Vehicle driving safety assessment method and device

Abstract

The present disclosure relates to the field of traffic technology, and provides a vehicle driving safety assessment method and device, the method comprising: constructing an abstract element situation field based on the driving environment information of the target vehicle and the motion data of traffic participants in the driving environment information; constructing a concrete element situation field based on the driving condition of the target vehicle; constructing a subjective cognitive field based on the expected driving trajectory of the target vehicle; and assessing the driving safety of the target vehicle based on the abstract element situation field, the concrete element situation field and the subjective cognitive field. The present disclosure can quantitatively describe the objective traffic risks in combination with the driving environment of the vehicle and the interaction between vehicles in the actual traffic scene, conduct a comprehensive and objective assessment of the driving safety of the target vehicle, and provide a safety evaluation for smart cars that is closer to human cognitive methods, ensuring that the decision-making planning of the automatic driving system can better meet the driver's safety expectations in the actual driving scene, and improve the safety of smart driving.

Description

Technical Field

[0001] The present disclosure relates to the field of transportation technology, and in particular to a vehicle driving safety assessment method and device. Background Art

[0002] Currently, safety assessments of decision-making and planning results from autonomous driving systems for intelligent vehicles primarily rely on distance-based models, such as TTC (Time to Collision) and HW (Headway Time). However, as higher-level autonomous driving systems increase their understanding and assessment of road traffic risks, single indicators or simple combinations of multiple indicators are no longer sufficient to fully reflect complex road traffic risks. Furthermore, instantaneous traffic risk indicators cannot adequately describe the risk distribution caused by dynamic traffic elements in the time domain, posing significant challenges to the research and evaluation of autonomous driving systems. Summary of the Invention

[0003] The purpose of the embodiments of the present disclosure is to provide a vehicle driving safety assessment method and device to solve technical problems in the existing technology, such as the inability to fully reflect complex road traffic risks and the inability to well describe the risk distribution caused by dynamic traffic elements in the time domain.

[0004] In order to solve the above technical problems, the embodiments of the present disclosure adopt the following technical solutions:

[0005] In a first aspect, an embodiment of the present disclosure provides a vehicle driving safety assessment method, comprising:

[0006] Constructing an abstract element situation field based on the driving environment information of the target vehicle and the motion data of traffic participants in the driving environment information;

[0007] Constructing a situation field of concrete elements based on the driving condition of the target vehicle;

[0008] constructing a subjective cognitive field based on the expected driving trajectory of the target vehicle;

[0009] The driving safety of the target vehicle is evaluated based on the abstract element situation field, the concrete element situation field and the subjective cognitive field.

[0010] In some embodiments, constructing an abstract element situation field based on the driving environment information of the target vehicle and the motion data of traffic participants in the driving environment information includes:

[0011] In the vertical direction of the tangent line of the current road point, the output of the one-dimensional Gaussian function is calculated according to the distance from the point on the vertical line to the road point to obtain the situation field strength distribution;

[0012] Classifying the driving environment information and the motion data of traffic participants in the driving environment information to obtain a classification result;

[0013] Fusing the classification result with the situation field strength distribution to obtain a fusion result;

[0014] The fusion result is input into a preset abstract element risk distribution calculation model to obtain a risk distribution field curve.

[0015] In some embodiments, the abstract element risk distribution calculation model is:

[0016]

[0017]

[0018] Among them, G represents the Gaussian coefficient, r ae represents the distance between the target vehicle’s current driving risk and the expected risk lane line, and σ represents the standard deviation of the model.

[0019] In some embodiments, the method further comprises:

[0020] Establish a relationship curve between risk type and risk level according to the preset risk level to obtain a risk type curve;

[0021] Determining that the risk factor distribution in the risk distribution field curve is a normal distribution;

[0022] According to the 3σ principle, the risk type curve is fitted with the risk distribution field curve to obtain the distribution of abstract element risks on straight roads and curves.

[0023] In some embodiments, constructing a situation field of a concrete element based on the driving condition of the target vehicle includes:

[0024] In the local coordinate system of the target vehicle, constructing the representational element situation field based on a two-dimensional Gaussian function;

[0025] The distribution area of ​​the two-dimensional Gaussian function is based on at least one of the vehicle size, vehicle speed, and acceleration of the target vehicle.

[0026] In some embodiments, constructing the representational element situation field based on a two-dimensional Gaussian function in the local coordinate system of the target vehicle includes:

[0027] Taking the stationary state of the target vehicle as a reference, calculating the situation field distribution when the target vehicle is traveling at a constant speed;

[0028] The calculation formula of the situation field distribution is:

[0029]

[0030] Where, Indicates the strength of the situation field at a certain point in the situation field, Indicates the minimum distance between the current target vehicle and other surrounding vehicles.

[0031] In some embodiments, constructing a subjective cognitive field based on the expected driving trajectory of the target vehicle includes:

[0032] Determining an expected driving trajectory of the target vehicle based on the wheelbase and steering wheel angle of the target vehicle;

[0033] Establishing a one-dimensional Gaussian function at each point on the expected driving trajectory in a direction perpendicular to the expected driving trajectory;

[0034] The subjective cognitive field is constructed according to the established multiple one-dimensional Gaussian functions.

[0035] In some embodiments, the subjective cognitive field includes a risk situation field under at least one driving scenario of a vehicle driving at a constant speed, accelerating, and driving in parallel lanes.

[0036] In some embodiments, evaluating the driving safety of the target vehicle based on the abstract element situation field, the concrete element situation field, and the subjective cognitive field includes:

[0037] The risk distributions under different situation fields are integrated to evaluate the driving risk of the target vehicle, wherein the driving risk includes the driving environment risk of the driving environment in which the target vehicle is located and the interaction risk between the target vehicle and other traffic participants.

[0038] In a second aspect, an embodiment of the present disclosure provides a vehicle driving safety assessment device, comprising:

[0039] A first building module is configured to build an abstract element situation field based on the driving environment information of the target vehicle and the motion data of the traffic participants in the driving environment information;

[0040] A second building module is configured to build a concrete element situation field based on the driving condition of the target vehicle;

[0041] a third building module configured to build a subjective cognitive field based on the expected driving trajectory of the target vehicle;

[0042] The safety assessment module is configured to assess the driving safety of the target vehicle based on the abstract element situation field, the concrete element situation field and the subjective cognitive field.

[0043] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned vehicle driving safety assessment method when executing the computer program on the memory.

[0044] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned vehicle driving safety assessment method when executed by a processor.

[0045] The vehicle driving safety assessment method and device provided by the embodiments of the present disclosure construct an abstract element situation field based on the driving environment information of the target vehicle and the motion data of traffic participants in the driving environment information; construct a concrete element situation field based on the driving condition of the target vehicle; and construct a subjective cognitive field based on the expected driving trajectory of the target vehicle. The driving safety of the target vehicle is assessed based on the abstract element situation field, the concrete element situation field and the subjective cognitive field. It can quantitatively describe the objective traffic risks in combination with the driving environment of the vehicle and the interaction relationship between vehicles in the actual traffic scene, and conduct a comprehensive and objective assessment of the driving safety of the target vehicle, more comprehensively consider road traffic risks, and solve the drawbacks of incomplete and non-objective risk assessment of complex road traffic scenes. At the same time, combined with the subjective cognitive field, it provides smart cars with a safety evaluation that is closer to human cognitive methods, ensuring that the decision-making planning of the automatic driving system can better meet the driver's safety expectations in actual driving scenarios, thereby improving the safety of smart driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present disclosure 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 only some embodiments recorded in the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 This is a flow chart of a vehicle driving safety assessment method according to an embodiment of the present disclosure;

[0048] Figure 2 A risk type curve diagram of an embodiment of the present disclosure;

[0049] Figure 3 The distribution of the abstract element risk on a straight road in an embodiment of the present disclosure;

[0050] Figure 4 The distribution of the abstract element risk on the curve in the embodiment of the present disclosure;

[0051] Figure 5This is a schematic diagram of target vehicle coordinate conversion according to an embodiment of the present disclosure;

[0052] Figure 6 A schematic diagram of distance calculation between a target vehicle and surrounding vehicles according to an embodiment of the present disclosure;

[0053] Figure 7 The distribution of risks of concrete elements in the embodiment of the present disclosure;

[0054] Figure 8 is the subjective cognitive field of the target vehicle in different driving scenarios according to the embodiment of the present disclosure;

[0055] Figure 9 Schematic diagram of the structure of the vehicle driving safety assessment device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0056] Various aspects and features of the present disclosure are described herein with reference to the accompanying drawings.

[0057] It should be understood that various modifications may be made to the embodiments disclosed herein. Therefore, the above description should not be considered as limiting, but merely as an example of an embodiment. Other modifications within the scope and spirit of the present disclosure will occur to those skilled in the art.

[0058] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the general description of the present disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the present disclosure.

[0059] These and other characteristics of the present disclosure will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0060] It should also be understood that although the present disclosure has been described with reference to certain specific examples, those skilled in the art will be able to realize many other equivalent forms of the present disclosure that have the characteristics recited in the claims and are therefore within the scope of protection defined thereby.

[0061] The above and other aspects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0062] Specific embodiments of the present disclosure will be described hereinafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of the present disclosure, which may be implemented in a variety of ways. Well-known and / or repetitive functions and structures are not described in detail to avoid obscuring the present disclosure with unnecessary or redundant detail. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but rather serve merely as a basis and representative basis for teaching those skilled in the art to variously employ the present disclosure with substantially any suitable detailed structure.

[0063] This description may use the phrases "in one embodiment," "in another embodiment," "in a further embodiment," or "in other embodiments," each of which may refer to one or more of the same or different embodiments according to the present disclosure.

[0064] Example 1

[0065] Figure 1 A flow chart of a vehicle driving safety assessment method according to an embodiment of the present disclosure is shown. Figure 1 As shown, a vehicle driving safety assessment method provided by an embodiment of the present disclosure includes:

[0066] S101: Constructing an abstract element situation field based on the driving environment information of the target vehicle and the motion data of traffic participants in the driving environment information.

[0067] Driving environment information includes information about the target vehicle's lane, traffic signals ahead, and other road conditions. For example, it can be used to determine whether the vehicle is on a straight road or a curve. Traffic participant motion data includes the target vehicle, surrounding vehicles, pedestrians, and electric vehicles. Traffic participant motion data can be described as spatiotemporal trajectories, which map motion data from time to space.

[0068] The constructed abstract element situation field is the spatiotemporal situation field of all objective information in the target vehicle's driving environment, which can objectively describe and evaluate the risks of complex road traffic scenarios.

[0069] S102: Constructing a situation field of concrete elements based on the driving condition of the target vehicle.

[0070] Based on the abstract element situation field, a concrete, objective spatiotemporal situation field can be constructed based on the specific driving conditions of the target vehicle. This objectively describes and assesses the risks of the driving environment surrounding the target vehicle and the risks of interactions between the target vehicle and other traffic participants (such as other vehicles around the target vehicle or pedestrians in front of the target vehicle). These abstract and concrete element situation fields can be constructed using spatiotemporal convolution.

[0071] S103: Constructing a subjective cognitive field based on the expected driving trajectory of the target vehicle.

[0072] Based on the abstract and concrete objective spatiotemporal situation field, subjective evaluation parameters can be added to construct a subjective cognitive field based on the vehicle's expected driving trajectory. This subjective spatiotemporal situation field can then be used to assess driving risk based on the user's subjective expected driving trajectory. The subjective cognitive field can be constructed using spatiotemporal convolution and attention mechanisms.

[0073] S104: Evaluate the driving safety of the target vehicle based on the abstract element situation field, the concrete element situation field, and the subjective cognitive field.

[0074] After constructing the above-mentioned abstract element situation field, concrete element situation field and subjective cognitive field using a description method similar to that of electric fields and magnetic fields, a comprehensive and unified spatiotemporal situation representation of the target vehicle's driving risk can be performed based on the three spatiotemporal situation fields, that is, a comprehensive quantitative assessment of the target vehicle's driving risk can be conducted by integrating subjective and objective factors.

[0075] The vehicle driving safety assessment method provided by the embodiment of the present disclosure constructs an abstract element situation field based on the driving environment information of the target vehicle and the motion data of traffic participants in the driving environment information; constructs a concrete element situation field based on the driving situation of the target vehicle; and constructs a subjective cognitive field based on the expected driving trajectory of the target vehicle. The driving safety of the target vehicle is assessed based on the abstract element situation field, the concrete element situation field, and the subjective cognitive field. The method can quantitatively describe the objective traffic risk in combination with the driving environment of the vehicle and the interaction relationship between vehicles in the actual traffic scene, and conduct a comprehensive and objective assessment of the driving safety of the target vehicle. It more comprehensively considers road traffic risks and solves the drawbacks of incomplete and non-objective risk assessment in complex road traffic scenes. At the same time, combined with the subjective cognitive field, it provides a safety assessment for smart cars that is closer to human cognitive methods, ensuring that the decision-making planning of the autonomous driving system can better meet the driver's safety expectations in actual driving scenarios, thereby improving the safety of smart driving. In addition, the concrete element situation field and the subjective cognitive field constructed in this embodiment can well describe the risk distribution caused by dynamic traffic elements in the time domain, thereby improving the effect of vehicle driving risk assessment.

[0076] In some embodiments, in step S104, evaluating the driving safety of the target vehicle based on the abstract element situation field, the concrete element situation field, and the subjective cognitive field includes:

[0077] The risk distributions under different situation fields are integrated to evaluate the driving risk of the target vehicle, wherein the driving risk includes the driving environment risk of the driving environment in which the target vehicle is located and the interaction risk between the target vehicle and other traffic participants.

[0078] Different situation fields have different risk distributions, and these risk distributions may be correlated. For example, the abstract element situation field primarily provides an objective description of the road traffic scenario risks within the target vehicle's driving environment. The concrete element situation field, based on the abstract element situation field and the target vehicle's dynamic driving conditions, is constructed to more accurately and objectively describe dynamic driving risks. The subjective cognitive field, based on the vehicle's current driving conditions and combined with road conditions and other information, describes the future driving risk distribution according to the user's expected driving trajectory. To comprehensively assess the target vehicle's driving risk, the risk distributions of the three situation fields are fused. Based on this fused risk distribution, the driving risks surrounding the target vehicle and the risks of interactions with other traffic participants are assessed. For example, the risk distribution curve of the abstract element situation field determines that there are multiple roadblocks in front of the target vehicle, and the risks of each roadblock are similar, and their impact on the target vehicle's driving is similar. The risk distribution curve of the concrete element situation field determines that the first roadblock directly in front of the target vehicle is likely to collide with the target vehicle when the distance between the target vehicle and the first roadblock is less than 30m. The risk of the first roadblock is relatively high, and other roadblocks (such as the second roadblock located in front of the left of the target vehicle) have little impact on the vehicle's driving. In the risk distribution curve of the subjective cognitive field, it is determined that the vehicle is about to turn left, and the second roadblock located in front of the left of the target vehicle may collide with the target vehicle after the left turn. The risk of the second roadblock is relatively high. At this time, the three situation fields are fused to determine whether the second roadblock will affect the driving of the target vehicle, whether the target vehicle will collide with the first roadblock before turning left, and whether other roadblocks will affect the driving of the target vehicle, thereby providing users with a safer obstacle avoidance driving route and improving driving safety.

[0079] In some embodiments, in step S101, constructing an abstract element situation field based on the driving environment information of the target vehicle and the motion data of traffic participants in the driving environment information includes:

[0080] S1011: In the vertical direction of the tangent line of the current road point, according to the distance from the point on the vertical line to the road point, the output of the one-dimensional Gaussian function is calculated to obtain the situation field strength distribution;

[0081] S1012: Classifying the driving environment information and the motion data of traffic participants in the driving environment information to obtain a classification result;

[0082] S1013: Fusing the classification result and the situation field strength distribution to obtain a fusion result;

[0083] S1014: Inputting the fusion result into a preset abstract element risk distribution calculation model to obtain a risk distribution field curve.

[0084] The abstract element situation field is constructed based on a one-dimensional Gaussian function. The output of this one-dimensional Gaussian function is calculated based on the distance from the point on the perpendicular line to the current road point, perpendicular to the tangent line. The output of this one-dimensional Gaussian function represents the situation field strength generated by that lane at that point on the perpendicular line. The situation field strengths at different points form a situation field strength distribution.

[0085] After data preprocessing, the driving environment data (also known as traffic environment data) and the motion data of traffic participants are classified. For example, the driving environment data can be classified into lane lines, and the motion data of traffic participants can be classified into spatiotemporal trajectories 1, 2, 3, ..., N, where N represents the number of traffic participants. These classification results are then fused with the situation field intensity distribution to generate a fusion result based on traffic situation evolution. This fusion result is then input into a pre-set risk distribution calculation model to obtain a risk distribution field curve for the abstract element. This allows for a comprehensive and objective description of traffic risk through spatiotemporal situation representation.

[0086] Furthermore, the abstract element risk distribution calculation model is:

[0087]

[0088]

[0089] Among them, G represents the Gaussian coefficient, r ae represents the distance between the target vehicle’s current driving risk and the expected risk lane line, and σ represents the standard deviation of the model.

[0090] The above-mentioned abstract element risk distribution calculation model calculates the risk distribution of abstract elements on the lane, which can be used to evaluate the road boundary risk of the vehicle.

[0091] In some embodiments, the method further comprises:

[0092] S201: Establishing a relationship curve between risk type and risk level according to a preset risk level to obtain a risk type curve;

[0093] S202: Determine whether the risk factor distribution in the risk distribution field curve is a normal distribution;

[0094] S203: Fitting the risk type curve to the risk distribution field curve according to the 3σ principle to obtain the distribution of abstract element risks on the straight and curved roads.

[0095] Specifically, such as Figure 2As shown in FIG, in this embodiment, the relationship curve between risk type and risk level is established by objectively calibrating four risk levels a, b, c, and d to obtain a risk type curve. Figure 2 From the risk type curve, we can see that at the same risk level, the field risk of risk type 1 is smaller than that of risk type 0.

[0096] Then, assuming that the distribution of risk factors satisfies the normal distribution, the risk type curve is fitted with the risk distribution field curve through the 3σ principle (used to describe the concentration of data in the normal distribution), and the distribution of abstract element risks on straight lines and curves is derived. Figure 3 Shows the distribution of abstract elements on the straight road ( Figure 3 (longitudinalposition represents the longitudinal position coordinate, lateralposition represents the lateral position coordinate). Figure 3 (a) shows the three-dimensional distribution of abstract element risk on the straight road. Figure 3 (b) is Figure 3 The top view in (a) shows the two-dimensional distribution of the abstract element risk on the straight road. Figure 4 Shows the distribution of abstract elements on the curve ( Figure 4 Solid lane is a single solid line, dashlane is a single dotted line). Figure 3 and Figure 4 The “ridge” in the figure can reveal the specific situation of the risk field distribution.

[0097] In some embodiments, in step S102, constructing a concrete element situation field based on the driving condition of the target vehicle includes:

[0098] S1021: Constructing the concrete element situation field in the local coordinate system of the target vehicle based on a two-dimensional Gaussian function;

[0099] The distribution area of ​​the two-dimensional Gaussian function is based on at least one of the vehicle size, vehicle speed, and acceleration of the target vehicle.

[0100] After constructing the spatiotemporal situation field for the abstract elements, the spatiotemporal situation field for the concrete elements needs to be constructed. This concrete element situation field is constructed based on a two-dimensional Gaussian function, whose coordinate system is the local coordinate system of the current target vehicle. Therefore, for each point where the situation field strength is to be calculated, the point must first be converted to the local coordinate system of the current target vehicle. The distribution area of ​​the two-dimensional Gaussian function is determined by the target vehicle's lateral and longitudinal dimensions, its speed, and its acceleration.

[0101] In some embodiments, in step S1021, constructing the concrete element situation field based on a two-dimensional Gaussian function in the local coordinate system of the target vehicle includes:

[0102] Taking the stationary state of the target vehicle as a reference, calculating the situation field distribution when the target vehicle is traveling at a constant speed;

[0103] The calculation formula of the situation field distribution is:

[0104]

[0105] Where, Indicates the strength of the situation field at a certain point in the situation field, Indicates the minimum distance between the current target vehicle and other surrounding vehicles.

[0106] In this step, the static state of the vehicle is used as a reference to analyze the situation field distribution of the target vehicle when it is traveling at a constant speed. When calculating, the vehicle coordinates are first transformed, such as Figure 5 As shown in FIG, the coordinate system centered on the target vehicle (the ego vehicle) is first converted to a coordinate system centered on O (the coordinate system centered on O is pre-set), and then the converted vehicle coordinates (Pxe, Pye) are calculated.

[0107] Further, such as Figure 6 As shown, for the convenience of calculation and analysis, the distance between the target vehicle and other vehicles around the target vehicle is scaled to obtain the distance between the target vehicle and other vehicles. Indicates the maximum distance between the current target vehicle and other surrounding vehicles. Represents the minimum distance between the current target vehicle and other surrounding vehicles. Then, the traffic data of the target vehicle in two driving states, static and uniform motion, are input into the calculation formula of the above situation field distribution, and the following is obtained: Figure 7 The spatial-temporal situation field of the concrete elements shown (the distribution of risks of concrete elements). Figure 7 The ridge of the middle curve shows that when the target vehicle moves at a constant speed, the risk of its spatiotemporal situation field is also uniformly distributed.

[0108] In the above embodiment, the spatiotemporal situation field of the target vehicle at a constant speed is analyzed. In specific implementations, the situation field distribution of the target vehicle during acceleration can also be analyzed, using the vehicle at rest or at a constant speed as a reference. Alternatively, the specific situation field distribution of the target vehicle in other driving scenarios (e.g., turning) can also be calculated and analyzed.

[0109] In some embodiments, in step S103, constructing a subjective cognitive field based on the expected driving trajectory of the target vehicle includes:

[0110] S1031: Determining an expected driving trajectory of the target vehicle based on the wheelbase and steering wheel angle of the target vehicle;

[0111] S1032: Establishing a one-dimensional Gaussian function in a direction perpendicular to the expected driving trajectory for each point on the expected driving trajectory;

[0112] S1033: Construct the subjective cognitive field according to the established multiple one-dimensional Gaussian functions.

[0113] Based on the abstract and concrete objective spatiotemporal situation fields, subjective evaluation parameters are added to construct a subjective cognitive field. This subjective cognitive field is constructed similarly to the abstract element situation field, but it is based on the vehicle's expected driving trajectory. Specifically, once the vehicle's wheelbase and steering wheel angle are determined, the vehicle's expected driving trajectory can be determined to be an arc. At each point on the arc, several one-dimensional Gaussian functions are constructed perpendicular to the arc. As the points on the arc gradually move away from the current position of the target vehicle, the width of the one-dimensional Gaussian function increases and the height decreases. This change is mainly related to the target vehicle's driving speed and steering angle. The subjective cognitive field is then constructed based on these several one-dimensional Gaussian functions.

[0114] In some embodiments, the subjective cognitive field includes a risk situation field under at least one driving scenario of a vehicle driving at a constant speed, accelerating, and driving in parallel lanes.

[0115] Figure 8 (a) shows the subjective cognitive field of the target vehicle in the constant speed and acceleration driving scenarios. Figure 8 (b) shows the subjective cognitive field of the target vehicle in the left and right lane merging scenarios, which allows for an intuitive assessment of the vehicle's driving risk based on the driver's subjective factors.

[0116] Example 2

[0117] Figure 9 FIG. 1 shows a schematic diagram of the structure of a vehicle driving safety assessment device according to an embodiment of the present disclosure. Figure 9 As shown, the embodiment of the present disclosure provides a vehicle driving safety assessment device, comprising:

[0118] A first construction module 10 is configured to construct an abstract element situation field based on the driving environment information of the target vehicle and the motion data of the traffic participants in the driving environment information;

[0119] A second construction module 20 is configured to construct a situation field of a concrete element based on the driving condition of the target vehicle;

[0120] A third building module 30 is configured to build a subjective cognitive field based on the expected driving trajectory of the target vehicle;

[0121] The safety assessment module 40 is configured to assess the driving safety of the target vehicle based on the abstract element situation field, the concrete element situation field and the subjective cognitive field.

[0122] In some embodiments, the first building block 10 is further configured to:

[0123] In the vertical direction of the tangent line of the current road point, the output of the one-dimensional Gaussian function is calculated according to the distance from the point on the vertical line to the road point to obtain the situation field strength distribution;

[0124] Classifying the driving environment information and the motion data of traffic participants in the driving environment information to obtain a classification result;

[0125] Fusing the classification result with the situation field strength distribution to obtain a fusion result;

[0126] The fusion result is input into a preset abstract element risk distribution calculation model to obtain a risk distribution field curve.

[0127] In some embodiments, the abstract element risk distribution calculation model is:

[0128]

[0129]

[0130] Among them, G represents the Gaussian coefficient, r ae represents the distance between the target vehicle’s current driving risk and the expected risk lane line, and σ represents the standard deviation of the model.

[0131] In some embodiments, the first building block 10 is further configured to:

[0132] Establish a relationship curve between risk type and risk level according to the preset risk level to obtain a risk type curve;

[0133] Determining that the risk factor distribution in the risk distribution field curve is a normal distribution;

[0134] According to the 3σ principle, the risk type curve is fitted with the risk distribution field curve to obtain the distribution of abstract element risks on straight roads and curves.

[0135] In some embodiments, the second building block 20 is further configured to:

[0136] In the local coordinate system of the target vehicle, constructing the representational element situation field based on a two-dimensional Gaussian function;

[0137] The distribution area of ​​the two-dimensional Gaussian function is based on at least one of the vehicle size, vehicle speed, and acceleration of the target vehicle.

[0138] In some embodiments, the second building block 20 is further configured to:

[0139] Taking the stationary state of the target vehicle as a reference, calculating the situation field distribution when the target vehicle is traveling at a constant speed;

[0140] The calculation formula of the situation field distribution is:

[0141]

[0142] Where, Indicates the strength of the situation field at a certain point in the situation field, Indicates the minimum distance between the current target vehicle and other surrounding vehicles.

[0143] In some embodiments, the third building block 30 is further configured to:

[0144] Determining an expected driving trajectory of the target vehicle based on the wheelbase and steering wheel angle of the target vehicle;

[0145] Establishing a one-dimensional Gaussian function at each point on the expected driving trajectory in a direction perpendicular to the expected driving trajectory;

[0146] The subjective cognitive field is constructed according to the established multiple one-dimensional Gaussian functions.

[0147] In some embodiments, the subjective cognitive field includes a risk situation field under at least one driving scenario of a vehicle driving at a constant speed, accelerating, and driving in parallel lanes.

[0148] In some embodiments, the security assessment module 40 is further configured to:

[0149] The risk distributions under different situation fields are integrated to evaluate the driving risk of the target vehicle. The driving risk includes the driving environment risk of the driving environment in which the target vehicle is located and the interaction risk between the target vehicle and other traffic participants.

[0150] The vehicle driving safety assessment device provided in the embodiment of the present disclosure corresponds to the vehicle driving safety assessment method in the above embodiment. Any optional items in the embodiment of the vehicle driving safety assessment method are also applicable to the embodiment of the vehicle driving safety assessment device and will not be repeated here.

[0151] Example 3

[0152] An embodiment of the present disclosure further provides an electronic device comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned vehicle driving safety assessment method when executing the computer program on the memory.

[0153] In some embodiments, the processor that executes the computer program may be a processing device including one or more general-purpose processing devices, such as a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), etc. More specifically, the processor may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor that runs other instruction sets, or a processor that runs a combination of instruction sets. The processor may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a system on a chip (SoC), etc.

[0154] The memory may be read-only memory (ROM), random access memory (RAM), phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), electrically erasable programmable read-only memory (EEPROM), other types of random access memory (RAM), flash disks or other forms of flash memory, cache, registers, static memory, compact disk read-only memory (CD-ROM), digital versatile disks (DVD) or other optical storage, magnetic tape cassettes or other magnetic storage devices, or any other possible non-transitory medium used to store information or instructions that can be accessed by a computer device.

[0155] The electronic devices of the embodiments of the present disclosure may include but are not limited to fixed terminal devices such as MCU controllers, servers, desktop computers, digital TVs, etc., as well as mobile terminal devices such as vehicle-mounted devices (such as head-up display devices), handheld devices (such as mobile phones, tablets, etc.), wearable devices (such as smart watches, smart bracelets, etc.), etc.

[0156] Example 4

[0157] An embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned vehicle driving safety assessment method is implemented.

[0158] The computer-readable storage medium of the embodiments of the present disclosure may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. In the embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device, for example, the memory described above.

[0159] The computer programs of the embodiments of the present disclosure may be organized into one or more computer-executable components or modules. Any number and combination of such components or modules may be used to implement various aspects of the present disclosure. For example, various aspects of the present disclosure are not limited to the specific computer-executable instructions or specific components or modules shown in the accompanying drawings and described herein. Other embodiments may include different computer-executable instructions or components with more or less functionality than shown and described herein.

[0160] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the present disclosure is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the scope of the above disclosure. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

Claims

1. A vehicle driving safety assessment method, characterized in that: include: Constructing an abstract element situation field based on the driving environment information of the target vehicle and the motion data of traffic participants in the driving environment information; Constructing a concrete element situation field based on the driving condition of the target vehicle; constructing a subjective cognitive field based on the expected driving trajectory of the target vehicle; Based on the abstract element situation field, the concrete element situation field and the subjective cognitive field, the driving safety of the target vehicle is evaluated, which includes fusing the risk distribution under different situation fields to evaluate the driving risk of the target vehicle; Among them, the abstract element situation field is used to objectively describe the road traffic scene risk in the driving environment of the target vehicle; the concrete element situation field is used to objectively describe the dynamic driving risk of the target vehicle; the subjective cognitive field is used to describe the future driving risk distribution based on the user's expected driving trajectory; The constructing of an abstract element situation field based on the driving environment information of the target vehicle and the motion data of traffic participants in the driving environment information includes: In the vertical direction of the tangent line of the current road point, the output of the one-dimensional Gaussian function is calculated according to the distance from the point on the vertical line to the road point to obtain the situation field strength distribution; Classifying the driving environment information and the motion data of traffic participants in the driving environment information to obtain a classification result; Fusing the classification result with the situation field strength distribution to obtain a fusion result; Inputting the fusion result into a preset abstract element risk distribution calculation model to obtain a risk distribution field curve; The method further comprises: Establish a relationship curve between risk type and risk level according to the preset risk level to obtain a risk type curve; Determining that the risk factor distribution in the risk distribution field curve is a normal distribution; The risk type curve is fitted with the risk distribution field curve according to the 3σ principle to obtain the distribution of abstract element risks on straight roads and curves.

2. The method according to claim 1, characterized in that The abstract element risk distribution calculation model is: , ; in, G represents the Gaussian coefficient, r ae Indicates the distance between the target vehicle’s current driving risk and the expected risk lane line. σ represents the standard deviation of the model.

3. The method according to claim 1, characterized in that: Constructing a concrete element situation field based on the driving condition of the target vehicle, including: In the local coordinate system of the target vehicle, constructing the situation field of the concrete element based on a two-dimensional Gaussian function; Wherein, the distribution area of ​​the two-dimensional Gaussian function is determined according to at least one of the vehicle size, vehicle speed and acceleration of the target vehicle.

4. The method according to claim 3, characterized in that: In the local coordinate system of the target vehicle, constructing the situation field of the concrete element based on a two-dimensional Gaussian function includes: Taking the stationary state of the target vehicle as a reference, calculating the situation field distribution when the target vehicle is traveling at a constant speed; Among them, the calculation formula of the situation field distribution is: ; In the formula ， Indicates the strength of the situation field at a certain point in the situation field, Indicates the minimum distance between the current target vehicle and other surrounding vehicles.

5. The method according to claim 1, characterized in that A subjective cognitive field is constructed based on the expected driving trajectory of the target vehicle, including: Determining an expected driving trajectory of the target vehicle according to the wheelbase and steering wheel angle of the target vehicle; Establishing a one-dimensional Gaussian function at each point on the expected driving trajectory in a direction perpendicular to the expected driving trajectory; The subjective cognitive field is constructed according to the established multiple one-dimensional Gaussian functions.

6. The method according to claim 1, characterized in that The subjective cognitive field includes a risk situation field under at least one driving scenario of a vehicle driving at a constant speed, driving at an accelerated speed, and driving in parallel.

7. The method according to claim 1, characterized in that The driving risk includes the driving environment risk of the driving environment in which the target vehicle is located and the interaction risk between the target vehicle and other traffic participants.

8. A vehicle driving safety assessment device, characterized in that: include: A first construction module is configured to construct an abstract element situation field based on the driving environment information of the target vehicle and the motion data of the traffic participants in the driving environment information; A second construction module is configured to construct a concrete element situation field based on the driving condition of the target vehicle; A third building module is configured to build a subjective cognitive field based on the expected driving trajectory of the target vehicle; A safety assessment module, configured to assess the driving safety of the target vehicle based on the abstract element situation field, the concrete element situation field and the subjective cognitive field, including fusing the risk distribution under different situation fields to assess the driving risk of the target vehicle; Among them, the abstract element situation field is used to objectively describe the road traffic scene risk in the driving environment of the target vehicle; the concrete element situation field is used to objectively describe the dynamic driving risk of the target vehicle; the subjective cognitive field is used to describe the future driving risk distribution based on the user's expected driving trajectory; The first construction module is further configured to: calculate the output of a one-dimensional Gaussian function in a direction perpendicular to the tangent line of the current road point according to the distance from the point on the vertical line to the road point to obtain the situation field strength distribution; Classifying the driving environment information and the motion data of traffic participants in the driving environment information to obtain a classification result; Fusing the classification result with the situation field strength distribution to obtain a fusion result; Inputting the fusion result into a preset abstract element risk distribution calculation model to obtain a risk distribution field curve; The first building block is further configured as: Establish a relationship curve between risk type and risk level according to the preset risk level to obtain a risk type curve; Determining that the risk factor distribution in the risk distribution field curve is a normal distribution; The risk type curve is fitted with the risk distribution field curve according to the 3σ principle to obtain the distribution of abstract element risks on straight roads and curves.

Images