CN115723776A

CN115723776A - Automatic driving decision method, device, equipment and storage medium

Info

Publication number: CN115723776A
Application number: CN202111009626.5A
Authority: CN
Inventors: 吴楠
Original assignee: Beijing Tusen Weilai Technology Co Ltd
Current assignee: Beijing Tusen Weilai Technology Co Ltd
Priority date: 2021-08-31
Filing date: 2021-08-31
Publication date: 2023-03-03

Abstract

The application provides an automatic driving decision-making method, device, equipment and storage medium, relates to the technical field of automatic driving, and is used for improving the response capability of an automatic driving vehicle to an unknown scene. The method comprises the following steps: determining a target safety level of a target scene according to a first parameter set and a first parameter value set of the target scene where a target vehicle is located; when the target safety level is lower than a first safety level threshold, determining whether a driver is present on the target vehicle; when the driver is determined to exist, outputting a first prompt signal, wherein the first prompt signal is used for prompting the driver that the safety level of the target scene is low; or when the driver does not exist, sending a second prompt signal to a background server, wherein the second prompt signal is used for prompting a background manager that the safety level of the target scene is low.

Description

Automatic driving decision method, device, equipment and storage medium

Technical Field

The application relates to the technical field of automatic driving, and provides an automatic driving decision method, an automatic driving decision device, an automatic driving decision equipment and a storage medium.

Background

At present, with the gradual development of the automobile industry, automatic Vehicles (AV) have come into existence, and by virtue of the advantages of being capable of adapting to more people, relieving traffic congestion, improving road safety and the like, the AV has gradually become a development trend of the automobile industry in the future. However, since the driving scenes corresponding to the autonomous vehicles are complex and variable, the autonomous driving scenes have the characteristics of uncertainty, unpredictability, inexhauseness and the like, and further, when the autonomous vehicles face unknown scenes, it is difficult to obtain the unmanned driving performance of the autonomous vehicles, and whether the autonomous vehicles can safely pass qualitative judgment of the unknown scenes, so that whether the unknown scenes are safe or not can not be judged in time, reasonable coping strategies cannot be made, and intervention or intervention cannot be searched for from a driver or an operation side in time to decide or control the autonomous vehicles, and finally unreasonable risks are caused, thereby reducing the coping capability of the autonomous vehicles for the unknown scenes.

Therefore, how to improve the response capability of the automatic driving vehicle to an unknown scene is an urgent problem to be solved.

Disclosure of Invention

The embodiment of the application provides an automatic driving decision method, an automatic driving decision device, an automatic driving decision equipment and a storage medium, which are used for improving the response capability of an automatic driving vehicle to an unknown scene.

In one aspect, an automated driving decision method is provided, the method comprising:

determining a target safety level of a target scene according to a first parameter set and a first parameter value set of the target scene where a target vehicle is located; the parameters contained in the first parameter set are all parameters of parameter values acquired aiming at the target scene, and the parameter values in the first parameter set correspond to the parameters in the first parameter set;

determining whether a driver is present on the target vehicle when the target safety level is below a first safety level threshold;

when the driver is determined to exist, outputting a first prompt signal, wherein the first prompt signal is used for prompting the driver that the safety level of the target scene is low; alternatively, the first and second liquid crystal display panels may be,

and when determining that no driver exists, sending a second prompt signal to a background server, wherein the second prompt signal is used for prompting a background manager that the safety level of the target scene is low.

In one aspect, an automated driving decision device is provided, the device comprising:

the first determining unit is used for determining a target safety level of a target scene according to a first parameter set and a first parameter value set of the target scene where a target vehicle is located; the parameters contained in the first parameter set are all parameters of parameter values acquired aiming at the target scene, and the parameter values in the first parameter set correspond to the parameters in the first parameter set;

a second determination unit for determining whether a driver is present on the target vehicle when the target safety level is lower than a first safety level threshold;

the first prompting unit is used for outputting a first prompting signal when the existence of a driver is determined, wherein the first prompting signal is used for prompting the driver that the safety level of the target scene is low; alternatively, the first and second electrodes may be,

and the second prompting unit is used for sending a second prompting signal to the background server when the driver is determined not to exist, wherein the second prompting signal is used for prompting a background manager that the safety level of the target scene is low.

Optionally, the first determining unit is specifically configured to:

judging whether at least one predefined scene with similarity greater than a set similarity threshold exists in a predefined scene library according to a first parameter set and a first parameter value set of a target scene where a target vehicle is located;

in response to the presence of the at least one predefined scene, selecting one predefined scene from the at least one predefined scene as a control scene; the control scene has a subset of parameters that is a subset of a first set of parameters of the target scene;

generating a parameter value subset of the target scene according to the parameter subset of the comparison scene; wherein parameter values in the subset of parameter values correspond to parameters in the subset of parameters, the subset of parameter values being a subset of the first set of parameter values;

and determining the target safety level of the target scene according to the parameter subset and the parameter value subset.

Optionally, the first determining unit is specifically further configured to:

in response to the absence of at least one predefined scenario, determining a target security level of the target scenario to be a first preset security level, the first preset security level being lower than the first security level threshold.

Optionally, the first prompting unit is further specifically configured to:

if the target security level is lower than a first security level threshold and higher than a second security level threshold, the first prompt signal is output in a delayed mode; the first security level threshold is higher than the second security level threshold;

and if the target safety level is lower than the second safety level threshold, immediately outputting the first prompt signal.

Optionally, after sending the second prompt signal to the background server, the second prompt unit is further specifically configured to:

receiving a remote control signal sent by the background server, and controlling the target vehicle to run based on an operation instruction of the remote control signal; the remote control signal is generated by the background server after a background administrator makes a decision operation on the prompt signal.

In one aspect, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of the above aspect when executing the computer program.

In one aspect, a computer storage medium is provided having computer program instructions stored thereon that, when executed by a processor, implement the steps of the method of the above aspect.

In the embodiment of the application, the target safety level of the target scene can be determined according to the first parameter set and the first parameter value set of the target scene where the target vehicle is located; when the target safety level is lower than the first safety level threshold, whether a driver exists on the target vehicle or not is determined; when the driver is determined to exist, outputting a first prompt signal to prompt the driver that the safety level of the target scene is low; or when the driver is determined not to exist, a second prompt signal can be sent to the background server to prompt the background manager that the safety level of the target scene is low. Therefore, in the embodiment of the application, after whether the target scene is safe is determined according to the target safety level, the prompt signal can be timely sent to the driver or a background manager when the target scene is determined to be low in safety, and then when safety risks occur, the automatic driving automobile can be timely taken over or assisted to plan, so that the overall risk coping capability of the automatic driving system is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments or related technologies of the present application, the drawings used in the description of the embodiments or related technologies will be briefly introduced below, it is obvious that the drawings in the description below are only the embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a schematic diagram of a division scenario provided in an embodiment of the present application;

FIG. 2 is a schematic diagram of an embodiment of the present application for reducing unsafe scenarios;

fig. 3 is a schematic view of an application scenario provided in an embodiment of the present application;

FIG. 4 is a schematic flow chart of an automatic driving decision method according to an embodiment of the present application;

fig. 5 is a schematic flowchart of determining a security level of a scene according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of an automatic driving decision device according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application. In the present application, the embodiments and features of the embodiments may be arbitrarily combined with each other without conflict. Also, while a logical order is shown in the flow diagrams, in some cases, the steps shown or described may be performed in an order different than here.

First, some terms in the present application will be explained.

(1) An automatic driving automobile, also called an unmanned automobile, a computer driving automobile or a wheeled mobile robot, is an intelligent automobile which realizes unmanned driving through a computer system. The automatic driving automobile depends on the cooperation of artificial intelligence, visual calculation, radar, monitoring device and global positioning system, so that the computer can automatically and safely operate the motor vehicle to move without any active operation of human.

(2) The driverless rating, society of Automotive Engineers (SAE), defines 6 driverless ratings, respectively rating 0 (fully manual) to 5 (fully automatic).

(3) The scene refers to the combination of driving occasions and driving scenes, and is deeply influenced by driving environments, such as roads, traffic, weather, illumination and other factors, and jointly forms the whole scene concept. The scene is a comprehensive reflection of the environment and the driving behavior in a certain time and space range, and describes external states such as roads, traffic facilities, meteorological conditions, traffic participants and the like and information such as driving tasks and states of the own vehicle.

(4) A scene quantitative classification description method is a method for quantitatively describing a target scene based on data acquired by a vehicle perception system aiming at the target scene, namely classifying perception results of other traffic participants and scene elements in a self-vehicle state, and quantitatively describing the target scene based on corresponding parameters in each scene element. The scene elements may be divided into traffic participants (objects), road conditions, environments, behaviors, and the like.

Currently, for the characteristics of uncertainty, unpredictability, inexhaustibility and the like of an automatic driving scene, a new standard, namely a Safety of expected function of a road vehicle (SOTIF) standard, is proposed by the International Organization for Standardization (ISO), and the SOTIF standard belongs to ISO/PAS 21448: the Road Vehicles standard, the ISO/PAS 21448 standard, is applicable to functions requiring proper environmental awareness, and concerns how to ensure the safety of the target function without vehicle failure, which is in sharp contrast to conventional functional safety (concerns how to reduce safety risks due to system failure).

Based on the SOTIF standard, for the automatic driving scenario, as shown in fig. 1, for a schematic diagram of the divided scenario provided in the embodiment of the present application, any scenario may be divided into four categories shown in fig. 1, namely, four categories, namely, a known safe scenario (Area 1), a known unsafe scenario (Area 2), an unknown unsafe scenario (Area 3), and an unknown safe scenario (Area 4).

The goal of the SOTIF standard is to evaluate two types of unsafe scenarios, namely Area2 and Area3, and further, as shown in fig. 2, a schematic diagram for reducing the unsafe scenarios provided in the embodiment of the present application may reduce the areas corresponding to the two types of unsafe scenarios, namely Area2 and Area3, through a series of technical measures, and simultaneously provide evidence that the two areas are small enough to allow the remaining residual hazard to be accepted. In addition, in the process, since the areas corresponding to the two unsafe scenes of Area2 and Area3 are reduced, the Area corresponding to Area1 is generally increased.

Further, when Area2 is evaluated, a risk scene with risks in Area2 can be identified by performing security analysis on Area2, and then a coping strategy is developed for the risk scene, so that a real-time simulation environment is built or a real-vehicle test is designed according to a known scene, and the strategy is optimized according to an experiment result, so that the Area corresponding to Area2 is gradually reduced.

When the Area3 is evaluated, the Area3 can be specifically processed in the following two ways, namely, the Area occupied by the Area3 can be reduced by improving the reliability of functions of vehicle systems and parts; the other way is to reduce the Area occupied by Area3 by accumulating a large amount of data through a real-vehicle road test or a simulation test, and in this way, the more data are accumulated, the more an unknown scene can be changed into a known scene.

However, the automatic driving scene has the characteristics of uncertainty, unpredictability, inexhauseness and the like, so that the service scenes recorded by the automatic driving vehicle are limited, and further, when the automatic driving vehicle faces an unknown scene, the risk that the safety level of the unknown scene cannot be identified rapidly exists, and the problems that the traffic safety cannot be guaranteed and the like occur.

Based on this, in the embodiment of the application, the target safety level of the target scene can be determined according to the first parameter set and the first parameter value set of the target scene where the target vehicle is located; when the target safety level is lower than the first safety level threshold, whether a driver exists on the target vehicle or not is determined; when the driver is determined to exist, outputting a first prompt signal to prompt the driver that the safety level of the target scene is low; or when the driver is determined not to exist, a second prompt signal can be sent to the background server to prompt the background manager that the safety level of the target scene is low. Therefore, in the embodiment of the application, after whether the target scene is safe is determined according to the target safety level, the prompt signal can be timely sent to the driver or a background manager when the target scene is determined to be low in safety, and then when safety risks occur, the automatic driving automobile can be timely taken over or assisted to plan, so that the overall risk coping capability of the automatic driving system is improved.

After introducing the design concept of the embodiment of the present application, some simple descriptions are provided below for application scenarios to which the technical solution of the embodiment of the present application can be applied, and it should be noted that the application scenarios described below are only used for describing the embodiment of the present application and are not limited. In a specific implementation process, the technical scheme provided by the embodiment of the application can be flexibly applied according to actual needs.

As shown in fig. 3, an application scenario provided for the embodiment of the present application is schematically illustrated, where the application scenario for automatic driving decision may include an automatic driving decision apparatus 10, a driver terminal 11, and a background server 12.

In the embodiment of the present application, the automatic driving decision device 10 may be configured to, after determining the safety level of the scene where the vehicle is located, quickly decide whether the automatic driving vehicle needs to seek intervention or intervention from a driver or a background administrator, so as to assist the automatic driving vehicle in driving, and further improve the overall risk response capability of the automatic driving system.

The automatic driving decision device 10 may be specifically a vehicle-mounted computer, a personal computer, or the like provided on the automatic driving vehicle. And the autopilot decision making apparatus 10 may include one or more processors 101, memory 102, input/output (I/O) interface 103, and database 104, among other things. The memory of the automatic driving decision device 10 may store program instructions of the automatic driving decision method provided in the embodiment of the present application, and when the program instructions are executed by the processor, the program instructions can be used to implement the steps of the automatic driving decision method provided in the embodiment of the present application.

The driver terminal 11 may be configured to receive the first prompt signal sent by the automatic driving decision device 10 to prompt that the security level of the target scene where the driver on the target vehicle is currently located is low, so that the driver terminal 11 may be an on-board computer on the target vehicle, that is, may directly output the corresponding first prompt signal on the on-board computer. Of course, the driver terminal 11 may be a mobile phone, a notebook computer, a tablet computer (PAD), or the like.

The background server 12 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a CDN, and a big data and artificial intelligence platform, but is not limited thereto.

In practical applications, when the automatic driving decision device 10 determines that the scene safety level of the target scene in which the target vehicle is currently located is lower than the first safety level threshold, it is determined whether a driver is present on the current target vehicle. When it is determined that the driver is present, the automatic driving decision-making device 10 may output a first prompt signal to the driver terminal 11 to prompt that the security level of the target scene of the driver is low, or, when it is determined that the driver is not present, the automatic driving decision-making device 10 may send a second prompt signal to the background server 12 to prompt that the security level of the target scene of the background manager is low. Furthermore, the driver can decide whether to take over manually or not, or a background manager can decide whether to carry out remote intervention and other operations so as to assist the target vehicle in driving, and further improve the overall risk coping capability of the automatic driving system.

Of course, the method provided in the embodiment of the present application is not limited to be used in the application scenario shown in fig. 1, and may also be used in other possible application scenarios, and the embodiment of the present application is not limited. Functions that can be implemented by each device of the application scenario shown in fig. 1 will be described together in the subsequent method embodiment, and will not be described in detail herein. Hereinafter, the method of the embodiment of the present application will be described with reference to the drawings.

Fig. 4 is a schematic flow chart of an automatic driving decision method provided in the embodiment of the present application, which may be executed by the automatic driving decision apparatus 10 in fig. 3, and the flow chart of the method is described as follows.

Step 401: and determining the target safety level of the target scene according to the first parameter set and the first parameter value set of the target scene where the target vehicle is located.

In this embodiment of the present application, the parameters included in the first parameter set are all parameters that can acquire parameter values for a target scene, including parameters whose parameter values are zero, and excluding parameters that do not exist or are failed to acquire, where the parameter values in the first parameter set correspond to the parameters in the first parameter set.

In practical application, when a target vehicle is in a target scene, the target vehicle acquires data of the target scene where the target vehicle is located through each sensor of the sensing system, and describes the target scene based on the acquired data through a scene quantitative classification description method. Therefore, in the embodiment of the present application, a first parameter set and a first parameter value set for describing the target scene may be generated based on the acquired data.

Furthermore, in order to quickly determine the security level of the target scene, in the embodiment of the present application, a predefined scene similar to the target scene may be selected from a predefined scene library to determine the security level of the target scene. The method specifically includes determining similarity between a target scene and a predefined scene according to the similarity between a first parameter set of the target scene and a second parameter set of the predefined scene, and then selecting a comparison scene which can be used for comparison of the target scene from a predefined scene library according to the determined similarity, so that a target security level of the target scene is determined according to value ranges of the comparison scene corresponding to different security levels and specific parameter values of a first parameter value set of the target scene. The parameters contained in the second parameter set are all parameters of which the parameter values can be acquired aiming at the predefined scene, including the parameter of which the parameter value is zero, and not including the parameters of which the acquisition fails and does not exist.

Step 402: when the target safety level is lower than the first safety level threshold, it is determined whether a driver is present on the target vehicle.

In the application embodiment, the first security level threshold may be used to measure whether the target scene is safe. When the target security level is not less than the first security level threshold, the target scene is a security scene, and when the target security level is less than the first security level threshold, the target scene is not a security scene. In addition, how to set the first security level threshold specifically can be set according to the requirement of the user.

Furthermore, in order to improve the risk response capability of the whole automatic driving system when the automatic driving vehicle encounters a safety risk, the occurrence of a safety accident can be avoided. Therefore, in the application embodiment, after the target security level of the target scene is determined, whether the target scene is safe or not is determined according to the determined target security level, that is, whether the target security level is lower than the first security level threshold or not is determined, and when the target scene is not lower than the first security level threshold, that is, the target scene is safe, the automatic driving vehicle can drive according to the originally set driving strategy.

In addition, if the driver is always on the target vehicle during driving, when the target vehicle encounters an unsafe scene, the driver can more intuitively determine what the current unsafe scene is specifically, and can make a corresponding decision on the current unsafe scene more timely, so that in order to process the current unsafe scene as soon as possible, when the target safety level is determined to be lower than the first safety level threshold, that is, when the target scene is an unsafe scene, whether the driver exists on the target vehicle can be determined first, and then how to perform the next decision operation can be further determined.

Step 403: when the presence of the driver is determined, a first prompt signal is output.

In the implementation of the application, the first prompt signal can be used for prompting the driver that the safety level of the target scene is low.

In order to process the current unsafe scene as soon as possible, when the driver is determined to be present, the first prompt signal may be directly output to the driver terminal 11 (for example, an in-vehicle computer) to prompt the driver that the target scene is low in safety level and needs to pay attention to safety, or the assistant driving is needed to improve the overall risk coping capability of the automatic driving system.

Step 404: and when the driver is determined not to exist, sending a second prompt signal to the background server.

In the implementation of the present application, the second prompt signal may be used to prompt that the security level of the target scene of the background administrator is low.

When it is determined that no driver exists, in order to improve the overall risk response capability of the automatic driving system, a second prompt signal may be sent to the background server to prompt a background manager that the target scene is low in safety level and needs to pay attention to safety, or auxiliary driving needs to be performed. Furthermore, the background administrator may further determine how to make an aid decision according to the situation of the current target scene, for example, send an instruction of the aid decision to the autonomous vehicle, such as normal driving, lane changing, deceleration, parking, turning around, and the like. Of course, the instructions can be completely completed by the automatic driving system, and a background manager can directly and remotely take over the whole vehicle control right of the automatic driving vehicle so as to remotely control the automatic driving vehicle.

In a possible implementation manner, since the automatic driving scenario has the characteristics of uncertainty, unpredictability, inexhaustibility and the like, the business scenarios recorded by the automatic driving vehicle are limited, however, in order to further improve the overall risk coping capability of the automatic driving system, so as to take coping strategies for the safety risks in time, in the embodiment of the present application, the decision time may be shortened by specifically identifying the safety level of each scenario, so as to take coping measures for the scenario with the risk in time, so as to improve the overall risk coping capability of the automatic driving system.

Fig. 4 is a schematic flowchart of a process for determining a scene security level according to an embodiment of the present application, which may be performed by the scene security level determining apparatus 10 in fig. 3, and the process of the process is described as follows.

Step 501: and judging whether at least one predefined scene with the similarity greater than a set similarity threshold exists in the predefined scene library according to the first parameter set and the first parameter value set of the target scene where the target vehicle is located.

In an embodiment of the application, the parameter values in the first parameter value set correspond to parameters in the first parameter set. The parameters included in the first parameter set are all parameters of parameter values that can be acquired by the target vehicle for the target scene, the predefined scene library includes 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 of which the importance degree of the driving safety degree of the corresponding predefined scene is greater than a set importance degree threshold value, that is, main parameters that can influence whether the corresponding predefined scene is safe or not, and the parameter values in the parameter value subset correspond to the parameters in the parameter subset.

In practical application, when a target vehicle is in a target scene, the target vehicle acquires data of the target scene where the target vehicle is located through each sensor of the sensing system, and defines the target scene based on the acquired data through a scene quantitative classification description method. Therefore, in the embodiment of the present application, after data acquisition of a target scene, a first parameter set and a first parameter value set for defining the target scene may be generated based on the acquired data.

For example, the first parameter set may be S ₁ = { the speed v1 of the vehicle, the acceleration a1 of the vehicle, the VL of the lane in which the vehicle is located, the inter-vehicle distance s, the speed v2 of the vehicle ahead, the acceleration a2 of the vehicle ahead, the type Veh of the vehicle ahead, the moving direction Hd of the vehicle ahead, the road type RT, the road speed limit RSL, the road angle RA, the number RLN of the lanes, the road visibility RV, the wind speed WS, the illumination condition LC, the signal intensity SL, \8230 }, and the first parameter value set is N ₁ = own vehicle speed v1=60km/h, own vehicle acceleration a1=2m/s, \8230;, vehicle-to-vehicle distance s =50m, preceding vehicle speed v2=55km/h, preceding vehicle acceleration a2=2m/s, \8230; }.

Furthermore, in the embodiment of the present application, for the purpose of quickly determining the security level of the target scene, a predefined scene similar to the target scene may be selected from a predefined scene library for determination, and certainly, in order to further ensure that the selected predefined scene can be more matched with the target scene, when the similar predefined scene is selected, a similarity threshold may be set, so that when the similarity between the target scene and the predefined scene is greater than the set similarity threshold, the security level of the target scene may be determined based on the predefined scene greater than the set similarity threshold. The similarity between the target scene and the predefined scene can be determined by adopting a cosine similarity solving mode.

Therefore, in the embodiment of the present application, after the first parameter set and the first parameter value set of the target scene are determined, the similarity between the first parameter set of the target scene and the second parameter set of each predefined scene in the predefined scene library is determined, and then it is determined whether at least one predefined scene with a similarity greater than the set similarity threshold exists in the predefined scene library, so that when at least one predefined scene with a similarity greater than the set similarity threshold exists, the scene security level determination may be performed on the target scene through the at least one predefined scene.

Step 502: in response to the at least one predefined scene, one predefined scene is selected from the at least one predefined scene as a control scene.

In an embodiment of the application, the control scene has a subset of parameters, which is a subset of the first set of parameters of the target scene. Of course, the control scene has a subset of parameters that is also a subset of the first parameter set of the control scene.

In practical applications, since there may be more than one predefined scene with similarity greater than the set similarity threshold value with the target scene in the predefined scene library, when determining the scene security level of the target scene based on the similar predefined scenes, it is necessary to select one predefined scene from the determined at least one predefined scene as a comparison scene to determine the scene security level of the target scene. The comparison scenario may be any one of the at least one predefined scenario, and of course, in order to make the comparison scenario and the target scenario more matched, a predefined scenario with the greatest similarity in the at least one predefined scenario may be selected as the comparison scenario, at this time, a parameter subset of the comparison scenario may be used as a parameter subset of the target scenario, for example, the parameter subset of the comparison scenario is a = { the vehicle speed v1, the vehicle acceleration a1, the vehicle-to-vehicle distance s, the vehicle-to-vehicle speed v2, the vehicle-to-vehicle acceleration a2}, and then the parameter subset of the target scenario is a = { the vehicle speed v1, the vehicle acceleration a1, the vehicle-to-vehicle distance s, the vehicle-to-vehicle speed v2, the vehicle-to-vehicle acceleration a2}.

Step 503: and generating a parameter value subset of the target scene according to the parameter subset of the comparison scene.

In the embodiment of the present application, since the parameter subset of the target scene is the same as the parameter subset of the control scene, after the parameter subset of the control scene is determined, the parameter value subset of the target scene may be determined from the first parameter value set of the target scene according to the parameter subset of the control scene. And 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.

Step 504: and determining the target safety level of the target scene according to the parameter subset and the parameter value subset.

In the embodiment of the present application, after the parameter subset and the parameter value subset of the target scene are determined, the value ranges of the parameters in the parameter subset of the comparison scene corresponding to the different security levels may be determined as the value ranges of the parameters in the parameter subset of the target scene corresponding to the different security levels, and then, the parameter security levels corresponding to the parameters in the parameter subset may be determined according to the specific parameter values in the parameter subset of the target scene, so as to synthesize the parameter security levels of the parameters to determine the target security level of the target scene.

For example, the parameter subset of the comparison scenario is a = { the vehicle speed v1, the vehicle acceleration a1, the time to collision TTC, the vehicle speed v2, and the vehicle acceleration a2}, and as shown in table 1, a value range of each parameter included in the parameter subset a in different safety levels is shown in an exemplary table.

	Level 1 (unsafe)	Level 2 (to be noted)	Level 3 (safety)
				Speed of bicycle v1 (km/h)	120～340	60～120	0～60
Acceleration a1 (m/s) of bicycle ² )	5～7.84	3～5	0～3
				Time to collision TTC(s)	0～4	4～10	10 to infinity
Front speed v2 (km/h)	0～20	20～60	60～340
				Front vehicle acceleration a2 (m/s) ² )	Negative infinity to negative 6	Minus 3 to minus 6	Negative 3 to positive infinity

TABLE 1

When the parameter value subset a' = {30,2, 50, 100,2.5} of the target scene, it can be known from the value ranges of different safety levels shown in table 1 that the parameter safety levels of the vehicle speed v1, the vehicle acceleration a1, the time to collision TTC, the vehicle speed v2 ahead, and the vehicle acceleration a2 ahead are all the 3 rd level, and therefore, by synthesizing the parameter safety levels of these 5 parameters, it can be determined that the target safety level of the target scene is the 3 rd level, that is, the current target scene is the safety scene.

In the embodiment of the present application, the scene security level corresponding to the target scene can be determined only when all parameters in the parameter subset of the target scene are the same parameter security level, for example, when all parameters in the parameter subset are the 1 st level, the target security level of the target scene is the 1 st level. In the parameter subset, if there is a parameter with a parameter security level different from that of other parameters, the scene security level of the target scene may be directly set to a preset scene security level, for example, directly set to the above level 1 (insecure) or level 2 (to be noticed); or when the parameters belong to different security levels respectively, determining the security level of the target scene according to the lowest security level corresponding to the parameters, for example, the parameters in the parameter subset belong to the 2 nd level and the 3 rd level respectively, and at this time, determining the 2 nd level as the target security level of the target scene. Of course, what scene security level it is specifically set to may be set by the user's own discretion.

In a possible embodiment, since a similarity threshold is set in order to make the selected similar scene more matched with the target scene, and only the predefined scene with the similarity greater than the set similarity threshold is likely to be selected as the comparison scene, when calculating the similarity between the target scene and the predefined scene, another situation may occur, namely, there is no predefined scene with the similarity greater than the preset similarity threshold in the predefined scene library.

Furthermore, in the embodiment of the present application, in order to improve the overall risk handling capability of the automatic driving system, in response to the situation that at least one predefined scene does not exist, the target security level of the target scene may be directly determined as the first preset security level, the target scene is added to the predefined scene library, and meanwhile, a corresponding subsequent processing mode is set. And if the first preset security level is lower than a first security level threshold, directly determining that the target scene is not a security scene. For example, the security level of the target scene may be directly determined as the above-described level 1 (insecure) or level 2 (to be noted). Of course, it is specifically determined why the scene security level can be set by the user's own discretion.

In a possible implementation manner, since the scene security level may be divided into a plurality of levels according to the security level, and different security levels correspond to different security levels, in consideration of the actual operation condition of the automatic driving system, in this embodiment of the present application, the prompt information may be sent according to different sending times according to different security levels, so as to reduce the operation burden of the automatic driving system.

Specifically, if the target security level of the target scene is lower than the first security level threshold and higher than the second security level threshold, the first prompt signal may be output with a delay, for example: the delay time is 30ms, 60ms and the like, and the specific delay time can be set according to the actual requirement and the processing capacity of the automatic driving system, wherein the first safety level threshold is higher than the second safety level threshold. And if the target safety level of the target scene is lower than the second safety level threshold, immediately outputting a first prompt signal.

	Level 1 (unsafe)	Level 2 (to be noted)	Level 3 (safety)
				Degree of safety	0～30	30～60	60～100

TABLE 2

For example, as shown in table 2, for the table of the relationship between the security degree and the security level provided in the embodiment of the present application, the security level may be divided into 3 levels, which are level 1 (insecure), level 2 (to be noted) and level 3 (secure), respectively, wherein the first security level threshold may be set to 60, and the second security level threshold may be set to 30. Then the alert signal may be output with a delay when the target security level is below 60 and above 30, i.e., the target security level is level 2. And the target safety level is lower than 30, that is, when the target safety level is level 1, the safety degree of the target scene is low, and the autonomous driving vehicle is in the scene, so that a safety risk may occur, and therefore, a prompt signal needs to be immediately output to timely cope with the risk scene.

For example, if the security level of the target scene is determined at 9 o 'clock, 10 o' clock, 11 o 'clock, 20 o' clock, then the first alert signal may be output to the in-vehicle computer at 21 o 'clock, 10 o' clock, 11 o 'clock, 9 o' clock, 21 o 'clock, 9 o' clock, 10 o 'clock, 11 o' clock, 30 o 'clock, 9 o' clock, 10 o 'clock, 11 o' clock, 40 o 'clock, when the security level is determined at level 1 o' clock, 2 o 'clock, 30 o' clock, 3 o 'clock, 40 o' clock, 9 o 'clock, 10 o' clock, 11 o 'clock, 40 o' clock.

In a possible implementation mode, when a driver/a safety person exists on a vehicle, the safety level of a target scene is prompted to the driver by outputting a first prompt signal, so that the driver can timely pay attention to the working state of the automatic driving system, and then can timely take over when needing manual taking over, and carry out corresponding control, so that the overall risk coping capability of the automatic driving system can be improved.

In a possible implementation manner, when it is determined that no driver exists and a prompt signal is sent to the background server, the background manager can analyze the target scene according to the received second prompt signal and improve the attention degree of the automatic driving vehicle, so that remote takeover can be performed in time when needed; when remote take-over is needed, a remote control signal is sent to the automatic driving vehicle, so that the automatic driving vehicle carries out corresponding operation based on the remote control information, and the overall risk coping capability of the automatic driving system is further improved.

In summary, in the embodiment of the present application, after determining whether the target scene is safe according to the target security level, since the prompt signal is sent to the driver or the background administrator in time when the target scene is determined to be low in security, the automatic driving vehicle can be timely taken over or assisted to plan when a security risk occurs, so as to improve the overall risk handling capability of the automatic driving system, and further reduce the number of background administrators and the decision pressure to the greatest extent.

As shown in fig. 6, based on the same inventive concept, an embodiment of the present application provides an automatic driving decision device 60, which includes:

a first determining unit 601, configured to determine a target security level of a target scene according to a first parameter set and a first parameter value set of the target scene where a target vehicle is located; the parameters contained in the first parameter set are all parameters of parameter values which can be acquired aiming at a target scene, the parameters comprise parameters with parameter values of zero and parameters which fail to be acquired or do not exist, and the parameter values in the first parameter set correspond to the parameters in the first parameter set;

a second determination unit 602, configured to determine whether a driver is present on the target vehicle when the target safety level is lower than the first safety level threshold;

a first prompting unit 603, configured to output a first prompting signal when it is determined that a driver is present, where the first prompting signal is used for prompting the driver that a safety level of a target scene is low; alternatively, the first and second electrodes may be,

and a second prompting unit 604, configured to send a second prompting signal to the background server when it is determined that the driver is not present, where the second prompting signal is used to prompt that the security level of the target scene of the background manager is low.

Optionally, the first determining unit 601 is specifically configured to:

in response to the at least one predefined scene, selecting one predefined scene from the at least one predefined scene as a control scene; having a subset of parameters against the scene, the subset of parameters being a subset of a first set of parameters of the target scene;

generating a parameter value subset of the target scene according to the parameter subset of the comparison scene; 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;

Optionally, the first determining unit 601 is specifically further configured to:

in response to the absence of the at least one predefined scene, determining a target security level of the target scene to be a first preset security level, the first preset security level being below a first security level threshold.

Optionally, the first prompting unit 603 is further specifically configured to:

if the target security level is lower than the first security level threshold and higher than the second security level threshold, delaying to output a first prompt signal; the first security level threshold is higher than the second security level threshold;

and if the target safety level is lower than the second safety level threshold, immediately outputting a first prompt signal.

Optionally, the second prompting unit 604 is further specifically configured to:

receiving a remote control signal sent by a background server, and controlling a target vehicle to run based on an operation instruction of the remote control signal; the remote control signal is generated by the background server after a background manager carries out decision operation on the second prompt signal.

The apparatus may be configured to execute the method in the embodiments shown in fig. 3 to fig. 5, and therefore, for functions and the like that can be realized by each functional module of the apparatus, reference may be made to the description of the embodiments shown in fig. 3 to fig. 5, which is not repeated here.

Referring to fig. 7, based on the same technical concept, the embodiment of the present application further provides a computer device 70, which may include a memory 701 and a processor 702.

The memory 701 is used for storing a computer program executed by the processor 702. The memory 701 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to use of the computer device, and the like. The processor 702 may be a Central Processing Unit (CPU), a digital processing unit, or the like. The specific connection medium between the memory 701 and the processor 702 is not limited in the embodiment of the present application. In the embodiment of the present application, the memory 701 and the processor 702 are connected by a bus 703 in fig. 7, the bus 703 is represented by a thick line in fig. 7, and the connection manner between other components is merely illustrative and is not limited. The bus 703 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but that does not indicate only one bus or one type of bus.

The memory 701 may be a volatile memory (volatile memory), such as a random-access memory (RAM); the memory 701 may also be a non-volatile memory (non-volatile memory) such as, but not limited to, a read-only memory (rom), a flash memory (flash memory), a hard disk (HDD) or solid-state drive (SSD), or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Memory 701 may be a combination of the above.

A processor 702, configured to execute the method performed by the apparatus in the embodiments shown in fig. 3 to fig. 5 when calling the computer program stored in the memory 701.

In some possible embodiments, various aspects of the methods provided herein may also be implemented in the form of a program product including program code for causing a computer device to perform the steps of the methods according to various exemplary embodiments of the present application described above in this specification when the program product is run on the computer device, for example, the computer device may perform the methods as described in the embodiments shown in fig. 3-5.

Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes. Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.

While the preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. An automated driving decision method, the method comprising:

outputting a first prompt signal in response to the presence of a driver on the target vehicle, the first prompt signal being for prompting the driver for a target safety level of the target scene; alternatively, the first and second electrodes may be,

and responding to the situation that no driver exists on the target vehicle, and sending a second prompt signal to a background server, wherein the second prompt signal is used for prompting a background manager about the target safety level of the target scene.

2. The method of claim 1, wherein determining the target safety level for the target scene based on the first set of parameter values for the target vehicle comprises:

generating a parameter value subset of the target scene according to the parameter subset of the control scene; wherein parameter values in the subset of parameter values correspond to parameters in the subset of parameters, the subset of parameter values being a subset of the first set of parameter values;

3. The method of claim 2, wherein the method further comprises:

in response to the absence of at least one predefined scene, determining a target security level of the target scene to be a first preset security level, the first preset security level being lower than the first security level threshold.

4. The method of claim 1, wherein outputting a first prompt signal in response to a presence of a driver on the target vehicle comprises:

if the target security level is lower than a first security level threshold and higher than a second security level threshold, delaying to output the first prompt signal; the first security level threshold is higher than the second security level threshold;

5. The method of claim 1, wherein the method further comprises:

receiving a remote control signal sent by the background server, and controlling the target vehicle to run based on the remote control signal; wherein the remote control signal is generated by the backend server.

6. An automated driving decision device, the device comprising:

a second determination unit configured to determine whether a driver is present on the target vehicle when the target safety level is lower than a first safety level threshold;

the first prompting unit is used for responding to the existence of a driver on the target vehicle and outputting a first prompting signal, and the first prompting signal is used for prompting the driver that the safety level of the target scene is low; alternatively, the first and second electrodes may be,

and the second prompt unit is used for responding to the situation that no driver exists on the target vehicle and sending a second prompt signal to the background server, wherein the second prompt signal is used for prompting a background manager that the safety level of the target scene is low.

7. The apparatus of claim 6, wherein the first determining unit is specifically configured to:

8. The apparatus as claimed in claim 6, wherein the first determining unit is further configured to:

9. The apparatus of claim 6, wherein the first prompting unit is further specifically configured to:

and if the target security level is lower than the second security level threshold, immediately outputting the first prompt signal.

10. The apparatus of claim 6, wherein the second prompting unit is further to:

11. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor,

the processor, when executing the computer program, realizes the steps of the method of any one of claims 1 to 5.

12. A computer storage medium having computer program instructions stored thereon, wherein,

the computer program instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 5.