Driving risk assessment method and device and driving risk early warning equipment

Abstract

The invention provides a driving risk assessment method and device and a driving risk early warning device, and belongs to the technical field of intelligent driving, and the method comprises the steps: obtaining an environment risk factor, a behavior risk factor and a driving scene type of a to-be-assessed traffic vehicle, constructing an external environment field according to the environment risk factor, constructing an internal behavior field according to the behavior risk factors, and constructing a comprehensive driving risk field according to the external environment field and the internal behavior field; performing driving risk potential energy analysis according to the comprehensive driving risk field and the driving scene type to obtain a relative driving safety index; and determining a safety threshold value and a danger threshold value according to the behavior risk factor, and performing comparison and grading on the relative driving safety index, the safety threshold value and the danger threshold value to obtain a driving risk grading evaluation result. According to the method, the comprehensive driving risk field is constructed through the external environment field and the internal behavior field, the influence of environment factors, vehicle factors and drivers on driving risks is comprehensively quantified, and the driving behavior risks can be accurately evaluated.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular, to a driving risk assessment method, device, and driving risk warning device. Background Art

[0002] With the rapid popularization of intelligent driving in different scenarios, driving safety issues have become increasingly prominent. In transportation modes such as highways, railways, and waterways, timely and accurate risk assessment and warning are the basis for ensuring driving safety.

[0003] Among the current driving risk assessment methods, the more common ones are the field theory method and the probability method. The field theory method evaluates the risk level by establishing a driving safety field model, which can accurately quantify the driving risks of various types of transportation vehicles. For example, in the ship risk field, a risk field can be established based on the field theory and encounter situations, combined with relevant factors such as the ship's size and weight, and the driving risk can be quantitatively evaluated according to the risk field. In the probability method, such as the dynamic following model, the probability risk of distracted driving can be estimated with the driver as the center. However, although the current safety assessment method based on field theory can effectively quantify the driving risks of vehicles, it focuses on the environment and rarely considers the influence of the vehicle itself and the driver on the driving risks. Although the probability method considers the influence of the driver on the driving risks, it lacks quantitative and qualitative criteria and has low accuracy. However, with the popularization of intelligent driving, the impact of the intelligent driving system of driving vehicles such as cars on driving safety has gradually increased (such as the automatic obstacle avoidance of the intelligent driving system and the early warning of the navigation system). Therefore, in driving risk assessment, the proportion of the influence of vehicle and driver factors on driving safety has gradually increased. Therefore, in driving risk assessment, in addition to quantifying environmental factors, how to accurately quantify the influence of the vehicle itself and the driver on the driving risks is also the basis for ensuring the accuracy of the assessment.

[0004] Therefore, the prior art has the problem that it cannot accurately quantify the environmental factors and the influence of the vehicle itself and the driver on the driving risks at the same time, resulting in a reduction in the accuracy of driving risk assessment, and improvement is needed. Summary of the Invention

[0005] In view of this, it is necessary to provide a driving risk assessment method, device, and driving risk warning device for accurately quantifying the influence of environmental factors, the vehicle itself, and the driver on the driving risks and improving the accuracy of driving risk assessment.

[0006] In a first aspect, the present invention provides a driving risk assessment method, including: Obtain the environmental risk factor, behavior risk factor, and driving scene type of the traffic vehicle to be evaluated, construct an external environment field according to the environmental risk factor, construct an internal behavior field according to the behavior risk factor, and construct a comprehensive driving risk field according to the external environment field and the internal behavior field; Performing driving risk potential energy analysis based on the comprehensive driving risk field and driving scenario type to obtain the relative driving safety index; Determining the safety threshold and the danger threshold according to the behavioral risk factors, comparing and classifying the relative driving safety index with the safety threshold and the danger threshold to obtain the driving risk classification assessment result.

[0007] In some possible implementation manners, the environmental risk factors include a motion indication factor, a position indication factor, an infrastructure coverage factor, and a traffic factor, and the behavioral risk factors include a driving behavior risk factor, a service life factor, an autonomous level factor, and a health status factor.

[0008] In some possible implementation manners, constructing an external environment field according to the environmental risk factors, including: Determining the equivalent mass of the vehicle according to the motion indication factor; Determining the traffic environment factor according to the infrastructure coverage factor and the traffic factor; Constructing the external environment field according to the motion indication factor, the position indication factor, the equivalent mass of the vehicle, and the traffic environment factor.

[0009] In some possible implementation manners, constructing an internal behavior field according to the behavioral risk factors, including: Determining the traffic carrier risk factor according to the service life factor, the autonomous level factor, and the health status factor; Constructing the internal behavior field according to the traffic carrier risk factor and the driving behavior risk factor.

[0010] In some possible implementation manners, performing driving risk potential energy analysis based on the comprehensive driving risk field and driving scenario type to obtain the relative driving safety index, including: Determining the vehicle risk source force according to the comprehensive driving risk field, and determining the risk potential energy and the risk potential energy change rate according to the vehicle risk source force; Determining the driving safety index according to the risk potential energy and the risk potential energy change rate; Determining the relative driving safety index according to the driving safety index and the preset standard safety index; Wherein, the preset standard safety index is determined according to the driving scenario type.

[0011] In some possible implementation manners, determining the driving safety index according to the risk potential energy and the risk potential energy change rate, including: Determining the risk logic weight according to the driving scenario type; Determining the driving safety index according to the risk logic weight, the risk potential energy, and the risk potential energy change rate.

[0012] In some possible implementation manners, the driving scenario type includes a safety type scenario and an efficiency type scenario, and determining the risk logic weight according to the driving scenario type, including: If the scenario type is a safety scenario, determine the risk logic weight according to the preset initial safety weight; If the scenario type is an efficiency scenario, adjust the preset initial efficiency weight according to the traffic flow to obtain the risk logic weight.

[0013] In some possible implementation manners, determine the safety threshold and the danger threshold according to the behavior risk factor, including: Determine the safety threshold according to the behavior risk factor and the preset risk threshold strategy; Determine the danger threshold according to the preset maximum behavior risk factor and the preset risk threshold strategy.

[0014] In a second aspect, the present invention provides a driving risk assessment device, including: A risk field construction unit, configured to obtain the environmental risk factor, the behavior risk factor, and the driving scenario type of the traffic vehicle to be evaluated, construct an external environment field according to the environmental risk factor, construct an internal behavior field according to the behavior risk factor, and construct a comprehensive driving risk field according to the external environment field and the internal behavior field; A risk potential energy analysis unit, configured to perform driving risk potential energy analysis according to the comprehensive driving risk field and the driving scenario type to obtain a relative driving safety index; A risk level assessment unit, configured to determine the safety threshold and the danger threshold according to the behavior risk factor, compare and classify the relative driving safety index with the safety threshold and the danger threshold, and obtain a driving risk classification assessment result.

[0015] In a third aspect, the present invention provides a driving risk warning device, including a memory and a processor, wherein, The memory is configured to store a program; The processor is coupled to the memory and configured to execute the program stored in the memory to implement the steps in the driving risk assessment method of any one of the above.

[0016] The beneficial effects of the above embodiments are as follows: The driving risk assessment method provided by the present invention quantifies the environmental risk factor as an external environment field, quantifies the behavior risk factor as an internal behavior field, and constructs a comprehensive driving risk field according to the external environment field and the internal behavior field, so as to comprehensively quantify the influence of environmental factors, vehicle own factors, and drivers on driving risks, and can accurately assess the driving behavior risks.

[0017] Furthermore, the present invention also considers the driving scenario type in the driving risk potential energy analysis process, improves the adaptability of the relative driving safety index to the scenario, and further improves the accuracy of driving risk assessment in different scenarios. Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a schematic flowchart of an embodiment of the driving risk assessment method provided by the present invention; Figure 2 It is a schematic flowchart of constructing an external environment field in an embodiment of the present invention; Figure 3 It is a schematic flowchart of constructing an internal behavior field in an embodiment of the present invention; Figure 4 It is a schematic flowchart of driving risk potential energy analysis in an embodiment of the present invention; Figure 5 It is a schematic flowchart of determining a driving safety index in an embodiment of the present invention; Figure 6 It is a schematic flowchart of determining a risk logic weight in an embodiment of the present invention; Figure 7 It is a schematic flowchart of determining a safety threshold and a danger threshold in an embodiment of the present invention; Figure 8 It is a result graph of an efficiency-type scenario experiment; Figure 9 It is a result graph of a collision avoidance safety-type scenario experiment; Figure 10 It is a result graph of an overtaking safety-type scenario experiment; Figure 11 It is a schematic structural diagram of an embodiment of the driving risk assessment device provided by the present invention; Figure 12 It is a schematic structural diagram of an embodiment of the driving risk warning device provided by the present invention. Detailed implementation manners

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0021] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the present invention illustrate operations implemented according to some embodiments of the present invention. It should be understood that the operations in the flowchart may not be implemented in sequence, and steps without logical context may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present invention. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.

[0022] In the embodiments of the present invention, the descriptions such as "first" and "second" are only for descriptive purposes, and cannot be construed as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Therefore, the technical features defined with "first" and "second" may explicitly or implicitly include at least one such feature.

[0023] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0024] The present invention provides a driving risk assessment method, device, and driving risk warning device, which will be described separately below.

[0025] It should be noted that in the following description of the embodiments, the traffic vehicle to be evaluated is described in detail in the form of a vehicle. However, it should be understood that the driving risk assessment method of the present invention can be applied to the driving risk assessment of various types of vehicles such as cars, new energy vehicles, and special operation vehicles in road traffic in some embodiments, and can also be applied to the risk assessment during train operation in railway traffic or the driving risk assessment during ship navigation in waterway traffic in other embodiments. The embodiments do not limit the specific type of the traffic vehicle.

[0026] Figure 1 It is a schematic flowchart of an embodiment of the driving risk assessment method provided by the present invention. As Figure 1 shown, the driving risk assessment method includes: S101. Obtain the environmental risk factors, behavioral risk factors, and driving scenario types of the traffic vehicle to be evaluated. Construct an external environmental field based on the environmental risk factors, construct an internal behavioral field based on the behavioral risk factors, and construct a comprehensive driving risk field based on the external environmental field and the internal behavioral field. Among them, the environmental risk factors include environmental factors that may affect driving safety during the driving process of the traffic vehicle to be evaluated, such as a vehicle, for example, several factors such as surrounding driving vehicles, traffic visibility, or road conditions. The behavioral risk factors include factors that may affect driving safety by the driver and the vehicle itself during the driving process, such as the driver's perception and decision-making ability, the vehicle's autonomous driving obstacle avoidance ability, or the vehicle's service life and other several factors.

[0027] In the embodiment, by abstracting these influencing factors into environmental risk factors and behavioral risk factors, the influence of various influencing factors on driving risk can be quantitatively represented. By separately constructing an external environmental field and an internal behavioral field, and combining the external environmental field and the internal behavioral field to construct a comprehensive driving risk field, the driving risk can be accurately quantified.

[0028] In addition, although the comprehensive driving risk field can effectively quantify the risk value and can intuitively and significantly represent the magnitude of the risk value, it cannot accurately represent the level of the risk. Because in different scenarios, different risk field value magnitudes may correspond to different levels. Therefore, it is also necessary to obtain the driving scenario type during the evaluation process. The driving scenario type can be divided into a safety type and an efficiency type in the embodiment, which is determined according to the specific scenario, and the corresponding parameter weights are adjusted accordingly according to the different driving scenario types in the subsequent evaluation.

[0029] S102. Conduct driving risk potential energy analysis based on the comprehensive driving risk field and the driving scenario type to obtain a relative driving safety index. Among them, during the driving risk potential energy analysis process, in the embodiment, according to the field theory method, the relative driving safety index can be quantitatively analyzed based on the established comprehensive driving risk field. At the same time, relevant parameter weights are adaptively adjusted according to the driving scenario type during the analysis process, so as to obtain the quantified relative driving safety index. The value of the relative driving safety index ranges from 0 to 1. The smaller the value, the smaller the current risk is considered, and the larger the value, the greater the risk is considered.

[0030] S103. Determine the safety threshold and the danger threshold according to the behavioral risk factors, compare and classify the relative driving safety index with the safety threshold and the danger threshold to obtain the driving risk classification evaluation result.

[0031] Among them, considering that the factors of the driver and the traffic vehicle itself are the most direct factors affecting traffic safety, the embodiments determine the safety threshold and the danger threshold according to the abstracted behavioral risk factors, where the safety threshold is less than the danger threshold, and the hierarchical evaluation is performed according to the determined thresholds. In the embodiments, if the relative driving safety index is less than the safety threshold, it is considered that the driving risk level is low risk at this time; if the relative driving safety index is greater than or equal to the safety threshold and less than the danger threshold, it is considered that the driving risk level is general risk at this time; if the relative driving safety index is greater than or equal to the danger threshold, it is considered that the driving risk level is high risk at this time.

[0032] Compared with the prior art, the driving risk assessment method provided by the embodiments of the present invention quantifies the environmental risk factors into an external environmental field, quantifies the behavioral risk factors into an internal behavioral field, constructs a comprehensive driving risk field according to the external environmental field and the internal behavioral field, and thus comprehensively quantifies the influence of environmental factors, vehicle factors and drivers on driving risks, and can accurately evaluate the driving behavior risks.

[0033] Furthermore, the present invention also considers the driving scenario type in the process of driving risk potential analysis, improves the adaptability of the relative driving safety index to the scenario, and further improves the accuracy of driving risk assessment in different scenarios.

[0034] In some embodiments of the present invention, the environmental risk factors include a movement indication factor, a position indication factor, an infrastructure coverage factor, and a traffic factor, and the behavioral risk factors include a driving behavior risk factor, a service life factor, an autonomous level factor, and a health status factor.

[0035] In the embodiments, the environmental risk factors include, but are not limited to, a movement indication factor, a position indication factor, an infrastructure coverage factor, and a traffic factor, etc.

[0036] Among them, the movement index factor is mainly determined by the speed and the magnitude of the acceleration of several traffic units, and the formula is expressed as:

[0037] Among them, represents the speed of the traffic unit , represents the acceleration of the traffic unit . The traffic unit can be stationary or moving. The constant 1 in the formula is to avoid that when the traffic unit is in a stationary state, makes the equation meaningless.

[0038] The position indicator factor is used to describe the position of the traffic unit in the traffic environment. Since the traffic unit has vectorial properties in the traffic environment and has different effects on driving risks in different directions, the relative position distance in the embodiment can be expressed as the vector distance between the center of mass of the vehicle and the center of mass of the traffic unit. The smaller the relative distance, the greater the driving risk. In addition, considering that if the shape and size of the obstacle are ignored and it is only regarded as a mass point, and only the distance between the mass points is considered, the safe distance between the main vehicle and the obstacle will be incorrectly estimated, thereby causing a certain deviation in the quantification of driving risks, so the shape factor also needs to be considered. In summary, the position indicator factor The formula is:

[0039] in, To connect the main vehicle and other traffic units The angle between the linear direction vector and the speed direction of the traffic unit. For the main vehicle With other traffic units The vector distance between For traffic units The shape size factor is the traffic unit aspect ratio.

[0040] Infrastructure coverage factor The focus is on the speed of improvement of navigation equipment, the coverage of traffic management systems, and the ability to respond to emergencies in the event of danger. Navigation instruments usually have positioning, traffic direction, and hazard warning functions. These functions are intuitive and reliable, helping to quickly respond to sudden environmental changes. The distribution of navigation aids affects navigation safety to varying degrees; the denser the arrangement of navigation aids, the higher the safety level. Infrastructure coverage factor in the embodiment The relationship between the value of and coverage can be shown in Table 1 below: Table 1: Comparison of infrastructure coverage rate and infrastructure coverage factor

[0041] In addition, traffic factors include traffic visibility , traffic dependency factor , traffic curvature and traffic gradient Four factors that may affect traffic conditions.

[0042] For behavioral risk factors, in the embodiments, they mainly consist of two parts: the behavior of the main driver and the vehicle itself. The driver's behavior can be represented by a driving behavior risk factor, and the vehicle itself can be represented by, but not limited to, a service life factor, an autonomous level factor, and a health status factor.

[0043] Among them, in the driver behavior factors, the driving behavior risk factor is mainly determined by the driver's perception ability, decision-making ability, and control ability during driving. This factor can be evaluated through, but not limited to, various factors such as the quantitative assessment of the driver, driver's license type, driving experience, and continuous driving duration.

[0044] Among the vehicle behavior factors, from the perception level, the service life factor is used to represent the impact on the perception of driving risk, mainly considering the length of vehicle use time; from the decision-making level, the autonomous level factor is used to represent the autonomous level of the vehicle, that is, to reflect the vehicle's driving decision-making ability; from the control level, the health status factor is used to represent, mainly considering the health status of the vehicle itself, which includes the braking and steering performance of the vehicle, the level of the power system, and the integrity of the metal structure, etc.

[0045] In some embodiments of the present invention, Figure 2 is a schematic flow chart of constructing an external environment field for the embodiments of the present invention. As Figure 2 shown, constructing an external environment field according to environmental risk factors includes: S201. Determine the equivalent mass of the vehicle according to the motion indication factor; Among them, the attributes and states of traffic units affect the magnitude of the driving risk of the host vehicle, which can be represented by the equivalent mass of the vehicle, mainly manifested in aspects such as the type of traffic unit, the mass of the traffic unit, and the motion state of the traffic unit. The type of traffic unit is mainly determined by the degree of damage caused by the collision between the host vehicle and the traffic unit. In addition, when the traffic unit type and mass are the same, the greater the vehicle speed, the greater the potential driving risk. Therefore, the equivalent mass of the vehicle can be expressed as:

[0046] Among them, is the shape coefficient of the traffic unit. Traffic units of the same type have the same shape coefficient. represents the influence of the vehicle speed of the traffic unit on the driving risk. , and are coefficients to be determined, obtained by fitting road safety data. and are the physical mass and speed of the traffic unit respectively.

[0047] S202. Determine the traffic environment factor based on the infrastructure coverage factor and the traffic factor; Among them, the traffic environment factor is used to characterize the current traffic condition, which is mainly determined by factors such as traffic visibility, traffic attachment coefficient, traffic curvature, traffic gradient, and road infrastructure condition. Therefore, the traffic environment factor can be expressed as:

[0048] Among them, is the road infrastructure coverage factor, , , and respectively represent the traffic visibility, traffic attachment factor, traffic curvature, and traffic gradient of the traffic unit at , and represents the influence function of these four traffic factors on the traffic environment factor.

[0049] Among them, the influence function of traffic visibility is expressed as:

[0050] Among them, is the standard traffic visibility.

[0051] The influence function of the traffic attachment coefficient is expressed as:

[0052] Among them, is the standard traffic attachment coefficient.

[0053] The influence function of traffic curvature is expressed as:

[0054] The influence function of traffic gradient is expressed as:

[0055] S203. Construct an external environment field based on the motion indication factor, the position indication factor, the equivalent mass of the vehicle, and the traffic environment factor.

[0056] Among them, after integrating the motion indication factor , the position indication factor , the equivalent mass of the vehicle and the traffic environment factor , the external environment field can be expressed as:

[0057] Through the above methods, the influence of the external environment on driving safety can be abstracted and represented in the form of a field, so as to achieve effective quantification.

[0058] In some embodiments of the present invention, Figure 3 is a schematic flow chart of constructing an internal behavior field for an embodiment of the present invention, as Figure 3 shown, constructing an internal behavior field according to behavior risk factors, including: S301. Determine the traffic carrier risk factor according to the service life factor, autonomy level factor, and health status factor; Among them, the behavior risk factors include factors of driver behavior and vehicle behavior. For the vehicle aspect, it is jointly determined by the service life factor, autonomy level factor, and health status factor. Considering that the influence degrees of the three different factors on vehicle behavior danger are not the same, therefore, by setting weights , and to comprehensively adjust the weights, where . Therefore, the traffic carrier risk factor can be expressed as:

[0059] Among them, the service life factor is mainly a function of the influence of the vehicle service life on driving risk. The longer the service life of the equipment, the greater the risk of structural failure, such as the failure of various sensors and other circuit systems, thus affecting the equipment's perception ability of driving risk. For the in-service performance of the vehicle, the current driving life and the planned driving life ratio are mainly considered, and the formula is expressed as:

[0060] The autonomy level factor represents the ability of autonomous perception, autonomous decision-making, and autonomous control. The higher the level of autonomous driving of the vehicle, the lower the degree of driver intervention; the driving process can rely on more complex sensing systems and more accurate and reliable decision-making methods to provide more precise control, and compared with the driving state with high driver participation, the risk is smaller.

[0061] The embodiment summarizes the classification criteria for different vehicle autonomy level indicators. Starting from the three indicators of perception ability, decision-making ability, and control ability, it is divided into four levels from L0 to L3, and the autonomy level factor value and the classification criteria are shown in Table 2: Table 2: Autonomy level factor value table

[0062] The health status factor It is mainly reflected in the risks of the vehicle steering and braking structure performance, the power system performance, and the metal structure integrity. When one of these risks increases, the vehicle's health attitude factor can be expressed as:

[0063] Among them, in the embodiment, the number of days of sensor alarms caused by braking steering braking system failures, power system failures, or metal structure failures within one year of the vehicle is calculated as , the higher the failure frequency, the higher the risk of the vehicle.

[0064] S302. Construct an internal behavior field according to the traffic carrier risk factor and the driving behavior risk factor.

[0065] Then, in the embodiment, the traffic carrier risk factor is combined with the driving risk factor, and considering the external environment field of other traffic units, the internal behavior field of the vehicle is constructed, and the formula is expressed as:

[0066] Among them, represents the behavior risk factor, which is jointly determined by the traffic carrier risk factor and the driving risk factor. and are the weights of the traffic carrier risk factor and the driving risk factor respectively, and . represents the external environment field.

[0067] In some embodiments of the present invention, Figure 4 is the flow schematic diagram of the driving risk potential energy analysis of the embodiment of the present invention. As shown in Figure 4 , the relative driving safety index is obtained by performing driving risk potential energy analysis according to the comprehensive driving risk field and the driving scene type, including: S401. Determine the vehicle risk source force according to the comprehensive driving risk field, and determine the risk potential energy and the risk potential energy change rate according to the vehicle risk source force; Among them, although the driving risk field can intuitively and significantly represent the magnitude of the risk value, it cannot accurately represent the risk level. For different scenarios, different risk field value magnitudes correspond to different risk levels, and the magnitude of the risk field value cannot be used to judge the risk of the main vehicle's driving. In this regard, the embodiment adopts the method of driving risk potential energy analysis to quantitatively analyze the risk level.

[0068] Among them, in the calculation of the vehicle risk source force, the field strength vector, the equivalent mass, and the behavior characteristics jointly determine the risk source force of the traffic unit on the main vehicle . These parameters can be determined according to the established comprehensive driving risk field, and the risk source force formula is expressed as:

[0069] Then, in the embodiment, a scalar is used as the risk potential energy, which is the energy that the host vehicle has due to the conservative field force in the driving safety field. Taking the driving risk field formed by the host vehicle as an example, the risk potential energy can be expressed as:

[0070] where, is the risk potential energy in the driving risk field formed by other traffic units and the host vehicle, is and is the distance between. is determined by the position of other traffic unit , reflecting the distribution of driving risk in space. The larger it is, the greater the surface risk.

[0071] In addition, the driving risk not only varies with space but also with time. However, the risk potential only represents the spatial variability of the driving risk. Therefore, another physical measure is needed to represent the driving risk. In the embodiment, the rate of change of with time is expressed as:

[0072] S402. Determine the driving safety index according to the risk potential energy and the rate of change of the risk potential energy; where, based on the obtained risk potential energy and the rate of change of the risk potential energy, the driving safety index can be expressed as:

[0073] where, and are the weight coefficients of the influence of two different risk logics and on the host vehicle, which are determined according to the driving scenario, and .

[0074] S403. Determine the relative driving safety index according to the driving safety index and the preset standard safety index; where, the preset standard safety index is determined according to the type of driving scenario.

[0075] In addition, considering that the driving safety index is an absolute risk index and its variation range is uncertain, so when evaluating the driving risk, the relative driving safety index is used to evaluate whether it is dangerous, and the formula is expressed as:

[0076] Among them, represents the standardized driving safety index, which is determined according to the type of driving scenario.

[0077] In some embodiments of the present invention, Figure 5 is a schematic flow chart for determining the driving safety index according to an embodiment of the present invention. As Figure 5 shown, the driving safety index is determined according to the risk potential energy and the change rate of risk potential energy, including: S501. Determine the risk logic weight according to the type of driving scenario; S502. Determine the driving safety index according to the risk logic weight, the risk potential energy, and the change rate of risk potential energy.

[0078] In some embodiments of the present invention, the types of driving scenarios include safe scenarios and efficiency scenarios. Figure 6 is a schematic flow chart for determining the risk logic weight according to an embodiment of the present invention. As Figure 6 shown, the risk logic weight is determined according to the type of driving scenario, including: S601. If the scenario type is a safe scenario, determine the risk logic weight according to the preset initial weight for the safe scenario; S602. If the scenario type is an efficiency scenario, adjust the preset initial weight for the efficiency scenario according to the traffic flow to obtain the risk logic weight.

[0079] Specifically, in the embodiment, the driving scenarios can be divided into safe scenarios and efficiency scenarios. For safe scenarios, the driving tasks in such scenarios aim at safety. For example, in a road scenario, a subsequent scenario where there is a vehicle in front; in a waterway scenario, a scenario where a ship may collide with an island or an obstacle; in a railway scenario, a railway section where there may be foreign objects in front of the train track.

[0080] For efficiency scenarios, it is hoped that the driver can complete the driving task faster and more accurately. For example, in a road scenario, the vehicle stops and starts or travels at a constant speed normally; in a waterway scenario, a ship mooring scenario; in a railway scenario, a train passing through a tunnel or traveling in the dark.

[0081] For safe scenarios, the risks mainly come from the external environment. At this time, it is necessary to quickly identify high risks and make responses. In this scenario, the risk potential energy has a greater impact on the driving risk. Therefore, in the driving safety index formula should be increased. In the embodiment, the initial value of for the safe scenario can be set to 0.7, and the initial value of

[0082] For the efficiency scenario, the risks mainly come from the impact of time efficiency and traffic flow, and it is necessary to balance efficiency and safety. In this scenario, the change rate of risk potential energy has a greater impact on driving risk. Therefore, in the driving safety index formula should be increased. In the embodiment, the initial value of the efficiency scenario can be set to 0.3, and the initial value of

[0083] can be set to 0.7.

[0084] In addition, as described above, traffic flow also has a certain impact in the efficiency scenario. Therefore, the embodiment can further introduce a traffic flow factor for adjustment, and the formula is expressed as: wherein, represents the traffic flow factor, and its value range is from 0 to 1, represents the initial value of

[0085] and here it can take the value of 0.7.

[0086] In addition, it should be understood that in some other embodiments, the driving scenario can also be more finely divided, and different risk logic weights and different standardized driving safety indices can be assigned to different scenarios. The above division method is only one division method of the present invention, not all division methods. Figure 7 In some embodiments of the present invention, Figure 7 is a schematic flowchart for determining the safety threshold and the danger threshold of the embodiment of the present invention. As shown, determining the safety threshold and the danger threshold according to the behavior risk factor includes: S701. Determine the safety threshold according to the behavior risk factor and the preset risk threshold strategy;

[0087] S702. Determine the danger threshold according to the preset maximum behavior risk factor and the preset risk threshold strategy. Specifically, after calculating the relative driving safety index, it is necessary to set the safety threshold and the danger threshold to judge the safety level of the identified traffic unit. Considering that the internal factors of the host vehicle are the direct factors for identifying driving risks, its value is related to the behavior risk factor That is, the ability of the driver or the vehicle itself to identify risks is directly related to the setting of the safety threshold. The safety threshold

[0088] For the danger threshold, it is to consider the situation where the internal behavior factor is the largest, that is, the perception threshold in the state where the perception ability of the host vehicle is the weakest. According to the definition of the behavior risk factor, its maximum value , so the danger threshold is expressed by the formula:

[0089] In addition, for different scenario types, the safety threshold can also be adjusted adaptively. For example, in the safety scenario, the safety threshold should be more stringent to avoid false negatives of high risks. In the formula it can also be further adjusted according to the vehicle's health status and autonomy level. For example, when the vehicle's health status is poor, then it decreases, and is lowered.

[0090] In addition, the present invention also sets up experiments under different scenarios to verify the effectiveness of the solution of the present invention.

[0091] Among them, Scenario 1 is a typical efficiency-based scenario. The most common efficiency-based scenarios are vehicle parking and waiting to start, and driving at a constant speed on the road. In the embodiment, the autonomous driving dataset BDD100K is used as the experimental dataset, and 4 typical efficiency-based scenarios are selected. The specific attribute settings of the scenarios are shown in Table 3 as follows: Table 3: Attribute parameter values of Scenario 1

[0092] Scenario 2 is a collision avoidance safety scenario. In this scenario, the safe driving of different traffic vehicles largely depends on whether they have an accurate perception system. The perception system can timely and effectively perceive and identify potential obstacles during driving, such as stationary or moving vehicles ahead on the highway, debris and pedestrians appearing ahead; in waterways, other ships, buoys, islands, etc.; in front of railway trains, railway tracks and other foreign objects. The specific attribute settings in Scenario 2 are shown in Table 4 as follows: Table 4: Attribute parameter values of Scenario 2

[0093] Among them , the safe collision avoidance distance on the road is determined by the following formula, and the safe collision distances on railways and waterways are determined by experience:

[0094] Among them, <s = 0.1 is the minimum clearance when the vehicle does not collide. The time required for the driver to see the obstacle and step on the brake pedal is , and the braking response time is , is the braking duration. This formula takes into account the reaction time after the driver sees the obstacle, which is related to the driver's behavior factors. Through It is determined by the behavioral factors of the vehicle considering vehicle performance. According to the literature, .

[0095] Scenario three sets up an overtaking safety scenario. 200 overtaking processes in the autonomous driving dataset BDD100K are selected as the experimental dataset. For the safety evaluation of overtaking a, both the shape and size factors of the host vehicle are set to 1, the lane traffic visibility is optimal, the traffic adhesion factor is 1, the road surface is flat and straight (without traffic curvature and traffic gradient), and the infrastructure coverage rate is 100%.

[0096] Through experimental analysis, among them, the key indicators for intelligent vehicle risk assessment are divided into five groups: time-based indicators, kinematics-based indicators, statistics-based indicators, potential field-based indicators, and unexpected driving behavior-based indicators. The metric based on time to collision (TTC) is accurate and effective in longitudinal scenarios. They are often applied to the design of anti-collision products such as warning systems, anti-collision mitigation systems, and braking systems. However, TTC is not sensitive to the lateral collision risk of moving obstacles and is prone to false alarms in the case of lane changing or cutting in. When the speed of the self-driving vehicle is the same as that of the target vehicle, TTC tends to infinity, and the wider the TTC, the safer the vehicle, which is contrary to the relative travel safety index RTSI. To make the comparison between indicators more obvious, we take the reciprocal of TTC as a reference indicator, denoted as TTCi. In the typical efficiency scenario 1, Figure 8 It is the experimental result graph of the efficiency scenario, recording the values of the relative risk driving safety index RTSI and TTCi. It can be seen that the trends of RTSI and TTCi of each transportation unit predicted by the host vehicle are the same. Therefore, the RTSI obtained by this scheme can accurately reflect the driving risk and driving state of the host vehicle.

[0097] Figure 9 It is the experimental result graph of the collision avoidance safety scenario, with 0.1 as the simulation unit, and the relative driving safety index between the moving vehicle and the obstacle at different separation distances under different autonomous levels is calculated respectively, obtaining a line graph as shown in Figure 9 . In this scenario, if the obstacle is directly in front of the host vehicle, the shorter the service time, the higher the autonomous level, and the better the vehicle health state, the larger the predicted , and vice versa, which is in line with the actual situation. In Scenario 2, if the same is used as the driving warning threshold for different vehicles with different service lengths, autonomous levels, and health states, the shorter the service length, the higher the autonomous level of the vehicle, and the better the health state, the faster and earlier the obstacle can be detected, giving the driver more time to control and handle risks.

[0098] Figure 10 It is the experimental result graph of the overtaking safety scenario, from Figure 10It can be seen that in the overtaking safety scenario, the trends of the RTSI index and the TTCi index are consistent, and the RTSI index has relatively stable predictive ability for various different scenarios.

[0099] In summary, in the driving risk assessment method provided by the present invention, by quantifying the environmental risk factors as an external environmental field and the behavioral risk factors as an internal behavioral field, and constructing a comprehensive driving risk field based on the external environmental field and the internal behavioral field, the impacts of environmental factors, vehicle itself factors, and the driver on driving risks can be comprehensively quantified, thereby achieving accurate assessment of driving behavior risks.

[0100] Furthermore, the present invention also considers the driving scenario type during the analysis of driving risk potential energy, improving the adaptability of the relative driving safety index to the scenario, and thus improving the accuracy of driving risk assessment in different scenarios.

[0101] To better implement the driving risk assessment method in the embodiments of the present invention, correspondingly, the embodiments of the present invention also provide a driving risk assessment device based on the driving risk assessment method. As Figure 11 shown, the driving risk assessment device 1100 includes: A risk field construction unit 1101, configured to obtain the environmental risk factors, behavioral risk factors, and driving scenario type of the traffic vehicle to be evaluated, construct an external environmental field according to the environmental risk factors, construct an internal behavioral field according to the behavioral risk factors, and construct a comprehensive driving risk field according to the external environmental field and the internal behavioral field; A risk potential energy analysis unit 1102, configured to perform driving risk potential energy analysis according to the comprehensive driving risk field and the driving scenario type to obtain a relative driving safety index; A risk level assessment unit 1103, configured to determine a safety threshold and a danger threshold according to the behavioral risk factors, compare and classify the relative driving safety index with the safety threshold and the danger threshold, and obtain a driving risk classification assessment result.

[0102] The driving risk assessment device 1100 provided in the above embodiments can implement the technical solutions described in the embodiments of the above driving risk assessment method. The specific implementation principles of the above modules or units can be referred to the corresponding content in the embodiments of the above driving risk assessment method, which will not be elaborated here.

[0103] As Figure 12 shown, the present invention also correspondingly provides a driving risk warning device 1200. The driving risk warning device 1200 includes a processor 1201, a memory 1202, and a display 1203. Figure 12 Only some components of the driving risk warning device 1200 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0104] In some embodiments, the memory 1202 may be an internal storage unit of the driving risk warning device 1200, such as a hard disk or memory of the driving risk warning device 1200. In some other embodiments, the memory 1202 may also be an external storage device of the driving risk warning device 1200, such as a plug-in hard disk equipped on the driving risk warning device 1200, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc.

[0105] In some embodiments, the processor 1201 may be a Central Processing Unit (CPU), a microprocessor or other data processing chips, and is used to run the program code stored in the memory 1202 or process data, such as the driving risk assessment method in the present invention.

[0106] In some embodiments, the display 1203 may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. The display 1203 is used to display information of the driving risk warning device 1200 and to display a visual user interface. The components 1201-1203 of the driving risk warning device 1200 communicate with each other through a system bus.

[0107] In some embodiments of the present invention, when the processor 1201 executes the driving risk assessment program in the memory 1202, the following steps can be implemented: Obtain the environmental risk factor, behavior risk factor and driving scenario type of the traffic vehicle to be evaluated, construct an external environment field according to the environmental risk factor, construct an internal behavior field according to the behavior risk factor, and construct a comprehensive driving risk field according to the external environment field and the internal behavior field; Perform driving risk potential energy analysis according to the comprehensive driving risk field and the driving scenario type to obtain a relative driving safety index; Determine a safety threshold and a danger threshold according to the behavior risk factor, compare and classify the relative driving safety index with the safety threshold and the danger threshold to obtain a driving risk classification evaluation result.

[0108] It should be understood that when the processor 1201 executes the driving risk assessment program in the memory 1202, in addition to the above functions, other functions can also be implemented. For specific details, reference can be made to the description of the relevant method embodiments above.

[0109] Those skilled in the art can understand that all or part of the processes for implementing the methods of the above embodiments can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.

[0110] The above has introduced in detail the driving risk assessment method, device and driving risk warning equipment provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A driving risk assessment method, characterized in that, Comprising: Obtain the environmental risk factor, behavioral risk factor, and driving scenario type of the traffic vehicle to be evaluated. Construct an external environmental field according to the environmental risk factor, construct an internal behavioral field according to the behavioral risk factor, and construct a comprehensive driving risk field according to the external environmental field and the internal behavioral field; Perform driving risk potential energy analysis according to the comprehensive driving risk field and the driving scenario type to obtain a relative driving safety index; Determine a safety threshold and a danger threshold according to the behavioral risk factor, and compare and classify the relative driving safety index with the safety threshold and the danger threshold to obtain a driving risk classification evaluation result.

2. The driving risk assessment method according to claim 1, wherein The environmental risk factor includes a motion indication factor, a position indication factor, an infrastructure coverage factor, and a traffic factor, and the behavioral risk factor includes a driving behavior risk factor, a service life factor, an autonomous level factor, and a health status factor.

3. The driving risk assessment method according to claim 2, wherein, The constructing of the external environmental field according to the environmental risk factor includes: Determine the equivalent mass of the vehicle according to the motion indication factor; Determine a traffic environment factor according to the infrastructure coverage factor and the traffic factor; Construct an external environmental field according to the motion indication factor, the position indication factor, the equivalent mass of the vehicle, and the traffic environment factor.

4. The driving risk assessment method according to claim 2, characterized in that, The constructing of the internal behavioral field according to the behavioral risk factor includes: Determine a traffic carrier risk factor according to the service life factor, the autonomous level factor, and the health status factor; Construct an internal behavioral field according to the traffic carrier risk factor and the driving behavior risk factor.

5. The driving risk assessment method according to claim 1, characterized in that The performing of driving risk potential energy analysis according to the comprehensive driving risk field and the driving scenario type to obtain a relative driving safety index includes: Determine the vehicle risk source force according to the comprehensive driving risk field, and determine the risk potential energy and the risk potential energy change rate according to the vehicle risk source force; Determine the driving safety index according to the risk potential energy and the risk potential energy change rate; Determine the relative driving safety index according to the driving safety index and a preset standard safety index; Wherein, the preset standard safety index is determined according to the driving scenario type.

6. The driving risk assessment method according to claim 5, characterized in that, The determining of the driving safety index according to the risk potential energy and the risk potential energy change rate includes: Determine a risk logic weight according to the driving scenario type; Determine the driving safety index according to the risk logic weight, the risk potential energy, and the risk potential energy change rate.

7. The driving risk assessment method according to claim 6, characterized in that, The driving scenario type includes a safety type scenario and an efficiency type scenario. The determining of the risk logic weight according to the driving scenario type includes: If the scenario type is the safety type scenario, determine the risk logic weight according to a preset safety type initial weight; If the scenario type is the efficiency type scenario, adjust a preset efficiency type initial weight according to the traffic flow to obtain the risk logic weight.

8. The driving risk assessment method according to claim 1, wherein, The determining of the safety threshold and the danger threshold according to the behavioral risk factor includes: Determine the safety threshold according to the behavioral risk factor and a preset risk threshold strategy; Determine the danger threshold according to a preset maximum behavioral risk factor and a preset risk threshold strategy.

9. A driving risk assessment device, characterized in that, Comprising: A risk field construction unit, configured to obtain environmental risk factors, behavioral risk factors, and driving scenario types of a traffic vehicle to be evaluated, construct an external environmental field according to the environmental risk factors, construct an internal behavioral field according to the behavioral risk factors, and construct a comprehensive driving risk field according to the external environmental field and the internal behavioral field; A risk potential energy analysis unit, configured to perform driving risk potential energy analysis according to the comprehensive driving risk field and the driving scenario type to obtain a relative driving safety index; A risk level assessment unit, configured to determine a safety threshold and a danger threshold according to the behavioral risk factors, compare and classify the relative driving safety index with the safety threshold and the danger threshold to obtain a driving risk classification assessment result.

10. A driving risk warning device, characterized in that, It includes a memory and a processor, wherein, The memory is configured to store programs; The processor is coupled to the memory and is configured to execute the programs stored in the memory to implement the steps in the driving risk assessment method described in any one of claims 1 to 8 above.

Images