A method, device, equipment and storage medium for determining the security level of a scenario

Abstract

The present application provides a method, apparatus, device and storage medium for determining the safety level of a scenario, relating to the field of autonomous driving technology, and is used to quickly determine the safety level of an unknown scenario. The method includes: judging whether there is at least one predefined scenario in a predefined scenario library whose similarity to the target scenario is greater than a set similarity threshold according to a first parameter set and a first parameter value set of a target scenario in which a target vehicle is located; in response to the at least one predefined scenario, selecting one predefined scenario from the at least one predefined scenario as a control scenario; generating a parameter value subset of the target scenario according to a parameter subset of the control scenario; and determining a target safety level of the target scenario according to the parameter subset and the parameter value subset.

Description

Technical Field

[0001] The present application relates to the technical field of autonomous driving, and provides a method, device, equipment and storage medium for determining the safety level of a scenario. Background Art

[0002] At present, in order to ensure traffic safety and the personal safety of drivers, most vehicles on the market have certain driving requirements, which prevent many people from driving because they do not meet the driving requirements. As a result, people's travel is affected.

[0003] In response to the above problems, with the gradual development of the automotive industry, autonomous vehicles (AVs) have emerged. With their advantages such as being able to accommodate more people, alleviating traffic congestion, and improving highway safety, they have gradually become the development trend of the future automotive industry. However, autonomous vehicles also have certain technical development requirements. They need to have the capabilities of autonomous driving, degraded driving, stop operation, being taken over manually in scenarios that the vehicle cannot handle autonomously, and remote intervention, etc. on the premise of ensuring safety in any business scenario. However, due to the characteristics of uncertainty, unpredictability, and inexhaustibility of autonomous driving scenarios, the business scenarios included in autonomous vehicles are limited. As a result, when an autonomous vehicle faces an unknown scenario, there may be a risk of being unable to quickly identify the safety level of the unknown scenario, thus resulting in problems such as being unable to ensure traffic safety.

[0004] Therefore, how to quickly determine the safety level of an unknown scenario is an urgent problem to be solved. Summary of the Invention

[0005] Embodiments of the present application provide a method, device, equipment and storage medium for determining the safety level of a scenario, which is used to quickly determine the safety level of an unknown scenario.

[0006] On the one hand, a method for determining the safety level of a scenario is provided. The method includes:

[0007] According to a first parameter set and a first parameter value set of a target scenario where a target vehicle is located, it is determined whether there is at least one predefined scenario in a predefined scenario library whose similarity to the target scenario is greater than a set similarity threshold; where the parameters included in the first parameter set are all parameters for which parameter values can be collected for the target scenario, and the parameter values in the first parameter value set correspond to the parameters in the first parameter set;

[0008] In response to the at least one predefined scenario, one predefined scenario is selected from the at least one predefined scenario as a reference scenario; the reference scenario has a parameter subset, and the parameter subset is a subset of the first parameter set of the target scenario;

[0009] Generate a subset of parameter values for the target scenario according to a subset of parameters of the reference scenario; wherein, the parameter values in the subset of parameter values correspond to the parameters in the subset of parameters, and the subset of parameter values is a subset of the first set of parameter values;

[0010] Determine the target security level of the target scenario according to the subset of parameters and the subset of parameter values.

[0011] On the one hand, a device for determining the security level of a scenario is provided, and the device includes:

[0012] A similar scenario determination unit, configured to determine whether there is at least one predefined scenario in a predefined scenario library whose similarity to the target scenario is greater than a set similarity threshold according to a first set of parameters and a first set of parameter values of a target scenario where a target vehicle is located; wherein, the parameters included in the first set of parameters are all parameters of the parameter values collected for the target scenario, and the parameter values in the first set of parameter values correspond to the parameters in the first set of parameters;

[0013] A reference scenario determination unit, in response to the at least one predefined scenario, selects one predefined scenario from the at least one predefined scenario as a reference scenario; the reference scenario has a subset of parameters, and the subset of parameters is a subset of the first set of parameters of the target scenario;

[0014] A subset of parameter values generation unit, configured to generate a subset of parameter values for the target scenario according to the subset of parameters of the reference scenario; wherein, the parameter values in the subset of parameter values correspond to the parameters in the subset of parameters, and the subset of parameter values is a subset of the first set of parameter values;

[0015] A security level determination unit, configured to determine the target security level of the target scenario according to the subset of parameters and the subset of parameter values.

[0016] Optionally, the security level determination unit is specifically configured to:

[0017] Determine the parameter security level corresponding to each parameter in the subset of parameters according to the value range of each parameter in the subset of parameters corresponding to different security levels and the parameter values in the subset of parameter values; and,

[0018] Determine the target security level of the target scenario according to the parameter security level.

[0019] Optionally, the device further includes: a predefined scenario library construction unit, and the predefined scenario library construction unit is configured to:

[0020] For each predefined scenario,

[0021] Determine a second parameter set and a second parameter value set of the predefined scenario according to the values of the respective parameters of the predefined scenario; wherein, the parameters included in the second parameter set are all the parameters for which parameter values are collected for the predefined scenario, and the parameter values in the second parameter value set correspond to the parameters in the second parameter set;

[0022] Determine a parameter subset of the predefined scenario from the second parameter set according to the importance levels of the respective parameters of the predefined scenario;

[0023] Determine the value ranges corresponding to different security levels for the respective parameters in the parameter subset according to the parameter value subset, where the parameter values in the parameter value subset correspond to the parameters in the parameter subset.

[0024] Optionally, the predefined scenario library construction unit is specifically configured to:

[0025] Determine a parameter subset of the predefined scenario from the second parameter set according to the first importance level corresponding to the respective parameters of the predefined scenario, where the first importance level is determined according to historical road measurement data or historical simulation data; or,

[0026] Determine a parameter subset of the predefined scenario from the second parameter set according to the second importance level corresponding to the respective parameters of the predefined scenario, where the second importance level is set according to empirical values.

[0027] Optionally, the predefined scenario library construction unit is specifically further configured to:

[0028] Determine the second parameter set of the predefined scenario according to the values of the respective parameters in the historical road measurement data or historical simulation data of the predefined scenario;

[0029] Determine a first parameter subset from the second parameter set according to the first importance level corresponding to the respective parameters of the predefined scenario; where the first importance level is determined according to historical road measurement data or historical simulation data;

[0030] Determine the parameter subset of the predefined scenario from the first parameter subset according to the second importance level corresponding to the respective parameters in the first parameter subset; where the second importance level is set according to empirical values.

[0031] Optionally, the predefined scenario library construction unit is specifically further configured to:

[0032] In response to at least two parameters of the predefined scenario being non-single parameters,

[0033] Determine a reference parameter from the at least two parameters according to the importance degree of driving safety of the predefined scenario with respect to the at least two parameters; wherein, the parameter value of the non-singularity parameter is related to the parameter values of at least one parameter in the parameter subset;

[0034] Determine the value range of the reference parameter at each safety level according to historical road measurement data, historical simulation data or empirical values;

[0035] According to the value range of the reference parameter at each safety level, respectively determine the value ranges of the remaining non-singularity parameters in the at least two parameters corresponding to each safety level.

[0036] Optionally, the safety level determination unit is further configured to:

[0037] In response to the fact that there is no at least one predefined scenario in the predefined scenario whose similarity to the target scenario is greater than a set similarity threshold, determine that the target safety level of the target scenario is a preset safety level.

[0038] On the one hand, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the method described in the above aspect are implemented.

[0039] On the one hand, a computer storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the steps of the method described in the above aspect are implemented.

[0040] In the embodiments of the present application, based on the first parameter set and the first parameter value set of the target scenario of the target vehicle, it can be determined whether there is at least one predefined scenario in the predefined scenario library whose similarity to the target scenario is greater than the set similarity threshold. Furthermore, when there is at least one predefined scenario, in response to the at least one predefined scenario, a predefined scenario is selected from the at least one predefined scenario as a control scenario, and the parameter subset of the control scenario includes key parameters that affect the safety of the control scenario. Then, according to the parameter subset and the first parameter value set, a parameter value subset can be generated, so that the target safety level of the target scenario can be determined based on the parameter subset and the parameter value subset. It can be seen that in the embodiments of the present application, by obtaining a similar scenario from the predefined scenario library and then obtaining a control scenario from the similar scenario to determine the target safety level of the target scenario, the target safety level of the target scenario can be directly determined based on the safety level range corresponding to the control scenario, greatly shortening the determination time of the target scenario safety level, so as to quickly adopt coping strategies for unknown scenarios. Moreover, since the parameter subset is a subset of the first parameter set and does not include all the parameters in the first parameter set, when determining the scenario safety level of the target scenario, the amount of calculation can be reduced and the processing efficiency can be improved, so as to further shorten the determination time of the target scenario safety level and improve the safety performance of autonomous vehicles step by step. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only those of the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on the provided drawings without creative efforts.

[0042] Figure 1 A schematic diagram of scenario division provided by an embodiment of the present application;

[0043] Figure 2 A schematic diagram of reducing an unsafe scenario provided by an embodiment of the present application;

[0044] Figure 3 An application scenario schematic diagram provided by an embodiment of the present application;

[0045] Figure 4 A flowchart of a method for determining the scenario safety level provided by an embodiment of the present application;

[0046] Figure 5 A flowchart of determining the parameter set and parameter value set of a predefined scenario;

[0047] Figure 6 It is a schematic flowchart for determining the value range of the safety level provided by an embodiment of the present application;

[0048] Figure 7 It is a schematic structural diagram of a device for determining the scene safety level provided by an embodiment of the present application;

[0049] Figure 8 It is a schematic structural diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0050] To make the objectives, technical solutions, and advantages of the present application more clear and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present application. Without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other arbitrarily. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0051] First, some terms in the present application are explained.

[0052] (1) An autonomous vehicle, also known as a driverless vehicle, a computer-driven vehicle, or a wheeled mobile robot, is an intelligent vehicle that realizes driverless through a computer system. An autonomous vehicle relies on the collaborative cooperation among artificial intelligence, computer vision, radar, monitoring devices, and the global positioning system, enabling the computer to automatically and safely operate a motor vehicle without any active operation by humans.

[0053] (2) The driverless level. The Society of Automotive Engineers (SAE) in the United States defines 6 driverless levels, namely level 0 (fully manual) - level 5 (fully automatic).

[0054] (3) A scene refers to the combination of a driving occasion and a driving scenario, which is deeply affected by the driving environment, such as factors like roads, traffic, weather, and lighting, jointly constituting the entire scene concept. A scene is a comprehensive reflection of the environment and driving behavior within a certain time and space range, describing external states such as roads, traffic facilities, meteorological conditions, and traffic participants, as well as information such as the driving tasks and states of the vehicle itself.

[0055] (4) The scene quantitative classification and description method is a method for defining a scene based on scene elements and using the key parameters corresponding to each scene element.

[0056] Among them, scene elements can be divided into traffic participants (objects), road conditions, environment, and behaviors, etc. Traffic participants can refer to other people or vehicles that appear in the scene, as well as other objects or animals that affect driving decisions or can move autonomously; road conditions can refer to the characteristics of the road and the characteristics of traffic control; the environment can refer to all possible changing environmental factors; behaviors can refer to the driving behaviors of the autonomous driving vehicle itself.

[0057] For traffic participants, the corresponding key parameters can include object type, object moving speed, object moving direction, object acceleration, object quantity, environmental awareness, etc. Among them, object types can include passenger cars, heavy trucks, pedestrians, street lights, trash cans, road signs, etc.; object moving speeds can include stationary, low-speed movement, high-speed movement; object moving directions can include going straight, reversing, U-turning, turning left, turning right, curving, leaving the lane, merging into the lane; object accelerations can include accelerating, decelerating, and moving at a constant speed; environmental awareness can refer to for living objects, the autonomous driving vehicle also needs to judge whether the object is looking at the road carefully, such as a drunk driver, a 5-year-old child, a young person looking at the mobile phone while walking, etc.

[0058] For road conditions, the corresponding key parameters can include intersection design, traffic control methods, number of lanes, lane lines, lane types, speed limits, road types, road angles, regions, etc. Among them, intersection designs can include crossroads, T-shaped intersections, Y-shaped intersections; traffic control methods can include traffic light styles, stop signs, yield signs; the number of lanes can include single lanes, 4 lanes; lane lines can include having dividing lines, no dividing lines; lane types can include bicycle lanes, bus lanes, overtaking lanes; speed limits can include 25 mph, speed limits in commercial areas, speed limits in residential areas; road types can include highways, ordinary roads, small roads; road angles can include uphill, downhill, bumpy; regions can include logistics hub areas, school areas, hospital areas, mountainous areas, construction areas, etc.

[0059] For the environment, the corresponding key parameters can include weather, light, road surface, signals, etc. Among them, weather can include rainfall, wind speed, temperature, visibility; light can include cloudy days, sunrise and sunset times, sunlight angles; road surface can include icing, waterlogging, construction; signals can include signal strength, etc.

[0060] At present, in view of the characteristics of uncertainty, unpredictability, and inexhaustibility in the autonomous driving scenario, the International Organization for Standardization (ISO) has proposed a new standard - Safety of the Intended Functionality (SOTIF) standard for road vehicles. This SOTIF standard belongs to the ISO / PAS 21448: Road Vehicles standard. The ISO / PAS 21448 standard applies to functions that require appropriate environmental perception, and this standard focuses on how to ensure the safety of the target function without vehicle failures, which forms a sharp contrast with traditional functional safety (which focuses on how to reduce safety risks caused by system failures).

[0061] Based on the SOTIF standard, for the autonomous driving scenario, as Figure 1 shown, it is a schematic diagram of scenario division provided by an embodiment of the present application. Any scenario can be divided into Figure 1 the four categories shown, namely the known safe scenario (Area1), the known unsafe scenario (Area2), the unknown unsafe scenario (Area3), and the unknown safe scenario (Area4).

[0062] Among them, the purpose of this SOTIF standard is to evaluate these two types of unsafe scenarios, namely Area2 and Area3. Furthermore, as Figure 2 shown, it is a schematic diagram of reducing unsafe scenarios provided by an embodiment of the present application. The areas corresponding to these two types of unsafe scenarios, namely Area2 and Area3, can be reduced through a series of technical measures, and at the same time, evidence is provided to prove that these two domains are small enough so that the remaining residual hazards can be accepted. In addition, during this process, since the areas corresponding to these two types of unsafe scenarios, namely Area2 and Area3, are reduced, the area corresponding to Area1 usually increases.

[0063] Furthermore, when evaluating Area2, the risky scenarios in Area2 can be identified by performing a safety analysis on Area2. Then, strategies for dealing with the risky scenarios are developed. Thus, a real-time simulation environment is built or a real vehicle test is designed based on the known scenarios, and the strategies are optimized according to the experimental results to gradually reduce the area corresponding to Area2.

[0064] When evaluating Area3, specifically, Area3 can be processed in the following two ways. One way is to reduce the area occupied by Area3 by improving the credibility of vehicle systems and component functions. The other way is to reduce the area occupied by Area3 by accumulating a large amount of data through real vehicle road tests or simulation tests. In this way, the more data is accumulated, the more unknown scenarios can be turned into known scenarios.

[0065] However, autonomous driving scenarios are characterized by uncertainty, unpredictability, and inexhaustibility, making the business scenarios included in autonomous vehicles limited. Furthermore, when an autonomous vehicle faces an unknown scenario, there may be a risk of being unable to quickly identify the safety level of the unknown scenario, resulting in problems such as an inability to ensure traffic safety.

[0066] Based on this, in the embodiments of the present application, according to the first parameter set and the first parameter value set of the target scenario where the target vehicle is located, it can be determined whether there is at least one predefined scenario in the predefined scenario library whose similarity to the target scenario is greater than the set similarity threshold. Then, when there is at least one predefined scenario, in response to the at least one predefined scenario, a predefined scenario is selected from the at least one predefined scenario as a reference scenario, and the parameter subset of the reference scenario includes key parameters that affect the safety of the reference scenario. Furthermore, according to the parameter subset and the first parameter value set, a parameter value subset can be generated, and thus, based on the parameter subset and the parameter value subset, the target safety level of the target scenario can be determined. It can be seen that in the embodiments of the present application, by obtaining similar scenarios from the predefined scenario library and then obtaining a reference scenario from the similar scenarios to determine the target safety level of the target scenario, the target safety level of the target scenario can be directly determined based on the safety level range corresponding to the reference scenario, greatly shortening the time for determining the target safety level, so as to quickly adopt coping strategies for unknown scenarios. Moreover, since the parameter subset is a subset of the first parameter set and does not include all the parameters in the first parameter set, when determining the scenario safety level of the target scenario, the amount of calculation can be reduced, the processing efficiency can be improved, and further, the time for determining the target safety level can be shortened, improving the safety performance of autonomous vehicles.

[0067] After introducing the design concept of the embodiments of the present application, the following briefly introduces the application scenarios applicable to the technical solutions of the embodiments of the present application. It should be noted that the application scenarios introduced below are only for explaining the embodiments of the present application and not for limitation. In the specific implementation process, the technical solutions provided by the embodiments of the present application can be flexibly applied according to actual needs.

[0068] Such as Figure 3As shown in the figure, it is a schematic diagram of an application scenario provided by an embodiment of the present application. Among them, the application scenario for determining the security level of the scenario may include vehicle A and vehicle B driving on the road. Among them, a scenario security level determination device 10 is provided on vehicle A.

[0069] In the embodiment of the present application, the scenario security level determination device 10 can be used to determine the security level of the scenario where vehicle A is located. Among them, the security level of the scenario can be set according to user needs. For example, the security level of the scenario can be set to 6 levels corresponding one-to-one to the driverless level (level 0 fully manual - level 5 fully automatic). When the security level of the scenario is higher, vehicle A is safer in this unknown scenario.

[0070] The scenario security level determination device 10 can specifically be a device such as an in-vehicle computer. And the scenario security level determination device 10 can include one or more processors, a memory, and an input / output (I / O) interface, etc. Among them, the memory of the scenario security level determination device 10 can store the program instructions of the scenario security level determination method provided by the embodiment of the present application. When these program instructions are executed by the processor, they can be used to implement the steps of the scenario security level determination method provided by the embodiment of the present application.

[0071] In actual application, as Figure 3 shown in the figure, along the driving direction of vehicle A, there is vehicle B in the same lane as vehicle A and with the same driving direction in front of vehicle A. When vehicle A detects through its own perception system that vehicle A is currently in an unknown scenario, the scenario security level determination device 10 of vehicle A will analyze the unknown scenario based on various parameters collected by each sensor of the perception system to quickly determine the security level of the unknown scenario. Then, vehicle A can select corresponding coping strategies according to the determined security level to respond. For example, when the security level of the unknown scenario is determined to be level 1 by the scenario security level determination device 10, that is, when the current unknown scenario is an unsafe scenario, it can notify the driver to take over manually, or perform operations such as remote intervention by the back-end management personnel to assist in driving, thereby improving the driving safety of vehicle A.

[0072] Of course, the method provided by the embodiment of the present application is not limited to the Figure 3 application scenario shown in the figure, and can also be used in other possible application scenarios, which are not limited by the embodiment of the present application. The functions that can be realized by each device in the Figure 3 application scenario shown in the figure will be described together in the subsequent method embodiments, and will not be elaborated here too much. Next, the method of the embodiment of the present application will be introduced with reference to the drawings.

[0073] AsFigure 4 As shown in Figure 4 , it is a schematic flowchart of a method for determining the scene safety level provided by an embodiment of the present application. This method can be executed by the scene safety level determination device 10 in Figure 3 , and the process of this method is introduced as follows. Figure 3 The process is as follows.

[0074] Step 401: According to the first parameter set and the first parameter value set of the target vehicle in the target scene, determine whether there is at least one predefined scene in the predefined scene library whose similarity to the target scene is greater than the set similarity threshold.

[0075] In an embodiment of the present application, the parameter values in the first parameter value set correspond to the parameters in the first parameter set. Among them, the parameters included in the first parameter set are all the parameters for which the target vehicle can collect parameter values for the target scene, including parameters with a parameter value of zero. And in the predefined scene library, there are a second parameter set, a second parameter value set, a parameter subset, and a parameter value subset corresponding to each predefined scene. The parameter subset is a subset of the second parameter set, and the parameters included in the parameter subset are key parameters whose importance for the driving safety level of the corresponding predefined scene is greater than the set importance threshold, that is, the main parameters that can affect whether the corresponding predefined scene is safe, and the parameter values in the parameter value subset correspond to the parameters in the parameter subset.

[0076] In actual application, when the target vehicle is in the target scene, the target vehicle will collect data on the target scene through various sensors of the perception system, and define the target scene based on the collected data through the scene quantitative classification description method. Therefore, in an embodiment of the present application, after collecting data on the target scene, a first parameter set and a first parameter value set for defining the target scene can be generated based on the collected data.

[0077] For example, the first parameter set can be S1 = {own vehicle speed v1, own vehicle acceleration a1, own vehicle lane VL, leading vehicle lane VL, inter-vehicle distance s, leading vehicle speed v2, leading vehicle acceleration a2, leading vehicle type Veh, leading vehicle moving direction Hd, road type RT, road speed limit RSL, road angle RA, number of lanes RLN, road visibility RV, wind speed WS, lighting condition LC, signal strength SL,...}, and the first parameter value set is N1 = {own vehicle speed v1 = 60 km / h, own vehicle acceleration a1 = 2 m / s,... inter-vehicle distance s = 50 m, leading vehicle speed v2 = 55 km / h, leading vehicle acceleration a2 = 2 m / s,...}.

[0078] Furthermore, in the embodiments of the present application, for the purpose of quickly determining the safety level of the target scenario, therefore, a predefined scenario similar to the target scenario can be selected from the predefined scenario library for determination. Of course, in order to further ensure that the selected predefined scenario can better match the target scenario, when selecting a similar predefined scenario, a similarity threshold can also be set, so that when the similarity between the target scenario and the predefined scenario is greater than the set similarity threshold, the safety level of the target scenario will be determined based on the predefined scenario with a similarity greater than the set similarity threshold. Among them, the similarity between the target scenario and the predefined scenario can be determined by using the solution method of cosine similarity.

[0079] Therefore, in the embodiments of the present application, after determining the first parameter set and the first parameter value set of the target scenario, the similarity between the first parameter set of the target scenario and the second parameter sets of each predefined scenario in the predefined scenario library will be determined first. Furthermore, it will be determined whether there is at least one predefined scenario in the predefined scenario library whose similarity to the target scenario is greater than the set similarity threshold, so that when there is at least one predefined scenario with a similarity greater than the set similarity threshold, the scenario safety level of the target scenario can be determined through this at least one predefined scenario.

[0080] Step 402: In response to at least one predefined scenario, select one predefined scenario from the at least one predefined scenario as the reference scenario.

[0081] In the embodiments of the present application, the reference scenario has a parameter subset, and this parameter subset is a subset of the first parameter set of the target scenario. Of course, the parameter subset of this reference scenario is also a subset of the first parameter set of this reference scenario.

[0082] In actual application, since there may be more than one predefined scenario in the predefined scenario library whose similarity to the target scenario is greater than the set similarity threshold, when determining the scenario safety level of the target scenario based on the similar predefined scenario, it is necessary to select one predefined scenario from the determined at least one predefined scenario as the reference scenario to determine the scenario safety level of the target scenario. This reference scenario can be any one of the at least one predefined scenario. Of course, in order to make the reference scenario better match the target scenario, here, the predefined scenario with the greatest similarity among the at least one predefined scenario can be selected as the reference scenario. At this time, the parameter subset of the reference scenario can be used as the parameter subset of the target scenario. For example, if the parameter subset of the reference scenario is A = {own vehicle speed v1, own vehicle acceleration a1, inter-vehicle distance s, leading vehicle speed v2, leading vehicle acceleration a2}, then the parameter subset of the target scenario is also A = {own vehicle speed v1, own vehicle acceleration a1, inter-vehicle distance s, leading vehicle speed v2, leading vehicle acceleration a2}.

[0083] Step 403: Generate a subset of parameter values for the target scenario based on the subset of parameters of the reference scenario.

[0084] In the embodiment of the present application, since the subset of parameters of the target scenario is the same as the subset of parameters of the reference scenario, after determining the subset of parameters of the reference scenario, the subset of parameter values of the target scenario can be determined from the first set of parameter values of the target scenario according to the subset of parameters of the reference scenario. Moreover, the parameter values in the subset of parameter values correspond to the parameters in the subset of parameters, and the subset of parameter values is a subset of the first set of parameter values.

[0085] Step 404: Determine the target safety level of the target scenario according to the subset of parameters and the subset of parameter values.

[0086] In the embodiment of the present application, after determining the subset of parameters and the subset of parameter values of the target scenario, the value ranges of different safety levels corresponding to each parameter in the subset of parameters of the reference scenario can be determined as the value ranges of different safety levels corresponding to each parameter in the subset of parameters of the target scenario. Furthermore, according to the specific parameter values in the subset of parameter values of the target scenario, the parameter safety levels corresponding to each parameter in the subset of parameters can be determined, and thus, by synthesizing the parameter safety levels of each parameter, the target safety level of the target scenario can be determined.

[0087] For example, the subset of parameters of the reference scenario is A = {ego vehicle speed v1, ego vehicle acceleration a1, time to collision TTC, leading vehicle speed v2, leading vehicle acceleration a2}. As shown in Table 1, it is a schematic table of the value ranges of each parameter included in the subset of parameters A provided by the embodiment of the present application at different safety levels.

[0088] Level 1 (Unsafe) Level 2 (Caution Required) Level 3 (Safe) Own Vehicle Speed v1 (km / h) 120～340 60～120 0～60 <![CDATA[Acceleration a1 of the own vehicle (m / s 2 )]]> 5～7.84 3～5 0～3 Time to Collision TTC (s) 0～4 4～10 10 to Infinity Leading Vehicle Speed v2 (km / h) 0～20 20～60 60～340 <![CDATA[Acceleration of the vehicle ahead a2 (m / s 2 )]]> Negative Infinity to -6 -3 to -6 -3 to Positive Infinity

[0089] Table 1

[0090] When the subset of parameter values A' of the target scenario = {30, 2, 50, 100, 2.5}, according to the value ranges of different safety levels shown in Table 1, the parameter safety levels of the ego vehicle speed v1, ego vehicle acceleration a1, time to collision TTC, leading vehicle speed v2, and leading vehicle acceleration a2 are all at the 3rd level. Therefore, by synthesizing the parameter safety levels of these 5 parameters, it can be determined that the target safety level of the target scenario is the 3rd level, that is, the current target scenario is a safe scenario.

[0091] In an embodiment of the present application, when all parameters in the parameter subset of the target scenario are of the same parameter security level, the scenario security level corresponding to the target scenario can be determined. For example, when all parameters in the parameter subset are of the first level, the target security level of the target scenario is the first level. In the parameter subset, if there is a parameter with a different parameter security level from other parameters, the scenario security level of the target scenario can be directly set to the preset scenario security level. For example, it can be directly set to the above-mentioned first level (unsafe) or second level (attention required); or when the parameters belong to different security levels, the security level of the target scenario is determined according to the lowest security level corresponding to the parameters. For example, the parameters in the parameter subset belong to the second level and the third level respectively, and at this time, the second level is determined as the target security level of the target scenario. Of course, the specific scenario security level can be set according to user needs.

[0092] In a possible implementation manner, since it is necessary to select a similar predefined scenario from the predefined scenario library to determine the scenario security level of the target scenario, therefore, in an embodiment of the present application, it is also necessary to construct a predefined scenario library. And since the predefined scenario library contains the second parameter set, the second parameter value set, the parameter subset, and the parameter value subset corresponding to each predefined scenario, when constructing the predefined scenario library, it is necessary to determine the second parameter set, the second parameter value set, the parameter subset, and the parameter value subset corresponding to each predefined scenario. In an embodiment of the present application, since the process of determining the second parameter set, the second parameter value set, the parameter subset, and the parameter value subset corresponding to each predefined scenario is the same, therefore, the determination process of predefined scenario 1 is taken as an example for introduction, as Figure 5 shown, which is a schematic flowchart of a method for determining the parameter set and parameter value set of a predefined scenario provided by an embodiment of the present application. This method can be executed by the scenario security level determination device 10 in Figure 3 and the specific process is introduced as follows.

[0093] Step 501: Determine the second parameter set and the second parameter value set of predefined scenario 1 according to the values of each parameter of predefined scenario 1.

[0094] In an embodiment of the present application, when the vehicle is in predefined scenario 1, data of predefined scenario 1 can be collected through various sensors of the perception system. Similarly, based on the data collected for predefined scenario 1 according to the scenario quantitative classification description method, predefined scenario 1 can be defined, and then the second parameter set and the second parameter value set corresponding to predefined scenario 1 can be determined. Among them, the parameters included in the second parameter value set are all parameters for which parameter values can be collected for predefined scenario 1, including parameters with a parameter value of zero, and the parameter values in the second parameter value set correspond to the parameters in the second parameter set.

[0095] Step 502: Determine the parameter subset of predefined scenario 1 from the second parameter set according to the importance levels of the various parameters of predefined scenario 1.

[0096] In actual use, after determining the second parameter set of predefined scenario 1, the importance levels of the various parameters of predefined scenario 1 for judging the safety level of the scenario can be considered. For example, for predefined scenario 1 Figure 3 as shown in the figure, along the driving direction of vehicle A, there is vehicle B in the same lane and with the same driving direction in front of vehicle A. In this predefined scenario 1, it is easy for vehicle A and vehicle B to collide. Therefore, for this predefined scenario 1, the own vehicle speed v1, the own vehicle acceleration a1, the leading vehicle speed v2, the leading vehicle acceleration a2, the distance s between the two vehicles, and the time to collision TTC are all the main parameters affecting the safety of this predefined scenario 1. Thus, the importance levels of the own vehicle speed v1, the own vehicle acceleration a1, the leading vehicle speed v2, the leading vehicle acceleration a2, the distance s between the two vehicles, and the time to collision TTC for this predefined scenario 1 are relatively high. So, determine the parameter subset B of predefined scenario 1 from the second parameter set: B = {own vehicle speed v1, own vehicle acceleration a1, leading vehicle speed v2, leading vehicle acceleration a2, distance s between the two vehicles, time to collision TTC}.

[0097] Furthermore, since the parameter values in the second parameter value set correspond to the parameters in the second parameter set, according to the parameter subset of predefined scenario 1, the corresponding parameter value subset can be determined from the second parameter value set.

[0098] Step 503: Determine the value ranges of the parameters in the parameter subset corresponding to different safety levels according to the parameter value subset of predefined scenario 1.

[0099] In the embodiment of the present application, since the scenario safety level of this predefined scenario 1 is known, according to the scenario safety level of this predefined scenario 1, as well as the second parameter value set and the parameter value subset of this predefined scenario 1, the value ranges of the various parameters in the parameter subset of this predefined scenario 1 corresponding to different safety levels can be determined.

[0100] In a possible implementation manner, during actual use, the parameters can be divided into single parameters and non-single parameters. Here, the parameter value of the non-single parameter is correlated with the parameter values of at least one parameter in the parameter subset. For example, as Figure 3In the shown scenario, along the driving direction of vehicle A, there is vehicle B in the same lane as vehicle A and with the same driving direction in front of vehicle A. When the distance s between vehicle A and vehicle B is greater than a certain value, for vehicle A, regardless of the values of the self-vehicle speed v1 and the preceding-vehicle speed v2, the self-vehicle speed v1 and the preceding-vehicle speed v2 can both be classified into the safe level. That is, for two strongly correlated parameters, if the safety level of one parameter affects the safety level of the other parameter, for example, when one parameter meets a certain condition, the other parameter can be classified into the same category (safe / unsafe / attention required) regardless of how it changes, then these two strongly correlated parameters can both be called non-singular parameters.

[0101] As Figure 6 shown, it is a schematic flowchart of a process for determining the value range of the safety level provided by an embodiment of the present application. This method can be executed by the scenario safety level determination device 10 in Figure 3 as follows. The specific process is introduced as follows.

[0102] Step 601: Determine a reference parameter from at least two non-singular parameters according to the importance degree of at least two non-singular parameters to the driving safety of the predefined scenario.

[0103] Since there is an influencing and being influenced relationship between non-singular parameters. For example, for the above-mentioned inter-vehicle distance s, self-vehicle speed v1, and preceding-vehicle speed v2, among these three non-singular parameters, because the safety level of the inter-vehicle distance s affects the safety levels of the self-vehicle speed v1 and the preceding-vehicle speed v2, that is, the safety level of the inter-vehicle distance s determines the safety levels of the self-vehicle speed v1 and the preceding-vehicle speed v2. Therefore, when determining the value range of the safety level of non-singular parameters, it can be determined in stages. For the above example, the value range of the safety level of the inter-vehicle distance s can be determined first, and then based on the value range of the safety level of the inter-vehicle distance s, the value ranges of the self-vehicle speed v1 and the preceding-vehicle speed v2 can be determined.

[0104] Therefore, in the embodiment of the present application, a reference parameter can be determined from at least two non-singular parameters according to the importance degree of at least two non-singular parameters to the driving safety of the predefined scenario. For example, for the above-mentioned inter-vehicle distance s, self-vehicle speed v1, and preceding-vehicle speed v2, according to the importance degree of the speed v1, speed v2, and distance s to the driving safety of the predefined scenario, it can be known that the importance degrees of these three non-singular parameters are distance s > speed v1 > speed v2. Therefore, the distance s can be determined as the reference parameter.

[0105] Step 602: Determine the value range of the reference parameter at each safety level according to historical road measured data, historical simulation data, or empirical values.

[0106] In the embodiments of the present application, since the scenario safety level of the predefined scenario 1 is known, therefore, based on historical road measurement data, historical simulation data, or empirical values, the value ranges of the reference parameters at each safety level can be determined. For example, for the non-single parameter workshop distance s, according to experience, when the scenario safety level of the predefined scenario 1 is the 3rd level (safe), the value range corresponding to the workshop distance s is [1 km, +∞), then the value range of the workshop distance s at the parameter safety level of the 3rd level (safe) is [1 km, +∞).

[0107] Step 603: According to the value ranges of the reference parameters corresponding to each safety level, determine the value ranges of the remaining non-single parameters among the at least two parameters corresponding to each safety level respectively.

[0108] Furthermore, after determining the value ranges of the reference parameters corresponding to each safety level, the value ranges of the remaining non-single parameters corresponding to each safety level can be determined respectively according to the value ranges of the reference parameters at each safety level.

[0109] For example, as shown in Table 2, which is a schematic table of the value ranges of non-single parameters in different safety levels provided by the embodiments of the present application, continuing with the above example, when the parameter safety level of the workshop distance s is the 3rd level (safe), that is, the value range is [1 km, +∞), for vehicle A, since no matter what the self-vehicle speed v1 and the front-vehicle speed v2 are, the self-vehicle speed v1 and the front-vehicle speed v2 can be classified into the 3rd level (safe) category, therefore, according to the value range [1 km, +∞) of the workshop distance s at the 3rd level (safe), the value range of the self-vehicle speed v1 at the 3rd level (safe) can be determined to be any value. Similarly, the value range of the front-vehicle speed v2 at the 3rd level (safe) can be determined to be any value.

[0110] Level 1 (Unsafe) Level 2 (Caution Required) Level 3 (Safe) Inter-Vehicle Distance (km) 0～0.1 0.1～1 1 to Positive Infinity Own Vehicle Speed v1 (km / h) 120～340 60～120 Any Value Leading Vehicle Speed v2 (km / h) 0～20 20～60 Any Value

[0111] Table 2

[0112] Of course, for single parameters, the value ranges of each single parameter at each safety level can be directly determined based on historical road measurement data, historical simulation data, or empirical values.

[0113] In a possible implementation manner, the parameter subset of the predefined scenario can be determined in the following two ways.

[0114] (1) The parameter subset of the predefined scenario can be determined from the second parameter set according to the first importance levels corresponding to each parameter of the predefined scenario.

[0115] In the embodiments of the present application, the first importance level may be determined according to historical road measurement data or historical simulation data.

[0116] In actual use, the performance of the vehicle during road tests for autonomous driving can be determined through methods such as real vehicle road tests or simulation tests. For example, in the predefined scenario, according to the performance of the vehicle under different parameter values, such as whether the vehicle needs manual takeover, whether a traffic accident occurs to the vehicle, or whether the simulation results meet the expected effects, etc., to further determine the parameter subset that has the greatest impact on the safety definition of the predefined scenario and the parameter values (or parameter change ranges, change rates) corresponding to each key parameter in the parameter subset. Of course, based on the results obtained from continuous real vehicle road tests or simulations, the parameter subset and the change ranges or change rates of each key parameter included in the parameter subset can be continuously optimized to obtain the best parameter subset. Or, form a parameter set strategy with high pertinence for different application scenarios.

[0117] (2) The parameter subset of the predefined scenario can be determined from the second parameter set according to the second importance level corresponding to each parameter of the predefined scenario.

[0118] In the embodiments of the present application, the second importance level may be set according to empirical values.

[0119] In actual use, the parameter subset can also be determined for scenarios that are not easily obtained through real vehicle road tests or simulations by means of forward scenario analysis. That is, for specific scenarios, for example, for road scenarios in heavy snow days, foggy days, etc., the key parameters of the scenario can be analyzed according to empirical values to further determine the parameter subset that has the greatest impact on the safety definition of the predefined scenario and the parameter values corresponding to each key parameter in the parameter subset.

[0120] For scenarios such as Figure 3 shown, the key parameters used to define other scenarios, such as the number of lanes, lane line type, road type, road angle, signal strength, etc., have a relatively minor impact on the safety of the Figure 3 shown scenario. Therefore, according to experience, it can be determined that these parameters are not Figure 3 the key parameters of the shown scenario. And for specific environmental parameters, such as environmental parameters such as weather and light, unified settings can be made according to the system processing capabilities.

[0121] In a possible implementation manner, the parameter subset of the predefined scenario can also be determined in the following way.

[0122] First, according to the first importance levels corresponding to the respective parameters of the predefined scenario, a first parameter subset can be determined from the second parameter set. Then, according to the second importance levels corresponding to the respective parameters in the first parameter subset, a parameter subset of the predefined scenario can be determined from the first parameter subset. Since this method combines the two methods of determining the parameter subset based on historical road measurement data and historical simulation test data, and determining the parameter subset based on empirical values, the determined parameter subset is more accurate and more capable of affecting the safety of the predefined scenario.

[0123] In a possible implementation manner, when determining the control scenario, in order to make the selected similar scenario more matched with the target scenario, a similarity threshold is set. Only the predefined scenarios with a similarity greater than the set similarity threshold are likely to be selected as the control scenario. Therefore, when calculating the similarity between the target scenario and the predefined scenario, there will be another situation, that is, in the predefined scenario library, there is no predefined scenario with a similarity greater than the preset similarity threshold to the target scenario. Then, at this time, in order to improve the safety of the vehicle, the target safety level of the target scenario can be directly determined as the preset safety level, and the corresponding subsequent processing method can be set. For example, the safety level of the target scenario can be directly determined as the above-mentioned Level 1 (unsafe) or Level 2 (attention required). Of course, the specific safety level determined for the scenario can be set according to user needs.

[0124] In addition, in order to be able to identify the target scenario subsequently, in the embodiments of the present application, the target scenario can be added to the predefined scenario library, and the second parameter set, the second parameter value set, the parameter subset, and the parameter value subset of the target scenario can be determined in combination with the above step of "constructing the predefined scenario library".

[0125] In summary, in the embodiments of the present application, since the method of obtaining the similar scenario from the predefined scenario library and then obtaining the control scenario from the similar scenario is adopted to determine the target safety level of the target scenario, the safety level of the target scenario can be directly determined according to the safety level range corresponding to the control scenario, greatly shortening the determination time of the target scenario safety level, so as to be able to quickly adopt countermeasures for unknown scenarios and further improve the safety performance of the autonomous vehicle. At the same time, since the parameter subset is a subset of the first parameter set and does not include all the parameters in the first parameter set, when determining the scenario safety level of the target scenario, the calculation amount can be reduced and the processing efficiency can be improved to further shorten the determination time of the target scenario safety level and improve the safety performance of the autonomous vehicle. Furthermore, it can be seen that the method shown in the present application is not limited to judging whether a known scenario is safe, but also has corresponding judgment criteria and capabilities for whether an unknown scenario or the expansion of a known scenario is safe.

[0126] In addition, according to the method described in the embodiments of the present application, after quickly determining the safety level of the current target scenario, subsequent processing methods can be further configured. For example, when the safety level of the target scenario is relatively high, no additional processing is required, or the control parameters of the autonomous driving system can be adjusted accordingly to improve the safety level; when the safety level of the target scenario is relatively low, a prompt message can also be sent to the vehicle occupants or the background administrator through the autonomous driving system to prompt for manual takeover, ultimately enhancing the real-time scenario response ability of the autonomous driving vehicle.

[0127] As Figure 7 shown, based on the same inventive concept, an embodiment of the present application provides a scenario safety level determination device 70, which includes:

[0128] A similar scenario determination unit 701, configured to determine whether there is at least one predefined scenario in the predefined scenario library whose similarity to the target scenario is greater than a set similarity threshold according to a first parameter set and a first parameter value set of the target scenario in which the target vehicle is located; wherein, the parameters included in the first parameter set are all parameters for which parameter values can be collected for the target scenario, including parameters with parameter values of zero, and the parameter values in the first parameter value set correspond to the parameters in the first parameter set;

[0129] A control scenario determination unit 702, in response to at least one predefined scenario, selects one predefined scenario from the at least one predefined scenario as a control scenario; the control scenario has a parameter subset, and the parameter subset is a subset of the first parameter set of the target scenario;

[0130] A parameter value subset generation unit 703, configured to generate a parameter value subset of the target scenario according to the parameter subset of the control scenario, wherein the parameter values in the parameter value subset correspond to the parameters in the parameter subset, and the parameter value subset is a subset of the first parameter value set;

[0131] A safety level determination unit 704, configured to determine the target safety level of the target scenario according to the parameter subset and the parameter value subset.

[0132] Optionally, the safety level determination unit 704 is specifically configured to:

[0133] Determine the parameter safety level corresponding to each parameter in the parameter subset according to the value range corresponding to different safety levels of each parameter in the parameter subset and the parameter values in the parameter value subset; and,

[0134] Determine the target safety level of the target scenario according to the parameter safety level.

[0135] Optionally, the device further includes: a predefined scenario library construction unit 705, and the predefined scenario library construction unit is used for:

[0136] For each predefined scenario,

[0137] determine a second parameter set for the predefined scenario according to the value taken by each parameter of the predefined scenario; wherein, the parameters included in the second parameter set are all the parameters for which parameter values can be collected for the predefined scenario, including parameters with parameter values of zero;

[0138] determine a parameter subset of the predefined scenario from the second parameter set according to the importance degree of each parameter of the predefined scenario;

[0139] determine the value range corresponding to different security levels for each parameter in the parameter subset according to the second parameter value set and the parameter value subset, where the parameter values in the second parameter value set correspond to the parameters in the second parameter set, and the parameter values in the parameter value subset correspond to the parameters in the parameter subset.

[0140] Optionally, the predefined scenario library construction unit 705 is specifically configured to:

[0141] determine a parameter subset of the predefined scenario from the second parameter set according to the first importance degree corresponding to each parameter of the predefined scenario, where the first importance degree is determined according to historical road measured data or historical simulation test data; or,

[0142] determine a parameter subset of the predefined scenario from the second parameter set according to the second importance degree corresponding to each parameter of the predefined scenario, where the second importance degree is set according to empirical values.

[0143] Optionally, the predefined scenario library construction unit 705 is further specifically configured to:

[0144] determine the second parameter set of the predefined scenario according to the value taken by each parameter in the historical road measured data or historical simulation data of the predefined scenario;

[0145] determine a first parameter subset from the second parameter set according to the first importance degree corresponding to each parameter of the predefined scenario; where the first importance degree is determined according to historical road measured data or historical simulation test data; and,

[0146] determine the parameter subset of the predefined scenario from the first parameter subset according to the second importance degree corresponding to each parameter in the first parameter subset; where the second importance degree is set according to empirical values.

[0147] Optionally, the predefined scenario library construction unit 705 is further specifically configured to:

[0148] In response to at least two parameters of the predefined scenario being non-single parameters,

[0149] Determine a reference parameter from at least two parameters according to the importance degree of driving safety of a predefined scenario with respect to at least two parameters; wherein, the parameter value of a non-singular parameter is correlated with the parameter values of at least one parameter in the parameter subset.

[0150] Determine the value range of the reference parameter at each safety level according to historical road measurement data, historical simulation data or empirical values.

[0151] According to the value range of the reference parameter corresponding to each safety level, respectively determine the value ranges of the remaining non-singular parameters in the at least two parameters corresponding to each safety level.

[0152] Optionally, the safety level determination unit 704 is further configured to:

[0153] In response to the absence of at least one predefined scenario in the predefined scenarios with a similarity greater than a set similarity threshold with respect to the target scenario, determine the target safety level of the target scenario as a preset safety level.

[0154] Optionally, the predefined scenario library construction unit 705 is further configured to:

[0155] In response to the absence of at least one predefined scenario in the predefined scenarios with a similarity greater than a set similarity threshold with respect to the target scenario, add the target scenario to the predefined scenario library, and determine the second parameter set, the second parameter value set, the parameter subset and the parameter value subset of the target scenario in combination with the above steps of "constructing the predefined scenario library".

[0156] This device can be used to execute Figure 3 to Figure 6 the method described in the embodiments shown, therefore, for the functions that can be realized by each functional module of this device, reference can be made to Figure 3 to Figure 6 the description of the embodiments shown, and details are not repeated here. It should be noted that Figure 7 the functional units shown in the dashed boxes are non-essential functional units of this device.

[0157] Please refer to Figure 8 , based on the same technical concept, an embodiment of the present application also provides a computer device 80, which may include a memory 801 and a processor 802.

[0158] The memory 801 is used to store computer programs executed by the processor 802. The memory 801 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc.; the data storage area can store data created according to the use of the computer device, etc. The processor 802 can be a central processing unit (CPU) or a digital processing unit, etc. In the embodiments of the present application, the specific connection medium between the above-mentioned memory 801 and the processor 802 is not limited. In the embodiments of the present application Figure 8 it is connected between the memory 801 and the processor 802 through a bus 803. The bus 803 is represented by a thick line in Figure 8 and the connection manners between other components are only for illustrative purposes and are not to be taken as limiting. The bus 803 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 8 it is only represented by a thick line in, but it does not mean that there is only one bus or one type of bus.

[0159] The memory 801 can be a volatile memory, such as a random-access memory (RAM); the memory 801 can also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), or the memory 801 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 801 can be a combination of the above-mentioned memories.

[0160] The processor 802 is used to execute the method executed by the device in the embodiments shown in Figure 3 to Figure 6 when calling the computer program stored in the memory 801.

[0161] In some possible implementation manners, each aspect of the method provided in the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a computer device, the program code is used to cause the computer device to execute the steps in the methods according to various exemplary embodiments of the present application described above in this specification. For example, the computer device can execute the method described in the embodiments shown in Figure 3 to Figure 6

[0162] ​Those of ordinary skill in the art will understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments. The aforementioned storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs. Alternatively, if the above integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0163] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present application.

[0164] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these changes and modifications.

Claims

1. A method for determining the scene safety level, characterized in that The method includes: Based on a first parameter set and a first parameter value set of a target scenario where the target vehicle is located, determining whether there is at least one predefined scenario in a predefined scenario library whose similarity to the target scenario is greater than a set similarity threshold; wherein, the parameters included in the first parameter set are all the parameters for which parameter values are collected for the target scenario, and the parameter values in the first parameter value set correspond to the parameters in the first parameter set; In response to the at least one predefined scenario, selecting one predefined scenario from the at least one predefined scenario as a control scenario; the control scenario has a parameter subset, and the parameter subset is a subset of the first parameter set of the target scenario; Generating a parameter value subset of the target scenario according to the parameter subset of the control scenario; wherein, the parameter values in the parameter value subset correspond to the parameters in the parameter subset, and the parameter value subset is a subset of the first parameter value set; and, Determining a target safety level of the target scenario according to the parameter subset and the parameter value subset; Wherein, the method further includes: In response to there being at least two non - single - valued parameters in the predefined scenario that have an influencing and an influenced relationship, Determining a reference parameter from the at least two parameters according to the importance of the at least two parameters to the driving safety of the predefined scenario; Determining the value range of the reference parameter at each safety level; According to the value range of the reference parameter at each safety level, respectively determining the value ranges of the remaining non - single - valued parameters in the at least two parameters corresponding to each safety level.

2. The method according to claim 1, wherein The determining the target safety level of the target scenario according to the parameter subset and the parameter value subset includes: Determining the parameter safety levels corresponding to the parameters in the parameter subset according to the value ranges of the parameters in the parameter subset corresponding to different safety levels and the parameter values in the parameter value subset; and, Determining the target safety level of the target scenario according to the parameter safety levels.

3. The method according to claim 1, wherein The method further includes: constructing a predefined scenario library, the predefined scenario library includes at least one predefined scenario, and the constructing the predefined scenario library specifically includes: For each predefined scenario, Determining a second parameter set and a second parameter value set of the predefined scenario according to the value of each parameter of the predefined scenario; wherein, the parameters included in the second parameter set are all the parameters for which parameter values are collected for the predefined scenario, and the parameter values in the second parameter value set correspond to the parameters in the second parameter set; Determining the parameter subset of the predefined scenario from the second parameter set according to the importance of each parameter of the predefined scenario; Determining the value ranges of the parameters in the parameter subset corresponding to different safety levels according to the parameter value subset, and the parameter values in the parameter value subset correspond to the parameters in the parameter subset.

4. The method according to claim 3, characterized in that The determining the parameter subset of the predefined scenario from the second parameter set according to the importance of each parameter of the predefined scenario includes: Determine a parameter subset of the predefined scenario from the second parameter set according to the first importance level corresponding to each parameter of the predefined scenario, where the first importance level is determined according to historical road measurement data or historical simulation data; or, Determine a parameter subset of the predefined scenario from the second parameter set according to the second importance level corresponding to each parameter of the predefined scenario, where the second importance level is set according to empirical values.

5. The method according to claim 3, characterized in that Determining the parameter subset of the predefined scenario from the second parameter set according to the importance level of each parameter of the predefined scenario includes: Determine a first parameter subset from the second parameter set according to the first importance level corresponding to each parameter of the predefined scenario; where the first importance level is determined according to historical road measurement data or historical simulation data; and, Determine the parameter subset of the predefined scenario from the first parameter subset according to the second importance level corresponding to each parameter in the first parameter subset; where the second importance level is set according to empirical values.

6. The method according to claim 1, wherein The parameter value of the non-singularity parameter is related to the parameter values of at least one parameter in the parameter subset; Determining the value range of the reference parameter at each safety level includes: Determine the value range of the reference parameter at each safety level according to historical road measurement data, historical simulation data or empirical values.

7. The method according to claim 1, wherein The method further includes: In response to the fact that there is no at least one predefined scenario in the predefined scenario whose similarity to the target scenario is greater than a set similarity threshold, determine that the target safety level of the target scenario is a preset safety level.

8. The method according to claim 1, wherein The method further includes: In response to the fact that there is no at least one predefined scenario in the predefined scenario whose similarity to the target scenario is greater than a set similarity threshold, add the target scenario to the predefined scenario library.

9. A device for determining the safety level of a scenario, characterized in that, The device includes: A similar scenario determination unit, configured to determine whether there is at least one predefined scenario in the predefined scenario library whose similarity to the target scenario is greater than a set similarity threshold according to a first parameter set and a first parameter value set of the target scenario in which the target vehicle is located; where the parameters included in the first parameter set are all the parameters for which parameter values can be collected for the target scenario, and the parameter values in the first parameter value set correspond to the parameters in the first parameter set; A comparison scenario determination unit, in response to the at least one predefined scenario, select a predefined scenario from the at least one predefined scenario as a comparison scenario; the comparison scenario has a parameter subset, and the parameter subset is a subset of the first parameter set of the target scenario; A parameter value subset generation unit, configured to generate a parameter value subset of the target scenario according to the parameter subset of the comparison scenario; where the parameter values in the parameter value subset correspond to the parameters in the parameter subset, and the parameter value subset is a subset of the first parameter value set; and, A safety level determination unit, configured to determine the target safety level of the target scenario according to the parameter subset and the parameter value subset; Among them, the device further includes a predefined scenario library construction unit, and the predefined scenario library construction unit is configured to: In response to there being at least two non-singular parameters in the predefined scenario whose parameters have an influencing and influenced relationship, Determine a reference parameter from the at least two parameters according to the importance degree of the at least two parameters to the driving safety of the predefined scenario; wherein, the parameter value of the non-singular parameter is related to the parameter value of at least one parameter in the parameter subset; Determine the value range of the reference parameter at each safety level; According to the value range of the reference parameter at each safety level, respectively determine the value ranges of the remaining non-singular parameters in the at least two parameters corresponding to each safety level.

10. The device according to claim 9, characterized in that, The safety level determination unit is specifically configured to: Determine the parameter safety levels corresponding to the parameters in the parameter subset according to the value ranges of the parameters in the parameter subset corresponding to different safety levels and the parameter values in the parameter value subset; And, Determine the target safety level of the target scenario according to the parameter safety levels.

11. The device according to claim 9, wherein The device further includes: a predefined scenario library construction unit, the predefined scenario library includes at least one predefined scenario, and the predefined scenario library construction unit is configured to: For each predefined scenario, Determine the second parameter set and the second parameter value set of the predefined scenario according to the value of each parameter of the predefined scenario; wherein, the parameters included in the second parameter set are all the parameters for which parameter values are collected for the predefined scenario, and the parameter values in the second parameter value set correspond to the parameters in the second parameter set; Determine the parameter subset of the predefined scenario from the second parameter set according to the importance degree of each parameter of the predefined scenario; Determine the value ranges of the parameters in the parameter subset corresponding to different safety levels according to the parameter value subset, and the parameter values in the parameter value subset correspond to the parameters in the parameter subset.

12. The device according to claim 11, characterized in that, The predefined scenario library construction unit is specifically configured to: Determine the parameter subset of the predefined scenario from the second parameter set according to the first importance degree corresponding to each parameter of the predefined scenario, wherein the first importance degree is determined according to historical road measurement data or historical simulation data; or, Determine the parameter subset of the predefined scenario from the second parameter set according to the second importance degree corresponding to each parameter of the predefined scenario, wherein the second importance degree is set according to empirical values.

13. The device according to claim 11, wherein The predefined scenario library construction unit is specifically further configured to: Determine the second parameter set of the predefined scenario according to the values of the respective parameters in the historical road measurement data or historical simulation data of the predefined scenario; Determine a first parameter subset from the second parameter set according to the first importance degree corresponding to each parameter of the predefined scenario; wherein the first importance degree is determined according to historical road measurement data or historical simulation data; and, Determine a parameter subset of the predefined scenario from the first parameter subset according to the second importance degrees corresponding to the parameters in the first parameter subset; wherein, the second importance degrees are set according to empirical values.

14. The device according to claim 11, wherein The parameter value of the non-unity parameter is related to the parameter values of at least one parameter in the parameter subset; The determining the value range of the reference parameter at each safety level includes: Determine the value range of the reference parameter at each safety level according to historical road measurement data, historical simulation data or empirical values.

15. The device according to claim 11, wherein The predefined scenario library construction unit is specifically further configured to: In response to the fact that there is no at least one predefined scenario in the predefined scenario whose similarity to the target scenario is greater than the set similarity threshold, add the target scenario to the predefined scenario library.

16. The device according to claim 9, characterized in that The safety level determination unit is further configured to: In response to the fact that there is no at least one predefined scenario in the predefined scenario whose similarity to the target scenario is greater than the set similarity threshold, determine that the target safety level of the target scenario is a preset safety level.

17. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

18. A computer storage medium, on which computer program instructions are stored, characterized in that, When the computer program instructions are executed by the processor, the method according to any one of claims 1 to 8 is implemented.

Images