Risk target selection method and device and vehicle-mounted terminal

Abstract

The invention relates to a risk target selection method and device and a vehicle-mounted terminal. The method relates to the technical field of automatic driving, and comprises the following steps: acquiring at least one candidate risk target with a collision risk of a current vehicle in a current driving environment; for each candidate risk target, determining a TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target; according to the current motion state of the current vehicle and the current motion state of the candidate risk target, determining a relative position relationship between the candidate risk target and the current vehicle under at least one candidate intervention measure at the corresponding TTR; selecting a target intervention measure corresponding to the candidate risk target from the at least one candidate intervention measure according to the corresponding relative position relationship under the at least one candidate intervention measure; according to the target intervention measures corresponding to the candidate risk targets, the final risk target is selected from the candidate risk targets, and the accuracy and the real-time performance are good.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device and vehicle-mounted terminal for selecting risky targets. Background Art

[0002] With the rapid development of intelligent driving technology, active safety features such as FCW (Forward Collision Warning) and AEB (Automatic Emergency Braking) are increasingly used in vehicles.

[0003] Traditional technologies usually rely on sensor technology, data fusion technology, machine learning or deep learning algorithms to accurately predict and evaluate surrounding driving risks to ensure that vehicles can drive safely under various road and traffic conditions.

[0004] However, the accuracy of the risk target affecting the vehicle determined by the above method is relatively low, and the calculation efficiency is not high. Summary of the invention

[0005] Based on this, it is necessary to provide a risk target selection method, device and vehicle-mounted terminal that can improve the accuracy and computational efficiency of risk target selection results in the current vehicle driving environment in response to the above-mentioned technical problems.

[0006] In a first aspect, the present application provides a risk target selection method, comprising:

[0007] Acquire at least one candidate risk target for which the current vehicle has a collision risk in the current driving environment;

[0008] For each candidate risk target, determine the arrival time TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target;

[0009] Determine, according to the current motion state of the current vehicle and the current motion state of the candidate risk target, a relative position relationship between the candidate risk target and the current vehicle under at least one candidate intervention measure in a corresponding TTR;

[0010] Selecting a target intervention measure corresponding to the candidate risk target from at least one candidate intervention measure according to a corresponding relative position relationship under at least one candidate intervention measure;

[0011] According to the target intervention measures corresponding to each candidate risk target, the final risk target is selected from each candidate risk target.

[0012] In one of the embodiments, a target intervention measure corresponding to a candidate risk target is selected from at least one candidate intervention measure based on the corresponding relative position relationship under at least one candidate intervention measure, including: determining intervention reference data based on the corresponding relative position relationship under at least one candidate intervention measure; wherein the intervention reference data includes whether the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, whether the candidate risk target is on the driving path of the current vehicle at the TTR moment, whether the candidate risk target can be turned to avoid, and whether the candidate risk target can be braked to avoid; based on the intervention reference data, a target intervention measure corresponding to the candidate risk target is selected from at least one candidate intervention measure.

[0013] In one of the embodiments, at least one candidate intervention measure includes no intervention measure, braking intervention measure, left turn intervention measure and right turn intervention measure; according to the intervention reference data, a target intervention measure corresponding to the candidate risk target is selected from the at least one candidate intervention measure, including: if the candidate risk target is not on the driving path of the current vehicle at both the current moment and the TTR moment, then no intervention measure is used as the target intervention measure corresponding to the candidate risk target; if the candidate risk target is on the driving path of the current vehicle at the current moment or the TTR moment, and the candidate risk target is traveling toward the current vehicle, then braking intervention measure is used as the target intervention measure corresponding to the candidate risk target; if the candidate risk target is on the driving path of the current vehicle at the current moment or the TTR moment, and the candidate risk target is not traveling toward the current vehicle, If the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not traveling toward the current vehicle, and the candidate risk target can brake to avoid but cannot turn to avoid, then the braking intervention measure is used as the target intervention measure corresponding to the candidate risk target; if the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not traveling toward the current vehicle, and the candidate risk target can brake to avoid but cannot turn to avoid, then the braking intervention measure is used as the target intervention measure corresponding to the candidate risk target; if the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not traveling toward the current vehicle, and the candidate risk target can both brake to avoid and turn to avoid, then the target intervention measure corresponding to the candidate risk target is selected from the braking intervention measures, the left turn intervention measures, and the right turn intervention measures.

[0014] In one of the embodiments, a target intervention measure corresponding to a candidate risk target is selected from left turn intervention measures and right turn intervention measures, including: determining a required acceleration for the candidate risk target to avoid a collision under the steering intervention measures based on a current motion state of the candidate risk target; wherein the steering intervention measures include left turn intervention measures and right turn intervention measures; and selecting a target intervention measure corresponding to the candidate risk target from the left turn intervention measures and the right turn intervention measures based on a relationship between the required acceleration under the left turn intervention measures and the required acceleration under the right turn intervention measures.

[0015] In one of the embodiments, a target intervention measure corresponding to a candidate risk target is selected from braking intervention measures, left turn intervention measures, and right turn intervention measures, including: determining the required acceleration for the candidate risk target to avoid a collision under braking intervention measures and steering intervention measures according to a current motion state of the candidate risk target; wherein the steering intervention measures include left turn intervention measures and right turn intervention measures; and selecting the target intervention measure corresponding to the candidate risk target from braking intervention measures, left turn intervention measures, and right turn intervention measures according to a size relationship between each required acceleration.

[0016] In one of the embodiments, the relative position relationship between the candidate risk target at the corresponding TTR and the current vehicle under at least one candidate intervention measure is determined based on the current motion state of the current vehicle and the current motion state of the candidate risk target, including: determining the first position of the current vehicle at the TTR moment based on the current motion state of the current vehicle; determining the critical acceleration of the candidate risk target when triggering at least one active safety function of the current vehicle and the critical acceleration of the candidate risk target to avoid collision with the current vehicle under the steering intervention measure based on the current motion state of the candidate risk target; wherein each active safety function corresponds to at least one other candidate intervention measure except the steering intervention measure; determining the second position of the candidate risk target at the TTR moment under the corresponding candidate intervention measure based on each critical acceleration and the current motion state of the candidate risk target; determining the relative position relationship between the candidate risk target and the current vehicle under the corresponding candidate intervention measure based on the first position and the second position of the candidate risk target at the TTR moment under each candidate intervention measure.

[0017] In one of the embodiments, the relative position relationship between the candidate risk target in a corresponding TTR and the current vehicle under at least one candidate intervention measure is determined based on the current motion state of the current vehicle and the current motion state of the candidate risk target, including: when the TTR corresponding to the candidate risk target is valid, the relative position relationship between the candidate risk target in a corresponding TTR and the current vehicle under at least one candidate intervention measure is determined based on the current motion state of the current vehicle and the current motion state of the candidate risk target; wherein, the valid TTR of the candidate risk target includes: the candidate risk target is located on the driving path of the current vehicle within the corresponding TTR; the TTR corresponding to the candidate risk target is less than a preset TTR upper limit; when the candidate risk target belongs to a first preset category, the distance between the candidate risk target and the current vehicle is less than a preset distance threshold; the candidate risk target belongs to a second preset category; the second preset category includes the first preset category.

[0018] In one of the embodiments, the arrival time TTR corresponding to the candidate risk target is determined according to the current motion state of the current vehicle and the current motion state of the candidate risk target, including: determining the intersection stop situation of the current vehicle or the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target; determining the TTR corresponding to the candidate risk target according to the intersection stop situation.

[0019] In a second aspect, the present application also provides a risk target selection device, comprising:

[0020] An acquisition module, used to acquire at least one candidate risk target for which the current vehicle has a collision risk in the current driving environment;

[0021] A first determination module is used to determine, for each candidate risk target, a TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target;

[0022] a second determination module, for determining a relative position relationship between a corresponding TTR and a current vehicle of a candidate risk target under at least one candidate intervention measure according to a current motion state of the current vehicle and a current motion state of the candidate risk target;

[0023] A first selection module is used to select a target intervention measure corresponding to a candidate risk target from at least one candidate intervention measure according to a relative position relationship corresponding to at least one candidate intervention measure;

[0024] The second selection module is used to select a final risk target from each candidate risk target according to the target intervention measures corresponding to each candidate risk target.

[0025] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0026] Acquire at least one candidate risk target for which the current vehicle has a collision risk in the current driving environment;

[0027] For each candidate risk target, determine the arrival time TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target;

[0028] Determine, according to the current motion state of the current vehicle and the current motion state of the candidate risk target, a relative position relationship between the candidate risk target and the current vehicle under at least one candidate intervention measure in a corresponding TTR;

[0029] Selecting a target intervention measure corresponding to the candidate risk target from at least one candidate intervention measure according to a corresponding relative position relationship under at least one candidate intervention measure;

[0030] According to the target intervention measures corresponding to each candidate risk target, the final risk target is selected from each candidate risk target.

[0031] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0032] Acquire at least one candidate risk target for which the current vehicle has a collision risk in the current driving environment;

[0033] For each candidate risk target, determine the arrival time TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target;

[0034] Determine, according to the current motion state of the current vehicle and the current motion state of the candidate risk target, a relative position relationship between the candidate risk target and the current vehicle under at least one candidate intervention measure in a corresponding TTR;

[0035] Selecting a target intervention measure corresponding to the candidate risk target from at least one candidate intervention measure according to a corresponding relative position relationship under at least one candidate intervention measure;

[0036] According to the target intervention measures corresponding to each candidate risk target, the final risk target is selected from each candidate risk target.

[0037] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0038] Acquire at least one candidate risk target for which the current vehicle has a collision risk in the current driving environment;

[0039] For each candidate risk target, determine the arrival time TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target;

[0040] Determine, according to the current motion state of the current vehicle and the current motion state of the candidate risk target, a relative position relationship between the candidate risk target and the current vehicle under at least one candidate intervention measure in a corresponding TTR;

[0041] Selecting a target intervention measure corresponding to the candidate risk target from the at least one candidate intervention measure according to the corresponding relative position relationship under the at least one candidate intervention measure;

[0042] According to the target intervention measures corresponding to each candidate risk target, the final risk target is selected from each candidate risk target.

[0043] The above-mentioned risk target selection method, device and vehicle-mounted terminal determine the TTR corresponding to the candidate risk target by introducing the current motion state of the current vehicle and the current motion state of the candidate risk target with which the current vehicle has a collision risk in the current driving environment, thereby determining the relative position relationship between the corresponding TTR and the current vehicle under different candidate intervention measures, and using this relative position relationship to determine the target intervention measures corresponding to the candidate risk target, thereby realizing the prediction of the intervention measures for the movement process of the candidate risk target, and subsequently selecting the final risk target from the candidate updated targets based on the target intervention measures corresponding to the candidate risk target. Since the target intervention measures to be taken by the candidate risk target are fully considered in the process of selecting the final risk target, the influence of directly taking all the candidate risk targets as the final risk targets on the accuracy of risk target selection is avoided. In addition, in the process of risk target selection, there is no need to rely on complex neural network models or machine learning models, and naturally there is no need to train the corresponding models, which reduces the manpower, time and computing costs of model training, making it easier to deploy in L2-level ADAS (Advanced Driver Assistance Systems), reducing system costs and meeting the corresponding real-time requirements at the millisecond level. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of a process for selecting a risk target in one embodiment;

[0046] Figure 2 A flowchart of the steps of selecting a target intervention measure in one embodiment;

[0047] Figure 3 is a schematic flow chart of a step of determining a relative position relationship in one embodiment;

[0048] Figure 4 Schematic diagram of a process for determining TTR in one embodiment;

[0049] Figure 5A A schematic diagram of a process for selecting a risk target in one embodiment;

[0050] Figure 5B A schematic diagram of a vehicle motion model in one embodiment;

[0051] Figure 6 It is a structural block diagram of a risk target selection device in one embodiment;

[0052] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] In an exemplary embodiment, Figure 1 As shown, a method for selecting risky targets is provided. This embodiment uses the method applied to a terminal as an example for illustration. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0055] S110, obtaining at least one candidate risk target for which the current vehicle has a collision risk in the current driving environment.

[0056] The candidate risk target can be understood as a target that poses a collision threat to the current vehicle in the current driving environment, and may include a moving object whose moving speed is greater than a preset speed threshold, such as other vehicles. The preset speed threshold can be set or adjusted by technicians according to needs or experience, or determined through a large number of experiments, and this application does not impose any restrictions on this. For example, the preset speed threshold can be 2 m / s.

[0057] In an optional embodiment, environmental perception data of the current vehicle in the current driving environment can be obtained; based on the environmental perception data in the current driving environment, at least one initial risk target of the current vehicle in the current driving environment is identified; and from each initial risk target, an initial risk target whose movement speed is greater than a preset speed threshold and is close to the current vehicle is selected as a candidate risk target.

[0058] The environmental perception data may include at least one of image data and point cloud data, etc. Optionally, the image data may be acquired based on a vehicle-mounted camera; and the point cloud data may be acquired based on a radar.

[0059] For example, based on the target perception model, the initial risk targets in the current driving environment can be identified according to the environmental perception data in the current driving environment, and the target type and detection frame position of each initial risk target can be obtained. Among them, the target perception model can be implemented based on a traditional machine learning model or a deep learning model, and this application does not impose any limitation on this.

[0060] Since the initial risk target at different running speeds poses different threats to the current vehicle in the current driving environment, and given that the present application is more concerned with the collision risk of high-speed moving objects to the current vehicle during driving, in an optional implementation, it is also possible to determine whether the initial risk target is a candidate risk target that needs to be further screened based on the moving speed of the initial risk target. Specifically, if the moving speed of the initial risk target is greater than the preset speed threshold, the initial risk target is used as a candidate risk target; if the moving speed of the initial risk target is not greater than the preset speed threshold, the initial risk target is no longer used as a candidate risk target.

[0061] S120 , for each candidate risk target, determine a TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target.

[0062] The current motion state may include a motion state and a static state. TTR may be understood as the time when the candidate risk target intersects with the current vehicle, or when one of the two stops moving.

[0063] Exemplarily, for each candidate risk target, the relative motion state between the current vehicle and the candidate risk target can be determined according to the current motion state of the current vehicle and the current motion state of the candidate risk target, and the TTR corresponding to the candidate risk target can be determined according to the relative motion state.

[0064] It is worth noting that the relative position relationship between the candidate risk target and the current vehicle will also change under different relative motion states. Therefore, the TTR corresponding to the candidate risk target is determined according to the relative motion state, which ensures the accuracy of the determined TTR.

[0065] S130, determining a relative position relationship between a corresponding TTR and the current vehicle of the candidate risk target under at least one candidate intervention measure according to the current motion state of the current vehicle and the current motion state of the candidate risk target.

[0066] The current motion state may also include state description data for numerically quantifying motion parameters in at least one state dimension. Optionally, the state description data may include at least one of motion speed, motion acceleration, current position, steering angle, and curvature radius.

[0067] The relative position relationship is used to characterize the relative position between the candidate risk target and the current vehicle at the TTR moment.

[0068] The at least one candidate intervention measure includes no intervention measure, a braking intervention measure, a left turn intervention measure, and a right turn intervention measure.

[0069] Exemplarily, no intervention measures represent that the candidate risk target moves normally according to the current motion state; braking intervention measures represent that a braking operation is performed on the candidate risk target, thereby changing the current motion state of the candidate risk target; left turn intervention measures represent that a left turn operation is performed on the candidate risk target, thereby changing the current motion state of the candidate risk target; right turn intervention measures represent that a right turn operation is performed on the candidate risk target, thereby changing the current motion state of the candidate risk target.

[0070] In an optional embodiment, the first position of the current vehicle at the TTR moment can be determined based on the current motion state of the current vehicle; for each candidate intervention measure, the second position of the candidate risk target at the TTR moment under the candidate intervention measure can be determined based on the current motion state of the candidate risk target; based on the first position and the second position, the relative position relationship between the candidate risk target at the corresponding TTR and the current vehicle under at least one candidate intervention measure is determined.

[0071] It is understandable that the TTR corresponding to the candidate risk target may have certain deviations, resulting in invalid TTR. Using an invalid TTR to determine the relative position relationship will inevitably affect the accuracy of the relative position relationship determination result. Since the relative position relationship serves as the basis for the subsequent determination of the target intervention measures corresponding to the candidate risk target, it affects the accuracy of the final risk target determination result. Therefore, when the TTR is invalid, it is necessary to no longer determine the relative position relationship between the candidate risk target under at least one candidate intervention measure and the current vehicle, so as to avoid large errors in the relative position relationship determination affecting subsequent calculation results.

[0072] In an optional embodiment, when the TTR corresponding to the candidate risk target is valid, the relative position relationship between the corresponding TTR and the current vehicle of the candidate risk target under at least one candidate intervention measure is determined according to the current motion state of the current vehicle and the current motion state of the candidate risk target. Wherein, the TTR of the candidate risk target is valid including: the candidate risk target is located on the driving path of the current vehicle within the corresponding TTR; the TTR corresponding to the candidate risk target is less than the preset TTR upper limit; when the candidate risk target belongs to the first preset category, the distance between the candidate risk target and the current vehicle is less than the preset distance threshold; the candidate risk target belongs to the second preset category; the second preset category includes the first preset category.

[0073] Among them, the preset TTR upper limit, the first preset category, the second preset category and the preset distance threshold can be set or adjusted by technical personnel according to needs or experience, or determined through a large number of experiments, and this application does not impose any limitation on this.

[0074] In some specific implementations, the preset TTR upper limit may be 3 seconds; the first preset category may include motorcycles; the preset distance threshold may be 50 meters; the second preset category may include motorcycles, vehicles, pedestrians, etc.

[0075] S140: Select a target intervention measure corresponding to the candidate risk target from at least one candidate intervention measure according to the corresponding relative position relationship under at least one candidate intervention measure.

[0076] For example, for each candidate intervention measure, it can be determined whether the candidate risk target can avoid collision with the current vehicle according to the corresponding relative position relationship under the candidate intervention measure; the target intervention measure can be selected from the candidate intervention measures that the candidate risk target can avoid collision with the current vehicle. Correspondingly, the target intervention measure can be selected from the candidate intervention measures that the candidate risk target can avoid collision with the current vehicle according to the difficulty and power consumption of the candidate risk target to execute each candidate intervention measure.

[0077] Or illustratively, based on the corresponding relative position relationship under at least one candidate intervention measure, a candidate intervention measure that can avoid the collision between the candidate risk target and the current vehicle as much as possible is selected as the target intervention measure.

[0078] S150, selecting a final risk target from each candidate risk target according to the target intervention measures corresponding to each candidate risk target.

[0079] The final risk target is the target that will inevitably collide with the current vehicle if neither the target nor the current vehicle performs any intervention measures.

[0080] Exemplarily, for any candidate risk target, if there is no target intervention measure for the candidate risk target that can avoid a collision with the current vehicle, the candidate risk target is used as the final risk target.

[0081] The above optional embodiment introduces the current motion state of the current vehicle and the current motion state of the candidate risk target with the risk of collision in the current driving environment, determines the TTR corresponding to the candidate risk target, and thus determines the relative position relationship between the corresponding TTR and the current vehicle under different candidate intervention measures, and determines the target intervention measures corresponding to the candidate risk target with the help of the relative position relationship, so as to predict the intervention measures of the candidate risk target motion process, and then selects the final risk target from the candidate update target according to the target intervention measures corresponding to the candidate risk target. Since the target intervention measures to be taken by the candidate risk target are fully considered in the process of selecting the final risk target, the influence of directly taking the full amount of candidate risk targets as the final risk target on the accuracy of risk target selection is avoided. In addition, in the process of selecting risk targets, there is no need to rely on complex neural network models or machine learning models, and naturally there is no need to train the corresponding models, which reduces the manpower cost, time cost and computing power cost of model training, making it easier to deploy in L2-level ADAS, reducing system costs, and meeting the corresponding real-time requirements at the millisecond level.

[0082] Based on the technical solutions of the above embodiments, in an optional embodiment, an active safety function can be performed on the final risk target; wherein the active safety function includes an FCW function and an AEB function. The FCW function is used to output a forward collision warning; and the AEB function is used to automatically trigger vehicle braking.

[0083] Exemplarily, when TTR is less than the preset TTR upper limit and not less than the preset TTR lower limit, the FCW function is executed; when TTR is less than the preset TTR lower limit, the AEB measure is executed. The preset TTR upper limit and the preset TTR lower limit can be set or adjusted by technicians according to needs or experience, or determined repeatedly through a large number of tests, and this application does not impose any limitation on this. Exemplarily, the preset TTR upper limit can be 3s; the preset TTR lower limit can be 1s.

[0084] The above scheme can effectively predict the potential conflict between the current vehicle and the final risk target, providing strong support for taking safety intervention measures in advance. It is worth noting that during the driving of the current vehicle, the current vehicle can be intervened only for the final risk target, avoiding the poor user experience caused by the intervention error, while ensuring the safe driving of the current vehicle.

[0085] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, the step of selecting the target intervention measures corresponding to S140 is refined.

[0086] See also Figure 2 The steps for selecting target interventions shown include:

[0087] S210: Determine intervention reference data according to a relative position relationship corresponding to at least one candidate intervention measure.

[0088] S220: Selecting a target intervention measure corresponding to the candidate risk target from at least one candidate intervention measure according to the intervention reference data.

[0089] The at least one candidate intervention measure includes no intervention measure, a braking intervention measure, a left turn intervention measure, and a right turn intervention measure.

[0090] Among them, the intervention reference data is used to characterize the path consistency between the candidate risk target and the current target at the current moment, and whether the candidate risk target can be avoided through different intervention measures.

[0091] Exemplarily, the intervention reference data includes whether the candidate risk target is on the driving path of the current vehicle at the current moment, whether the candidate risk target is on the driving path of the current vehicle at the TTR moment, whether the candidate risk target can steer to avoid, and whether the candidate risk target can brake to avoid.

[0092] In an optional embodiment, if the candidate risk target is not on the driving path of the current vehicle at both the current time and the TTR time, no intervention measure is used as the target intervention measure corresponding to the candidate risk target.

[0093] It is worth noting that when it is determined that the candidate risk target is not on the driving path of the current vehicle, a relatively strict strategy is adopted. Only when the candidate risk target is not on the formal path of the current vehicle at both the current moment and the TTR moment, is it determined that the candidate risk target is not on the driving path of the current vehicle. This can avoid prematurely intervening with the candidate risk target as the ultimate risk target that affects vehicle driving, which would bring a poor driving experience to users.

[0094] In another optional embodiment, if the candidate risk target is on the driving path of the current vehicle at the current moment or the TTR moment, and the candidate risk target is traveling toward the current vehicle, the braking intervention measure is used as the target intervention measure corresponding to the candidate risk target.

[0095] When the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is driving towards the current vehicle, the candidate risk target is likely to brake for driving intervention to avoid collision. Therefore, the braking intervention measure can be directly used as the target intervention measure.

[0096] In another optional embodiment, if the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not driving towards the current vehicle, and the candidate risk target can turn to avoid but cannot brake to avoid, then the target intervention measures corresponding to the candidate risk target are selected from the left turn intervention measures and the right turn intervention measures.

[0097] If the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not driving towards the current vehicle, it can be checked whether only steering avoidance is possible; if only steering avoidance is possible, the intervention measure that is easier to implement or consumes less power is selected from the left turn intervention measures and the right turn intervention measures as the target intervention measure.

[0098] Exemplarily, the required acceleration for the candidate risk target to avoid collision under steering intervention measures can be determined based on the current motion state of the candidate risk target; wherein the steering intervention measures include left turn intervention measures and right turn intervention measures; based on the relationship between the required acceleration under the left turn intervention measures and the required acceleration under the right turn intervention measures, the target intervention measures corresponding to the candidate risk target are selected from the left turn intervention measures and the right turn intervention measures.

[0099] The required acceleration can be understood as the acceleration at which the candidate risk target can just avoid a collision with the current vehicle.

[0100] For example, the critical acceleration of the candidate risk target to avoid collision with the current vehicle under the steering intervention measure can be determined according to the current motion speed and current motion acceleration of the candidate risk target, and the critical acceleration is used as the required acceleration of the candidate risk target. Accordingly, the required acceleration under the left turn intervention measure is compared with the required acceleration under the right turn intervention measure, and the steering intervention measure with the smaller required acceleration is used as the target intervention measure.

[0101] It is worth noting that, since different types of candidate risk targets may have different ways of determining critical acceleration, it is also possible to introduce the target type of the candidate risk target and determine the target determination function that matches the target type; based on the target determination function, according to the current motion speed and current motion acceleration of the candidate risk target, determine the critical acceleration for the candidate risk target to avoid collision with the current vehicle under steering intervention measures. Among them, the independent variables of the target determination function are the current motion speed and current motion acceleration of the candidate risk target; the dependent variable of the target determination function is the critical acceleration; the target determination function can be implemented based on existing machine learning models, deep learning models or other mathematical models, and this application does not impose any restrictions on this. It should be noted that the function branches of the corresponding target determination function under different intervention measures are different.

[0102] In another optional embodiment, if the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not driving towards the current vehicle, and the candidate risk target can brake to avoid but cannot turn to avoid, then the braking intervention measure will be used as the target intervention measure corresponding to the candidate risk target.

[0103] If the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not driving towards the current vehicle, it can be checked whether only braking avoidance is possible and steering avoidance is not possible; if only braking avoidance is possible, braking intervention measures are used as target intervention measures.

[0104] In another optional embodiment, if the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not driving towards the current vehicle, and the candidate risk target can both brake and turn to avoid, then the target intervention measures corresponding to the candidate risk target are selected from the braking intervention measures, left turn intervention measures and right turn intervention measures.

[0105] If the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not driving towards the current vehicle, it can be checked whether it can be automatically avoided and steered to avoid it; when both braking and steering avoidance are possible, from the braking intervention measures, left turn intervention measures and right turn intervention measures, the intervention measures that are easier to implement or consume less power are selected as the target intervention measures.

[0106] Exemplarily, the required acceleration for the candidate risk target to avoid collision under braking intervention measures and steering intervention measures can be determined respectively according to the current motion state of the candidate risk target; wherein the steering intervention measures include left turn intervention measures and right turn intervention measures; according to the size relationship between the required accelerations, the target intervention measures corresponding to the candidate risk target are selected from the braking intervention measures, left turn intervention measures and right turn intervention measures.

[0107] For example, the critical acceleration of the candidate risk target to avoid collision with the current vehicle under different intervention measures can be determined according to the current movement speed and current movement acceleration of the candidate risk target, and the critical acceleration is used as the required acceleration of the candidate risk target. The different intervention measures include braking intervention measures, left turn intervention measures, and right turn intervention measures.

[0108] It is worth noting that, since different types of candidate risk targets may have different ways of determining critical acceleration, it is also possible to introduce the target type of the candidate risk target and determine the target determination function that matches the target type; for any intervention measure, based on the target determination function, according to the current motion speed and current motion acceleration of the candidate risk target, determine the critical acceleration for the candidate risk target to avoid collision with the current vehicle under the intervention measure. Among them, the independent variables of the target determination function are the current motion speed and current motion acceleration of the candidate risk target; the dependent variable of the target determination function is the critical acceleration; the target determination function can be implemented based on existing machine learning models, deep learning models or other mathematical models, and this application does not impose any restrictions on this. It should be noted that the function branches of the corresponding target determination function under different intervention measures are different.

[0109] Exemplarily, selecting target intervention measures corresponding to the candidate risk target from braking intervention measures, left turn intervention measures and right turn intervention measures based on the size relationship between the demand accelerations may include: selecting reference intervention measures from the left turn intervention measures and the right turn intervention measures based on the size relationship between the demand acceleration under the left turn intervention measures and the demand acceleration under the right turn intervention measures; selecting target intervention measures corresponding to the candidate risk target from the reference intervention measures and the braking intervention measures based on the size relationship between the demand acceleration under the reference intervention measures and the demand acceleration under the braking intervention measures.

[0110] In an optional implementation, from the required acceleration under the left-turn intervention measure, the required acceleration under the right-turn intervention measure, and the required acceleration under the braking intervention measure, an intervention measure with the smallest required acceleration is selected as the target intervention measure.

[0111] Optionally, from the demand acceleration under the left-turn intervention measure and the demand acceleration under the right-turn intervention measure, an intervention measure with a smaller demand acceleration is selected as a reference intervention measure; from the demand acceleration under the reference intervention measure and the demand acceleration under the braking intervention measure, an intervention measure with a smaller demand acceleration is selected as a target intervention measure.

[0112] It is worth noting that when determining that a candidate risk target is on the driving path of the current vehicle, a relatively loose strategy is adopted. If the candidate risk target is on the formal path of the current vehicle at the current moment or at any moment in the TTR moment, it can be considered that the candidate risk target is on the driving path of the current vehicle. This can avoid prematurely intervening with the candidate risk target as the ultimate risk target that affects vehicle driving, which would bring a poor driving experience to users.

[0113] The above optional embodiment determines the intervention reference data by introducing the relative position relationship under different candidate intervention measures, and selects the target intervention measure corresponding to the candidate risk target from at least one candidate intervention measure according to whether the candidate risk target is on the driving path of the current vehicle at the current moment, whether the candidate risk target is on the driving path of the current vehicle at the TTR moment, whether the candidate risk target can turn to avoid, and whether the candidate risk target can brake to avoid, thereby improving the accuracy of the target intervention measure determination result. The target intervention measure determination result of the candidate risk target is subsequently used as a reference for the subsequent selection of the final risk target, which helps to improve the accuracy of the final risk target determination result.

[0114] On the basis of the technical solutions of the above-mentioned embodiments, the present application also provides an optional embodiment. In this optional embodiment, the step of determining the relative position relationship corresponding to S130 is refined.

[0115] See also Figure 3 The steps for determining the relative position relationship shown include:

[0116] S310, determining a first position of the current vehicle at the TTR time according to the current motion state of the current vehicle.

[0117] In an optional embodiment, the following formula may be used to determine the first position of the current vehicle at the TTR time:

[0118] ;

[0119] Among them, pos_pred is the first position of the current vehicle; pos is the current position of the current vehicle; vel is the current moving speed of the current vehicle; time is TTR; acc is the current acceleration of the current vehicle.

[0120] S320, determining, based on the current motion state of the candidate risk target, a critical acceleration of the candidate risk target when at least one active safety function of the current vehicle is triggered, and a critical acceleration of the candidate risk target to avoid collision with the current vehicle under steering intervention measures.

[0121] Each active safety function corresponds to at least one other candidate intervention measure except the steering intervention measure.

[0122] Among them, active safety functions include FCW (Forward Collision Warning) function and AEB (Automatic Emergency Braking) function. Among them, FCW function is used to output forward collision warning; AEB function is used to automatically trigger vehicle braking.

[0123] Exemplarily, the FCW function corresponds to a preset TTR upper limit, indicating that the FCW function needs to be triggered for collision warning when the preset TTR upper limit is reached; the AEB function corresponds to a preset TTR lower limit, indicating that the AEB function needs to be triggered for emergency braking when the preset TTR lower limit is reached.

[0124] Optionally, the first critical acceleration of the candidate risk target when the FCW function is triggered may be determined according to the current motion state of the candidate risk target, that is, the first critical acceleration when the candidate risk target just enters the boundary area of ​​the FCW function of the current vehicle.

[0125] Alternatively, the second critical acceleration of the candidate risk target when the AEB function is triggered may be determined according to the current motion state of the candidate risk target, that is, the second critical acceleration when the candidate risk target just enters the AEB function boundary area of ​​the current vehicle.

[0126] Or optionally, according to the current motion state of the candidate risk target, a third critical acceleration for the candidate risk target to avoid collision with the current vehicle under the steering intervention measure is determined.

[0127] The first critical acceleration, the second critical acceleration and the third critical acceleration may include at least one of lateral acceleration, longitudinal acceleration and steering acceleration.

[0128] S330: Determine the second position of the candidate risk target at the TTR time under the corresponding candidate intervention measure according to each critical acceleration and the current motion state of the candidate risk target.

[0129] For no intervention measures, the second position of the candidate risk target at the TTR moment is determined directly according to at least one current motion state such as current speed, current acceleration, current position, heading angle and curvature radius;

[0130] For the braking intervention measures corresponding to the FCW function, the second position of the candidate risk target at the TTR moment can be determined based on at least one current motion state such as the current speed, current position, heading angle and curvature radius, and the first critical acceleration, assuming that the candidate risk target enters the collision warning boundary.

[0131] For the braking intervention measures corresponding to the AEB function, the second position of the candidate risk target at the TTR moment can be determined based on at least one current motion state such as the current speed, current position, heading angle and curvature radius, and the second critical acceleration, assuming that the candidate risk target enters the emergency braking boundary.

[0132] For left-turn intervention measures, the second position of the candidate risk target at the TTR moment when the candidate risk target turns left can be determined based on at least one current motion state such as the current speed, current position, heading angle and curvature radius, and the third critical acceleration.

[0133] For the right turn intervention measure, the second position of the candidate risk target at the TTR moment is determined assuming that the candidate risk target turns right based on at least one current motion state such as the current speed, current position, heading angle and curvature radius, and the third critical acceleration.

[0134] It should be noted that the second position of the candidate risk target at the TTR moment can be determined based on at least one current motion state such as the current speed, current acceleration, current position, heading angle and radius of curvature, and at least one of the traditional methods, and this application does not impose any restrictions on this. When determining the second position of the candidate risk target at the TTR moment under different candidate intervention measures based on at least one current motion state such as the current speed, current position, heading angle and radius of curvature, and the critical acceleration, it is only necessary to replace the current acceleration in the current motion state with the critical acceleration.

[0135] S340: Determine a relative position relationship between the candidate risk target under the corresponding candidate intervention measure and the current vehicle according to the first position and the second position of the candidate risk target under each candidate intervention measure at the TTR moment.

[0136] Exemplarily, for each candidate intervention measure, the first position can be converted into a curvilinear coordinate system, and each second position can be converted into a curvilinear coordinate system to determine the relative position between the candidate risk target and the current vehicle at the TTR moment under the corresponding candidate intervention measure, thereby characterizing the relative position relationship between the two.

[0137] The above-mentioned optional embodiment introduces the critical acceleration of the candidate risk target when introducing at least one active safety function and the critical acceleration for avoiding collision with the current vehicle under steering intervention measures, and respectively determines the second position of the candidate risk target at the TTR moment when executing different candidate intervention measures, thereby determining the relative position relationship between the candidate risk target and the current vehicle under different candidate intervention measures, thereby ensuring the comprehensiveness and accuracy of the relative position relationship determined by the candidate risk target when executing different candidate intervention measures, thereby predicting relatively accurate target intervention measures for the candidate wind selection targets, and providing a guarantee for the accurate prediction of the final risk target.

[0138] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, the step of determining the TTR corresponding to S120 is refined.

[0139] See also Figure 4 The steps for determining the TTR shown include:

[0140] S410: Determine the intersection stop status of the current vehicle or the candidate risk target according to the current motion status of the current vehicle and the current motion status of the candidate risk target.

[0141] The intersection stop condition may include at least one of whether the current vehicle or the candidate risk target can stop moving, whether the current vehicle and the candidate risk target can intersect, and whether the current vehicle or the candidate risk target can stop moving before intersecting.

[0142] Optionally, it can be determined whether the two can intersect and whether to stop moving before intersecting based on the current moving speed of the current vehicle, the current moving acceleration of the current vehicle, the current moving speed of the candidate risk target and the current acceleration of the candidate risk target.

[0143] Alternatively, it is also possible to determine whether the candidate risk target can intersect with the current vehicle and whether to stop moving before the intersection based on the relative movement speed and relative movement acceleration of the candidate risk target with respect to the current vehicle.

[0144] S420: Determine the TTR corresponding to the candidate risk target according to the intersection stop condition.

[0145] In an optional embodiment, if the intersection stop condition indicates that the current vehicle and the candidate risk target cannot intersect, a preset default value is used as the TTR corresponding to the candidate risk target.

[0146] In another optional embodiment, if the intersection stop condition indicates that the current vehicle or the candidate risk target can stop moving before the intersection, the TTR corresponding to the candidate risk target is determined according to the stop time of the current vehicle and the candidate risk target.

[0147] If the intersection stop situation indicates that the current vehicle or the candidate risk target can stop moving before the intersection, it means that the current vehicle and the candidate risk target cannot intersect because at least one of them stops moving. At this time, the stopped party among the current vehicle and the candidate risk target can be used as the stopped moving target; according to the stopping time of the stopped moving target, the TTR corresponding to the candidate risk target is determined.

[0148] Optionally, if the stopped moving target includes only one party, the stop time corresponding to the stopped moving target is used as the TTR corresponding to the candidate risk target. Alternatively, if the stopped moving target includes two parties, the smaller stop time is selected from the stop times of each stopped moving target as the TTR corresponding to the candidate risk target.

[0149] In another optional embodiment, if the intersection stop condition indicates that the current vehicle or the candidate risk target does not stop moving before the intersection, the TTR corresponding to the candidate risk target is determined according to the intersection time between the current vehicle and the candidate risk target.

[0150] If the intersection stop situation indicates that the current vehicle or the candidate risk target has not stopped moving before the intersection, it means that the current vehicle and the candidate risk target will collide according to their respective current motion states. At this time, the intersection time when the current vehicle and the candidate risk target intersect can be directly used as the TTR corresponding to the candidate risk target.

[0151] If the intersection stop condition indicates that the current vehicle and the candidate risk target cannot intersect, it means that when the current vehicle and the candidate risk target move in the same direction, the movement speed of the candidate risk target is not less than the movement speed of the current vehicle, and the movement acceleration of the candidate risk target is not less than the movement acceleration of the current vehicle. At this time, the preset default value can be directly used as the TTR corresponding to the candidate risk target. The preset default value can be preset by a technician and can be a default maximum value.

[0152] In another optional embodiment, it can be assumed that both the current vehicle and the candidate risk target are in motion, and the motion TTI (Time To Intersection) in the motion state is determined; it can be assumed that the current vehicle can stop moving, and the vehicle TTI when the current vehicle stops moving is determined; it can be assumed that the candidate risk target can stop moving, and the target TTI when the candidate risk target stops moving is determined. Accordingly, according to the intersection stop situation, the TTR corresponding to the candidate risk target is selected from the motion TTI, vehicle TTI, target TTI and preset default value.

[0153] Optionally, when the intersection stop situation represents that the current vehicle or the candidate risk target can stop moving before the intersection, if both the current vehicle and the candidate risk target can stop moving before the intersection, the smaller one is selected from the vehicle TTI and the target TTI as the TTR corresponding to the candidate risk target; if only the current vehicle can stop moving before the intersection, the vehicle TTI is used as the TTR corresponding to the candidate risk target; if only the candidate risk target can stop moving before the intersection, the target TTI is used as the TTR corresponding to the candidate risk target.

[0154] Or optionally, when the intersection stop condition indicates that the current vehicle or the candidate risk target does not stop moving before the intersection, the moving TTI is used as the TTR corresponding to the candidate risk target.

[0155] Alternatively, if the intersection stop condition indicates that the current vehicle and the candidate risk target cannot intersect, a preset default value is used as the TTR corresponding to the candidate risk target.

[0156] The above optional embodiment determines the TTR corresponding to the candidate risk target by introducing the intersection stop situation of the current vehicle or the candidate risk target, thereby ensuring the accuracy of the determined TTR and providing data support for the subsequent determination of the relative position relationship, thereby helping to improve the accuracy of the relative position relationship determination result.

[0157] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment, in which a risk target selection method is described in detail.

[0158] See also Figure 5A The risk target selection method shown is applied to the vehicle-mounted terminal of the current vehicle, including:

[0159] S501, obtaining the curvature radius, current movement speed, current acceleration and environment perception data of the current vehicle in the current driving environment;

[0160] See also Figure 5BThe schematic diagram of the vehicle motion model shown in FIG. 1 can be used to determine the curvature radius of the current vehicle using the following formula based on the vehicle motion model:

[0161] ;

[0162] Among them, Crvt is the curvature radius of the current vehicle; WheelAngle is the wheel angle; RearSlipAngle is the rear caster angle of the current vehicle; FrontSlipAngle is the front caster angle of the current vehicle; L f is the distance from the center of mass of the current vehicle to the front axle; L r is the distance from the center of mass of the current vehicle to the rear axle; M is the mass of the current vehicle; V is the speed of the current vehicle; C f is the front axial stiffness of the current vehicle; C r is the rear axial stiffness of the current vehicle; R is the center of mass curvature radius of the current vehicle.

[0163] S502, identifying at least one candidate risk target in the current driving environment of the current vehicle based on the target detection model and according to the environmental perception data in the current driving environment;

[0164] S503, selecting a candidate risk target whose moving speed is greater than a preset speed threshold and is close to the current vehicle as a candidate risk target;

[0165] The preset speed threshold may be set by a technician according to needs or experience, for example, may be 2 m / s.

[0166] S504, determining the intersection stop status of the current vehicle or the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target;

[0167] S505, determining a motion TTI when both the current vehicle and the candidate risk target are in motion, a vehicle TTI when the current vehicle can stop moving, and a target TTI when the candidate risk target can stop moving;

[0168] S506, selecting a TTR corresponding to the candidate risk target from the motion TTI, the vehicle TTI, the target TTI and the preset default value according to the intersection stop condition;

[0169] S507, determining a first position corresponding to the current vehicle at the TTR time according to the current motion state of the current vehicle;

[0170] S508, determining a critical acceleration for avoiding a collision with the current vehicle under different candidate intervention measures according to the target type, current motion speed, and current acceleration of the candidate risk target;

[0171] S509, determining a second position corresponding to the candidate risk target at the TTR time under at least one candidate intervention measure according to the current motion state and critical acceleration of the candidate risk target;

[0172] S510, determining a relative position relationship between the candidate risk target and the current vehicle under the corresponding candidate intervention measure according to the second position and the first position under each candidate intervention measure;

[0173] S511A, if the relative position relationship represents situation 1, then no intervention measure is used as the target intervention measure corresponding to the candidate risk target;

[0174] Among them, situation 1 is that the candidate risk target is not on the driving path of the current vehicle at both the current time and the TTR time.

[0175] S511B, if the relative position relationship represents situation 2, the braking intervention measure is used as the target intervention measure corresponding to the candidate risk target;

[0176] Among them, situation 2 is that the candidate risk target is on the driving path of the current vehicle at the current time or TTR time, and the candidate risk target is driving towards the current vehicle.

[0177] S511C, if the relative position relationship represents situation 3, then select the target intervention measure corresponding to the candidate risk target from the left-turn intervention measures and the right-turn intervention measures;

[0178] Among them, situation 3 is that the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not driving towards the current vehicle, and the candidate risk target can turn to avoid but cannot brake to avoid.

[0179] S511D, if the relative position relationship represents situation 4, the braking intervention measure is used as the target intervention measure corresponding to the candidate risk target;

[0180] Among them, situation 4 is that the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not driving towards the current vehicle, and the candidate risk target can brake to avoid but cannot turn to avoid.

[0181] S511E, if the relative position relationship represents situation 5, then select a target intervention measure corresponding to the candidate risk target from the braking intervention measures, the left turn intervention measures, and the right turn intervention measures;

[0182] Among them, situation 5 is that the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, and the candidate risk target is not driving towards the current vehicle, and the candidate risk target can both brake and turn to avoid.

[0183] S512, if there is no target intervention measure for the candidate risk target that can avoid a collision with the current vehicle, the candidate risk target is used as the final risk target;

[0184] S513A, if the TTR of the final risk target is less than the preset TTR upper limit and not less than the preset TTR lower limit, then execute the FCW measure;

[0185] S513B, if the TTR of the final risk target is less than the preset TTR lower limit, the AEB measure is executed.

[0186] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0187] Based on the same inventive concept, the embodiment of the present application also provides a risk target selection device for implementing the risk target selection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more risk target selection device embodiments provided below can refer to the limitations on the risk target selection method above, and will not be repeated here.

[0188] In an exemplary embodiment, Figure 6 As shown, a risk target selection device is provided, including: an acquisition module 610, a first determination module 620, a second determination module 630, a first selection module 640 and a second selection module 650. Among them:

[0189] An acquisition module 610 is used to acquire at least one candidate risk target for which the current vehicle has a collision risk in the current driving environment;

[0190] A first determination module 620 is used to determine, for each candidate risk target, a TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target;

[0191] A second determination module 630, for determining a relative position relationship between a corresponding TTR and a current vehicle of a candidate risk target under at least one candidate intervention measure according to a current motion state of the current vehicle and a current motion state of the candidate risk target;

[0192] A first selection module 640 is used to select a target intervention measure corresponding to a candidate risk target from at least one candidate intervention measure according to a relative position relationship corresponding to at least one candidate intervention measure;

[0193] The second selection module 650 is used to select a final risk target from each candidate risk target according to the target intervention measures corresponding to each candidate risk target.

[0194] In one embodiment, the first selection module 640 includes: a first determination unit, used to determine intervention reference data based on the corresponding relative position relationship under at least one candidate intervention measure; wherein the intervention reference data includes whether the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment, whether the candidate risk target is on the driving path of the current vehicle at the TTR moment, whether the candidate risk target can be turned to avoid, and whether the candidate risk target can be braked to avoid; the first selection unit is used to select the target intervention measure corresponding to the candidate risk target from at least one candidate intervention measure according to the intervention reference data.

[0195] In one embodiment, at least one candidate intervention measure includes no intervention measure, braking intervention measure, left turn intervention measure and right turn intervention measure; the first selection unit includes: a first selection subunit, which is used to use no intervention measure as the target intervention measure corresponding to the candidate risk target if the candidate risk target is not on the driving path of the current vehicle at both the current moment and the TTR moment; a second selection subunit, which is used to use braking intervention measure as the target intervention measure corresponding to the candidate risk target if the candidate risk target is on the driving path of the current vehicle at the current moment or the TTR moment, and the candidate risk target is traveling toward the current vehicle; a third selection subunit, which is used to use braking intervention measure as the target intervention measure corresponding to the candidate risk target if the candidate risk target is on the driving path of the current vehicle at the current moment or the TTR moment, and the candidate risk target is not traveling toward the current vehicle, and when the candidate risk target can if the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment and the candidate risk target is not traveling toward the current vehicle, and the candidate risk target can brake to avoid but cannot steer to avoid, then the braking intervention measure is used as the target intervention measure corresponding to the candidate risk target; if the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment and the candidate risk target is not traveling toward the current vehicle, and the candidate risk target can brake to avoid but cannot steer to avoid, then the braking intervention measure is used as the target intervention measure corresponding to the candidate risk target; if the candidate risk target is on the driving path of the current vehicle at the current moment or TTR moment and the candidate risk target is not traveling toward the current vehicle, and the candidate risk target can both brake to avoid and steer to avoid, then the target intervention measure corresponding to the candidate risk target is selected from the braking intervention measures, the left turn intervention measures and the right turn intervention measures.

[0196] In one of the embodiments, the third selection sub-unit is specifically used to: determine the required acceleration of the candidate risk target to avoid collision under the steering intervention measures based on the current motion state of the candidate risk target; wherein the steering intervention measures include left turn intervention measures and right turn intervention measures; and select the target intervention measures corresponding to the candidate risk target from the left turn intervention measures and the right turn intervention measures based on the relationship between the required acceleration under the left turn intervention measures and the required acceleration under the right turn intervention measures.

[0197] In one of the embodiments, the fifth selection sub-unit is specifically used to determine, based on the current motion state of the candidate risk target, the required acceleration of the candidate risk target to avoid collision under braking intervention measures and steering intervention measures; wherein the steering intervention measures include left turn intervention measures and right turn intervention measures; based on the size relationship between each required acceleration, the target intervention measures corresponding to the candidate risk target are selected from the braking intervention measures, left turn intervention measures and right turn intervention measures.

[0198] In one embodiment, the second determination module 630 includes: a second determination unit, used to determine the first position of the current vehicle at the TTR moment according to the current motion state of the current vehicle; a third determination unit, used to determine the critical acceleration of the candidate risk target when triggering at least one active safety function of the current vehicle, and the critical acceleration of the candidate risk target to avoid collision with the current vehicle under the steering intervention measure according to the current motion state of the candidate risk target; wherein each active safety function corresponds to at least one other candidate intervention measure except the steering intervention measure; a fourth determination unit, used to determine the second position of the candidate risk target under the corresponding candidate intervention measure at the TTR moment according to each critical acceleration and the current motion state of the candidate risk target; and a fifth determination unit, used to determine the relative position relationship between the candidate risk target and the current vehicle under the corresponding candidate intervention measure according to the first position and the second position of the candidate risk target under each candidate intervention measure at the TTR moment.

[0199] In one embodiment, the second determination module 630 is specifically used to: when the TTR corresponding to the candidate risk target is valid, determine the relative position relationship between the candidate risk target in the corresponding TTR and the current vehicle under at least one candidate intervention measure according to the current motion state of the current vehicle and the current motion state of the candidate risk target; wherein the TTR of the candidate risk target is valid includes: the candidate risk target is located on the driving path of the current vehicle within the corresponding TTR; the TTR corresponding to the candidate risk target is less than the preset TTR upper limit; when the candidate risk target belongs to the first preset category, the distance between the candidate risk target and the current vehicle is less than the preset distance threshold; the candidate risk target belongs to the second preset category; the second preset category includes the first preset category.

[0200] In one embodiment, the first determination module 620 includes: a sixth determination unit, used to determine the intersection stop situation of the current vehicle or the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target; a seventh determination unit, used to determine the TTR corresponding to the candidate risk target according to the intersection stop situation.

[0201] Each module in the risk target selection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0202] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a risk target selection method is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0203] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0204] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0205] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0206] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0207] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0208] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0209] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0210] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A risk target selection method, characterized in that: include: Acquire at least one candidate risk target for which the current vehicle has a collision risk in the current driving environment; For each of the candidate risk targets, determining the arrival time TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target; Determining, according to the current motion state of the current vehicle and the current motion state of the candidate risk target, a relative position relationship between the candidate risk target and the current vehicle in a corresponding TTR under at least one candidate intervention measure; Selecting a target intervention measure corresponding to the candidate risk target from the at least one candidate intervention measure according to the corresponding relative position relationship under the at least one candidate intervention measure; A final risk target is selected from the candidate risk targets according to the target intervention measures corresponding to the candidate risk targets.

2. The method according to claim 1, characterized in that The selecting, according to the relative position relationship corresponding to the at least one candidate intervention measure, the target intervention measure corresponding to the candidate risk target from the at least one candidate intervention measure comprises: Determine intervention reference data according to the relative position relationship corresponding to the at least one candidate intervention measure; wherein the intervention reference data includes whether the candidate risk target is on the driving path of the current vehicle at the current moment or the TTR moment, whether the candidate risk target is on the driving path of the current vehicle at the TTR moment, whether the candidate risk target can be steered to avoid, and whether the candidate risk target can be braked to avoid; A target intervention measure corresponding to the candidate risk target is selected from the at least one candidate intervention measure according to the intervention reference data.

3. The method according to claim 2, characterized in that The at least one candidate intervention measure includes no intervention measure, braking intervention measure, left turn intervention measure and right turn intervention measure; and selecting, according to the intervention reference data, a target intervention measure corresponding to the candidate risk target from the at least one candidate intervention measure includes: If the candidate risk target is not on the driving path of the current vehicle at both the current time and the TTR time, no intervention measure is used as the target intervention measure corresponding to the candidate risk target; If the candidate risk target is on the driving path of the current vehicle at the current time or the TTR time, and the candidate risk target is driving toward the current vehicle, the braking intervention measure is used as the target intervention measure corresponding to the candidate risk target; If the candidate risk target is on the driving path of the current vehicle at the current moment or the TTR moment, and the candidate risk target is not driving toward the current vehicle, and the candidate risk target can be steered but cannot be braked, then a target intervention measure corresponding to the candidate risk target is selected from the left-turn intervention measures and the right-turn intervention measures; If the candidate risk target is on the driving path of the current vehicle at the current time or TTR time, and the candidate risk target is not driving towards the current vehicle, and the candidate risk target can be braked for avoidance but cannot be turned for avoidance, then the braking intervention measure is used as the target intervention measure corresponding to the candidate risk target; If the candidate risk target is on the driving path of the current vehicle at the current moment or the TTR moment, and the candidate risk target is not driving towards the current vehicle, and the candidate risk target can be both braked and turned to avoid, then the target intervention measures corresponding to the candidate risk target are selected from the braking intervention measures, left turn intervention measures and right turn intervention measures.

4. The method according to claim 3, characterized in that The selecting the target intervention measure corresponding to the candidate risk target from the left-turn intervention measures and the right-turn intervention measures includes: Determining, according to the current motion state of the candidate risk target, the required acceleration of the candidate risk target to avoid collision under the steering intervention measure; wherein the steering intervention measure includes a left turn intervention measure and a right turn intervention measure; According to the magnitude relationship between the required acceleration under the left-turn intervention measure and the required acceleration under the right-turn intervention measure, a target intervention measure corresponding to the candidate risk target is selected from the left-turn intervention measure and the right-turn intervention measure.

5. The method according to claim 3, characterized in that: The selecting the target intervention measure corresponding to the candidate risk target from the braking intervention measures, the left turn intervention measures and the right turn intervention measures includes: According to the current motion state of the candidate risk target, respectively determine the required acceleration of the candidate risk target to avoid collision under braking intervention measures and steering intervention measures; wherein the steering intervention measures include left turn intervention measures and right turn intervention measures; According to the magnitude relationship between the required accelerations, a target intervention measure corresponding to the candidate risk target is selected from the braking intervention measure, the left turn intervention measure and the right turn intervention measure.

6. The method according to any one of claims 1 to 5, characterized in that: The determining, according to the current motion state of the current vehicle and the current motion state of the candidate risk target, a relative position relationship between the candidate risk target in a corresponding TTR and the current vehicle under at least one candidate intervention measure comprises: Determine the first position of the current vehicle at the TTR time according to the current motion state of the current vehicle; Determining, according to the current motion state of the candidate risk target, a critical acceleration of the candidate risk target when at least one active safety function of the current vehicle is triggered, and a critical acceleration of the candidate risk target to avoid collision with the current vehicle under a steering intervention measure; wherein each of the active safety functions corresponds to at least one other candidate intervention measure except the steering intervention measure; Determine, according to each of the critical accelerations and the current motion state of the candidate risk target, the second position of the candidate risk target at the TTR time under the corresponding candidate intervention measure; According to the first position and the second position of the candidate risk target under each candidate intervention measure at the TTR moment, a relative position relationship between the candidate risk target under the corresponding candidate intervention measure and the current vehicle is determined.

7. The method according to any one of claims 1 to 5, characterized in that: The determining, according to the current motion state of the current vehicle and the current motion state of the candidate risk target, a relative position relationship between the candidate risk target in a corresponding TTR and the current vehicle under at least one candidate intervention measure comprises: When the TTR corresponding to the candidate risk target is valid, determining the relative position relationship between the candidate risk target and the current vehicle under at least one candidate intervention measure in the corresponding TTR according to the current motion state of the current vehicle and the current motion state of the candidate risk target; The TTR of the candidate risk target is effective including: The candidate risk target is located on the driving path of the current vehicle in the corresponding TTR; The TTR corresponding to the candidate risk target is less than the preset TTR upper limit; In the case where the candidate risk target belongs to the first preset category, the distance between the candidate risk target and the current vehicle is less than a preset distance threshold; The candidate risk target belongs to a second preset category; the second preset category includes the first preset category.

8. The method according to any one of claims 1 to 5, characterized in that: The determining, according to the current motion state of the current vehicle and the current motion state of the candidate risk target, the arrival time TTR corresponding to the candidate risk target includes: Determining an intersection stop condition of the current vehicle or the candidate risk target according to a current motion state of the current vehicle and a current motion state of the candidate risk target; According to the intersection stop condition, a TTR corresponding to the candidate risk target is determined.

9. A risk target selection device, characterized in that: include: An acquisition module, used to acquire at least one candidate risk target for which the current vehicle has a collision risk in the current driving environment; A first determination module is used to determine, for each of the candidate risk targets, a TTR corresponding to the candidate risk target according to the current motion state of the current vehicle and the current motion state of the candidate risk target; A second determination module is used to determine the relative position relationship between the candidate risk target and the current vehicle under at least one candidate intervention measure in a corresponding TTR according to the current motion state of the current vehicle and the current motion state of the candidate risk target; A first selection module, configured to select a target intervention measure corresponding to the candidate risk target from the at least one candidate intervention measure according to a relative position relationship corresponding to the at least one candidate intervention measure; The second selection module is used to select a final risk target from each of the candidate risk targets according to the target intervention measures corresponding to each of the candidate risk targets.

10. A vehicle-mounted terminal, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images