Vehicle unmanned driving system decision situation assessment method, device, equipment and medium

Abstract

The present application provides a method, device, equipment and medium for evaluating the decision situation of an unmanned vehicle driving system, which relates to the field of intelligent driving. The method includes: obtaining an environmental element set and a decision target set for the unmanned vehicle driving system; determining the influence of the environmental element 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; assigning weights 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; based on the comprehensive situation represented by the target degree of certainty, a comprehensive situation diagram is drawn with time as the horizontal axis; and decision planning is performed. The present application is based on a multi-objective value consistency metric, which can eliminate the differential cognition and ambiguity between different objectives at the cognitive level, and effectively solves the problem of subjective preference and cognitive inconsistency of the unmanned vehicle driving system in a complex decision-making environment.

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 autonomous driving technology, autonomous intelligent vehicles face a complex and ever-changing external environment during their autonomous driving decision-making process. In such an environment, autonomous driving systems must not only identify surrounding obstacles and dynamic traffic conditions but also make optimal decisions quickly within a limited timeframe to ensure driving safety and efficiency. Therefore, scientifically evaluating autonomous driving decision-making dynamics is crucial to improving its safety, reliability, and adaptability.

[0003] Situation assessment is a 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 decision-making and form an accurate grasp of the overall decision-making situation.

[0004] In related technologies, the driving decision situation assessment problem specifically involves evaluating the driving decision situation formed by the impact of surrounding environmental factors on various aspects of the decision-making system during the driving process of an autonomous intelligent vehicle. However, the process of evaluating the decision situation of an unmanned vehicle system involves multiple interrelated decision-making objectives. These objectives may cover different levels and conflict with each other. These objectives belong to cognitive concepts at different levels and have inconsistent measurement standards. As a result, the evaluation scales of decision-making objectives are inconsistent, making it difficult to directly compare and balance them, and it is difficult to effectively address the subjective preferences and cognitive inconsistencies in complex decision-making environments. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, 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 faced by the vehicle unmanned driving system when performing decision situation evaluation, that is, the evaluation scales of multiple decision targets are inconsistent, they cannot be directly compared with each other, and it is difficult to balance them.

[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-making 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; assigning weights to the first certainty, the second certainty and the third certainty through a preset combined weight method, and obtaining a target certainty 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-making 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 elements 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, and obtaining the first certainty, second certainty and third certainty that characterize the safety value situation, the comfort value situation and the high-efficiency value situation, may specifically include: in the current decision-making environment, according to the environmental state, the vehicle state and the surrounding vehicle state, performing an impact measurement on each sub-level, calculating the potential impact of the environmental factor set on the decision targets of different sub-levels, and obtaining an impact value cloud droplet; determining the typical cloud droplet corresponding to each sub-level, and calculating the Gaussian cloud parameters under different value situation concepts; based on the Gaussian cloud parameters and the impact value cloud droplet, the first certainty, second certainty and 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] Where CD is the conceptual ambiguity, which is used to characterize the degree of discreteness of a concept's extension and reflects 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's extension is, and CD > 1 indicates that the concept's 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, calculating the first risk field force suffered by the ego vehicle, and determining that the first risk field force is a typical cloud droplet when the safety value situation of the 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, calculating the second risk field force suffered by the ego vehicle, and determining that the second risk field force is a typical cloud droplet when the safety value situation of the vehicles 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, calculating the third risk field force suffered by the ego vehicle, and determining 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 assessment 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 Under the condition of t The typical cloud droplet 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 This is a typical cloud droplet whose comfort value 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 efficient value situation, the vehicle unmanned driving system decision situation evaluation method further includes: measuring the efficiency of driving by the degree of 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 to be 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 to be a typical cloud droplet with high efficiency value situation in 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 vehicle's head to the preceding vehicle's head; des is the headway time corresponding to the minimum safe 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, which includes: an acquisition module, a determination module, a weight distribution module, a drawing module and a decision planning module; specifically, the acquisition module is used to obtain 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; the determination module is used to determine the impact of the environmental factor set on different sub-levels formed by the decision target set, and obtain a first certainty, a second certainty and a third certainty that characterize the safety value situation, the comfort value situation and the efficiency value situation; the weight distribution 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 the OWA operator subjective weighting method and the entropy weight method; the drawing module is used to draw a comprehensive situation map with time as the horizontal axis based on the comprehensive situation represented by the target certainty; the decision planning module is used to perform 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.

[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. 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-making situation of an unmanned vehicle system. Compared with the existing technology, it has the following advantages:

[0020] In the process of evaluating the decision-making situation of a vehicle's 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, 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 about 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 to give weight to each value situation, thereby weighing the relationship between different decision-making targets 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 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 following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 This is a flow chart of a method for evaluating a decision-making situation of an unmanned vehicle driving system provided in an embodiment of the present application;

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

[0024] Figure 2-b Schematic diagram of the acceleration of the vehicle provided in the embodiment of the present application;

[0025] Figure 2-c 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 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 This is a schematic diagram of the impact of environmental factors on decision-making objectives at different levels provided by the embodiment of the present application;

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

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

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

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

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

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

[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 faced by the unmanned driving system of a vehicle when performing decision situation evaluation, that is, the evaluation scales of multiple decision objectives are inconsistent, they cannot be directly compared with each other, and it is difficult to balance them.

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

[0036] With the rapid development of autonomous driving technology, autonomous intelligent vehicles face a complex and ever-changing external environment during their autonomous driving decision-making process. In such an environment, autonomous driving systems must not only identify surrounding obstacles and dynamic traffic conditions but also make optimal decisions quickly within a limited timeframe to ensure driving safety and efficiency. Therefore, scientifically evaluating autonomous driving decision-making dynamics is crucial to improving its safety, reliability, and adaptability.

[0037] With the development of autonomous intelligence, machines are increasingly capable of self-perception, self-learning, self-decision-making, self-execution, and self-adaptation. These machines can serve as human partners, independently completing decision-making tasks and helping people escape the tedious grind of labor. Autonomous perception, a primary requirement for achieving autonomous machine intelligence, requires efficient and accurate situation assessment. Situation refers to both state and situation. State refers to the static decision-making environment at the current moment, composed of various environmental factors. Situation refers to the changing trends of the decision-making environment over time, as well as an understanding of the relationship between environmental factors and the decision-making objectives.

[0038] Situational assessment is the process of dynamically evaluating the status and situation of elements in the decision-making environment. It involves collecting environmental data through perception modules, integrating and initially analyzing this data, identifying environmental events, and conducting situational analysis through understanding and analyzing key events and predicting future environmental changes. This allows for accurate assessment of the impact of these events on decision-making, ultimately leading to a precise understanding of the overall decision-making landscape. Situational assessment emphasizes understanding the overall situation and involves perceiving the temporal changes, relevance, and overall dynamics of targets, scenarios, and other environmental elements. Therefore, situational awareness prioritizes comprehensiveness, dynamism, real-time capabilities, and accuracy.

[0039] In related technologies, the driving decision-making situation assessment problem specifically involves evaluating the driving decision-making situation formed by the impact of surrounding environmental factors on various aspects of the decision-making system during the driving process of an autonomous intelligent vehicle. However, the decision-making situation assessment process for unmanned vehicle systems involves multiple interrelated decision-making objectives. These objectives may cover different levels and conflict with each other. They belong to cognitive concepts at different levels and have inconsistent measurement standards for different objectives. As a result, the evaluation scales of decision-making objectives are inconsistent, making direct comparison and balance difficult.

[0040] Common solutions to the problem of inconsistent evaluation scales include: (1) By dividing the influencing indicators at all levels into different levels, a unified evaluation standard is defined for each indicator. (2) By using standardization methods, the original dimensioned indicators are converted into dimensionless values, 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 processing, and then analyzes the gap between alternative solutions and ideal solutions through the measurement of optimal functions and utility to eliminate the influence of different measurement units. (3) Gray system theory uses gray correlation analysis to deal with data uncertainty and scale inconsistency. For example, the gray correlation theory is combined with fuzzy set theory and applied to the assessment of smart city information security risks. By determining the correlation between each risk factor, the indicator values ​​of different scales are mapped to correlation values ​​to analyze their impact on the overall risk.

[0041] However, grading methods are highly subjective and difficult to ensure consistency. Methods such as standardization and the gray correlation system use mathematical means to unify the evaluation scales of different indicators, primarily by eliminating dimensions and calculating correlations to address relationships between data. However, these methods only achieve mathematical scalar unification and struggle to eliminate cognitive differences and ambiguity between different objectives. Consequently, they are unable to effectively address subjective preferences and cognitive inconsistencies 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 with reference to 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] The present invention provides a flow chart of a method for evaluating the decision-making situation of an unmanned driving system of a vehicle. Figure 1 As shown, the vehicle unmanned driving system decision situation assessment method may include the following steps S110-S150.

[0045] S110. Obtain 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.

[0046] S120. Determine the influence of the environmental factor set on different sub-levels of the decision target set, and obtain a first degree of certainty, a second degree of certainty, and a third degree of certainty representing the safety value situation, the comfort value situation, and the efficiency value situation.

[0047] S130. Assign weights to the first degree of certainty, the second degree of certainty, and the third degree of certainty through a preset combined weighting method to obtain a target degree of certainty to balance subjective and objective differences; wherein the combined weighting method includes an OWA operator subjective weighting method and an entropy weighting 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 based on the comprehensive situation map, where the comprehensive situation map is used to represent the comprehensive driving situation of the vehicle's 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 affecting driving decision-making situations mainly include environmental factors, ego vehicle factors, and traffic participant factors. Environmental factors refer to the influence of the external physical and natural environment on driving decision-making situations. These factors mainly include: weather conditions such as rain, snow, and fog, which affect road slipperiness and visibility; road conditions such as road adhesion coefficient, road slope, road curvature, and road markings; and traffic signals such as traffic lights and traffic signs (speed limit signs, direction signs, and warning signs). Own vehicle factors refer to the influence of the vehicle's own characteristics and status on driving decision-making situations. These factors mainly include factors such as the ego vehicle's type, mass, speed, acceleration, and driving style. Traffic participant factors refer to the influence of other vehicles, pedestrians, and obstacles on the road. These factors mainly include factors such as the type of traffic participants (e.g., motor vehicles, non-motor vehicles, pedestrians, obstacles), location, size, mass, motion state (moving or stationary), speed, and acceleration.

[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 optimal outcome. In autonomous driving decisions, the decision goal usually involves multiple aspects to ensure that the vehicle can operate safely and efficiently without human intervention. Specifically, the vehicle's autonomous driving system needs to consider the following:

[0053] (1) Safety focuses on maintaining 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 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 enjoyment. The main influencing factors during vehicle driving are the vehicle's vibration frequency, namely 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 possible time, minimizing fuel consumption, and minimizing time wasted in traffic jams. Improving driving efficiency can save time and costs, and reduce environmental impact. 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 this application. In the process of conducting the vehicle unmanned driving system decision situation assessment, this application analyzes the impact of the environmental factor set on the different sub-levels of 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 decision makers' cognitive differences in 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, empowers each value situation, and thus weighs the relationship between different decision-making goals to form 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 efficiency value situation each correspond to a sub-level. The aforementioned determination of the impact of the environmental factor set on the different sub-levels formed by the decision target set obtains a first degree of certainty, a second degree of certainty, and a third degree of certainty representing the safety value situation, the comfort value situation, and the efficiency value situation. Specifically, the aforementioned S120 may 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, second certainty, and third certainty of the potential impact on the ego-vehicle at different sub-levels are obtained 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 super entropy He satisfies the expression:

[0063]

[0064] Where CD is the conceptual ambiguity, which is used to characterize the degree of discreteness of a concept's extension and reflects 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's extension is, and CD > 1 indicates that the concept's 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 (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 factors 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 factors 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 degree of influence of each factor in the decision environment on the safety level of the ego vehicle i. The smaller F is, the safer the ego vehicle and the decision environment it faces are, and vice versa. G, λ1, λ2, λ3, and λ4 are constant coefficients greater than 0; R a 、R b 、R c 、R i It is a road condition influencing factor determined by factors such as road adhesion coefficient, slope, visibility, etc. a 、M i is the equivalent mass of traffic participant a and vehicle i, which is determined by factors such as the actual mass, type, and speed of the object. η is the different types of lane markings, 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, and 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 braking, calculate the first risk field force on the ego vehicle and determine the typical cloud droplet when the safety value situation of the 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 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, 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 embodiments of the present application, it is understood that for two vehicles in adjacent lanes, when the longitudinal distance between the two vehicles is less than the minimum safe lane change distance, the vehicle behind must always be on guard against the vehicle ahead attempting to cut in, as any attempt by the vehicle ahead to cut in would pose a significant safety threat to both vehicles. At the current relative speed of the two vehicles, if the longitudinal distance between the two vehicles reaches the desired longitudinal distance, even if the two vehicles are in adjacent lanes, a lane change by the vehicle ahead would not pose a safety threat to either vehicle.

[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 Gauss Cloud's "3E Rule", a typical cloud droplet F of security value situation saf The contribution to the dangerous value situation can be ignored and 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 danger 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, En saf 、En dan are the entropies of the concepts of safety value situation and danger 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 ride comfort is measured by the instantaneous velocity change rate and the instantaneous acceleration change rate in the lateral and longitudinal directions. For example, the impact measurement process corresponding to the comfort value state satisfies the expression:

[0082]

[0083] Where, J i To measure the impact of comfort value situation, x(t) is the displacement time function of the center point of the vehicle's rear axle along the x-axis, and y(t) is the displacement function in the y-axis direction. By taking high-order derivatives of the vehicle's lateral and longitudinal displacements, the lateral and longitudinal velocity change rates and acceleration change rates are obtained.

[0084] When the vibration frequency of the vehicle exceeds the preset tolerance threshold J t Under the condition 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 J of the passengers exp In the case of expThis is a typical cloud droplet whose comfort value 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 different horizontal and vertical directions under the action of force, thereby generating vibrations of different frequencies; indicators such as acceleration and the rate of change of acceleration can reflect the force acting on the vehicle and the change in the force; when the force acting on the vehicle changes 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 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 When the body is usually very comfortable, the definition of J exp This is a typical cloud droplet whose comfort value 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; 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 regarded as the boundary point of the uncomfortable value situation concept [Ex-3En,Ex+3En].

[0089] Typical cloud drop J of unsuitable value situation 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 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] Driving efficiency is measured by the headway between the vehicle and the preceding vehicle, as well as the vehicle's speed.

[0097] In v i =v exp , h i =h exp In the case of , the potential impact of the current metric is determined to be a typical cloud droplet with 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 to be a typical cloud droplet with high efficiency value situation in 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 vehicle's head to the preceding vehicle's head; des is the headway time corresponding to the minimum safe distance, h exp is the expected headway.

[0100] In the embodiments of the present application, it is understood that in the efficiency level impact measurement, in order to ensure driving efficiency, the vehicle needs to maintain the desired speed as much as possible under different road and traffic conditions to shorten driving time and improve 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 driving smoothness and reducing unnecessary stops and lane changes; therefore, the present application measures driving efficiency by the degree of proximity between the current vehicle speed and the desired speed and the headway to the preceding vehicle, 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, P 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 vehicle's driving is; the lower the current speed, the less efficient it is; from the perspective of driving space, the larger the headway between the vehicle and the preceding vehicle, 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 efficient 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 drop E with high efficiency value hig The contribution to the inefficient value situation can be ignored and can be regarded as the boundary point of the inefficient value situation concept [Ex-3En,Ex+3En].

[0107] Typical cloud drop E with low efficiency value situation sol The contribution to the efficient value situation can be ignored and 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, En hig 、En sol 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] Because the NGISM dataset does not provide information such as road adhesion coefficient, slope, and visibility, and the selected driving data is from the same road section within the same time period, the road condition factor is assumed to be 1 and the parameters are set. The sampling period for the selected driving data is 0.1 seconds. Vehicle 2224 is selected and assumed to be the current unmanned vehicle. The vehicle ahead in the current lane is 2208. Some driving state parameters for vehicle 2224 and vehicle 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 indicators of decision-making environment factors on decision-making goals have a large fluctuation range, and their relative values ​​cannot always accurately reflect the degree of influence of driving situations at all levels. The decision situation assessment 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. The certainty of the three value situations of the decision environment calculated based on this is 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 method of quantitative determination based on a unified scale helps to more clearly and explainably evaluate the impact of driving situations at all levels.

[0118] Regarding the safety value trend, for the first 6.7 seconds, the ego vehicle (car 2224) was faster than the preceding vehicle (car 2208), and the relative distance between the two vehicles gradually decreased, indicating an overall downward trend in safety value. From 5 to 11 seconds, the relative distance between the two vehicles was small, and the relative speeds began to decrease from 8.9 to 9.4 seconds. Therefore, the safety value trend of car 2224 approached zero during these periods, indicating a high degree of danger in the environment. As the relative distance between the two vehicles gradually increased, the safety value trend of car 2224 began to increase from 10.8 to 11.9 seconds.

[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. The comfort value trend of car No. 2224 was approximately 1, and the passengers in the car felt very comfortable. 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 value of human discomfort. 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 in 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-gThis macroscopic analysis reflects the comprehensive driving decision-making situation facing the vehicle. It integrates the changing trends of the value situations across the three evaluation dimensions. Changes in any single value situation will not have a drastic impact on the overall situation, maintaining relative stability. For example, in the first three seconds, the overall trend is positive due to the strong safety and comfort values ​​of vehicle #2224. However, this value remains around 0.7, indicating that the overall situation still has room for improvement. The vehicle could improve its driving efficiency by switching to a less crowded lane. Another example is the rapid decline in the overall situation between 3.5 and 4.2 seconds, prompting vehicle #2224 to maintain a stable speed and relative distance from the vehicle ahead. However, between 10.5 and 11 seconds, the safety value situation shows an upward trend, but the overall situation declines. This is because the vehicle's speed and acceleration fluctuate significantly during this period, indicating that the vehicle's comfort is poor and that it should maintain stable driving to enhance the passenger 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 configured to acquire an environmental factor set and a decision-making target set for the vehicle autonomous driving system; the environmental factor set includes environmental influencing factors, vehicle influencing factors, and traffic participation influencing factors; and the decision-making target set includes safety, comfort, and efficiency;

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

[0125] A weight assignment module 330 is configured to assign weights to the first degree of certainty, the second degree of certainty, and the third degree of certainty using a preset combined weighting method to obtain a target degree of certainty to balance subjective and objective differences; wherein the combined weighting method includes an OWA operator subjective weighting method and an entropy weighting 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, which is used to represent 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, determination module 320, weight assignment module 330, drawing module 340, and decision planning module 350 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module.

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

[0130] In the current decision-making environment, based on the state of the environment, the state of the vehicle itself, and the state of surrounding vehicles, 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;

[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 the 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 concept 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 situation assessment method and can achieve its corresponding technical effect. For the sake of brevity, it will not be repeated here.

[0134] In some embodiments, the present application provides an electronic device, the structural 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. Where appropriate, the memory 420 may include removable or non-removable (or fixed) media. Where appropriate, 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 magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Therefore, generally, 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 one 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 components of online data flow metering equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry 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 application considers any suitable bus or interconnection.

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

[0144] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of 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, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segments can be downloaded via computer networks such as the Internet, intranets, 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. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0147] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments 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 is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the 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 an unmanned driving system of a vehicle, this application analyzes the impact of a set of environmental factors on different sub-levels of the formation of a set of decision-making objectives, introduces a value system to unify the evaluation scale of the potential impact of environmental factors on decision-making objectives, quantifies the value contribution of environmental factors to each decision-making objective to form a value situation, and eliminates the ambiguity and uncertainty in qualitative concepts and the cognitive differences of decision makers regarding concepts.

[0150] 2. This application balances subjective and objective differences through combined weights, empowers each value situation, and thus weighs the relationship between different decision-making goals to 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 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 they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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 various embodiments of the present invention.

Claims

1. A method for evaluating the decision-making situation of an unmanned vehicle driving system, characterized in that: include: Obtaining an environmental element set and a decision-making target set for a vehicle's 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; Determining the influence of the environmental factor set on different sub-levels formed by the decision target set, and obtaining 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; weighting the first degree of certainty, the second degree of certainty, and the third degree of certainty using a preset combined weighting method to obtain a target degree of certainty to balance subjective and objective differences; wherein the combined weighting method includes an OWA operator subjective weighting method and an entropy weighting method; Based on the comprehensive situation represented by the target certainty, a comprehensive situation diagram is drawn with time as the horizontal axis; Perform decision planning based on the comprehensive situation map, wherein the comprehensive situation map is used to represent the comprehensive driving situation of the vehicle unmanned driving system in the current decision environment; The safety value situation, the comfort value situation, and the efficiency value situation each correspond to one sub-level; Determining 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, based on 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, a first certainty, a second certainty, and a third certainty of the potential impact on the ego-vehicle at different sub-levels are obtained using a concept certainty calculation formula preset in a forward Gaussian cloud algorithm; 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 process of determining the 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 braking, calculate the first risk field force on the ego vehicle and 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, calculate the second risk field force on the ego vehicle and 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 desired longitudinal distance between the two vehicles, the third risk field force on the ego 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; 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 instantaneous rate of change of lateral and longitudinal speed and the instantaneous rate of change of acceleration; 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 J of the passengers exp In the case of exp The typical cloud droplet is in a comfortable state in terms of comfort value; 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: Driving efficiency is measured by the headway between the vehicle and the preceding vehicle, as well as the vehicle's speed. In v i =v exp , h i =h exp In the case of , the potential impact of the current metric is determined to be a typical cloud droplet with 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 to be a typical cloud droplet with high efficiency value situation in 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 vehicle's head to the preceding vehicle's head; des is the headway time corresponding to the minimum safe distance, h exp is the expected headway.

2. The method for evaluating the decision-making situation of an unmanned vehicle driving system according to claim 1, wherein: 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 situation.

3. The method for evaluating the decision-making situation of an unmanned vehicle driving system according to claim 1, wherein: The Gaussian cloud parameters include: ,entropy and super entropy ; wherein, the super entropy Satisfies the expression: Where CD is the conceptual ambiguity, which is used to characterize the degree of discreteness of a concept's extension and reflects 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's extension is, and CD > 1 indicates that the concept's extension is divergent.

4. A vehicle unmanned driving system decision situation assessment device, characterized in that: include: An acquisition module, used to obtain 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, configured 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 assignment module, configured to assign weights to the first degree of certainty, the second degree of certainty, and the third degree of certainty using a preset combined weighting method to obtain a target degree of certainty to balance subjective and objective differences; wherein the combined weighting method includes an OWA operator subjective weighting method and an entropy weighting method; A drawing module, configured to draw a comprehensive situation map based on the comprehensive situation represented by the target certainty, with time as the horizontal axis; A decision-making planning module, configured to perform decision-making planning based on the comprehensive situation map, wherein the comprehensive situation map is configured to represent the comprehensive driving situation of the vehicle's unmanned driving system in the current decision-making environment; The safety value situation, the comfort value situation, and the efficiency value situation each correspond to one sub-level; Determining 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, based on 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, a first certainty, a second certainty, and a third certainty of the potential impact on the ego-vehicle at different sub-levels are obtained using a concept certainty calculation formula preset in a forward Gaussian cloud algorithm; 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 process of determining the 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 braking, calculate the first risk field force on the ego vehicle and 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, calculate the second risk field force on the ego vehicle and 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 desired longitudinal distance between the two vehicles, the third risk field force on the ego 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; 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 instantaneous rate of change of lateral and longitudinal speed and the instantaneous rate of change of acceleration; 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 J of the passengers exp In the case of exp The typical cloud droplet is in a comfortable state in terms of comfort value; 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: Driving efficiency is measured by the headway between the vehicle and the preceding vehicle, as well as the vehicle's speed. In v i =v exp , h i =h exp In the case of , the potential impact of the current metric is determined to be a typical cloud droplet with 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 to be a typical cloud droplet with high efficiency value situation in 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 vehicle's head to the preceding vehicle's head; des is the headway time corresponding to the minimum safe distance, h exp is the expected headway.

5. 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 for a vehicle as claimed in any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the vehicle unmanned driving system decision situation assessment method according to any one of claims 1 to 3 is implemented.

Images