Target risk level determination method and related device

Abstract

The embodiment of the invention discloses a target risk level determination method. The method comprises the following steps: acquiring a first relative longitudinal distance between a target vehicle and a vehicle, a first longitudinal speed of the target vehicle and a second longitudinal speed of the vehicle; determining one or more risk level evaluation indexes of the target vehicle according to the first relative longitudinal distance, the first longitudinal speed and the second longitudinal speed; determining a risk level evaluation threshold value of the target vehicle; and determining a first risk level assessment result based on a preset risk level assessment model according to the plurality of risk level assessment indexes and the plurality of risk level assessment thresholds. The traffic environment of the intelligent driving vehicle in actual driving is complex and changeable, so that factors of multiple dimensions are considered in the acquired evaluation index and the preset value influence factor, the danger level is determined based on multiple different types of parameters, and the accuracy and the stability of the target danger level are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and particularly to a method for determining a target risk level and related devices. Background Art

[0002] With the development of artificial intelligence technology, the degree of vehicle driving intelligence is also getting higher and higher. And driving safety, as the primary requirement of users for intelligent driving functions, should receive the highest attention priority.

[0003] Among them, safety involves two aspects. On the one hand, it is the safety objectively demonstrated by the vehicle when facing external complex environments and emergencies, that is, objective safety. On the other hand, it is the sense of security and trust brought by the vehicle to the user through human-machine interaction, that is, subjective safety. The safety provided by intelligent driving is the unity of objective safety and subjective safety.

[0004] Related technologies evaluate the danger levels of various surrounding targets when the vehicle is driving, and then feedback the evaluation results to the user to improve the safety of intelligent driving. However, the involved dimensions of the evaluation considerations in related technologies are limited, and there are deviations between the evaluation results in complex scenarios and the true perceptions of drivers. Summary of the Invention

[0005] To solve the above technical problems, this application provides a method for determining a target risk level and related devices, which improves the accuracy and stability of the target danger level.

[0006] The embodiments of this application disclose the following technical solutions:

[0007] In a first aspect, the embodiments of this application disclose a method for determining a target risk level, and the method includes:

[0008] Obtain the first relative longitudinal distance between the target vehicle and the own vehicle, the first longitudinal speed of the target vehicle, and the second longitudinal speed of the own vehicle;

[0009] Determine one or more risk level evaluation indicators of the target vehicle according to the first relative longitudinal distance, the first longitudinal speed, and the second longitudinal speed;

[0010] Determine the risk level evaluation threshold of the target vehicle;

[0011] Based on the plurality of risk level evaluation indicators and the plurality of risk level evaluation thresholds, determine a first risk level evaluation result based on a preset risk level evaluation model.

[0012] Optionally, the risk level evaluation indicators include the collision time between the target vehicle and the own vehicle or the following distance of the own vehicle relative to the target vehicle.

[0013] Optionally, determining one or more risk level assessment indicators of the target vehicle according to the first relative longitudinal distance, the first longitudinal speed, and the second longitudinal speed includes:

[0014] Calculating the longitudinal speed difference between the first longitudinal speed and the second longitudinal speed;

[0015] Calculating the time to collision according to the first relative longitudinal distance and the longitudinal speed difference;

[0016] Calculating the time headway according to the first relative longitudinal distance and the first longitudinal speed.

[0017] Optionally, determining the risk level assessment threshold of the target vehicle includes:

[0018] Obtaining a plurality of influencing factors of the target vehicle relative to the host vehicle;

[0019] Performing normalization processing on the plurality of influencing factors to determine the influencing weights corresponding to each influencing factor;

[0020] Calculating the risk level assessment threshold of the target vehicle according to the plurality of influencing factors and the plurality of influencing weights corresponding to the plurality of influencing factors.

[0021] Optionally, the method further includes:

[0022] Determining a second risk level assessment result based on a preset risk level jump model according to the first risk level assessment result.

[0023] Optionally, the preset risk level jump model includes a target correlation model and a target risk level determination model;

[0024] Determining the second risk level assessment result based on the preset risk level jump model according to the first risk level assessment result includes:

[0025] When the first risk level assessment result is greater than the preset risk level assessment result, calculating a second relative longitudinal distance between the target vehicle and the host vehicle within a preset time;

[0026] In response to determining that the second relative longitudinal distance is greater than a preset distance, determining that the target vehicle is a relevant vehicle of the host vehicle based on the target correlation model;

[0027] When the target vehicle is a relevant vehicle of the host vehicle, determining the second risk level assessment result of the target vehicle based on the target risk level determination model.

[0028] Second aspect, embodiments of the present application disclose a target risk level determination device, the device includes

[0029] An acquisition unit, configured to acquire a first relative longitudinal distance between a target vehicle and the vehicle itself, a first longitudinal speed of the target vehicle, and a second longitudinal speed of the vehicle itself;

[0030] A first determination unit, configured to determine one or more risk level evaluation indicators of the target vehicle according to the first relative longitudinal distance, the first longitudinal speed, and the second longitudinal speed;

[0031] A second determination unit, configured to determine a risk level evaluation threshold of the target vehicle;

[0032] A third determination unit, configured to determine a first risk level evaluation result based on a preset risk level evaluation model according to the plurality of risk level evaluation indicators and the plurality of risk level evaluation thresholds.

[0033] Optionally, the risk level evaluation indicators include a collision time between the target vehicle and the vehicle itself or a following time distance of the vehicle itself relative to the target vehicle.

[0034] The first determination unit is further configured to:

[0035] Calculate a longitudinal speed difference between the first longitudinal speed and the second longitudinal speed;

[0036] Calculate the collision time according to the first relative longitudinal distance and the longitudinal speed difference;

[0037] Calculate the following time distance according to the first relative longitudinal distance and the first longitudinal speed.

[0038] Optionally, the second determination unit is further configured to:

[0039] Acquire a plurality of influencing factors of the target vehicle relative to the vehicle itself;

[0040] Perform normalization processing on the plurality of influencing factors to determine influence weights corresponding to each influencing factor respectively;

[0041] Calculate the risk level evaluation threshold of the target vehicle according to the plurality of influencing factors and the plurality of influence weights corresponding to the plurality of influencing factors.

[0042] Optionally, the device further includes:

[0043] A fourth determination unit, configured to determine a second risk level evaluation result based on a preset risk level jump model according to the first risk level evaluation result.

[0044] Optionally, the preset risk level jump model includes a target relevance model and a target risk level determination model;

[0045] The third determination unit is further configured to:

[0046] When the first risk level evaluation result is greater than the preset risk level evaluation result, calculate a second relative longitudinal distance between the target vehicle and the own vehicle within a preset time;

[0047] In response to determining that the second relative longitudinal distance is greater than the preset distance, based on the target relevance model, determine that the target vehicle is a relevant vehicle of the own vehicle;

[0048] When the target vehicle is a relevant vehicle of the own vehicle, based on the target risk level determination model, determine a second risk level evaluation result of the target vehicle.

[0049] In a third aspect, an embodiment of the present application discloses a computer device, where the computer device includes a processor and a memory:

[0050] The memory is used to store program code and transmit the program code to the processor;

[0051] The processor is configured to execute the target risk level determination method as described in the first aspect and any optional item of the first aspect according to the instructions in the program code.

[0052] In a fourth aspect, an embodiment of the present application discloses a computer-readable storage medium, where the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the target risk level determination method as described in the first aspect and any optional item of the first aspect when executed by a processor.

[0053] It can be seen from the above technical solutions that by obtaining the first relative longitudinal distance between the target vehicle and the own vehicle, the first longitudinal speed of the target vehicle and the second longitudinal speed of the own vehicle; according to the first relative longitudinal distance, the first longitudinal speed and the second longitudinal speed, determining one or more risk level evaluation indicators of the target vehicle; determining a risk level evaluation threshold of the target vehicle; according to the multiple risk level evaluation indicators and the multiple risk level evaluation thresholds, based on a preset risk level evaluation model, determining a first risk level evaluation result. Since the actual driving traffic environment of intelligent driving vehicles is complex and changeable, the collected evaluation indicators and preset value influencing factors consider factors in multiple dimensions such as road information, vehicle status, weather environment, perception ability, and driver preference, and determine the danger level based on various different types of parameters, improving the accuracy and stability of the target danger level. Description of the Drawings

[0054] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0055] Figure 1 It is a flowchart of a method for determining a target risk level provided by an embodiment of the present application;

[0056] Figure 2 It is a structural block diagram of a device for determining a target risk level provided by an embodiment of the present application;

[0057] Figure 3 It is a structural block diagram of a computer device for determining a target risk level provided by an embodiment of the present application. Detailed implementation manners

[0058] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments.

[0059] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, which is only a way of distinguishing objects with the same attributes when describing the embodiments of the present application.

[0060] With the development of artificial intelligence technology, the degree of vehicle driving intelligence is also getting higher and higher. And driving safety, as the primary demand of users for intelligent driving functions, should receive the highest attention priority.

[0061] Among them, safety involves two aspects. On the one hand, it is the safety objectively demonstrated by the vehicle when facing external complex environments and emergencies, that is, objective safety. On the other hand, it is the sense of security and trust brought by the vehicle to the user through human-machine interaction, that is, subjective safety. The safety provided by intelligent driving is the unity of objective safety and subjective safety.

[0062] The related art evaluates the risk levels of various surrounding targets when the vehicle is driving, and then feeds back the evaluation results to the user to improve the safety of intelligent driving. However, the evaluation in the related art has limited dimensions in terms of the considered factors, and there are deviations between the evaluation results in complex scenarios and the driver's true perception.

[0063] To solve the above technical problems, embodiments of the present application provide a method for determining a target risk level and related devices. In the following embodiments, the present vehicle refers to the vehicle for determining the target risk level, and the target vehicle refers to the target whose risk level is determined.

[0064] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for determining a target risk level provided by an embodiment of the present application. The method includes S101 - S104:

[0065] S101: Obtain the first relative longitudinal distance between the target vehicle and the present vehicle, the first longitudinal speed of the target vehicle, and the second longitudinal speed of the present vehicle.

[0066] Among them, the first relative longitudinal distance between the target vehicle and the present vehicle refers to the longitudinal distance between the two vehicles in the driving direction. The first longitudinal speed of the target vehicle and the second longitudinal speed of the present vehicle also refer to the longitudinal speeds of the two vehicles in the driving direction. The above - mentioned data can be obtained after processing the perception data transmitted by sensors such as cameras and lidar on the present vehicle.

[0067] S102: Determine one or more risk - level evaluation indicators of the target vehicle according to the first relative longitudinal distance, the first longitudinal speed, and the second longitudinal speed.

[0068] Among them, the risk - level evaluation indicators include the time - to - collision between the target vehicle and the present vehicle or the following - distance of the present vehicle relative to the target vehicle.

[0069] As a possible implementation, the calculation method of the risk - level evaluation indicator is shown in the following formula:

[0070]

[0071] Among them, LD represents the first relative longitudinal distance between the target vehicle and the present vehicle, TTC represents the time - to - collision between the target vehicle and the present vehicle, TD represents the following - distance of the present vehicle relative to the target vehicle, d obj is the longitudinal distance of the target vehicle; d ego is the longitudinal distance of the present vehicle. Taking the center of the rear axle of the present vehicle as the coordinate system, this value is 0; v obj is the longitudinal speed of the target vehicle; v ego is the longitudinal speed of the present vehicle.

[0072] In some possible implementation manners, there are effectiveness limitations of mutual restriction in the application process of the risk level evaluation indexes. For example: when the speed of this vehicle is the same as that of the target vehicle, the relative speed between this vehicle and the target vehicle is 0, so there is no collision time, and the evaluation index of TTC fails; another example: when the speed of this vehicle is relatively low or close to 0, the following distance of this vehicle will be very large, so the effectiveness of the TD evaluation index is relatively low; also, when the relative speed between this vehicle and the target vehicle is large enough, the predictability of the LD evaluation index decreases. Therefore, the three dimensions cooperate with each other to comprehensively evaluate the safety risk level of surrounding targets of the intelligent driving vehicle in various complex traffic scenarios.

[0073] S103: Determine the risk level evaluation threshold of the target vehicle.

[0074] In some possible implementation manners, to determine the risk level evaluation threshold, comprehensive calculation can be performed through multiple influencing factors, so as to obtain the corresponding threshold:

[0075] Obtain multiple influencing factors of the target vehicle relative to this vehicle;

[0076] Perform normalization processing on the multiple influencing factors to determine the influence weights corresponding to each influencing factor respectively;

[0077] Calculate the risk level evaluation threshold of the target vehicle according to the multiple influencing factors and the multiple influence weights corresponding to the multiple influencing factors.

[0078] For example, the multiple influencing factors can be divided into three categories: A, B, and C. Category A is environmental information, Category B is functional status, and Category C is driver's preset preferences. The influencing factors of Category A are specifically {the speed of this vehicle A1, the speed of the target vehicle A2, the longitudinal distance of the target vehicle A3, the acceleration of this vehicle A4, the type of the target vehicle A5}, the influencing factors of Category B {functional scenario B1, weather condition B2, perceived visibility B3, the stage at which the intelligent driving function is located B4}, and the influencing factors of Category C {desired following distance C1, driving style C2}. The influencing factors of Category A mainly focus on the motion states and relative position information of the target vehicle and this vehicle, and mainly distinguish the differences in the driver's perception of the target danger level in high-speed and low-speed scenarios; the influencing factors of Category B mainly focus on the current functional status of the intelligent driving and the current perception ability of the vehicle. For example, when the driver has a strong intention to change lanes, the acceptance ability of the target danger level during the lane change process is relatively high, and when the lane change is about to be completed, the driver's attention to the danger level of the vehicle behind decreases, etc.; the influencing factors of Category C mainly evaluate the driver's own perception level of the target danger level. For example, a driver who chooses an aggressive driving style has a relatively high acceptance ability of the target danger level. The three categories of influencing factors are equally important.

[0079] After that, the parameters of the above-mentioned various influencing factors are normalized. In some possible implementation manners, the formula for normalization is as follows:

[0080]

[0081] In the formula, n is the number of evaluation contents of the parameters of each influencing factor, and x i is the quantified value of the parameter of each influencing factor, and Y(x i ) is the value of the parameter of each influencing factor after normalization.

[0082] At this time, the influencing factor parameters include values and units. Since the units of different influencing factors are different, normalization processing is performed to convert the value of each influencing factor parameter into a value within the range of [0, 1].

[0083] In some other possible implementation manners, since different influencing factors have different degrees of influence on the preset threshold, after determining the number of influencing factors, it is necessary to determine the influence weight of each influencing factor on the preset threshold.

[0084] At this time, first, distinguish the importance of the three types of influencing factors, and secondly, distinguish the importance of the sub-influencing factors in each type of influencing factor, and set the weights according to the standard that the sum of the weights of the 11 influencing factors is 1.

[0085] For example, the calculation of the influence degree of the influencing factor on the threshold can be shown by the following formula:

[0086]

[0087] In the formula, w j is the weight of the jth influencing factor, and Y(x j ) is the normalized parameter value of the jth influencing factor.

[0088] Then, the formula for calculating the preset threshold according to the influencing factor is as follows:

[0089]

[0090] In the formula, represents the mth preset threshold of the nth evaluation index, represents the influence degree of the influencing factor on the mth preset threshold of the nth evaluation index, represents the mth basic preset threshold of the nth evaluation index.

[0091] S104: Based on the multiple risk level evaluation indexes and the multiple risk level evaluation thresholds, and based on a preset risk level evaluation model, determine a first risk level evaluation result.

[0092] In some possible implementation manners, the target security risk can be divided into three levels. Therefore, each evaluation index model requires two preset thresholds to distinguish the three levels of danger. Determine the target security risk level according to the preset thresholds of the evaluation indexes obtained in steps S102 and S103. The specific calculation formula is as follows:

[0093]

[0094] In the formula, F i is the i-th evaluation index, T i 1 , T i 2 are the two preset thresholds of the i-th evaluation index, and L i is the risk assessment result of the i-th evaluation index model.

[0095] To further improve the accuracy and stability of the determination of the target risk level, based on the above embodiments, further, the method further includes:

[0096] According to the first risk level assessment result, based on the preset risk level jump model, determine the second risk level assessment result.

[0097] In some other possible implementation manners, in the step of determining the risk level evaluation index, the effectiveness of the evaluation results of LD, TTC, and TD can also be evaluated according to the evaluation index calculation method.

[0098] Among them, the LD model is related to the prediction effectiveness; the TTC model is related to the vehicle speed of the vehicle itself and the acceleration of the vehicle itself. When the vehicle speed of the vehicle is low and the deceleration is large, the vehicle is about to stop. As long as the braking distance of the vehicle is less than the relative distance between the vehicle and the target vehicle, this working condition can be determined to be safe; the TD model is related to the relative vehicle speed between the vehicle and the target vehicle. When the vehicle speed of the target vehicle is much greater than that of the vehicle itself, it can be determined that there is a deviation in the TD judgment at the current moment.

[0099] In some possible embodiments, a finiteness calculation model can be established to evaluate the effectiveness of the above three indexes.

[0100] Among them, the effectiveness of the LD evaluation index can be shown by the following formula:

[0101]

[0102] In the formula is the threshold with the effectiveness of v, is the threshold with the effectiveness of 1.

[0103] Among them, the effectiveness of the TTC evaluation index is shown by the following formula:

[0104]

[0105]

[0106] where RT represents the ratio of the braking distance of the host vehicle to the longitudinal distance from the target vehicle, is the threshold value with an effectiveness of 0, is the threshold value with an effectiveness of 1.

[0107] Among them, the effectiveness of the TD evaluation index is shown in the following formula:

[0108]

[0109]

[0110] where DV represents the value by which the target vehicle speed is higher than the host vehicle speed, is the threshold value with an effectiveness of 0, is the threshold value with an effectiveness of 1.

[0111] After that, the predicted results of the effective evaluation indexes are comprehensively processed. For example, in some possible implementation manners, it can be set that when the effectiveness of the evaluation index is lower than 0.6, this evaluation index is discarded. When the effectiveness of all three evaluation indexes is lower than 0.6, the evaluation index with the highest effectiveness is set as the effective evaluation index. When the evaluation results of all effective risk levels are 2, the highest risk level is output, and in other cases, the maximum value of the evaluation results of the effective risk levels is output.

[0112] That is, the specific calculation idea is shown in the following formula:

[0113]

[0114] where Lj represents the risk assessment result of the jth effective evaluation index model. L = 1 represents target safety, and there will be no movement interference with the host vehicle in a future period of time; L = 2 represents that the target is slightly dangerous, and the driver is reminded to pay attention to the surrounding environment; L = 3 represents that the target is significantly dangerous, and the driver is reminded that they may need to take over the vehicle. L is the preliminary risk level evaluation result of the target obtained in step S103.

[0115] In some possible implementation manners, the preset risk level jump model includes a target correlation model and a target risk level determination model;

[0116] Determining the second risk level evaluation result based on the preset risk level jump model according to the first risk level evaluation result includes:

[0117] When the first risk level assessment result is greater than the preset risk level assessment result, calculate the second relative longitudinal distance between the target vehicle and the own vehicle within a preset time;

[0118] In response to determining that the second relative longitudinal distance is greater than the preset distance, based on the target correlation model, determine that the target vehicle is a relevant vehicle of the own vehicle;

[0119] When the target vehicle is a relevant vehicle of the own vehicle, based on the target risk level determination model, determine the second risk level assessment result of the target vehicle.

[0120] Among them, the target correlation model is used to judge the correlation between the target vehicle and the current intelligent driving function state of the own vehicle, and only performs risk level processing on targets with clear correlation. The risk levels of the remaining targets are default set to 0 and not concerned. The correlation judgment mainly involves the degree of movement interference between the target vehicle and the own vehicle. When the lateral position of the target vehicle is relatively close to the own vehicle, and the trends of the relative lateral speed and the relative longitudinal speed make the collision risk between the two vehicles higher, the target vehicle is determined as a key attention vehicle at this time. Calculate the lateral distance between the own vehicle and the target vehicle within the next 5 s seconds, with a sampling period of 0.2 s seconds, to obtain the lateral distance matrix M = [ΔLatDist t0 , ΔLatDist t1 ,......ΔLatDist ti . If the lateral distance is less than 0 at more than 50% of the moments in the matrix, it is determined that the target is relevant to the current intelligent driving function of the own vehicle.

[0121] Among them, the target risk level determination model triggers and suppresses the risk level jump for targets with clear correlation. First, clarify the risk level jump trigger conditions and suppression conditions. The trigger conditions include the stability of the target historical state, the credibility of the risk level, and the change state of the lane where the own vehicle is located. The suppression conditions include the credibility of the risk level exit, the degree of danger of the risk level, and whether there is an obvious change in the motion state between the own vehicle and the target vehicle. Furthermore, according to the high and low jumps of the danger level, preset thresholds for distinguishing the trigger conditions and suppression conditions are set. Through the risk level jump model, the stability of the target risk level is greatly improved.

[0122] Please refer to Figure 2 , Figure 2 which is the structural block diagram of a target risk level determination device provided by an embodiment of the present application. The device includes

[0123] an acquisition unit 210, configured to acquire the first relative longitudinal distance between the target vehicle and the own vehicle, the first longitudinal speed of the target vehicle, and the second longitudinal speed of the own vehicle;

[0124] A first determination unit 220, configured to determine one or more risk level evaluation indicators of a target vehicle according to the first relative longitudinal distance, the first longitudinal speed, and the second longitudinal speed;

[0125] A second determination unit 230, configured to determine a risk level evaluation threshold of the target vehicle;

[0126] A third determination unit 240, configured to determine a first risk level evaluation result based on a preset risk level evaluation model according to the multiple risk level evaluation indicators and the multiple risk level evaluation thresholds.

[0127] As a possible implementation manner, the risk level evaluation indicator includes a collision time between the target vehicle and the own vehicle or a following distance of the own vehicle relative to the target vehicle.

[0128] As a possible implementation manner, the first determination unit is further configured to:

[0129] Calculate a longitudinal speed difference between the first longitudinal speed and the second longitudinal speed;

[0130] Calculate the collision time according to the first relative longitudinal distance and the longitudinal speed difference;

[0131] Calculate the following distance according to the first relative longitudinal distance and the first longitudinal speed.

[0132] As a possible implementation manner, the second determination unit is further configured to:

[0133] Obtain multiple influencing factors of the target vehicle relative to the own vehicle;

[0134] Perform normalization processing on the multiple influencing factors to determine influence weights respectively corresponding to each influencing factor;

[0135] Calculate a risk level evaluation threshold of the target vehicle according to the multiple influencing factors and the multiple influence weights corresponding to the multiple influencing factors.

[0136] As a possible implementation manner, the apparatus further includes:

[0137] A fourth determination unit, configured to determine a second risk level evaluation result based on a preset risk level jump model according to the first risk level evaluation result.

[0138] As a possible implementation manner, the preset risk level jump model includes a target correlation model and a target risk level determination model;

[0139] The third determination unit is further configured to:

[0140] When the first risk level assessment result is greater than the preset risk level assessment result, calculate a second relative longitudinal distance between the target vehicle and the own vehicle within a preset time;

[0141] In response to determining that the second relative longitudinal distance is greater than a preset distance, based on the target relevance model, determine that the target vehicle is a relevant vehicle of the own vehicle;

[0142] When the target vehicle is a relevant vehicle of the own vehicle, based on the target risk level determination model, determine a second risk level assessment result of the target vehicle.

[0143] It can be seen from the above technical solutions that by obtaining a first relative longitudinal distance between the target vehicle and the own vehicle, a first longitudinal speed of the target vehicle and a second longitudinal speed of the own vehicle; according to the first relative longitudinal distance, the first longitudinal speed and the second longitudinal speed, determine one or more risk level assessment indicators of the target vehicle; determine a risk level assessment threshold of the target vehicle; according to the multiple risk level assessment indicators and the multiple risk level assessment thresholds, based on a preset risk level assessment model, determine a first risk level assessment result. Since the actual driving traffic environment of intelligent driving vehicles is complex and changeable, the collected assessment indicators and preset value influencing factors consider factors in multiple dimensions such as road information, vehicle status, weather environment, perception ability, driver preference, etc., and determine the danger level based on multiple different types of parameters, improving the accuracy and stability of the target danger level.

[0144] Please refer to Figure 3 , Figure 3 which is a structural block diagram of a computer device for target risk level determination provided by an embodiment of the present application. The computer device includes a processor 310 and a memory 320:

[0145] The memory 320 is used to store program codes and transmit the program codes to the processor 310;

[0146] The processor 310 is used to execute the target risk level determination method according to any one of the above embodiments according to the instructions in the program codes.

[0147] An embodiment of the present application also discloses a computer-readable storage medium, which is used to store a computer program, and the computer program is used to execute the target risk level determination method according to any one of the above embodiments when being executed by a processor.

[0148] It can be understood that this method can be applied to a processing device, which is a processing device capable of performing motion control. For example, it can be a terminal device or a server with motion control functions. This method can be independently executed by a terminal device or a server, or can be applied to a network scenario where a terminal device and a server communicate, and is executed in cooperation with the terminal device and the server. Among them, the terminal device can be a device such as a computer or a mobile phone. The server can be understood as an application server or a Web server. In actual deployment, the server can be an independent server or a cluster server.

[0149] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium can be at least one of the following media: read-only memory (abbreviation: ROM), RAM, magnetic disk, or optical disc, etc., various media that can store program codes.

[0150] It should be noted that the various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments. The device and system embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0151] The above is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for determining a target risk level, characterized in that The method includes: Obtaining a first relative longitudinal distance between a target vehicle and the host vehicle, a first longitudinal speed of the target vehicle, and a second longitudinal speed of the host vehicle; Determining one or more risk level assessment indicators of the target vehicle according to the first relative longitudinal distance, the first longitudinal speed, and the second longitudinal speed; Determining a risk level assessment threshold of the target vehicle; Determining a first risk level assessment result based on the plurality of risk level assessment indicators and the plurality of risk level assessment thresholds according to a preset risk level assessment model.

2. The method according to claim 1, characterized in that, The risk level assessment indicators include a time to collision between the target vehicle and the host vehicle or a following time of the host vehicle relative to the target vehicle.

3. The method according to claim 2, characterized in that, The determining one or more risk level assessment indicators of the target vehicle according to the first relative longitudinal distance, the first longitudinal speed, and the second longitudinal speed includes: Calculating a longitudinal speed difference between the first longitudinal speed and the second longitudinal speed; Calculating the time to collision according to the first relative longitudinal distance and the longitudinal speed difference; Calculating the following time according to the first relative longitudinal distance and the first longitudinal speed.

4. The method according to claim 1, wherein The determining the risk level assessment threshold of the target vehicle includes: Obtaining a plurality of influencing factors of the target vehicle relative to the host vehicle; Performing a normalization process on the plurality of influencing factors to determine an influence weight corresponding to each influencing factor; Calculating the risk level assessment threshold of the target vehicle according to the plurality of influencing factors and the plurality of influence weights corresponding to the plurality of influencing factors.

5. The method according to claim 1, wherein The method further includes: Determining a second risk level assessment result based on a preset risk level jump model according to the first risk level assessment result.

6. The method according to claim 5, characterized in that, The preset risk level jump model includes a target correlation model and a target risk level determination model; The determining the second risk level assessment result based on the preset risk level jump model according to the first risk level assessment result includes: When the first risk level assessment result is greater than a preset risk level assessment result, calculating a second relative longitudinal distance between the target vehicle and the host vehicle within a preset time; In response to determining that the second relative longitudinal distance is greater than a preset distance, determining that the target vehicle is a relevant vehicle of the host vehicle based on the target correlation model; When the target vehicle is a relevant vehicle of the host vehicle, determining the second risk level assessment result of the target vehicle based on the target risk level determination model.

7. A target risk level determination device, characterized in that, The device includes An obtaining unit, configured to obtain a first relative longitudinal distance between a target vehicle and the host vehicle, a first longitudinal speed of the target vehicle, and a second longitudinal speed of the host vehicle; A first determining unit, configured to determine one or more risk level assessment indicators of the target vehicle according to the first relative longitudinal distance, the first longitudinal speed, and the second longitudinal speed; A second determining unit, configured to determine the risk level assessment threshold of the target vehicle; A third determination unit, configured to determine a first risk level evaluation result based on the plurality of risk level evaluation indicators and the plurality of risk level evaluation thresholds, based on a preset risk level evaluation model.

8. The device according to claim 7, characterized in that, The apparatus further includes: A fourth determination unit, configured to determine a second risk level evaluation result based on the first risk level evaluation result, based on a preset risk level jump model.

9. A computer device, characterized in that, The computer device includes a processor and a memory: The memory is configured to store program code and transmit the program code to the processor; The processor is configured to execute the target risk level determination method according to any one of claims 1-6 based on the instructions in the program code.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is configured to store a computer program, and the computer program is configured to execute the target risk level determination method according to any one of claims 1-6 when being executed by a processor.

Images