Danger level determination method, device, electronic device and storage medium

Abstract

The present invention provides a hazard level determination method, device, electronic device and storage medium. By sensing information of potential dangerous targets around the vehicle's driving area, the dangerous targets are classified into hazard levels, thereby further providing the best opportunity for the control operation of the assisted driving function, reducing the potential collision risk, significantly improving safety, and further optimizing the driving experience.

Description

Technical Field

[0001] The present invention relates to the field of vehicle active safety technology, and more specifically, to a method, device, electronic device and storage medium for determining the danger level of a potential collision risk target in road traffic safety. Background Art

[0002] Currently, advanced driver assistance systems (ADAS) are widely used in vehicles to help drivers avoid driving hazards. ADAS includes features such as forward collision warning (FCW), automatic emergency braking (AEB), rear-end collision avoidance (RCA), adaptive cruise control (ACC), and blind spot monitoring (BSD).

[0003] However, all of the above systems need to monitor objects around the vehicle to reduce or avoid collision risks. Therefore, how to determine the danger level of the monitored objects is an urgent problem to be solved in this field. Summary of the Invention

[0004] In view of this, in order to solve the above problems, the present invention provides a hazard level determination method, device, electronic device and storage medium. The technical solution is as follows:

[0005] A method for determining a hazard level, the method comprising:

[0006] Acquiring perception information of dangerous targets around the vehicle, the perception information including at least relative speed, relative distance, and relative acceleration;

[0007] Calculating a dangerous collision distance and a dangerous exit distance between the dangerous target and the vehicle at different danger levels based on the relative speed and the relative acceleration;

[0008] The actual danger level of the dangerous target is determined based on a comparison result of the relative distance with the dangerous collision distance and the dangerous exit distance under different danger levels.

[0009] Preferably, the calculating, based on the relative speed and the relative acceleration, the dangerous collision distance and the dangerous exit distance between the dangerous target and the vehicle at different danger levels includes:

[0010] For each danger level, determining a dangerous collision time of the relative speed at the danger level;

[0011] The dangerous collision distance and the dangerous exit distance under the dangerous level are calculated according to the dangerous collision time, the relative speed and the relative acceleration.

[0012] Preferably, the calculating of the dangerous collision distance and the dangerous exit distance at the dangerous level according to the dangerous collision time, the relative speed and the relative acceleration includes:

[0013] Determine a following distance threshold for the relative speed at the risk level;

[0014] The dangerous collision distance and the dangerous exit distance under the danger level are calculated according to the dangerous collision time, the relative speed, the relative acceleration and the following vehicle time threshold.

[0015] Preferably, the calculating of the dangerous collision distance and the dangerous exit distance under the dangerous level according to the dangerous collision time, the relative speed, the relative acceleration and the following distance threshold includes:

[0016] determining an offset between the dangerous target and the vehicle;

[0017] Obtaining an adjustment coefficient that matches the bias;

[0018] The dangerous collision distance and the dangerous exit distance under the danger level are calculated according to the dangerous collision time, the relative speed, the relative acceleration, the following vehicle time threshold and the adjustment coefficient.

[0019] Preferably, determining the actual danger level of the dangerous target according to the comparison result of the relative distance with the dangerous collision distance and the dangerous exit distance under different danger levels includes:

[0020] determining a movement trend of the dangerous target relative to the vehicle based on the relative distance;

[0021] If the movement trend is from far to near, the danger level at which the dangerous collision distance is greater than the relative distance is used as the actual danger level of the dangerous target;

[0022] If the movement trend is from near to far, the danger level when the dangerous collision distance is greater than the relative distance, or the dangerous collision distance is less than the relative distance and the dangerous exit distance is greater than the relative distance is taken as the actual danger level of the dangerous target.

[0023] Preferably, before calculating the dangerous collision distance and the dangerous exit distance between the dangerous target and the vehicle at different danger levels based on the relative speed and the relative acceleration, the method further includes:

[0024] Filter effective dangerous targets from the dangerous targets based on the perception information.

[0025] Preferably, the method further comprises:

[0026] The actual risk level is output to a target ADAS system, so that the target ADAS system performs corresponding operations according to the actual risk level.

[0027] A device for determining a danger level, comprising:

[0028] An information acquisition module, configured to acquire perception information of dangerous targets around the vehicle, the perception information including at least relative speed, relative distance, and relative acceleration;

[0029] a distance calculation module, configured to calculate a dangerous collision distance and a dangerous exit distance between the dangerous target and the vehicle at different danger levels based on the relative speed and the relative acceleration;

[0030] The level determination module is used to determine the actual danger level of the dangerous target based on the comparison result of the relative distance with the dangerous collision distance and the dangerous exit distance under different danger levels.

[0031] An electronic device comprises: at least one memory and at least one processor; the memory stores a program, the processor calls the program stored in the memory, and the program is used to implement any one of the hazard level determination methods described above.

[0032] A storage medium, characterized in that the storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute any one of the hazard level determination methods.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The danger level determination method, device, electronic device and storage medium provided by the present invention classify the danger levels of dangerous targets by sensing information of potential dangerous targets around the vehicle's driving area, thereby further providing the best opportunity for the control operation of the assisted driving function, reducing potential collision risks, significantly improving safety, and further optimizing the driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0036] Figure 1 A flow chart of a method for determining a danger level according to an embodiment of the present invention;

[0037] Figure 2A schematic diagram of a dangerous target provided by an embodiment of the present invention;

[0038] Figure 3 A schematic diagram of the classification of danger levels provided by an embodiment of the present invention;

[0039] Figure 4 A partial flow chart of a method for determining a danger level according to an embodiment of the present invention;

[0040] Figure 5 A flow chart of another part of the method for determining the danger level provided by an embodiment of the present invention;

[0041] Figure 6 A schematic structural diagram of a danger level determination device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0043] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] The embodiment of the present invention provides a method for determining a danger level, the method flow chart of which is as follows: Figure 1 As shown, the following steps are included:

[0045] S10, acquiring perception information of dangerous targets around the vehicle, where the perception information includes at least relative speed, relative distance, and relative acceleration.

[0046] In an embodiment of the present invention, a fusion perception system or device can be set up with the vehicle body to obtain perception information of targets around the vehicle, that is, dangerous targets. Since the present invention is mainly used in ADAS systems, the range around the vehicle body can be limited to the area in front of the vehicle body.

[0047] Compared with traditional vehicles, fusion perception systems or devices include but are not limited to sensors such as ultrasonic radar, millimeter-wave radar, lidar and cameras that can detect target position, speed and other attributes. They can detect perception information of the environment in front of the vehicle and feed this information back to the vehicle CAN network through the on-board CAN bus, so that the vehicle controller can obtain this information.

[0048] Furthermore, the perception information includes relative speed, relative distance, relative acceleration, target height and width, target attributes (passenger cars, motorcycles, commercial vehicles, non-motor vehicles, pedestrians and animals, etc.), motion status (stationary, moving, moving to stationary, oncoming moving target, oncoming moving to stationary target), ID number, target fusion source (only radar monitoring target, only camera detection target, fusion target), target tracking status (new target, locked target, continuously updated target) and target continuous tracking time, etc., among which the relative speed includes at least one of the lateral relative speed and the longitudinal relative speed, the relative distance includes at least one of the lateral relative distance and the longitudinal relative distance, and the relative acceleration includes at least one of the lateral relative acceleration and the longitudinal relative acceleration.

[0049] On this basis, in order to screen out effective dangerous targets and perform subsequent danger level judgment, the dangerous targets obtained in step S10 are preliminarily screened. The embodiment of the present invention further includes the following steps:

[0050] Filter effective dangerous targets from dangerous targets based on perceived information.

[0051] In the embodiment of the present invention, target attributes, motion status, ID number, target fusion source, target tracking status and target continuous tracking time in the perception information are considered.

[0052] Target attributes can be used to identify vehicle targets and vulnerable road users (VRUs) among dangerous targets. For example, pedestrians, bicycles, two-wheeled motorcycles and two-wheeled electric vehicles are all vulnerable road users.

[0053] For the motion state, non-stationary targets among vehicle targets and road vulnerable targets can be screened, and different relative speed and relative acceleration threshold ranges can be set for vehicle targets and road vulnerable targets to screen targets within the threshold range.

[0054] Furthermore, each ID number corresponds to a single target tracking state, thus excluding new targets from vehicles and other vulnerable road targets. Furthermore, in different scenarios, targets from vehicles and other vulnerable road targets can be filtered out from high-accuracy target fusion sources. For example, during the day, you can select "only camera-detected targets" or "fused targets," while at night, you can select "only radar-detected targets."

[0055] Finally, the target continuous tracking time is taken into consideration to provide redundant time for target tracking, so as not to easily abandon the targets that suddenly disappear among vehicle targets and weak road targets.

[0056] S20, calculating a dangerous collision distance and a dangerous exit distance between the dangerous target and the vehicle at different danger levels based on the relative speed and the relative acceleration.

[0057] In the embodiment of the present invention, the danger level can be divided into three categories: "No Potential Danger", "Potential Danger Collision Level", and "Potential Danger Warning Level". Of course, according to the target attributes, the vehicle targets can be further divided into "No Potential Danger (No Danger)", "Potential Danger Vehicle Collision Level (VehBrkDngr)", and "Potential Danger Vehicle Warning Level (VehWrningDngr)". For vulnerable road targets, they can be further divided into "No Potential Danger (No Danger)", "Potential Danger VRU Collision Level (VRUBrkDngr)", and "Potential Danger VRU Warning Level (VRUWrningDngr)", that is, a total of five danger level categories.

[0058] In some application scenarios, the "Potential Collision Level" and "Potential Warning Level" can be further divided into multiple levels. For example, each level can be divided into six levels with decreasing severity: "Red, LgtRed, Orng, LgtOrng, YeLo, LgtYeLo." Therefore, if the classification has been completed in advance based on target attributes, there are a total of 25 risk levels for vehicle targets and vulnerable road targets. Figure 3 A schematic diagram of the danger level classification provided by an embodiment of the present invention.

[0059] For different danger levels, different dangerous collision times can be set, that is, the time distance when the two vehicles collide is predicted. Based on the dangerous collision time, relative speed and relative acceleration, the dangerous collision distance and dangerous exit distance under the corresponding danger level are calculated respectively.

[0060] It should be noted that the dangerous collision distance refers to the threshold value for the collision danger / warning danger between the vehicle and the dangerous target. When the relative distance between the vehicle and the dangerous target is less than the dangerous collision distance, a collision danger / warning danger will arise; the dangerous exit distance refers to the threshold value for whether the collision danger / warning danger is eliminated. When the relative distance between the vehicle and the dangerous target is greater than the dangerous exit distance, the collision danger / warning danger will be eliminated.

[0061] It should be noted that both relative velocity and relative acceleration have horizontal and vertical dimensions. In actual scenarios, the perceived information may only contain relative velocity and relative acceleration in the horizontal dimension (i.e., horizontal relative velocity and horizontal relative acceleration), or only contain relative velocity and relative acceleration in the vertical dimension (i.e., vertical relative velocity and vertical relative acceleration), or both contain relative velocity and relative acceleration in the horizontal and vertical dimensions (i.e., horizontal relative velocity, horizontal relative acceleration, vertical relative velocity, and vertical relative acceleration).

[0062] In this regard, in embodiments of the present invention, the dimensions that may be present can be used to determine the dangerous collision distance and dangerous exit distance in the corresponding dimensions, and then the actual danger level in the corresponding dimensions can be calculated according to step S30. If both horizontal and vertical dimensions are present, then after step S30, the actual danger level in the horizontal dimension and the actual danger level in the vertical dimension can be obtained. In this case, the highest actual danger level can be selected for output.

[0063] In the specific implementation process, the following steps can be adopted in step S20 to "calculate the dangerous collision distance and dangerous exit distance between the dangerous target and the vehicle at different danger levels based on the relative speed and relative acceleration". The method flow chart is as follows: Figure 4 As shown:

[0064] S201 : For each danger level, determine a dangerous collision time of a relative speed at the danger level.

[0065] In the embodiment of the present invention, for each danger level, a corresponding collision schedule can be set by actual vehicle calibration, that is, Figure 3 The 25 danger levels shown can set up 25 collision timetables. The collision timetable records the dangerous collision time corresponding to the relative speed under each danger level. For example:

[0066] The horizontal axis X of the collision time table is the relative speed of the dangerous target relative to the vehicle in the collision direction (lateral or longitudinal), in km / h.

[0067] X=[-15,-10,-5,0,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,120];

[0068] The vertical axis T of the collision time table is the dangerous collision time, in seconds.

[0069] T=[0,0,0,0,0.7,0.6,0.5,0.5,0.56,0.62,0.7,0.75,0.87,1,1.21,1.32,1.32,1.46,1.53,1.56,1.61,1.68,1.72,1.77,1.79,1.8].

[0070] It should be noted that, for the same relative speed, the higher the danger level, the shorter the corresponding dangerous collision time, that is, the dangerous collision time is inversely proportional to the danger level.

[0071] Therefore, for each danger level, the collision time table corresponding to the danger level is retrieved and then matched with the relative speed to determine the dangerous collision time of the relative speed at the danger level.

[0072] S202: Calculate the dangerous collision distance and dangerous exit distance under the dangerous level according to the dangerous collision time, relative speed and relative acceleration.

[0073] In the embodiment of the present invention, the dangerous collision distance can be calculated according to the following formula (1), and the dangerous exit distance can be calculated according to the following formula (2):

[0074] D b =ΔV*T+0.5*ΔA*T 2 +Z0 (1)

[0075] Among them, D b represents the dangerous collision distance, ΔV represents the relative speed, ΔA represents the relative acceleration, T represents the dangerous collision time, and Z0 represents the compensation amount of the safety distance between the two vehicles, which is related to the relative speed;

[0076] D Exit =ΔV*T+0.5*ΔA*T 2 +Z1 (2)

[0077] Among them, D Exit It represents the dangerous exit distance, Z1 represents the compensation amount of the safety distance between the two vehicles when the dangerous collision time is proposed as the function, and is related to the relative speed.

[0078] On this basis, if the dangerous collision distance and the dangerous exit distance are calculated respectively according to the above formula (1) and formula (2), then for the scenario where the speed of the vehicle is similar to that of the dangerous target, such as when the relative speed between the vehicle and the preceding vehicle is 0 or a small value close to 0, the calculated dangerous collision distance and dangerous exit distance will be a minimum value, and the actual danger level finally calculated will not accurately assess the danger level of the dangerous target. Therefore, the embodiment of the present invention further enters the time distance THW to characterize the convergence trend in the steady-state following process.

[0079] At this time, step S202 "calculating the dangerous collision distance and dangerous exit distance under the dangerous level according to the dangerous collision time, relative speed and relative acceleration" can adopt the following steps:

[0080] Determine the following distance threshold value for the relative speed at the danger level; calculate the dangerous collision distance and dangerous exit distance at the danger level based on the dangerous collision time, relative speed, relative acceleration and the following distance threshold value.

[0081] In the embodiment of the present invention, for each danger level, a corresponding following distance threshold table can be set by actual vehicle calibration, that is, for Figure 3 The 25 danger levels shown in the figure can set 25 following distance threshold tables. The following distance threshold table records the following distance threshold corresponding to the relative speed under each danger level. The following distance threshold is the empirical value of the following distance calibrated by the actual vehicle. For example:

[0082] The horizontal coordinate X of the following distance threshold table is the relative speed of the dangerous target relative to the vehicle in the collision direction (lateral or longitudinal), and the unit is km / h.

[0083] X=[-15,-10,-5,0,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,120];

[0084] The horizontal axis T of the following distance threshold table THW is the following distance threshold,

[0085] T THW =[0.85,0.7,0.65,0.6,0.7,0.6,0.75,0.85,0.85,0.86,0.92,0.97,0.95,0.97,

[0086] 1,1.21,1.32,1.32,1.46,1.53,1.56,1.61,1.68,1.72,1.77,1.79,1.8].

[0087] It should be noted that, for the same relative speed, the higher the danger level, the smaller the corresponding following distance threshold, that is, the following distance threshold is inversely proportional to the danger level.

[0088] Therefore, for each danger level, the following time threshold value table corresponding to the danger level is retrieved and then matched with the relative speed to determine the following time threshold value for the relative speed at the danger level.

[0089] Furthermore, when the relative speed between the vehicle and the preceding vehicle is low, the dangerous collision distance and dangerous exit distance calculated under different danger levels are small, and thus cannot be compared with the actual relative distance between the two vehicles. Therefore, the dangerous collision distance and dangerous exit distance after introducing the following distance can be calculated using the following formulas (3) and (4), respectively:

[0090] D b =ΔV*T+0.5*ΔA*T 2 +Z0+T THW *v h (3)

[0091] D Exit =ΔV*T+0.5*ΔA*T 2 +Z1+T THW *v h (4)

[0092] Among them, T THW represents the following distance threshold, v h Indicates the speed of the vehicle (own vehicle) in the collision direction (lateral or longitudinal).

[0093] On this basis, embodiments of the present invention further consider the presence of a certain degree of offset between the dangerous target and the vehicle. If the dangerous target and the vehicle do not overlap at all (i.e., the offset is 0%), meaning the vehicle and the preceding vehicle are not in the same lane or on the same driving trajectory, then there is no danger level. However, if the dangerous target and the vehicle completely overlap (i.e., the offset is 100%), a danger level determination must be made. Of course, if the dangerous target and the vehicle have a certain degree of overlap, the danger level will be lower than if there is complete overlap.

[0094] Therefore, the above-mentioned "calculating the dangerous collision distance and dangerous exit distance under the dangerous level based on the dangerous collision time, relative speed, relative acceleration and following distance threshold" can be specifically carried out in the following steps:

[0095] Determine the offset between the dangerous target and the vehicle; obtain an adjustment coefficient that matches the offset; and calculate the dangerous collision distance and dangerous exit distance under the danger level based on the dangerous collision time, relative speed, relative acceleration, following time threshold, and adjustment coefficient.

[0096] In the embodiment of the present invention, the offset between the dangerous target and the vehicle can be calculated according to the following formula (5):

[0097]

[0098] Among them, overlap represents the bias, W Ego Indicates the width of the vehicle (this vehicle), W Tgt Indicates the width of the dangerous target (for example, the width of the car in front), D Lat Indicates the lateral relative distance between the vehicle and the dangerous target.

[0099] Furthermore, in the embodiment of the present invention, the piecewise function of the adjustment coefficient is shown in the following formula (6):

[0100]

[0101] Among them, α overlap Indicates the adjustment coefficient, a% indicates the lower limit bias calibration value, and b% indicates the upper limit bias calibration value.

[0102] Finally, the dangerous collision distance and dangerous exit distance after introducing the bias can be calculated using the following formulas (7) and (8), respectively:

[0103]

[0104] Therefore, the embodiment of the present invention further calculates the actual danger level of the dangerous target by introducing the following distance threshold and the adjustment coefficient of the offset, providing a danger level judgment scheme for scenarios where the speed of the vehicle is close to that of the preceding vehicle, and scenarios where there is a certain offset between the vehicle and the preceding vehicle.

[0105] S30: Determine the actual danger level of the dangerous target based on a comparison result of the relative distance with the dangerous collision distance and the dangerous exit distance under different danger levels.

[0106] In this embodiment of the present invention, the relative distance between the dangerous target and the vehicle in the perceived information is compared with the dangerous collision distance and dangerous exit distance for different danger levels. For a given danger level, if the relative distance is greater than the dangerous exit distance for that danger level, the vehicle exits that danger level. If the relative distance is less than the dangerous collision distance for that danger level, the danger level is output as the actual danger level.

[0107] In the specific implementation process, considering the movement trend of the dangerous target relative to the vehicle, that is, from far to near or from near to far, step S30 "determining the actual danger level of the dangerous target based on the comparison results of the relative distance with the dangerous collision distance and dangerous exit distance under different danger levels" can be specifically implemented by the following steps. The method flow chart is as follows Figure 5 As shown:

[0108] S301, determining a movement trend of a dangerous target relative to the vehicle based on a relative distance.

[0109] In an embodiment of the present invention, the movement trend of the dangerous target relative to the vehicle (this vehicle) can be determined based on the relative distance within a certain period of time. If the relative distance becomes smaller, the movement trend is from far to near. Conversely, if the relative distance becomes larger, the movement trend is from near to far.

[0110] S302: If the movement trend is from far to near, the danger level at which the dangerous collision distance is greater than the relative distance is used as the actual danger level of the dangerous target.

[0111] In the embodiment of the present invention, for a scenario where the dangerous target moves from far to near, the actual danger level can be determined using the following formula (9):

[0112]

[0113] Among them, DangerDistLevel Indicates the actual danger level, False indicates an error (i.e., exiting the corresponding danger level), True indicates correctness (i.e., outputting the corresponding danger level as the actual danger level), D sen Indicates the relative distance between the dangerous target and the vehicle, && indicates "D sen >D b ” and “D sen <D Exit "Both conditions are met at the same time.

[0114] According to formula (9), the distance between the dangerous target and the vehicle is from far to near, assuming D Exit =15m, D b =10m, when D sen When >15m, the corresponding danger level is False; when 10m <D sen <15m, the corresponding danger level is still False; if and only if D sen When the distance is less than 10m, the corresponding danger level is True.

[0115] S303: If the movement trend is from near to far, the danger level of the dangerous target is determined as follows: the dangerous collision distance is greater than the relative distance, or the dangerous collision distance is less than the relative distance and the dangerous exit distance is greater than the relative distance.

[0116] In the embodiment of the present invention, for a scenario where the dangerous target moves from near to far, the actual danger level can be determined using the following formula (10):

[0117]

[0118] Among them, DangerDist Level Indicates the actual danger level, False indicates an error (i.e., exiting the corresponding danger level), True indicates correctness (i.e., outputting the corresponding danger level as the actual danger level), D sen Indicates the relative distance between the dangerous target and the vehicle, && indicates "D sen >D b ” and “D sen <D Exit "Both conditions are met at the same time.

[0119] According to formula (10), the distance between the dangerous target and the vehicle increases from near to far. Assuming D Exit =15m, D b =10m, when D sen <10m, the corresponding danger level is True; when 10m <D sen <15m, the corresponding danger level is still True; if and only if D senWhen the distance is >15m, the corresponding danger level is False.

[0120] In some other embodiments, due to the different control strategies of different control algorithms in the ADAS system, such as different control strategies for the ego vehicle such as ACC or AEB, the corresponding actions performed based on the actual danger level are also different.

[0121] Therefore, in the embodiment of the present invention, the actual danger level is further output to the target ADAS system, so that the target ADAS system performs corresponding operations according to the actual danger level, thereby activating corresponding functions to further perform actions such as warning, braking or steering.

[0122] In this regard, when the vehicle meets different danger levels, it can perform different operations or actions according to different danger levels; for example, when the "potential danger warning level" is met, the driver can be alarmed and reminded of dangerous targets; when the "potential danger collision level" is met, the vehicle can take active actions to avoid the danger or minimize the possible danger.

[0123] In summary, the present invention coordinates and unifies the triggering logic and timing of multiple driver assistance functions. By classifying potentially collision-prone targets according to their risk levels, it unifies and integrates multiple software system architectures, reducing the complexity of control algorithms and models and optimizing the software architecture. The ADAS system uses the risk level output by the present invention as a trigger signal for each function, executing corresponding operations and controls based on the corresponding risk level trigger signal.

[0124] Based on the danger level determination method provided in the above embodiment, the embodiment of the present invention further provides a device for implementing the above danger level determination method. The structural diagram of the device is shown in FIG. Figure 6 Shown, including:

[0125] An information acquisition module 10 is used to acquire perception information of dangerous targets around the vehicle, where the perception information includes at least relative speed, relative distance, and relative acceleration;

[0126] A distance calculation module 20 is used to calculate the dangerous collision distance and dangerous exit distance between the dangerous target and the vehicle at different danger levels based on the relative speed and relative acceleration;

[0127] The level determination module 30 is used to determine the actual danger level of the dangerous target based on the comparison result of the relative distance with the dangerous collision distance and the dangerous exit distance under different danger levels.

[0128] Optionally, the distance calculation module 20 is specifically configured to:

[0129] For each danger level, determine the dangerous collision time of the relative speed at that danger level; and calculate the dangerous collision distance and dangerous exit distance at that danger level based on the dangerous collision time, relative speed and relative acceleration.

[0130] Optionally, the distance calculation module 20 is configured to calculate the dangerous collision distance and the dangerous exit distance at the dangerous level according to the dangerous collision time, relative speed, and relative acceleration, and is specifically configured to:

[0131] Determine the following distance threshold value for the relative speed at the danger level; calculate the dangerous collision distance and dangerous exit distance at the danger level based on the dangerous collision time, relative speed, relative acceleration and the following distance threshold value.

[0132] Optionally, a distance calculation module 20 for calculating a dangerous collision distance and a dangerous exit distance at a certain danger level based on the dangerous collision time, relative speed, relative acceleration, and following distance threshold is specifically configured to:

[0133] Determine the offset between the dangerous target and the vehicle; obtain an adjustment coefficient that matches the offset; and calculate the dangerous collision distance and dangerous exit distance under the danger level based on the dangerous collision time, relative speed, relative acceleration, following time threshold, and adjustment coefficient.

[0134] Optionally, the level determination module 30 is specifically configured to:

[0135] Determine the movement trend of the dangerous target relative to the vehicle based on the relative distance; if the movement trend is from far to near, the danger level where the dangerous collision distance is greater than the relative distance is used as the actual danger level of the dangerous target; if the movement trend is from near to far, the danger level where the dangerous collision distance is greater than the relative distance, or the dangerous collision distance is less than the relative distance and the dangerous exit distance is greater than the relative distance is used as the actual danger level of the dangerous target.

[0136] Optionally, the information acquisition module 10 is further configured to:

[0137] Filter effective dangerous targets from dangerous targets based on perceived information.

[0138] Optionally, the level determination module 30 is further configured to:

[0139] The actual danger level is output to the target ADAS system so that the target ADAS system performs corresponding operations according to the actual danger level.

[0140] It should be noted that the detailed functions of each module in the embodiment of the present invention can be found in the corresponding part of the above-mentioned danger level determination method, which will not be repeated here.

[0141] An embodiment of the present invention also provides an electronic device, comprising: at least one memory and at least one processor; the memory stores a program, the processor calls the program stored in the memory, and the program is used to implement the danger level determination method provided in the above embodiment.

[0142] An embodiment of the present invention further provides a storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the danger level determination method provided in the above embodiment.

[0143] The above is a detailed introduction to the hazard level determination method, device, electronic device and storage medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0144] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0145] It should also be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that the process, method, article, or apparatus comprising a series of elements inherent to the elements, or also including elements inherent to these processes, methods, articles, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0146] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a danger level, characterized in that: The method comprises: Acquiring perception information of dangerous targets around the vehicle, the perception information including at least relative speed, relative distance, and relative acceleration; For each danger level, determining a dangerous collision time of the relative speed at the danger level; Determine a following distance threshold for the relative speed at the risk level; Calculate the dangerous collision distance and dangerous exit distance at the danger level based on the dangerous collision time, the relative speed, the relative acceleration, and the following vehicle time threshold, where the dangerous collision time is the time distance between the predicted collision moment of the two vehicles, the dangerous collision distance is the threshold value for the vehicle to generate collision danger / warning danger with the dangerous target, and the dangerous exit distance is the threshold value for whether the collision danger / warning danger is eliminated; determining a movement trend of the dangerous target relative to the vehicle based on the relative distance; If the movement trend is from far to near, the danger level at which the dangerous collision distance is greater than the relative distance is used as the actual danger level of the dangerous target; If the movement trend is from near to far, the danger level when the dangerous collision distance is greater than the relative distance, or the dangerous collision distance is less than the relative distance and the dangerous exit distance is greater than the relative distance is taken as the actual danger level of the dangerous target.

2. The method according to claim 1, characterized in that The calculating, based on the dangerous collision time, the relative speed, the relative acceleration, and the following distance threshold, the dangerous collision distance and the dangerous exit distance under the dangerous level includes: Determining an offset between the dangerous target and the vehicle, wherein the offset is a degree of overlap between the dangerous target and the vehicle; Obtaining an adjustment coefficient that matches the bias; The dangerous collision distance and the dangerous exit distance under the danger level are calculated according to the dangerous collision time, the relative speed, the relative acceleration, the following vehicle time threshold and the adjustment coefficient.

3. The method according to claim 1, characterized in that Before determining the dangerous collision time of the relative speed at each danger level, the method further includes: Filter effective dangerous targets from the dangerous targets based on the perception information.

4. The method according to claim 1, wherein The method further comprises: The actual risk level is output to a target ADAS system, so that the target ADAS system performs corresponding operations according to the actual risk level.

5. A device for determining a danger level, characterized in that: The device comprises: An information acquisition module, configured to acquire perception information of dangerous targets around the vehicle, the perception information including at least relative speed, relative distance, and relative acceleration; A distance calculation module, configured to determine, for each danger level, a dangerous collision time of the relative speed at the danger level; Determine a following distance threshold for the relative speed at the risk level; Calculate the dangerous collision distance and dangerous exit distance at the danger level based on the dangerous collision time, the relative speed, the relative acceleration, and the following vehicle time threshold, where the dangerous collision time is the time distance between the predicted collision moment of the two vehicles, the dangerous collision distance is the threshold value for the vehicle to generate collision danger / warning danger with the dangerous target, and the dangerous exit distance is the threshold value for whether the collision danger / warning danger is eliminated; a level determination module, configured to determine a movement trend of the dangerous target relative to the vehicle based on the relative distance; If the movement trend is from far to near, the danger level at which the dangerous collision distance is greater than the relative distance is used as the actual danger level of the dangerous target; If the movement trend is from near to far, the danger level when the dangerous collision distance is greater than the relative distance, or the dangerous collision distance is less than the relative distance and the dangerous exit distance is greater than the relative distance is taken as the actual danger level of the dangerous target.

6. An electronic device, characterized in that: include: at least one memory and at least one processor; The memory stores a program, and the processor calls the program stored in the memory, where the program is used to implement the hazard level determination method according to any one of claims 1 to 4.

7. A storage medium, characterized in that: The storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute the hazard level determination method according to any one of claims 1 to 4.

Images