehicles for collision avoidance warning in step S6 adopt a differential game method to make appropriate warning decisions, including:

[0033] (1) Define the differential game profit and loss function of the two game participants of the conflicting vehicles

[0034]

[0035] The conflicting vehicles only include the main vehicle HV and the remote vehicle RV, h(·) is the final profit of both participants, and J(·) is the collision cost function of both parties. In order to simplify the calculation, the final profit is defined as a constant, S t is the trajectory parameter of the game participants (i.e., the conflicting vehicles), u HV (t),u RV (t) is the control variable of both parties in the game, and the time when the early warning game ends is t e ;

[0036] (2) Collision cost function of the two game participants of the conflicting vehicles

[0037] After the early warning game process is triggered, the host vehicle and the remote vehicle at the uncontrolled intersection with a collision risk need to estimate the collision cost of the conflicting parties according to the constructed collision cost function. When the collision cost is the smallest, the vehicle will obtain the greatest benefit.

[0038] The collision cost function of the game participants of the conflicting vehicles is constructed from the three aspects of safety characteristics, environmental characteristics and driver characteristics of the conflicting parties:

[0039]

[0040] Among them, the safety performance index is I safe , the environmental characteristic index is I eot , the driver characteristic index parameter is κ;

[0041] It can be seen that a larger κ indicates that the conflict vehicle driver is more aggressive, so κ is related to the environmental characteristic index I eot The weight of is proportional to the traffic efficiency when calculating the collision risk. κ is more important than the safety characteristic index I safe Inversely proportional, conservative drivers place more emphasis on traffic safety;

[0042] (3) Obtaining the optimal decision of the leader of the conflicting vehicles during the game

[0043] The vehicle that first triggers the early warning game process is the leader;

[0044] The method to calculate the leader's optimal decision is to first calculate the follower's optimal decision set under any leader's decision condition based on the follower's profit and loss function, and then the leader calculates the decision that maximizes the leader's profit and loss based on its own profit and loss function.

[0045] In the second aspect, the present application also provides a vehicle collision avoidance warning device based on differential game, including:

[0046] A vehicle trajectory parameter acquisition module, used to acquire vehicle trajectory parameters, wherein the vehicle trajectory parameters include vehicle position coordinate parameters and vehicle speed parameters;

[0047] A vehicle trajectory parameter prediction module is used to process the collected vehicle trajectory parameters to obtain vehicle prediction trajectory parameters;

[0048] A collision risk probability acquisition module is used to perform collision risk detection on the vehicle based on the acquired vehicle prediction trajectory parameters to acquire the probability of vehicle collision risk occurrence;

[0049] A safety warning distance judgment module is used to obtain the safety warning distance of the conflicting vehicle and judge the relationship between the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection;

[0050] The early warning game trigger judgment module is used to determine whether to trigger the early warning game process according to the probability of vehicle collision risk and the relationship between the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection;

[0051] The differential game warning module is used to use the differential game method to make appropriate warning decisions for the conflicting vehicles facing the collision avoidance warning if the warning game process is triggered.

[0052] In a third aspect, the present application provides an electronic device, including:

[0053] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, cause the device to perform the method as described in the first aspect.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method described in the first aspect.

[0055] In a fifth aspect, the present application provides a computer program, which, when executed by a computer, is used to execute the method described in the first aspect.

[0056] In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged together with the processor, or may be stored in whole or in part on a memory not packaged together with the processor.

[0057] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0058] 1. The uncontrolled intersection collision avoidance warning method provided in this application uses V2X technology to realize data interaction between conflicting vehicles in long-distance or non-line-of-sight environments, with strong data reliability and high real-time performance.

[0059] 2. The collision risk detection method provided in this application uses Kalman filtering technology to predict vehicle trajectory parameters, which can reflect the driver's dynamic adjustment process of the vehicle when the vehicle enters the intersection, making the data support for collision risk detection closer to reality and ensuring the success rate of early warning.

[0060] 3. The vehicle collision warning provided in this application is triggered based on the distance index and the collision risk index as triggering conditions, which can avoid premature and invalid warnings and reduce warning redundancy.

[0061] 4. This application obtains the maximum benefit of the vehicle by constructing a collision cost function based on the safety characteristics, environmental characteristics and driver characteristics of both parties in the vehicle conflict, which can not only ensure the driving safety performance at the intersection, but also improve the traffic efficiency of the intersection.

[0062] 5. The vehicle collision avoidance warning method based on differential game provided in this application comprehensively considers the benefits and costs of both parties in the game process, can avoid issuing warnings to conflicting vehicles at the same time, effectively eliminate the collision intensity, and greatly improve the effectiveness of the warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is an exemplary system architecture diagram to which the embodiments of the present application can be applied.

[0064] Figure 2 This is a flow chart of the vehicle collision avoidance warning method based on differential game in this application.

[0065] Figure 3 This is a flowchart of obtaining vehicle prediction trajectory parameters in this application.

[0066] Figure 4 It is a schematic diagram of the intersection warning scenario under the conflict environment of this application.

[0067] Figure 5 It is a schematic diagram of a typical traffic scenario at a conflict intersection according to an embodiment of the present application.

[0068] Figure 6 It is a schematic diagram of the collision avoidance warning decision-making game process of an embodiment of the present application.

[0069] Figure 7 It is a schematic diagram of a device according to an embodiment of the present application.

[0070] Figure 8 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0071] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0072] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0073] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0074] like Figure 1 As shown, the system architecture 10 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0075] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0076] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers and desktop computers, etc.

[0077] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0078] It should be noted that the differential game-based vehicle collision avoidance warning method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the differential game-based vehicle collision avoidance warning device is generally arranged in a server / terminal device.

[0079] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0080] Continue to refer Figure 2 , the figure shows the driving collision avoidance warning method based on differential game of the present application, the method comprises:

[0081] Step S1, collecting vehicle trajectory parameters, wherein the vehicle trajectory parameters include vehicle position coordinate parameters and vehicle speed parameters;

[0082] The step S1 of collecting vehicle trajectory parameters includes:

[0083] The vehicle trajectory parameters are acquired according to the vehicle trajectory parameters obtained by various sensors equipped on the vehicle, so as to realize the collection of vehicle trajectory parameters.

[0084] Step S2, processing the collected vehicle trajectory parameters to obtain vehicle predicted trajectory parameters;

[0085] Please continue to refer to Figure 3 , Figure 3 A flow chart of obtaining vehicle prediction trajectory parameters is shown, and the collected vehicle trajectory parameters are processed to obtain the vehicle prediction trajectory parameters, including:

[0086] S21, constructing a vehicle trajectory state equation according to the vehicle trajectory parameters;

[0087] According to the vehicle trajectory parameters, assuming t i The trajectory parameters of the vehicle at time That is t i The vehicle trajectory parameters at time t are shown in formula (1):

[0088]

[0089] In the formula, (x(t i ),y(t i )) is t i The position coordinate parameters of the vehicle at the moment, v(t i) is t i The speed parameter of the vehicle at time t i+1 The trajectory parameters of the vehicle at the moment It will change dynamically according to the vehicle trajectory state equation, which is shown in formula (2):

[0090]

[0091] Where F is the vehicle state transfer matrix, which satisfies formula (3):

[0092]

[0093] I is the control input matrix, which gives the influence of control parameters on vehicle trajectory parameters and satisfies formula (4):

[0094]

[0095] u(t i ) is the control parameter vector, which mainly describes the acceleration parameters of the vehicle; is the noise vector that affects the trajectory parameters, which obeys a normal distribution with an expected value of 0, and its covariance is determined by the covariance matrix Q.

[0096] S22, obtaining the observed values ​​of the vehicle trajectory parameters and constructing the vehicle observed trajectory state equation;

[0097] In order to accurately predict the future trajectory of the vehicle, the Kalman filter algorithm introduces the observation equation, assuming that t i+1 The observation trajectory parameter detected by the vehicle at time is O(t i+1 ), O(t i+1 ) satisfies formula (5):

[0098]

[0099] In the formula, (X(t i+1 ),Y(t i+1 )) and V(t i+1 ) are the detected vehicle position and speed respectively. At the same time, O(t i+1 ) parameters satisfy the vehicle observation trajectory state equation as shown in formula (6):

[0100]

[0101] Where H is the transformation matrix that maps the vehicle trajectory vector parameters to the measurement domain. This application only considers the measurement error. Therefore, H satisfies formula (7):

[0102]

[0103] is the measurement error vector, which is mainly affected by the detection accuracy of the equipment. In this application, the measurement error also obeys the normal distribution with an expectation of 0, and its covariance is determined by the covariance matrix R;

[0104] S23, constructing a prediction equation for vehicle trajectory parameters based on the Kalman filter algorithm;

[0105] When predicting the vehicle trajectory parameters using the above equation, first use t i The vehicle trajectory parameters at time t i+1 The vehicle trajectory parameters at the time are estimated. According to the Kalman filter algorithm, the prediction equation of the vehicle trajectory parameters satisfies formula (8):

[0106]

[0107] In the formula, t i+1 The state estimation value of the vehicle trajectory parameters at time , t i+1 The state estimation covariance of the vehicle trajectory parameters at time , t i The optimal estimate of the vehicle trajectory parameters at time , t i The optimal estimate variance of the vehicle trajectory parameters at time .

[0108] S24, based on the Kalman filter algorithm, construct an update equation for the vehicle trajectory parameters.

[0109] By using the state estimation value and state estimation covariance of the vehicle trajectory parameters obtained above, on the basis of reading the observed value of the vehicle trajectory parameters, the optimal estimation of the vehicle trajectory parameters is obtained with the help of the vehicle trajectory parameter update equation, and the vehicle trajectory parameter update equation satisfies equation (9):

[0110]

[0111] Where K is the Kalman gain, t i+1 The optimal estimate of the vehicle trajectory parameters at time , t i+1 The optimal estimate variance of the vehicle trajectory parameters at time .

[0112] Step S3, based on the obtained vehicle prediction trajectory parameters, performing collision risk detection on the vehicle to obtain the probability of vehicle collision risk occurrence;

[0113] The step S3 of performing collision risk detection on the vehicle based on the obtained vehicle prediction trajectory parameters to obtain the probability of vehicle collision risk occurrence includes:

[0114] If the main vehicle HV and the remote vehicle RV drive straight into the intersection and arrive at the collision area one after another within a certain period of time, a collision accident may occur; conversely, if the remote vehicle RV has left the collision area boundary when the main vehicle HV arrives at the collision area boundary, or the remote vehicle RV has not reached the collision area boundary when the main vehicle HV leaves the collision area boundary, the two vehicles will not collide;

[0115] Let the collision at the intersection be a random event C. Then the probability of the random event C occurring P(C) satisfies formula (10):

[0116]

[0117] Where D HV and D RV are the distances between the front of the main vehicle and the front of the remote vehicle and the boundary of the collision area, l HV and l RV are the lengths of the host vehicle and the remote vehicle, respectively, w HV and w RV are the vehicle widths of the host vehicle and the remote vehicle, v HV and v RV are the driving speeds of the host vehicle and the remote vehicle respectively;

[0118] When the main vehicle HV reaches the boundary of the collision area, the remote vehicle RV has already left the boundary of the collision area, which is a random event A; when the main vehicle HV leaves the boundary of the collision area, the remote vehicle RV has not reached the boundary of the collision area, which is a random event B. Then the random events A and B satisfy formula (11):

[0119]

[0120] Since random events A and B are independent and mutually exclusive, equation (11) can be simplified to equation (12):

[0121] P(C)=1-P(A∪B)=1-P(A)-P(B) (12)

[0123] Furthermore, for random event A, let Then the probability P(A) of random event A can be simplified as formula (13):

[0124]

[0125] Note i The predicted values ​​of the host vehicle HV and remote vehicle RV at time t i+1 The trajectory parameters at each time are and Satisfying formula (14):

[0126]

[0127] According to the Kalman filter algorithm, and It obeys the normal distribution and satisfies formula (15):

[0128]

[0129] The speed value in the vehicle driving state parameter also obeys the normal distribution and satisfies formula (16):

[0130]

[0131] Furthermore, i+1 k at time A is a constant, assuming that the speeds of the host vehicle and the remote vehicle are independently distributed, then the probability P(A) of the random event A satisfies formula (17):

[0132] P(A)=P(v HV <k A ·v RV )=P{v HV -k A ·v RV <0} (17)

[0133] According to the independent normal distribution operation rule, t i+1 Moment (v HV -k A ·v RV ) also obeys the normal distribution, that is, it satisfies formula (18):

[0134]

[0135] Obviously, formula (18) can be transformed into formula (19):

[0136]

[0137] Note(v HV -k A ·v RV ) is v HR ,make Then formula (18) can be transformed into formula (20):

[0138] v HR ~N(v μ ,v σ )(20)

[0139] Furthermore, this normal distribution is standardized according to formula (21):

[0140]

[0141] Then the process of formula (19) can be simplified to formula (22):

[0142]

[0143] At this time, the probability P(A) of random event A can be obtained by querying the probability table, and the probability P(B) of random event B can be obtained using the same method. Further, the probability P(C) of collision random event C can be obtained.

[0144] The step S3 of performing collision risk detection on the vehicle based on the obtained vehicle predicted trajectory parameters to obtain the probability of vehicle collision risk occurrence also includes:

[0145] If the probability of random event C occurring P(C)>0.05, it is determined that there is a collision risk between the main vehicle HV and the remote vehicle RV, and it is necessary to decide whether to trigger the early warning game process based on the current position information of the vehicle; if the probability of random event C occurring P(C)≤0.05, the driver still drives the vehicle in a natural driving state.

[0146] Step S4, obtaining the safety warning distance of the conflicting vehicle, and determining the relationship between the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection;

[0147] The collision warning game process of the intersection with multiple following vehicles behind the conflicting vehicle is studied. Figure 4 As shown in the figure, the main vehicle HV is traveling from south to north, and the remote vehicle RV is traveling from west to east. There is a certain risk of collision between HV and RV in the scene, and it is necessary to use the corresponding early warning mechanism to send early warning signals to vehicles to avoid collision. In the early warning scene, the four branches are also single-lane. HV and RV keep going straight and are closest to the intersection area, followed by randomly distributed following vehicles. The conflicting vehicles can collect and broadcast vehicle trajectory parameters and traffic flow state parameters in real time.

[0148] Assume that the trajectory parameter vector S of the conflicting vehicles HV and RV at time t is HV(t) , S HV(t) They satisfy equations (23) and (24) respectively:

[0149] S HV(t) =[x HV (t),y HV (t),v HV (t)] T (twenty three)

[0150] S RV(t) =[x RV (t),y RV (t),v RV (t)] T (twenty four)

[0151] Similarly, x(t) and y(t) are the position coordinates of the vehicle, and v(t) is the vehicle speed.

[0152] The focus of the early warning method in the conflict environment using game theory is to determine the warning target vehicle based on the gains and losses of the conflicting parties. During the game, the two parties are the conflicting vehicles HV and RV, and the strategies include issuing a warning to the vehicle or not issuing a warning. The gains and losses indicate the expected gains and losses of the participants under a specific strategy combination.

[0153] The set of participants, strategy set, profit and loss set and the common knowledge of the participants in the game can be marked as:

[0154] (1) The set of game participants: players = {HV, RV};

[0155] (2) The decision set of each participant: strategies = {WS HV ,WS RV};

[0156] (3) Profits and losses of each participant: profits = {PF HV (WS HV ,WS RV ),PF RV (WS HV ,WS RV )};

[0157] (4) Common knowledge of participants: commonknowledge = {S HV(t) ,S RV(t)}.

[0158] The warning target vehicle is determined according to the gains and losses of the conflicting parties, and the target vehicle is prompted to slow down through the warning. The main issue here is the vehicle speed adjustment process. Therefore, in order to facilitate the construction of the gain and loss function, the warning strategy is equivalently transformed with the vehicle speed adjustment process, and the warning strategy WS is defined to satisfy formula (25):

[0159]

[0160] Let u(t) be the control variable of the vehicle V of the game participant, which can be intuitively understood as the acceleration of the vehicle. If and only if u(t) is the minimum value among the control variables of all game participants, that is, u(t) = min(u HV ,u RV ), the vehicle’s warning strategy WS=1.

[0161] Therefore, the early warning decision set of participants can be transformed into: strategies = {u HV ,u RV}, further, the profit and loss set of the participants can be converted into: profits = {PF HV (u HV ,u RV ),PF RV (u HV ,u RV )}.

[0162] Take the safety warning distance as the upper limit of the distance that triggers the warning game, and record the safety warning distance as D W , satisfying formula (26):

[0163]

[0164] Where v is the current speed of the vehicle, a d It is the safety braking deceleration, the value range is -2m / s 2 To -0.9m / s 2 Between. D B is the minimum braking distance, satisfying formula (27):

[0165]

[0166] Among them, a max is the maximum braking deceleration of the vehicle, t r is the driver’s reaction time, t d Delay time for the braking system.

[0167] Step S5, judging whether to trigger the early warning game process according to the relationship between the probability of vehicle collision risk and the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection;

[0168] The step S5 determines whether to trigger the early warning game process according to the probability of vehicle collision risk and the relationship between the safety early warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection, including:

[0169] Take the safety warning distance as the upper limit of the distance that triggers the warning game, and record the safety warning distance as D W , let the distance between the conflicting vehicle and the stop line of the intersection be D, if and only if D and P(C) simultaneously satisfy equation (28):

[0170]

[0171] The conflicting vehicles trigger the early warning game process.

[0172] Furthermore, the distance D of the vehicle to the boundary of the collision area and the minimum braking distance D B The ratio D / D B Classify the warning levels. If D / DB If it is greater than 1.1, the conflicting vehicles are very close to the intersection, triggering a secondary warning to remind the vehicle to decelerate at the maximum braking deceleration; otherwise, a primary warning is triggered to remind the vehicle to decelerate at a comfortable braking deceleration.

[0173] Step S6: If the early warning game process is triggered, the differential game method is used for the conflicting vehicles facing the collision avoidance warning to make appropriate early warning decisions.

[0174] (1) Define the differential game profit and loss function of the two game participants of the conflicting vehicles

[0175] The time when the conflicting vehicles trigger the early warning game process is 0, and the time when the early warning game ends is t e , the conflicting vehicles only include the main vehicle HV and the remote vehicle RV, t∈[0,t e ], the state equation of the vehicle in the early warning game satisfies equation (29):

[0176]

[0177] Among them, S t is the trajectory parameter of the game participants (i.e., the conflicting vehicles), f(·) is the state function of the two game parties, u HV (t),u RV (t) is the control variable of both parties in the game, satisfying formula (30):

[0178]

[0179] Among them, U is the set of all control variables of the conflicting vehicles. During the differential game between the conflicting vehicles, the goal of both participants is to maximize their own gains and losses.

[0180] For game participants, the profit and loss function is defined to satisfy equation (31):

[0181]

[0182] Among them, h(·) is the final profit of both participants, and J(·) is the collision cost function of both parties in the game. In order to simplify the calculation, the final profit is defined as a constant 1.

[0183] (2) Collision cost function of the two game participants of the conflicting vehicles

[0184] After the early warning game process is triggered, the host vehicle and the remote vehicle at the uncontrolled intersection with a collision risk need to estimate the collision cost of the conflicting parties according to the constructed collision cost function. When the collision cost is the smallest, the vehicle will obtain the greatest benefit.

[0185] The collision cost function of the game participants of the conflicting vehicles is constructed from the three aspects of safety characteristics, environmental characteristics and driver characteristics of the conflicting parties:

[0186] ①Safety characteristic indicators

[0187] The safety performance index is quantitatively calculated using the safety time, and the safety performance index is recorded as I safe , if the distances between the vehicles of the two conflicting parties and the boundaries of the collision area at time t are D HV and D RV The speeds of the two vehicles are v HV and v RV , then I safe Satisfying equations (32) to (34):

[0188]

[0189] Among them, TTC is the time difference between the two parties in the game reaching the boundary of the collision area, γ determines whether there is a potential collision risk between the two parties in the game, and τ is a constant greater than 0, which is taken as 2 here. Obviously, the smaller the time difference between the two vehicles reaching the boundary of the conflict area, the greater the collision cost.

[0190] ②Environmental characteristics indicators

[0191] From the perspective of the overall traffic efficiency of the intersection, when a vehicle enters the intersection, if there are more vehicles on other branches, the driver should be given a warning to slow down during the game to avoid the conduction effect of congestion; from the perspective of the overall safety performance of the intersection, if the traffic density on the two branches is the same, in order to give the following vehicle a larger reaction distance to avoid rear-end collisions, a warning should be issued to the party with a larger distance between vehicles to slow down during the game. Figure 5 Two typical traffic scenarios at intersections with collision conflicts are given, where the conflicting vehicles are HV and RV respectively. Figure 5 In (a), the traffic density behind the HV is high, so the RV should slow down and give way; Figure 5 In (b), the distance between RV and the vehicle behind is larger, so RV should slow down and give way.

[0192] Based on the above ideas, the environmental characteristic index is defined with the help of the traffic density factor and the vehicle spacing factor to describe the status of the vehicle following the conflicting vehicle. Assuming that the conflicting vehicle can read the traffic data of the surrounding vehicles, the collection range is set to 100m behind the conflicting vehicle.

[0193] The environmental characteristic index is I eot The number of following vehicles behind the conflicting vehicles HV and RV in the acquisition range is n respectively. HV and n RV , the distance between the i-th following vehicle and the conflicting vehicle is but Satisfying equations (35) to (38):

[0194]

[0195] Among them, α and β are both random numbers, α∈(0.5,1). Den is the traffic density factor in the environmental characteristic index. This parameter is the normalized parameter value of the total number of following vehicles of the conflicting parties within the collection range. It can be seen that Gap is the inter-vehicle distance factor in the environmental characteristic index, satisfying When there are multiple following vehicles, the impact of the following vehicles on the game process is related to the ranking of the following vehicles in the following traffic flow. The later the ranking, the smaller the impact on the game process. Obviously, the environmental characteristic index is proportional to the total number of following vehicles. The more the total number of following vehicles, the larger the environmental characteristic index, and the higher the collision cost; the environmental characteristic index is inversely proportional to the distance between following vehicles. The smaller the distance between following vehicles, the larger the distance factor, the larger the environmental characteristic index, and the higher the collision cost.

[0196] ③Driver characteristic index parameters

[0197] For the conflicting vehicles at the intersection, since the driver type is closely related to driving behavior, if the driver type of the conflicting vehicles can be determined, the warning decision made will be more reasonable. For aggressive drivers, the vehicle pays more attention to traffic efficiency during driving, and the frequency of vehicle speed adjustment is relatively high; for conservative drivers, because they pursue safety performance more, the vehicle driving speed is relatively low, and the speed change is relatively small.

[0198] With reference to the above ideas, the driver characteristic index is quantitatively calculated with the help of the vehicle acceleration change rate, and normalized with reference to the maximum-minimum principle.

[0199] The driver characteristic index parameter is κ, which satisfies formula (39):

[0200]

[0201] Among them, a i 、a i-1 The vehicles are i Time and t i-1 The acceleration at the moment, a max is the maximum acceleration of the vehicle. Obviously, κ∈(0,1). If the acceleration of the vehicle changes greatly between adjacent moments, it means that the vehicle speed changes quickly and the driver's driving style is relatively aggressive.

[0202] Based on the definition of the above characteristic indicators, the safety characteristic indicator I is calculated by the driver characteristic indicator κ. safe and Environmental Characteristics Index I eot Different weights are assigned to characterize the driving behaviors of both parties in the game, and the collision cost function J(·) of both parties in the game is constructed. i The collision cost function J(·) between the two players at the moment satisfies equation (40):

[0203]

[0204] It can be seen that since a larger κ indicates that the conflict vehicle driver is more aggressive, κ and the environmental characteristic index I eot The weight of is proportional to the traffic efficiency when calculating the collision risk. κ is more important than the safety characteristic index I safe Inversely proportional, conservative drivers pay more attention to traffic safety.

[0205] (3) Obtaining the optimal decision of the leader of the conflicting vehicles during the game

[0206] The vehicle that first triggers the early warning game process is the leader; the method for calculating the leader's optimal decision is to first calculate the optimal decision set of the followers under any leader's decision condition based on the followers' profit and loss function, and then the leader calculates the decision that maximizes the leader's profit and loss based on its own profit and loss function.

[0207] Assume that the leader of the conflicting vehicles in the game is HV and the follower is RV. At time t, the decisions and optimal decisions made by both parties are (u HV ,u RV )and

[0208] According to the previous analysis, any decision made for HV is u HV , RV will make corresponding decisions u RV , so that the profit and loss function PF of RV HV (u HV ,u RV ) is the largest, obviously, u RV with u HV Furthermore, for the decision set u containing all control variables of the HV vehicle HV ∈U, there will be a decision set ρ(u HV ), so that u RV =ρ(u HV ).

[0209] At this time, for the leader HV, if the decision of both parties in the game Satisfying equations (41) to (43):

[0210]

[0211] It is believed that It is the optimal decision that satisfies the Steinberg equilibrium.

[0212] Formula (41) determines the correlation between RV decision and HV decision, ensuring the existence of corresponding reaction functions between the two; Formula (42) requires that RV decision always belongs to the allowed decision set, ensuring the legitimacy of RV decision; Formula (43) gives the judgment condition of Steinberg equilibrium decision.

[0213] Specifically, in a game, the conflicting parties calculate the optimal decision that satisfies the Steinberg equilibrium. The process can be divided into two steps:

[0214] ① First, the leader HV calculates the reaction function between the follower RV and the leader HV.

[0215] ②The leader HV then determines the optimal decision set based on the profit and loss function.

[0216] According to Pontryagin's maximum principle, for [0,t e ] time contains two game participants in the differential game process, if any t∈[0,t e The state equation of both parties at the moment f(t,S t ,u HV (t),u RV (t)) is continuously differentiable on the set of real numbers, the final payoff function h(·) and the collision cost function J(·) of all game participants are continuously differentiable on the set of real numbers, and is the optimal decision set for both parties to satisfy the Steinberg equilibrium, then the follower RV must have an accompanying vector ξ RV , satisfying equations (44) to (47):

[0217]

[0218] At this time, the optimal decision for RV is Satisfying formula (48):

[0219]

[0220] It can be seen that in formula (45), when the adjoint vector ξ RV When it is determined, the optimal decision solution of RV under the current reaction function can be obtained, and the optimal decision solution is recorded as Then the optimal decision solution of leader HV is Will satisfy formula (49):

[0221]

[0222] At the same time, equation (49) satisfies equations (50) to (53):

[0223]

[0224] Continue to refer Figure 6 , Figure 6 A flowchart of a collision avoidance warning decision game process is shown, and the specific steps are as follows:

[0225] Step 1: Get updated vehicle trajectory parameters and proceed to step 2;

[0226] Step 2: Determine the distance between the conflicting vehicle and the stop line at the intersection as D and the safety warning distance D W the relationship between;

[0227] If the distance D between the conflicting vehicle and the stop line at the intersection is less than or equal to the safety warning distance D W , then go to step 3;

[0228] If the distance D between the conflicting vehicle and the stop line of the intersection is greater than the safety warning distance D W , then return to step 1;

[0229] Step 3: Obtain the value of the collision risk probability P(C) of the two vehicles; if P(C) ≥ 0.05, proceed to step 4;

[0230] If P(C) < 0.05, recalculate the collision risk and return to step 1;

[0231] Step 4: Trigger the early warning game process;

[0232] Step 5: Determine the identities of the game participants;

[0233] Step 6: Determine the best decision for the leader;

[0234] Step 7: Determine the warning object;

[0235] Step 8: Determine the distance between the conflicting vehicle and the stop line at the intersection as D and the minimum braking distance D B If the relationship between D / D B ≥1.1, a first-level warning is triggered; if D / D B <1.1, a second-level warning will be triggered.

[0236] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0237] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified in the present application, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0238] Continue to refer Figure 7 The vehicle collision avoidance warning device based on differential game described in this embodiment includes:

[0239] The vehicle trajectory parameter acquisition module 701 is used to acquire vehicle trajectory parameters, wherein the vehicle trajectory parameters include vehicle position coordinate parameters and vehicle speed parameters;

[0240] The vehicle trajectory parameter prediction module 702 is used to process the collected vehicle trajectory parameters to obtain the vehicle prediction trajectory parameters;

[0241] A collision risk probability acquisition module 703 is used to perform a collision risk detection on the vehicle based on the acquired vehicle prediction trajectory parameters to acquire the probability of vehicle collision risk occurrence;

[0242] The safety warning distance determination module 704 is used to obtain the safety warning distance of the conflicting vehicle and determine the relationship between the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection;

[0243] The early warning game triggering judgment module 705 is used to determine whether to trigger the early warning game process according to the probability of vehicle collision risk and the relationship between the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection;

[0244] The differential game warning module 706 is used to use the differential game method to make appropriate warning decisions for the conflicting vehicles facing the collision avoidance warning if the warning game process is triggered.

[0245] To solve the above technical problems, the present application also provides a computer device. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0246] The computer device 8 includes a memory 8a, a processor 8b, and a network interface 8c that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 8 with components 8a-8c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0247] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0248] The memory 8a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 8a can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 8a can also be an external storage device of the computer device 8, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 8. Of course, the memory 8a can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 8a is generally used to store the operating system and various application software installed on the computer device 8, such as the program code of the vehicle collision avoidance warning method and processing device based on differential game, etc. In addition, the memory 8a can also be used to temporarily store various types of data that have been output or are to be output.

[0249] The processor 8b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 8b is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 8b is used to run the program code or process data stored in the memory 8a, such as running the program code of the vehicle collision avoidance warning method and processing device based on differential game.

[0250] The network interface 8c may include a wireless network interface or a wired network interface. The network interface 8c is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0251] The present application also provides another implementation mode, namely, providing a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a program of a vehicle collision avoidance warning method and processing device based on differential game, and the vehicle collision avoidance warning method and processing device based on differential game can be executed by at least one processor, so that the at least one processor executes the steps of the vehicle collision avoidance warning method and processing device based on differential game as described above.

[0252] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0253] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A vehicle collision avoidance warning method based on differential game, characterized in that: include: Step S1, collecting vehicle trajectory parameters, wherein the vehicle trajectory parameters include vehicle position coordinate parameters and vehicle speed parameters; Step S2, processing the collected vehicle trajectory parameters to obtain vehicle predicted trajectory parameters; Step S3, based on the obtained vehicle prediction trajectory parameters, performing collision risk detection on the vehicle to obtain the probability of vehicle collision risk occurrence; Step S4, obtaining the safety warning distance of the conflicting vehicle, and determining the relationship between the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection; Step S5, judging whether to trigger the early warning game process according to the relationship between the probability of vehicle collision risk and the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection; Step S6: If the early warning game process is triggered, the differential game method is used for the conflicting vehicles facing the collision avoidance warning to make appropriate early warning decisions.

2. The vehicle collision avoidance warning method based on differential game according to claim 1 is characterized in that: The step S1 of collecting vehicle trajectory parameters includes: The vehicle trajectory parameters are acquired according to the vehicle trajectory parameters obtained by various sensors equipped on the vehicle, so as to realize the collection of vehicle trajectory parameters.

3. The vehicle collision avoidance warning method based on differential game according to claim 2 is characterized in that: The step S2 of processing the collected vehicle trajectory parameters to obtain the vehicle predicted trajectory parameters includes: (1) Construct the vehicle trajectory state equation based on the vehicle trajectory parameters; (2) Based on the Kalman filter algorithm, a prediction equation for vehicle trajectory parameters is constructed; (3) Obtain the observed values ​​of vehicle trajectory parameters and construct the vehicle observation trajectory state equation; (4) Based on the Kalman filter algorithm, the update equation of vehicle trajectory parameters is constructed.

4. The vehicle collision avoidance warning method based on differential game according to claim 1, characterized in that: The step S3 of performing collision risk detection on the vehicle based on the obtained vehicle prediction trajectory parameters to obtain the probability of vehicle collision risk occurrence includes: If the main vehicle HV and the remote vehicle RV drive straight into the intersection and arrive at the collision area one after another within a certain period of time, a collision accident may occur; conversely, if the remote vehicle RV has left the collision area boundary when the main vehicle HV arrives at the collision area boundary, or the remote vehicle RV has not reached the collision area boundary when the main vehicle HV leaves the collision area boundary, the two vehicles will not collide; When the main vehicle HV reaches the boundary of the collision area, the remote vehicle RV has already left the boundary of the collision area, which is a random event A; when the main vehicle HV leaves the boundary of the collision area, the remote vehicle RV has not reached the boundary of the collision area, which is a random event B; then random events A and B are independent and mutually exclusive; Let the collision at the intersection be a random event C, then the probability of the random event C occurring P(C) is: P(C)=1-P(A∪B)=1-P(A)-P(B) The probability P(A) of random event A is obtained by querying the probability table, and the probability P(B) of random event B is obtained by the same method. The probability P(C) of collision random event C can be obtained.

5. The vehicle collision avoidance warning method based on differential game according to claim 4 is characterized in that: The step S3 of performing collision risk detection on the vehicle based on the obtained vehicle predicted trajectory parameters to obtain the probability of vehicle collision risk occurrence also includes: If the probability of random event C occurring P(C)>0.05, it is determined that there is a collision risk between the main vehicle HV and the remote vehicle RV, and it is necessary to decide whether to trigger the early warning game process based on the current position information of the vehicle; if the probability of random event C occurring P(C)≤0.05, the driver still drives the vehicle in a natural driving state.

6. The vehicle collision avoidance warning method based on differential game according to claim 1, characterized in that: The step S5 determines whether to trigger the early warning game process according to the probability of vehicle collision risk and the relationship between the safety early warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection, including: Take the safety warning distance as the upper limit of the distance that triggers the warning game, and record the safety warning distance as D W , let the distance between the conflicting vehicle and the stop line of the intersection be D, if and only if D and P(C) simultaneously satisfy the following formula: The conflicting vehicles trigger the early warning game process.

7. The vehicle collision avoidance warning method based on differential game according to claim 1, characterized in that: The conflicting vehicles for collision avoidance warning in step S6 adopt a differential game method to make appropriate warning decisions, including: (1) Define the differential game profit and loss function of the two game participants of the conflicting vehicles The conflicting vehicles only include the main vehicle HV and the remote vehicle RV, h(·) is the final profit of both participants, and J(·) is the collision cost function of both parties. In order to simplify the calculation, the final profit is defined as a constant, S t is the trajectory parameter of the game participants (i.e., the conflicting vehicles), u HV (t),u RV (t) is the control variable of both parties in the game, and the time when the early warning game ends is t e ; (2) Collision cost function of the two game participants of the conflicting vehicles After the early warning game process is triggered, the host vehicle and the remote vehicle at the uncontrolled intersection with a collision risk need to estimate the collision cost of the conflicting parties according to the constructed collision cost function. When the collision cost is the smallest, the vehicle will obtain the greatest benefit. The collision cost function J(·) of the two game participants of the conflicting vehicles is constructed from the three aspects of safety characteristics, environmental characteristics and driver characteristics: Among them, the safety performance index is I safe , the environmental characteristic index is I eot , the driver characteristic index parameter is κ; It can be seen that a larger κ indicates that the conflict vehicle driver is more aggressive, so κ is related to the environmental characteristic index I eot The weight of is proportional to the traffic efficiency when calculating the collision risk. κ is more important than the safety characteristic index I safe Inversely proportional, conservative drivers place more emphasis on traffic safety; (3) Obtaining the optimal decision of the leader of the conflicting vehicles during the game The vehicle that first triggers the early warning game process is the leader; the method for calculating the leader's optimal decision is to first calculate the optimal decision set of the followers under any leader's decision condition based on the followers' profit and loss function, and then the leader calculates the decision that maximizes the leader's profit and loss based on its own profit and loss function.

8. A vehicle collision avoidance warning processing device based on differential game, characterized in that: The processing device comprises: A vehicle trajectory parameter acquisition module, used to acquire vehicle trajectory parameters, wherein the vehicle trajectory parameters include vehicle position coordinate parameters and vehicle speed parameters; A vehicle trajectory parameter prediction module is used to process the collected vehicle trajectory parameters to obtain vehicle prediction trajectory parameters; A collision risk probability acquisition module is used to perform collision risk detection on the vehicle based on the acquired vehicle prediction trajectory parameters to acquire the probability of vehicle collision risk occurrence; A safety warning distance judgment module is used to obtain the safety warning distance of the conflicting vehicle and judge the relationship between the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection; The early warning game trigger judgment module is used to determine whether to trigger the early warning game process according to the probability of vehicle collision risk and the relationship between the safety warning distance of the conflicting vehicle and the distance between the conflicting vehicle and the stop line at the intersection; The differential game warning module is used to use the differential game method to make appropriate warning decisions for the conflicting vehicles facing the collision avoidance warning if the warning game process is triggered.

9. An electronic device, characterized in that: include: One or more processors, a memory, and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, and when the instructions are executed by the device, the device performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 7.

Images