Decision situation assessment method, device and equipment for vehicle unmanned driving system and medium

Abstract

The invention provides a vehicle unmanned driving system decision-making situation assessment method, device and equipment and a medium, and relates to the field of intelligent driving, and the method comprises the steps: obtaining an environment element set and a decision-making target set facing a vehicle unmanned driving system; determining the influence of the environment element set on different sub-levels formed by the decision target set to obtain a first determination degree, a second determination degree and a third determination degree; carrying out weight distribution on the first determination degree, the second determination degree and the third determination degree to obtain a target determination degree so as to balance subjective and objective differences; drawing a comprehensive situation map by taking time as a horizontal coordinate based on the comprehensive situation represented by the target certainty degree; and decision planning is carried out. According to the invention, based on multi-target value consistency measurement, differential cognition and fuzziness among different targets can be eliminated on a cognition level, and the problem that subjective preference and cognition of the vehicle unmanned driving system in a complex decision-making environment are inconsistent is effectively solved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and specifically to a method, device, equipment and medium for evaluating the decision-making situation of an unmanned driving system of a vehicle. Background Art

[0002] With the rapid development of unmanned driving technology, autonomous intelligent vehicles face complex and changing external environments in the process of autonomous driving decision-making. In such an environment, unmanned driving systems must not only identify surrounding obstacles and dynamic traffic conditions, but also make optimal decisions quickly within a limited time to ensure driving safety and efficiency. Therefore, scientific evaluation of the decision-making situation of unmanned driving has become the key to improving its safety, reliability and adaptability.

[0003] Situation assessment is the process of dynamically evaluating the status and situation of decision-making environment elements. It refers to collecting data in the environment through perception modules, integrating and preliminarily analyzing the perceived data, identifying events in the environment, and conducting situation analysis through understanding and analyzing important events and predicting future environmental changes to accurately judge the impact of events on decisions and form an accurate grasp of the overall decision-making situation.

[0004] In the related art, the driving decision situation assessment problem is specifically manifested as the assessment of the driving decision situation formed by the influence of the surrounding environmental factors on various aspects of the decision system during the driving process of the autonomous intelligent vehicle. However, the process of evaluating the decision situation of the vehicle unmanned driving system involves multiple interrelated decision goals, which may cover different levels and conflict with each other. They belong to cognitive concepts at different levels and the measurement standards of different goals are inconsistent, which leads to inconsistent evaluation scales of decision goals, and it is difficult to compare them directly and find a balance between them, and it is difficult to effectively deal with the problems of subjective preferences and cognitive inconsistency in complex decision-making environments. Summary of the invention

[0005] In response to the shortcomings of the prior art, the present application provides a method, device, equipment and medium for evaluating the decision situation of a vehicle unmanned driving system, which solves the problem that the evaluation scales of multiple decision targets are inconsistent, they cannot be directly compared with each other, and are difficult to balance when the vehicle unmanned driving system performs decision situation evaluation.

[0006] To achieve the above objectives, this application is implemented through the following technical solutions:

[0007] In the first aspect, an embodiment of the present application provides a method for evaluating the decision situation of a vehicle unmanned driving system, the method comprising: obtaining an environmental element set and a decision target set for the vehicle unmanned driving system; the environmental element set comprises environmental influencing factors, vehicle influencing factors and traffic participation influencing factors, and the decision target set comprises safety, comfort and efficiency; determining the influence of the environmental element set on different sub-levels formed by the decision target set, and obtaining a first certainty, a second certainty and a third certainty representing the safety value situation, the comfort value situation and the efficiency value situation; through a preset combined weight method, weights are assigned to the first certainty, the second certainty and the third certainty, and a target certainty is obtained to balance subjective and objective differences; wherein the combined weight method comprises an OWA operator subjective weighting method and an entropy weight method; based on the comprehensive situation represented by the target certainty, a comprehensive situation map is drawn with time as the horizontal axis; decision planning is performed according to the comprehensive situation map, and the comprehensive situation map is used to represent the comprehensive driving situation of the vehicle unmanned driving system in the current decision environment.

[0008] According to the first aspect of the embodiment of the present application, the first degree of certainty, the second degree of certainty and the third degree of certainty are respectively used to characterize the impact of the set of environmental factors on safety, comfort and efficiency; the environmental influencing factors are used to characterize the impact of the external physical and natural environment on the driving decision-making situation; the vehicle influencing factors are used to characterize the impact of the vehicle's own characteristics and status on the driving decision-making situation; the traffic participation influencing factors are used to characterize the impact of other vehicles, pedestrians, obstacles, etc. on the road on the driving decision-making situation.

[0009] According to the first aspect of the embodiment of the present application, the safety value situation, the comfort value situation and the high-efficiency value situation each correspond to a sub-level; the aforementioned determination of the influence of the environmental factor set on the different sub-levels formed by the decision target set obtains the first certainty, the second certainty and the third certainty that characterize the safety value situation, the comfort value situation and the high-efficiency value situation, which may specifically include: in the current decision-making environment, according to the environmental state, the vehicle state and the surrounding vehicle state, the impact measurement is performed on each sub-level, the potential impact of the environmental factor set on the decision targets of different sub-levels is calculated, and the impact value cloud droplets are obtained; the typical cloud droplets corresponding to each sub-level are determined, and the Gaussian cloud parameters under different value situation concepts are calculated; based on the Gaussian cloud parameters and the impact value cloud droplets, the first certainty, the second certainty and the third certainty of the potential impact on the vehicle at different sub-levels are obtained through the concept certainty calculation formula preset in the forward Gaussian cloud algorithm.

[0010] According to a first aspect of an embodiment of the present application, Gaussian cloud parameters include: expectation Ex, entropy En and super entropy He; wherein the super entropy He satisfies the expression:

[0011]

[0012] In the formula, CD is the concept ambiguity, which is used to characterize the discrete degree of a concept extension, reflecting the degree to which the distribution of the Gaussian cloud deviates from the Gaussian distribution; the closer CD is to 0, the more convergent the concept extension is, and CD>1 indicates that the concept extension is divergent.

[0013] According to the first aspect of the embodiment of the present application, in the influence metric corresponding to the safety value situation, the potential field is divided into multiple potential fields formed by traffic participants, road boundaries and lane markings; in the process of determining the typical cloud droplets corresponding to the safety value situation, the vehicle unmanned driving system decision situation evaluation method may also include: for two vehicles in the same lane, if the longitudinal distance between the two vehicles reaches the minimum safe distance between vehicles during the braking process, the first risk field force to which the vehicle is subjected is calculated, and it is determined that the first risk field force is a typical cloud droplet when the safety value situation of vehicles in the same lane is in a dangerous state; for two vehicles in adjacent lanes, when the longitudinal distance between the two vehicles is less than the minimum safe distance for lane changing, the second risk field force to which the vehicle is subjected is calculated, and it is determined that the second risk field force is a typical cloud droplet when the safety value situation of vehicles in adjacent lanes is in a dangerous state; at the current relative speed of the two vehicles, when the longitudinal distance between the two vehicles reaches the expected longitudinal vehicle distance, the third risk field force to which the vehicle is subjected is calculated, and it is determined that the third risk field force is a typical cloud droplet when the safety value situation is in a safe state.

[0014] According to the first aspect of the embodiment of the present application, in the process of determining the typical cloud droplets corresponding to the comfort value situation, the vehicle unmanned driving system decision situation evaluation method further includes: using the lateral and longitudinal instantaneous velocity change rate and instantaneous acceleration change rate to measure the ride comfort; when the vibration frequency of the vehicle exceeds the preset tolerance threshold J t In the case of t The typical cloud droplets when the comfort value is in an uncomfortable state; when the vibration frequency is at the expected value of the passengers J exp In the case of exp It is a typical cloud droplet whose comfort value status is in a comfortable state.

[0015] According to the first aspect of the embodiment of the present application, in the process of determining the typical cloud droplets corresponding to the high-efficiency value situation, the vehicle unmanned driving system decision situation evaluation method further includes: measuring the driving efficiency by the headway between the vehicle and the preceding vehicle and the speed of the vehicle; in v i =v exp ,h i =h exp In the case of v, the potential impact of the current metric is determined as a typical cloud droplet with a high efficiency value situation in the high efficiency state; i =0,h i =h desIn the case of , the potential impact of the current metric is determined as a typical cloud droplet with high efficiency value situation in the low efficiency state; where v i is the current vehicle speed, v exp is the expected vehicle speed, h i h is the headway between the vehicle and the preceding vehicle, which represents the travel time from the front of the vehicle to the front of the preceding vehicle; des is the headway time corresponding to the minimum safety distance, h exp is the expected headway.

[0016] In the second aspect, an embodiment of the present application provides a vehicle unmanned driving system decision situation assessment device, the device comprising: an acquisition module, a determination module, a weight allocation module, a drawing module and a decision planning module; specifically, the acquisition module is used to acquire an environmental element set and a decision target set for the vehicle unmanned driving system; the environmental element set includes environmental influencing factors, self-vehicle influencing factors and traffic participation influencing factors, and the decision target set includes safety, comfort and efficiency; the determination module is used to determine the influence of the environmental element set on different sub-levels formed by the decision target set, and obtain a first certainty, a second certainty and a third certainty representing the safety value situation, the comfort value situation and the high efficiency value situation; the weight allocation module is used to assign weights to the first certainty, the second certainty and the third certainty through a preset combined weight method, and obtain a target certainty to balance subjective and objective differences; wherein the combined weight method includes an OWA operator subjective weighting method and an entropy weight method; the drawing module is used to draw a comprehensive situation map with time as the horizontal coordinate based on the comprehensive situation represented by the target certainty; the decision planning module is used to make decision plans based on the comprehensive situation map, and the comprehensive situation map is used to represent the comprehensive driving situation of the vehicle unmanned driving system in the current decision environment.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the vehicle unmanned driving system decision situation assessment method described in the first aspect is implemented.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a program or instruction. When the program or instruction is executed by a processor, the vehicle unmanned driving system decision situation assessment method in the aforementioned first aspect is implemented.

[0019] This application provides a method, device, equipment and medium for evaluating the decision situation of an unmanned driving system of a vehicle. Compared with the prior art, it has the following beneficial effects:

[0020] In the process of evaluating the decision-making situation of the vehicle unmanned driving system, this application analyzes the impact of the environmental factor set on the different sub-levels formed by the decision-making target set, introduces a value system to unify the evaluation scale of the potential impact of environmental factors on decision-making targets, and quantifies the value contribution of environmental factors to each decision-making target to form a value situation, so as to eliminate the ambiguity and uncertainty in qualitative concepts and the cognitive differences of decision makers on concepts. After obtaining the first degree of certainty, the second degree of certainty and the third degree of certainty that characterize the safety value situation, the comfort value situation and the efficiency value situation, the subjective and objective differences are balanced by combining weights, and each value situation is weighted, so as to weigh the relationship between different decision-making targets and form a comprehensive situation assessment in the decision-making environment; this application is based on multi-objective value consistency measurement, which can eliminate the differential cognition and ambiguity between different targets at the cognitive level, and effectively solves the problem of subjective preference and cognitive inconsistency of vehicle unmanned driving systems in complex decision-making environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 It is a flowchart of a method for evaluating a decision situation of an unmanned driving system of a vehicle provided in an embodiment of the present application;

[0023] Figure 2-a is a schematic diagram of the speed of the vehicle provided in an embodiment of the present application;

[0024] Figure 2-b is a schematic diagram of the acceleration of the vehicle provided in an embodiment of the present application;

[0025] Figure 2-c is a schematic diagram of the relative speed between the vehicle and the preceding vehicle provided in an embodiment of the present application;

[0026] Figure 2-d is a schematic diagram of the relative distance between the vehicle and the preceding vehicle provided in an embodiment of the present application;

[0027] Figure 2-e It is a schematic diagram of the impact of environmental factors on decision-making targets at different levels provided by the embodiment of the present application;

[0028] Figure 2-f It is a schematic diagram of the value situation at each level provided by the embodiment of the present application;

[0029] Figure 2-g It is a comprehensive situation diagram provided by the embodiment of the present application;

[0030] Figure 3 It is a structural schematic diagram of a vehicle unmanned driving system decision situation assessment device provided in an embodiment of the present application;

[0031] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0034] The embodiments of the present application provide a method, device, equipment and medium for evaluating the decision situation of an unmanned driving system of a vehicle, thereby solving the problem that the evaluation scales of multiple decision targets of an unmanned driving system of a vehicle are inconsistent when performing decision situation evaluation, and they cannot be directly compared with each other, making them difficult to balance.

[0035] The technical solution in the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0036] With the rapid development of unmanned driving technology, autonomous intelligent vehicles face complex and changing external environments in the process of autonomous driving decision-making. In such an environment, unmanned driving systems must not only identify surrounding obstacles and dynamic traffic conditions, but also make optimal decisions quickly within a limited time to ensure driving safety and efficiency. Therefore, scientific evaluation of the decision-making situation of unmanned driving has become the key to improving its safety, reliability and adaptability.

[0037] With the development of autonomous intelligence, machines are increasingly equipped with the capabilities of self-perception, self-learning, self-decision-making, self-execution, and self-adaptation. Machines with autonomous intelligence can serve as human partners, independently complete decision-making tasks, and help people get out of the complicated labor production. Autonomous perception, as the primary condition for realizing machine autonomous intelligence, is inseparable from efficient and accurate situation assessment. Situation refers to state and situation. State refers to the static decision-making environment at the current decision moment composed of various environmental factors. Situation refers to the changing trend of the decision-making environment over time and the understanding of the relationship between environmental factors and decision-making goals.

[0038] Situation assessment is the process of dynamically evaluating the status and situation of decision-making environmental elements. It refers to collecting data in the environment through perception modules, integrating and preliminarily analyzing the perceived data, realizing the identification of events in the environment, and conducting situation analysis through understanding and analyzing important events and predicting future environmental changes to accurately judge the impact of events on decision-making and form an accurate grasp of the overall decision-making situation. Situation assessment emphasizes the understanding of the overall situation. It involves the perception of the temporal changes, relevance and overall dynamics of targets, scenes and other environmental elements. Therefore, situation awareness pays more attention to comprehensiveness, dynamism, real-timeness, and accuracy.

[0039] In the related art, the driving decision situation assessment problem is specifically manifested as the assessment of the driving decision situation formed by the influence of the surrounding environmental factors on various aspects of the decision system during the driving process of the autonomous intelligent vehicle. However, the process of evaluating the decision situation of the vehicle unmanned driving system involves multiple interrelated decision goals, which may cover different levels and conflict with each other. They belong to cognitive concepts at different levels and the measurement standards of different goals are inconsistent, resulting in inconsistent evaluation scales of decision goals, which cannot be directly compared with each other and are difficult to balance.

[0040] Common solutions to the problem of inconsistent evaluation scales include: (1) By classifying the influencing indicators at all levels, a unified evaluation standard is defined for each indicator. (2) The original dimensional indicators are converted into dimensionless values ​​through standardization methods, so that different indicators can be compared and aggregated at the same scale. For example, the additive ratio evaluation system converts indicators of different units and dimensions into dimensionless ratios through standardization and proportionality, and then analyzes the gap between alternative solutions and ideal solutions through the optimal function and utility measurement to eliminate the influence of different measurement units. (3) Grey system theory uses grey correlation analysis to deal with data uncertainty and scale inconsistency. For example, the grey correlation theory is combined with the fuzzy set theory and applied to the assessment of smart city information security risks. By determining the correlation of each risk factor, the indicator values ​​of different scales are mapped to correlation values ​​to analyze their impact on the overall risk.

[0041] However, the grading method is highly subjective and it is difficult to ensure its consistency. Standardization, grey correlation system and other methods use mathematical means to unify the evaluation scales of different indicators, mainly by eliminating dimensions and calculating correlation to deal with the relationship between data. However, these methods can only achieve scale unification at the mathematical level, and it is difficult to eliminate the differences and ambiguity between different goals at the cognitive level, and cannot effectively deal with the problems of subjective preferences and cognitive inconsistency in complex decision-making environments.

[0042] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0043] The following first introduces a method for evaluating the decision-making situation of an unmanned driving system of a vehicle provided in an embodiment of the present application.

[0044] A flowchart of a method for evaluating a decision-making situation of an unmanned driving system of a vehicle provided in an embodiment of the present application is as follows: Figure 1 As shown, the vehicle unmanned driving system decision situation assessment method may include the following steps S110-S150.

[0045] S110, obtaining an environmental factor set and a decision target set for a vehicle unmanned driving system; the environmental factor set includes environmental influencing factors, vehicle influencing factors, and traffic participation influencing factors, and the decision target set includes safety, comfort, and efficiency.

[0046] S120, determining the influence of the environmental factor set on different sub-levels formed by the decision target set, and obtaining the first degree of certainty, the second degree of certainty and the third degree of certainty representing the safety value situation, the comfort value situation and the high efficiency value situation.

[0047] S130. Allocate weights for the first degree of certainty, the second degree of certainty, and the third degree of certainty through a preset combined weight method to obtain a target degree of certainty to balance subjective and objective differences; wherein the combined weight method includes an OWA operator subjective weighting method and an entropy weight method.

[0048] S140. Based on the comprehensive situation represented by the target certainty, a comprehensive situation map is drawn with time as the horizontal axis.

[0049] S150. Decision planning is performed according to the comprehensive situation map, where the comprehensive situation map is used to represent the comprehensive driving situation of the vehicle unmanned driving system in the current decision-making environment.

[0050] It should be noted that the first degree of certainty, the second degree of certainty and the third degree of certainty are used to characterize the impact of the environmental factor set on safety, comfort and efficiency respectively; the environmental influencing factors are used to characterize the impact of the external physical and natural environment on the driving decision-making situation; the vehicle influencing factors are used to characterize the impact of the vehicle's own characteristics and status on the driving decision-making situation; the traffic participation influencing factors are used to characterize the impact of other vehicles, pedestrians, obstacles, etc. on the road on the driving decision-making situation.

[0051] It can be understood that the environmental factors of driving decision-making situation mainly include environmental influencing factors, self-vehicle influencing factors and traffic participation influencing factors. Environmental influencing factors refer to the influence of external physical and natural environment on driving decision-making situation. Environmental influencing factors mainly include: weather conditions such as rainy days, snowy days, foggy days, etc. on the slipperiness and visibility of the road; road conditions such as road adhesion coefficient, road slope, road curvature, road markings, etc.; traffic signals such as traffic lights, traffic signs (speed limit signs, indication signs, warning signs), etc. Self-vehicle influencing factors refer to the influence of the vehicle's own characteristics and status on the driving decision-making situation, mainly including factors such as the type, mass, speed, acceleration and driving style of the self-vehicle. Traffic participation influencing factors refer to the influence of other vehicles, pedestrians, obstacles, etc. on the road on the driving decision-making situation. It mainly includes factors such as the type of traffic participants (such as motor vehicles, non-motor vehicles, pedestrians, obstacles), position, size, mass, motion state (moving or stationary), speed, acceleration, etc.

[0052] It should also be noted that the decision goal is the desired state to be achieved or optimized when making a decision. The decision goal is a key criterion in the decision-making process, used to guide the decision maker to choose the best course of action or achieve the best result. In autonomous driving decisions, the decision goal usually involves multiple aspects to ensure that the vehicle can drive safely and efficiently without human intervention. Specifically, the vehicle's autonomous driving system needs to consider the following:

[0053] (1) Safety focuses on keeping the vehicle in good condition, complying with traffic regulations, driving legally and compliantly, and effectively predicting and responding to road and traffic conditions to avoid accidents and injuries. It is usually related to factors such as relative distance, relative speed, position, speed, road conditions, and weather conditions. Driving safety is related to the safety of passengers' lives and is crucial in driving decisions.

[0054] (2) Comfort focuses on the riding experience during driving, including reducing vibration and noise, providing good seat support, maintaining appropriate temperature and air quality, etc., to reduce passenger discomfort and improve travel comfort and pleasure. The main influencing factors during vehicle driving are the vehicle's vibration frequency, that is, the lateral (longitudinal) speed, the rate of change of lateral (longitudinal) acceleration, etc. Improving comfort can reduce passenger fatigue and discomfort.

[0055] (3) Efficiency focuses on optimizing resource utilization during driving, including reaching the destination in the shortest time, minimizing fuel consumption, and minimizing time wasted in traffic jams. Improving driving efficiency can save time and cost, and reduce the impact on the environment. It is related to factors such as speed, acceleration, distance, and driving mode.

[0056] The above is a specific implementation method of the vehicle unmanned driving system decision situation assessment method provided in the embodiment of the present application. In the process of conducting the vehicle unmanned driving system decision situation assessment, the present application analyzes the impact of the environmental factor set on the different sub-levels formed by the decision target set, introduces a value system to unify the evaluation scale of the potential impact of environmental factors on decision targets, quantifies the value contribution of environmental factors to each decision target to form a value situation, so as to eliminate the ambiguity and uncertainty in qualitative concepts and the cognitive differences of decision makers regarding concepts.

[0057] Furthermore, after obtaining the first, second and third degrees of certainty that characterize the safety value situation, comfort value situation and efficiency value situation, the present application balances the subjective and objective differences through combined weights, and weights each value situation, thereby weighing the relationship between different decision-making goals and forming a comprehensive situation assessment in the decision-making environment; the present application is based on multi-objective value consistency measurement, which can eliminate the differential cognition and ambiguity between different goals at the cognitive level, and effectively solves the problem of subjective preference and cognitive inconsistency of vehicle unmanned driving systems in complex decision-making environments.

[0058] In some embodiments, the safety value situation, the comfort value situation, and the high efficiency value situation each correspond to a sub-level. The aforementioned determination of the influence of the environmental factor set on the different sub-levels formed by the decision target set obtains the first degree of certainty, the second degree of certainty, and the third degree of certainty that characterize the safety value situation, the comfort value situation, and the high efficiency value situation, that is, the aforementioned S120 may specifically include the following steps:

[0059] S210. In the current decision-making environment, based on the environmental state, the vehicle state, and the surrounding vehicle state, the impact measurement is performed on each sub-level, and the potential impact of the environmental factor set on the decision-making objectives of different sub-levels is calculated to obtain the impact value cloud droplet.

[0060] S220. Determine the typical cloud droplets corresponding to each sub-level, and calculate the Gaussian cloud parameters under different value situation concepts.

[0061] S230. Based on the Gaussian cloud parameters and the impact value cloud droplets, the first certainty, the second certainty, and the third certainty of the potential impact on the ego-vehicle at different sub-levels are obtained by using the concept certainty calculation formula preset in the forward Gaussian cloud algorithm.

[0062] In one example, Gaussian cloud parameters include: expectation Ex, entropy En, and super entropy He; wherein the super entropy He satisfies the expression:

[0063]

[0064] In the formula, CD is the concept ambiguity, which is used to characterize the discrete degree of a concept extension, reflecting the degree to which the distribution of the Gaussian cloud deviates from the Gaussian distribution; the closer CD is to 0, the more convergent the concept extension is, and CD>1 indicates that the concept extension is divergent.

[0065] In some embodiments, in the impact measurement corresponding to the safety value situation, the potential field is divided into multiple potential fields formed by traffic participants, road boundaries and lane markings. In the embodiment of the present application, it can be understood that in the vehicle unmanned driving system, the driving safety field (Driving Safety Field, DSF) is based on the potential field theory to regard each element in the traffic environment as a source of a potential field, which can comprehensively consider various elements in the environment, explore the risk formation mechanism and have certain physical significance. Based on this, the present application measures the impact of environmental factors on the decision-making target at the safety level based on DSF; in an autonomous intelligent environment, according to the type of traffic environment elements faced by the unmanned vehicle when making autonomous decisions, the potential field can be divided into potential fields formed by traffic participants, potential fields formed by road boundaries, and potential fields formed by lane markings.

[0066] In some embodiments, the impact measurement process corresponding to the security value situation satisfies the expression:

[0067]

[0068] In the above formula, E P-ai 、E B-i 、E L-ci are the potential fields formed by traffic participant a, road boundary b and lane marking c at the ego vehicle i, E i is the total field strength generated by environmental factors on vehicle i, F i is the corresponding field force, which can characterize the influence of various factors in the decision-making environment on the safety level of the ego vehicle i. The smaller F is, the safer the ego vehicle and the decision-making environment it faces are, and vice versa. G, λ1, λ2, λ3, and λ4 are constant term coefficients greater than 0; R a , R b , R c , R i It is a factor affecting road conditions determined by factors such as road adhesion coefficient, slope, visibility, etc. a 、M i is the equivalent mass of traffic participant a and ego vehicle i, which is determined by factors such as the actual mass, type, and speed of the object. η is the lane marking of different types, H is the lane width, and rai 、r bi 、r ci are the distance vectors between traffic participants, the road boundary closest to the vehicle, the vehicle markings and the vehicle, v a 、v i is the speed of traffic participants and the ego vehicle, θ a ,θ i It is the angle between the speed direction of the traffic participant and the vehicle and their distance.

[0069] In some embodiments, during the process of determining typical cloud droplets corresponding to the safety value situation, the vehicle unmanned driving system decision situation assessment method further includes:

[0070] For two vehicles in the same lane, if the longitudinal distance between the two vehicles reaches the minimum safe distance between vehicles during the braking process, the first risk field force on the ego vehicle is calculated, and the first risk field force is determined to be a typical cloud droplet when the safety value situation of vehicles in the same lane is in a dangerous state;

[0071] For two vehicles in adjacent lanes, when the longitudinal distance between the two vehicles is less than the minimum safe distance for lane change, the second risk field force on the ego vehicle is calculated to determine the second risk field force is a typical cloud droplet when the safety value situation of the vehicle in the adjacent lane is in a dangerous state;

[0072] At the current relative speed of the two vehicles, when the longitudinal distance between the two vehicles reaches the expected longitudinal distance between the two vehicles, the third risk field force on the vehicle is calculated, and the third risk field force is determined to be a typical cloud droplet when the safety value situation is in a safe state.

[0073] In the embodiment of the present application, it can be understood that for two vehicles in adjacent lanes, when the longitudinal distance between the two vehicles is less than the minimum safe distance for lane change: the vehicle in the rear must always be on guard against the vehicle in front changing lanes, because if the vehicle in front has the intention to change lanes, it will cause a greater safety threat to both vehicles. At the current relative speed of the two vehicles, if the longitudinal distance between the two vehicles reaches the expected longitudinal vehicle distance, even if the two vehicles are in adjacent lanes, the vehicle in front changing lanes will not cause a safety threat to the two vehicles.

[0074] It should also be noted that in the process of calculating the Gaussian cloud parameters corresponding to the security value situation, the typical cloud droplets of each sub-concept are taken as the expected Ex of the sub-concept, F dan =Ex dan , F saf =Ex saf , based on Gaussian Cloud's "3E Rule", a typical cloud droplet F of the security value situation saf The contribution to the dangerous value situation can be ignored, and it can be used as the boundary point of the dangerous value situation concept [Ex-3En, Ex+3En] interval; the typical cloud droplet F of the dangerous value situationdan The contribution to the safety value situation can be ignored and can be used as the boundary point of the safety value situation concept [Ex-3En, Ex+3En] interval; then the Gaussian cloud parameters of the safety value situation and dangerous value situation concepts are calculated as follows:

[0075] F saf =Ex saf

[0076] F dan =Ex dan

[0077] Ex saf +3En saf =Ex dan

[0078] Ex dan -3En dan =Ex saf

[0079] In the above formula, Ex saf 、Ex dan are the expectations of the Gaussian clouds of the concepts of safety value situation and danger value situation, respectively. saf 、En dan They are the entropies of the concepts of safe value situation and dangerous value situation respectively.

[0080] In some embodiments, during the process of determining typical cloud droplets corresponding to the comfort value situation, the vehicle unmanned driving system decision situation assessment method further includes:

[0081] The instantaneous velocity change rate and the instantaneous acceleration change rate in the lateral and longitudinal directions are used to measure the riding comfort. For example, the influence measurement process corresponding to the comfort value state satisfies the expression:

[0082]

[0083] In the formula, J i is the influence of comfort value situation measurement, x(t) is the displacement time function of the center point of the rear axle of the vehicle along the x-axis, y(t) is the displacement function in the y-axis direction, and the lateral and longitudinal velocity change rates and acceleration change rates are obtained by taking high-order derivatives of the lateral and longitudinal displacements of the vehicle.

[0084] When the vibration frequency of the vehicle exceeds the preset tolerance threshold J t In the case of t It is a typical cloud droplet when the comfort value situation is in an uncomfortable state.

[0085] When the vibration frequency is at the expected value of the passengers J exp In the case of expIt is a typical cloud droplet whose comfort value status is in a comfortable state.

[0086] In the embodiments of the present application, it can be understood that ride comfort is often closely related to the vibration frequency of the vehicle. The vehicle's motion state will change in the horizontal and vertical directions under the action of force, thereby generating vibrations of different frequencies. The forces acting on the vehicle and the changes in the forces acting on the vehicle can be reflected by indicators such as acceleration and the rate of change of acceleration. When the forces acting on the vehicle change drastically, the ride comfort of the passengers will often be affected.

[0087] Based on this, when the vibration frequency of the vehicle exceeds the human body's tolerance threshold J t When the passenger usually feels extremely uncomfortable, the definition of J t The typical cloud droplets when the comfort value is in an uncomfortable state; when the vibration frequency is at the expected value of the passengers J exp When the human body usually feels very comfortable, define J exp It is a typical cloud droplet whose comfort value status is in a comfortable state.

[0088] It should also be noted that in the process of calculating the Gaussian cloud parameters corresponding to the comfort value situation, the typical cloud droplets of each sub-concept are taken as the expected Ex of the sub-concept; J t =Ex bum , J exp =Ex com , based on the "3E rule" of Gaussian cloud, a typical cloud drop J of the comfort value situation exp The contribution to the uncomfortable value situation can be ignored and can be used as the boundary point of the uncomfortable value situation concept [Ex-3En,Ex+3En].

[0089] Typical cloud droplets that are not suitable for value situation J t The contribution to the comfort value situation can be ignored and can be used as the boundary point of the comfort value situation concept [Ex-3En, Ex+3En]. The Gaussian cloud parameters of the comfort value situation and discomfort value situation concepts are calculated as follows:

[0090] J t =Ex bum

[0091] J exp =Ex com

[0092] Ex com +3En com =Ex bum

[0093] Ex bum -3En bum =Ex com

[0094] In the above formula, Ex com 、Ex bum are the expectations of the Gaussian clouds of the concepts of comfort value situation and discomfort value situation, En com 、En bum They are the entropies of the concepts of comfort value situation and discomfort value situation respectively.

[0095] In some embodiments, during the process of determining typical cloud droplets corresponding to the high-efficiency value situation, the vehicle unmanned driving system decision situation assessment method further includes:

[0096] The driving efficiency is measured by the headway between the vehicle and the vehicle ahead, as well as the speed of the vehicle.

[0097] In v i =v exp ,h i =h exp In the case of , the potential impact of the current metric is determined as a typical cloud droplet with a high efficiency value situation in the high efficiency state;

[0098] In v i =0,h i =h des In the case of , the potential impact of the current metric is determined as a typical cloud droplet with high efficiency value situation in the low efficiency state;

[0099] Among them, v i is the current vehicle speed, v exp is the expected vehicle speed, h i h is the headway between the vehicle and the preceding vehicle, which represents the travel time from the front of the vehicle to the front of the preceding vehicle; des is the headway time corresponding to the minimum safety distance, h exp is the expected headway.

[0100] In the embodiment of the present application, it can be understood that in the efficiency level impact measurement, in order to ensure the efficiency of driving, the vehicle needs to maintain the expected speed as much as possible under different roads and traffic conditions to shorten the driving time and improve the overall driving efficiency; the vehicle can also optimize the driving path and dynamically adjust the driving strategy to effectively utilize road resources and obtain a larger driving space, thereby improving the smoothness of driving and reducing unnecessary stops and lane changes; therefore, the present application measures the efficiency of driving by the degree of proximity between the current vehicle speed and the expected vehicle speed and the headway with the vehicle in front; as shown in the following formula:

[0101] P i =P v +P h

[0102]

[0103]

[0104] Among them, P v , P h They are the measures of the impact of vehicle speed and driving space on efficiency, respectively. i is a comprehensive measure of the impact on efficiency; k1 and k2 are constant coefficients greater than 0, and v i is the vehicle speed, v exp is the expected vehicle speed, h i is the headway between the vehicle and the preceding vehicle, i.e., the travel time from the front of the vehicle to the front of the preceding vehicle, h i =r ij / v i , r ij is the vector distance between the two vehicles, h exp is the expected headway.

[0105] It should be noted that, from the perspective of vehicle speed, the closer the current vehicle speed is to the expected vehicle speed v exp , the more efficient the driving of the vehicle is; the lower the current speed is, the less efficient it is; from the perspective of driving space, the larger the headway between the vehicle and the vehicle in front is, the closer it is to the expected headway h exp The larger the available driving space for the vehicle, the greater the potential efficiency. For safety reasons, the headway between the two vehicles cannot be less than the headway h corresponding to the minimum safe distance. des .

[0106] It should also be noted that in the process of calculating the Gaussian cloud parameters corresponding to the high-efficiency value situation, the typical cloud droplets of each sub-concept are taken as the expected Ex, E of the sub-concept. hig =Ex hig , E sol =Ex sol , based on Gauss Cloud's "3E Rule", a typical cloud droplet E with high efficiency value hig The contribution to the inefficient value situation can be ignored and can be used as the boundary point of the inefficient value situation concept [Ex-3En,Ex+3En].

[0107] Typical cloud drop E of inefficient value situation sol The contribution to the efficient value situation can be ignored, and it can be used as the boundary point of the efficient value situation concept [Ex-3En, Ex+3En]. The Gaussian cloud parameters of the comfortable value situation and uncomfortable value situation concepts are calculated as follows:

[0108] E hig =Ex hig

[0109] E sol =Exsol

[0110] Ex hig +3En hig =Ex sol

[0111] Ex sol -3En sol =Ex hig

[0112] In the above formula, Ex hig 、Ex sol are the expectations of the Gaussian clouds of the concepts of efficient value situation and inefficient value situation, respectively. hig 、En sol They are the entropies of the concepts of efficient value situation and inefficient value situation respectively.

[0113] In some embodiments, in order to verify the effectiveness and accuracy of the above-mentioned vehicle unmanned driving system decision situation assessment method, this application uses part of the driving data in the NGISM data set to verify and analyze the safety, comfort, efficiency value situation and comprehensive situation under the following condition.

[0114] Since the NGISM dataset does not provide information such as road adhesion coefficient, slope, and visibility, and the selected driving data is located on the same road section in the same time period, the road condition factor is assumed to be 1 and the parameters are set. In the selected driving data, the data sampling period is 0.1s, the vehicle No. 2224 is selected and assumed to be the current unmanned vehicle, the vehicle No. 2208 in front of the current lane, and some driving state parameters of the vehicle No. 2224 and the front vehicle No. 2208 are shown in Table 1.

[0115] Table 1 Vehicle driving state parameters

[0116]

[0117] Please refer to Figure 2-a to Figure 2-g ,contrast Figure 2-e and Figure 2-fIt can be seen that the impact index of decision-making environment factors on decision-making goals has a large fluctuation range, and its relative value cannot always accurately reflect the degree of influence of driving situations at all levels. The decision situation evaluation method based on the cloud model proposed in this application, by considering the unification of the evaluation scale, clarifies the typical cloud droplet selection criteria for different value situations at each moment, and the certainty of the three value situations of the decision environment calculated on this basis are all in the interval [0,1]. Its size can effectively reflect the potential situation level of the decision environment in terms of safety, comfort and efficiency. This quantitative method of determination based on a unified scale helps to more clearly and explainably evaluate the impact of driving situations at all levels.

[0118] As for the safety value trend, in the first 6.7 seconds, the speed of the self-vehicle No. 2224 was greater than that of the front vehicle No. 2208, and the relative distance between the two vehicles was gradually decreasing, and the overall safety value showed a downward trend. The relative distance between the two vehicles was small from 5s to 11s, and the relative speed of the two vehicles began to decrease from 8.9s to 9.4s, so the safety value trend of the No. 2224 vehicle was close to 0 from 5s to 11s, indicating that the current environment of the self-vehicle was very dangerous. As the relative distance between the two vehicles gradually increased, the safety value trend of the No. 2224 vehicle began to increase again from 10.8s to 11.9s.

[0119] As for the comfort value trend, the acceleration and speed hardly changed in the first 1.4s, 2.4s-3.2s, 4.4s-6.6s, 7.5s-8.1s, 9.6s-10.3s and 12.3s-13.3s, and the comfort value trend of car No. 2224 was approximately 1, and the passengers in the car felt very comfortable; while at 3.9s-4.1s, 9.1s-9.3s, 11s-11.3s and 14s, the rate of change of speed and acceleration was close to the threshold of human discomfort, and the comfort value trend of car No. 2224 was approximately 0, and the passengers in the car might feel very bumpy.

[0120] The high-efficiency value trend has been at a low level because the speed of vehicle No. 2224 is relatively slow during the current period, never exceeding 25ft / s, and the relative distance from the vehicle in front is not far, so the potential driving space is small.

[0121] Comprehensive situation Figure 2-gFrom a macro perspective, it reflects the comprehensive driving decision-making situation currently faced by the vehicle. On the whole, it combines the trend of value situation changes at the three evaluation levels. The change of a single value situation will not have an extreme impact on the comprehensive situation and has relative stability. For example, in the first 3 seconds, due to the good safety value situation and comfort value situation of the self-vehicle No. 2224, the overall trend is good, but it only remains at around 0.7, indicating that there is still room for improvement in the comprehensive situation. The self-vehicle can improve driving efficiency by switching to a lane with fewer vehicles. For another example, the comprehensive situation drops rapidly from 3.5s to 4.2s, reminding the self-vehicle No. 2224 to maintain the stability of the vehicle speed and the relative distance from the vehicle in front. In 10.5s-11s, the safety value situation shows an increasing trend, but the comprehensive situation is declining, because the speed and acceleration of the self-vehicle during this period of time have a large fluctuation amplitude, indicating that the comfort of the self-vehicle at this time is very poor, and the driving should be kept stable to improve the passenger's riding experience.

[0122] In some embodiments, the present application provides a vehicle unmanned driving system decision situation assessment device 300, such as Figure 3 As shown, the device may include the following modules:

[0123] An acquisition module 310 is used to acquire an environmental factor set and a decision target set for the vehicle unmanned driving system; the environmental factor set includes environmental influencing factors, vehicle influencing factors and traffic participation influencing factors, and the decision target set includes safety, comfort and efficiency;

[0124] A determination module 320 is used to determine the influence of the environmental factor set on different sub-levels formed by the decision target set, and obtain a first degree of certainty, a second degree of certainty, and a third degree of certainty representing a safety value situation, a comfort value situation, and an efficiency value situation;

[0125] A weight allocation module 330 is used to allocate weights to the first degree of certainty, the second degree of certainty and the third degree of certainty by a preset combined weight method to obtain a target degree of certainty to balance subjective and objective differences; wherein the combined weight method includes an OWA operator subjective weighting method and an entropy weight method;

[0126] A drawing module 340 is used to draw a comprehensive situation map based on the comprehensive situation represented by the target certainty, with time as the horizontal axis;

[0127] The decision planning module 350 is used to make decision planning based on the comprehensive situation map, and the comprehensive situation map is used to characterize the comprehensive driving situation of the vehicle unmanned driving system in the current decision environment.

[0128] According to an embodiment of the present application, any multiple modules among the acquisition module 310, the determination module 320, the weight allocation module 330, the drawing module 340 and the decision planning module 350 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0129] In some embodiments, the determination module 320 may be specifically configured to:

[0130] In the current decision-making environment, the impact measurement is performed on each sub-level according to the environmental state, the vehicle state and the surrounding vehicle state, and the potential impact of the environmental factor set on the decision-making objectives of different sub-levels is calculated to obtain the impact value cloud droplet;

[0131] Determine the typical cloud droplets corresponding to each sub-level and calculate the Gaussian cloud parameters under different value situation concepts;

[0132] Based on Gaussian cloud parameters and influence value cloud droplets, the first certainty, second certainty and third certainty of the potential impact on the ego-vehicle at different sub-levels are obtained through the conceptual certainty calculation formula preset in the forward Gaussian cloud algorithm.

[0133] Figure 3 Each module in the device shown has the function of implementing each step in the aforementioned vehicle unmanned driving system decision-making situation assessment method and can achieve its corresponding technical effect. For the sake of concise description, it will not be repeated here.

[0134] In some embodiments, the present application provides an electronic device, the structure diagram of the electronic device is as follows Figure 4 shown.

[0135] The electronic device may include a processor 410 and a memory 420 storing computer program instructions.

[0136] Specifically, the processor 410 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0137] The memory 420 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 420 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 420 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 420 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 420 is a non-volatile solid-state memory.

[0138] The memory 420 may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, typically, the memory 420 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any of the vehicle unmanned driving system decision situation assessment methods in the above-mentioned embodiments.

[0139] The processor 410 implements any one of the vehicle unmanned driving system decision situation assessment methods in the above embodiments by reading and executing computer program instructions stored in the memory 420.

[0140] In one example, the electronic device may further include a communication interface 430 and a bus 400. Figure 4 As shown, the processor 410, the memory 420, and the communication interface 430 are connected via a bus 400 and communicate with each other.

[0141] The communication interface 430 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0142] Bus 400 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 400 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0143] In addition, in combination with the vehicle unmanned driving system decision situation assessment method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the vehicle unmanned driving system decision situation assessment methods in the above embodiment is implemented.

[0144] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0145] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0146] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0147] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0148] In summary, compared with the prior art, this application has the following beneficial effects:

[0149] 1. In the process of evaluating the decision-making situation of the vehicle unmanned driving system, this application analyzes the impact of the environmental factor set on the different sub-levels of the decision-making target set, introduces a value system to unify the evaluation scale of the potential impact of environmental factors on decision-making targets, quantifies the value contribution of environmental factors to each decision target to form a value situation, so as to eliminate the ambiguity and uncertainty in qualitative concepts and the cognitive differences of decision makers on concepts.

[0150] 2. This application balances subjective and objective differences through combined weights, empowers each value situation, thereby weighing the relationship between different decision-making goals and forming a comprehensive situation assessment in the decision-making environment; this application is based on multi-objective value consistency measurement, which can eliminate the differential cognition and ambiguity between different goals at the cognitive level, and solve the problem of subjective preference and cognitive inconsistency of vehicle unmanned driving systems in complex decision-making environments.

[0151] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the decision situation of an unmanned driving system of a vehicle, characterized in that: include: Obtaining an environmental element set and a decision target set for a vehicle unmanned driving system; The environmental factor set includes environmental influencing factors, vehicle influencing factors and traffic participation influencing factors, and the decision-making goal set includes safety, comfort and efficiency; Determine the influence of the environmental factor set on different sub-levels formed by the decision target set, and obtain a first degree of certainty, a second degree of certainty, and a third degree of certainty representing a safety value situation, a comfort value situation, and an efficiency value situation; By using a preset combined weight method, weights are assigned to the first degree of certainty, the second degree of certainty and the third degree of certainty to obtain a target degree of certainty to balance subjective and objective differences; wherein the combined weight method includes an OWA operator subjective weighting method and an entropy weight method; Based on the comprehensive situation represented by the target certainty, a comprehensive situation diagram is drawn with time as the horizontal axis; Decision planning is performed based on the comprehensive situation map, and the comprehensive situation map is used to characterize the comprehensive driving situation of the vehicle unmanned driving system in the current decision-making environment.

2. The vehicle unmanned driving system decision situation assessment method according to claim 1, characterized in that: The first degree of certainty, the second degree of certainty and the third degree of certainty are used to characterize the influence of the set of environmental factors on safety, comfort and efficiency respectively; The environmental influencing factors are used to characterize the impact of the external physical and natural environment on the driving decision-making situation; The vehicle influencing factors are used to characterize the impact of the vehicle's own characteristics and status on the driving decision-making situation; The traffic participation influencing factors are used to characterize the impact of other vehicles, pedestrians, obstacles, etc. on the road on the driving decision situation.

3. The vehicle unmanned driving system decision situation assessment method according to claim 1, characterized in that: The safety value situation, the comfort value situation, and the high efficiency value situation each correspond to one sub-level; The determining of the influence of the environmental factor set on different sub-levels formed by the decision target set to obtain a first degree of certainty, a second degree of certainty and a third degree of certainty representing a safety value situation, a comfort value situation and an efficiency value situation includes: In the current decision-making environment, according to the environmental state, the vehicle state and the surrounding vehicle state, the impact measurement is performed on each of the sub-levels, and the potential impact of the environmental factor set on the decision-making objectives of different sub-levels is calculated to obtain the impact value cloud droplet; Determine the typical cloud droplets corresponding to each of the sub-levels, and calculate Gaussian cloud parameters under different value situation concepts; Based on the Gaussian cloud parameters and the impact value cloud droplets, the first certainty, the second certainty and the third certainty of the potential impact on the ego-vehicle at different sub-levels are obtained through the conceptual certainty calculation formula preset in the forward Gaussian cloud algorithm.

4. The method for evaluating the decision-making situation of an unmanned driving system of a vehicle according to claim 3, characterized in that: The Gaussian cloud parameters include: expectation Ex, entropy En and super entropy He; wherein the super entropy He satisfies the expression: In the formula, CD is the concept ambiguity, which is used to characterize the discrete degree of a concept extension, reflecting the degree to which the distribution of the Gaussian cloud deviates from the Gaussian distribution; the closer CD is to 0, the more convergent the concept extension is, and CD>1 indicates that the concept extension is divergent.

5. The vehicle unmanned driving system decision situation assessment method according to claim 3, characterized in that: In the impact metric corresponding to the safety value situation, the potential field is divided into multiple potential fields formed by traffic participants, road boundaries and lane markings; In the process of determining typical cloud droplets corresponding to the safety value situation, the vehicle unmanned driving system decision situation assessment method further includes: For two vehicles in the same lane, if the longitudinal distance between the two vehicles reaches the minimum safe distance between vehicles during the braking process, the first risk field force on the vehicle is calculated to determine that the first risk field force is a typical cloud droplet when the safety value situation of vehicles in the same lane is in a dangerous state; For two vehicles in adjacent lanes, when the longitudinal distance between the two vehicles is less than the minimum safe distance for lane change, the second risk field force on the vehicle is calculated to determine that the second risk field force is a typical cloud droplet when the safety value situation of the vehicle in the adjacent lane is in a dangerous state; At the current relative speed of the two vehicles, when the longitudinal distance between the two vehicles reaches the expected longitudinal vehicle distance, the third risk field force on the vehicle is calculated, and the third risk field force is determined to be a typical cloud droplet when the safety value situation is in a safe state.

6. The method for evaluating the decision-making situation of an unmanned driving system of a vehicle according to claim 3, characterized in that: In the process of determining the typical cloud droplets corresponding to the comfort value situation, the vehicle unmanned driving system decision situation assessment method further includes: The ride comfort is measured by the lateral and longitudinal instantaneous velocity change rate and instantaneous acceleration change rate; When the vibration frequency of the vehicle exceeds the preset tolerance threshold J t In the case of t It is a typical cloud droplet when the comfort value situation is in an uncomfortable state; When the vibration frequency is at the expected value of the passengers J exp In the case of exp It is a typical cloud droplet whose comfort value status is in a comfortable state.

7. The vehicle unmanned driving system decision situation assessment method according to claim 3, characterized in that: In the process of determining the typical cloud droplets corresponding to the high-efficiency value situation, the vehicle unmanned driving system decision situation assessment method further includes: The driving efficiency is measured by the headway between the vehicle and the vehicle ahead, as well as the speed of the vehicle. In v i =v exp ,h i =h exp In the case of , the potential impact of the current metric is determined as a typical cloud droplet with a high efficiency value situation in the high efficiency state; In v i =0,h i =h des In the case of , the potential impact of the current metric is determined as a typical cloud droplet with high efficiency value situation in the low efficiency state; Among them, v i is the current vehicle speed, v exp is the expected vehicle speed, h i h is the headway between the vehicle and the preceding vehicle, which represents the travel time from the front of the vehicle to the front of the preceding vehicle; des is the headway time corresponding to the minimum safety distance, h exp is the expected headway.

8. A vehicle unmanned driving system decision situation assessment device, characterized in that: include: An acquisition module, used to acquire an environmental element set and a decision target set for a vehicle unmanned driving system; The environmental factor set includes environmental influencing factors, vehicle influencing factors and traffic participation influencing factors, and the decision-making goal set includes safety, comfort and efficiency; A determination module, used to determine the influence of the environmental factor set on different sub-levels formed by the decision target set, and obtain a first degree of certainty, a second degree of certainty and a third degree of certainty representing a safety value situation, a comfort value situation and an efficiency value situation; A weight allocation module, used to allocate weights to the first degree of certainty, the second degree of certainty and the third degree of certainty by a preset combined weight method to obtain a target degree of certainty to balance subjective and objective differences; wherein the combined weight method includes an OWA operator subjective weighting method and an entropy weight method; A drawing module, used for drawing a comprehensive situation map with time as the horizontal axis based on the comprehensive situation represented by the target certainty degree; The decision-making planning module is used to perform decision-making planning based on the comprehensive situation map, and the comprehensive situation map is used to characterize the comprehensive driving situation of the vehicle unmanned driving system in the current decision-making environment.

9. An electronic device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the method for evaluating the decision-making situation of an unmanned driving system of a vehicle as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the vehicle unmanned driving system decision situation assessment method as described in any one of claims 1 to 7 is implemented.

Images