Coupling relationship determination method, device, electronic device and storage medium

Abstract

The present disclosure relates to a method, device, electronic device and storage medium for determining a coupling relationship. The method is applied to an autonomous driving function software system, wherein the software system includes at least a first module and a second module, wherein the first module and the second module are respectively used to implement corresponding autonomous driving functions; the method includes: determining that an output result of the first module is a first result based on the second module; determining that an output result of the first module is a second result not based on the second module; determining difference information between the first result and the second result, and determining a coupling relationship between the first module and the second module based on the difference information; that is, the present disclosure sorts out the coupling relationship between each autonomous driving function module by analyzing the difference information between the output results before and after decoupling the autonomous driving function module, thereby providing a technical basis for building a modular autonomous driving function software system.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving, and in particular to a method, device, electronic device and storage medium for determining a coupling relationship. Background Art

[0002] The current autonomous driving industry is in a period of rapid development, and the demand for the development of autonomous driving technology is increasing day by day. Therefore, the research and development of autonomous driving technology has a very broad application prospect.

[0003] In the development process of traditional autonomous driving technology, developers develop massive amounts of code for specific driving environments. However, since this development method is targeted at specific driving environments, the developed code cannot be reused, resulting in developers needing to redevelop when faced with new driving environments. This leads to low development efficiency, and as driving environments become more diverse and complex, the technical threshold for developers is also getting higher and higher. Therefore, in order to conveniently and quickly develop various autonomous driving solutions, it is very necessary to realize the modularization of autonomous driving functions. The most critical step in modularization is to sort out the relationship between various autonomous driving function modules. However, there is currently a lack of a method for sorting out the relationship between various autonomous driving function modules. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a method, device, electronic device and storage medium for determining a coupling relationship.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for determining a coupling relationship is provided, which is applied to an autonomous driving function software system, wherein the software system includes at least a first module and a second module, and the first module and the second module are respectively used to implement corresponding autonomous driving functions; the method includes: determining that an output result of the first module is a first result based on the second module; determining that an output result of the first module is a second result not based on the second module; determining difference information between the first result and the second result, and determining the coupling relationship between the first module and the second module based on the difference information.

[0006] As an optional embodiment of the present disclosure, determining the coupling relationship between the first module and the second module according to the difference information includes: determining whether the first module and the second module are coupled according to whether the difference information meets a preset condition.

[0007] As an optional embodiment of the present disclosure, the preset condition includes a first preset threshold; determining whether the first module and the second module are coupled based on whether the difference information satisfies the preset condition includes: comparing a difference information value corresponding to the difference information with the first preset threshold; if the difference information value is greater than the first preset threshold, determining that the first module and the second module are coupled; if the difference information value is less than the first preset threshold, determining that the first module and the second module are not coupled.

[0008] As an optional embodiment of the present disclosure, determining the coupling relationship between the first module and the second module according to the difference information includes: determining a coupling coefficient between the first module and the second module according to the difference information, wherein the coupling coefficient is used to represent the coupling strength between the first module and the second module.

[0009] As an optional embodiment of the present disclosure, the method also includes: comparing the coupling coefficient with a second preset threshold; if the coupling coefficient is greater than the second preset threshold, determining that the first module and the second module are coupled; if the coupling coefficient is less than the second preset threshold, determining that the first module and the second module are uncoupled.

[0010] As an optional embodiment of the present disclosure, the method also includes: determining whether the first module has a program crash without relying on the second module; if so, determining that the first module and the second module are coupled; if not, determining the coupling relationship between the first module and the second module based on the difference information.

[0011] As an optional embodiment of the present disclosure, the method further includes: traversing each module in the software system to determine the coupling relationship between each module and other modules.

[0012] As an optional embodiment of the present disclosure, the method also includes: determining an autonomous driving function category corresponding to the first module, the autonomous driving function category corresponding to the first module corresponds to multiple modules including the first module; if it is determined that at least one module among the multiple modules is uncoupled from the second module, then determining that the autonomous driving function category corresponding to the first module is uncoupled from the autonomous driving function category corresponding to the second module.

[0013] As an optional embodiment of the present disclosure, the method also includes: if it is determined that each module of the multiple modules has a program crash without being based on the second module, then determining that the autonomous driving function category corresponding to the first module is coupled with the autonomous driving function category corresponding to the second module.

[0014] As an optional embodiment of the present disclosure, the first result is a preset output result of the first module based on the second module; or, the first result is a real-time output result of the first module based on the second module.

[0015] As an optional embodiment of the present disclosure, the preset condition corresponds to the first module and the second module whose coupling relationship is to be determined, and is determined based on at least one of the following autonomous driving information: autonomous driving scene information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

[0016] As an optional embodiment of the present disclosure, the second preset threshold corresponds to the first module and the second module whose coupling relationship is to be determined, and is determined based on at least one of the following autonomous driving information: autonomous driving scene information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

[0017] As an optional embodiment of the present disclosure, the difference information includes at least one of the following: vector distance, cosine distance, chi-square distance, and information entropy.

[0018] According to a second aspect of an embodiment of the present disclosure, a device for determining a coupling relationship is provided, and the device is applied to an autonomous driving function software system, the software system comprising at least a first module and a second module, the first module and the second module being respectively used to implement corresponding autonomous driving functions; the device comprising: a first unit, for determining that an output result of the first module is a first result based on the second module; a second unit, for determining that an output result of the first module is a second result not based on the second module; a determination unit, for determining difference information between the first result and the second result, and determining the coupling relationship between the first module and the second module based on the difference information.

[0019] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the method for determining the coupling relationship provided in the first aspect of the present disclosure.

[0020] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the method for determining the coupling relationship provided in the first aspect of the present disclosure are implemented.

[0021] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by sorting out the coupling relationship between the autonomous driving function modules through the difference information between the output results before and after the decoupling of the autonomous driving function modules, a technical basis is provided for building a modular autonomous driving function software system.

[0022] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0024] Figure 1 It is a structural diagram of an automatic driving function software system according to an exemplary embodiment.

[0025] Figure 2 The figure is a schematic diagram of the structure of another automatic driving function software system according to an exemplary embodiment.

[0026] Figure 3 The present invention is a flowchart of a method for determining a coupling relationship according to an exemplary embodiment.

[0027] Figure 4 The figure is a flow chart of another method for determining a coupling relationship according to an exemplary embodiment.

[0028] Figure 5 The figure is a flow chart of another method for determining a coupling relationship according to an exemplary embodiment.

[0029] Figure 6 is a flow chart of yet another method for determining a coupling relationship according to an exemplary embodiment.

[0030] Figure 7 is a flow chart of yet another method for determining a coupling relationship according to an exemplary embodiment.

[0031] Figure 8 The present invention is a block diagram of a device for determining a coupling relationship according to an exemplary embodiment.

[0032] Fig. 9 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0033] Exemplary embodiments will be described in detail below with reference to the accompanying drawings.

[0034] It should be pointed out that the relevant embodiments and drawings are only for describing exemplary embodiments provided by the present disclosure, rather than all embodiments of the present disclosure, and it should not be understood that the present disclosure is limited to the relevant exemplary embodiments.

[0035] It should be noted that the terms "first", "second", etc. used in the present disclosure are only used to distinguish different steps, devices or modules, etc. The related terms neither represent any specific technical meanings nor indicate the order or interdependence between them.

[0036] It should be noted that the modifications of the terms "one", "multiple", and "at least one" used in the present disclosure are illustrative rather than restrictive. Unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0037] It should be noted that the term "and / or" used in this disclosure is used to describe the association relationship between associated objects, and generally indicates that there are at least three association relationships. For example, A and / or B can at least indicate the existence of three association relationships: A exists alone, A and B exist at the same time, and B exists alone.

[0038] It should be noted that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. Unless otherwise specified, the scope of the present disclosure is not limited by the order of description of the steps in the relevant embodiments.

[0039] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0040] Figure 1 is a structural diagram of an automatic driving function software system according to an exemplary embodiment. Figure 1 As shown, the software system 100 includes several modules, such as a first module, a second module, ... an Nth module, and each module is used to implement a corresponding automatic driving function.

[0041] Specifically, the autonomous driving function software system includes a plurality of function modules, wherein the first module and the second module are any two function modules in the autonomous driving function software system. As an example only, this specification is described by taking the coupling relationship between the first module and the second module as an example.

[0042] exist Figure 1 Based on the embodiment shown, Figure 2 FIG. 1 is a schematic diagram of another structure of an automatic driving function software system according to an exemplary embodiment. Figure 2As shown, the software system 200 includes multiple functional modules, such as functional module 1, functional module 2...functional module i; the functional modules are used to implement corresponding autonomous driving functions; each of the functional modules at least includes: function category information, function implementation unit and module dependency information, such as functional module 1 includes function category information 11, function implementation unit 12 and module dependency information 13, functional module 2 includes function category information 21, function implementation unit 22 and module dependency information 23, and functional module i includes function category information i1, function implementation unit i2 and module dependency information i3; the function category information is used to indicate the autonomous driving function category corresponding to the functional module; the function implementation unit is used to implement the autonomous driving function corresponding to the functional module; the module dependency information is used to indicate the dependency relationship with other functional modules.

[0043] Specifically, the autonomous driving function software system includes multiple functional modules, and each functional module includes at least functional category information, functional implementation unit and module dependency. Among them, the functional category information refers to several major categories that developers have agreed to abstract and summarize the business processes of autonomous driving, including but not limited to positioning, perception, prediction, planning, control, safety, etc. The functional implementation unit is a specific implementation method for implementing the autonomous driving function according to a specific algorithm or logic, such as realizing vehicle positioning based on a visual mileage algorithm, realizing vehicle path planning based on a probabilistic roadmap, etc. Module dependency information is used to represent the coupling relationship between the current functional module and other functional modules, which can be determined by the coupling relationship determination method provided in the embodiment of the present disclosure.

[0044] Optionally, for the autonomous driving function category, there is at least one corresponding function module. Figure 2 As shown, each autonomous driving function category includes multiple functional modules, and each functional module can realize the autonomous driving function corresponding to the autonomous driving function category, that is, each major category can be subdivided into several functional modules in parallel.

[0045] In constructing Figure 1 When building a modular autonomous driving function software system as shown in FIG. 2 or 3, it is necessary to sort out the relationship between the various autonomous driving function modules in the software system. Only when the relationship between the various autonomous driving function modules is sorted out clearly, it is convenient to modularize the subsequent autonomous driving solution and shorten the solution development cycle. However, there is currently a lack of a convenient and systematic method to sort out the coupling relationship between the various autonomous driving function modules.

[0046] In response to the above technical problems, the inventive concept of the disclosed embodiment is: by sorting out the coupling relationship between the autonomous driving function modules through the difference information between the output results before and after the decoupling of the autonomous driving function modules, technical support is provided for building a modular autonomous driving function software system.

[0047] Figure 3 is a flow chart of a method for determining a coupling relationship according to an exemplary embodiment. Figure 3 As shown, the coupling relationship determination method is applied to Figure 1 or Figure 2 The autonomous driving functional software system shown includes the following steps.

[0048] In step S310, based on the second module, it is determined that the output result of the first module is the first result.

[0049] Specifically, two groups of processes are set for the first module and the second module whose coupling relationship is to be determined. The first group of processes is based on the second module, which means that the input of the first module includes the output of the second module and other input sources, and the output result of the first module of the first group of processes is determined to be the first result.

[0050] As an optional embodiment, the first result is a preset output result of the first module based on the second module; or, the first result is a real-time output result of the first module based on the second module. Specifically, the first result can be an expected value set by those skilled in the art based on experience, or can be a real-time output result of the first module based on the second module.

[0051] In step S320, without relying on the second module, it is determined that the output result of the first module is the second result.

[0052] Specifically, the second set of processes is not based on the second module, which means that the input of the first module only includes other input sources, and the output result of the first module of the second set of processes is determined to be the second result. It should be noted that the other input sources of the two sets of processes are exactly the same, and the only difference is that in the second set of processes, the input of the first module does not include the second module.

[0053] In step S330, difference information between the first result and the second result is determined, and a coupling relationship between the first module and the second module is determined according to the difference information.

[0054] Specifically, the difference between the first result and the second result of the two sets of processes is calculated. If the difference is large, it means that the existence of the second module seriously affects the functional realization of the first module, that is, there is a strong coupling between the two modules; if the difference is small, it means that the existence of the second module has little effect on the first module, that is, the coupling between the two modules is weak.

[0055] As an optional embodiment, the difference information includes at least one of the following: vector distance, cosine distance, chi-square distance, and information entropy.

[0056] Specifically, due to the diversity of information output by the autonomous driving function modules, the methods for calculating the difference information of the output results of different autonomous driving function modules are usually different, including but not limited to: vector distance, cosine distance, chi-square distance, information entropy, etc. in different norm spaces. Even for the same autonomous driving function module, there may be different methods for calculating the difference information.

[0057] As an optional embodiment, without relying on the second module, determine whether the first module has crashed; if so, determine whether the first module and the second module are coupled; if not, determine the coupling relationship between the first module and the second module based on the difference information.

[0058] Specifically, if the first module crashes during operation without relying on the second module, it means that the function implementation of the first module needs to rely on the second module, that is, the first module and the second module are coupled; if the program crashes, it is necessary to further determine the coupling relationship between the two modules based on the difference information.

[0059] The method for determining the coupling relationship provided in this embodiment is applied to an autonomous driving function software system, wherein the software system includes at least a first module and a second module, wherein the first module and the second module are respectively used to implement corresponding autonomous driving functions, and in a case where the output result of the first module is based on the second module, the output result of the first module is determined to be the first result; in a case where the output result of the first module is not based on the second module, the output result of the first module is determined to be the second result; difference information between the first result and the second result is determined, and the coupling relationship between the first module and the second module is determined based on the difference information; that is, this embodiment sorts out the coupling relationship between the autonomous driving function modules by the difference information between the output results before and after the decoupling of the autonomous driving function modules, thereby providing a technical basis for building a modular autonomous driving function software system.

[0060] Based on the above embodiments, Figure 4 is a flow chart showing another method for determining a coupling relationship according to an exemplary embodiment. Figure 4 As shown, the following steps are included.

[0061] In step S410, based on the second module, it is determined that the output result of the first module is the first result.

[0062] In step S420, the output result of the first module is determined to be the second result without being based on the second module.

[0063] In step S430, whether the first module and the second module are coupled is determined according to whether the difference information meets a preset condition.

[0064] The implementation methods of steps S410 and S420 in this embodiment are similar to those of steps S310 and S320 in the above embodiment, and are not described again here.

[0065] The difference from the above embodiment is that this embodiment further defines a specific implementation method for determining the coupling relationship between the autonomous driving function modules. In step S430, it is determined whether the first module and the second module are coupled according to whether the difference information meets a preset condition.

[0066] In step S430, it is directly determined whether the two autonomous driving function modules are coupled based on the difference information. Among them, the preset condition can be a preset decoupling condition. If the difference information meets the preset decoupling condition, it can be determined that the first module and the second module are not coupled, and the two modules can be decoupled. If the difference information does not meet the preset decoupling condition, it is determined that the first module and the second module are coupled, and a prompt message that the decoupling cannot be performed can be output. Alternatively, the preset condition is a preset coupling condition. If the difference information meets the preset coupling condition, it can be determined that the first module and the second module are coupled, and a prompt message that the decoupling cannot be performed is output; if the difference information does not meet the preset coupling condition, it is determined that the first module and the second module are not coupled, and the two modules can be decoupled.

[0067] As an optional embodiment, the preset condition corresponds to the first module and the second module whose coupling relationship is to be determined, and is determined based on at least one of the following autonomous driving information: autonomous driving scene information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

[0068] Specifically, the preset conditions are usually different in different scenarios of autonomous driving solutions, different autonomous driving levels, different autonomous driving performance requirements or other specific requirements. And the preset conditions are generally different for different modules. The preset conditions can be obtained based on at least one piece of autonomous driving information among the autonomous driving scenario information, autonomous driving level information, autonomous driving performance information, and other preset requirement information. There are two specific determination methods: the first is given by the specific requirements of the autonomous driving solution; the second is given according to the standards or industry experimental results, and the standards or industry experimental results should meet the requirements of all other input information.

[0069] As an optional embodiment, the preset condition includes a first preset threshold; the step S430 includes: comparing the difference information value corresponding to the difference information with the first preset threshold; if the difference information value is greater than the first preset threshold, determining that the first module and the second module are coupled; if the difference information value is less than the first preset threshold, determining that the first module and the second module are uncoupled.

[0070] Specifically, the difference information value can be compared with the first preset threshold value corresponding to the preset condition. If it is greater than the first preset threshold value, it is determined that the first module and the second module are coupled; if it is less than the first preset threshold value, it is determined that the first module and the second module are not coupled. The first preset threshold value is closely related to input conditions such as the autonomous driving scene and the autonomous driving level. It is usually obtained through experiments under specified conditions. In different modules, the first preset threshold value is generally different, and the present disclosure does not limit this.

[0071] The method for determining the coupling relationship provided in this embodiment determines whether the first module and the second module are coupled based on whether the difference information meets a preset condition. That is, the embodiment of the present disclosure directly determines whether the autonomous driving function modules are coupled based on the difference information between the output results before and after the decoupling of the autonomous driving function modules, thereby providing a technical basis for building a modular autonomous driving function software system.

[0072] Based on the above embodiments, Figure 5 is a flow chart of another method for determining a coupling relationship according to an exemplary embodiment. Figure 5 As shown, the following steps are included.

[0073] In step S510, based on the second module, it is determined that the output result of the first module is the first result.

[0074] In step S520, without relying on the second module, it is determined that the output result of the first module is the second result.

[0075] In step S530, a coupling coefficient between the first module and the second module is determined according to the difference information, where the coupling coefficient is used to represent the coupling strength between the first module and the second module.

[0076] Steps S510 and S520 in this embodiment are implemented in similar ways to steps S310 and S320 in the above embodiment, and are not described again here.

[0077] The difference from the above embodiment is that this embodiment further defines another specific implementation method for determining the coupling relationship of the autonomous driving function modules. In this embodiment, the coupling coefficient between the first module and the second module is determined according to the difference information, and the coupling coefficient is used to represent the coupling strength between the first module and the second module.

[0078] Specifically, Figure 4 The embodiment shown directly determines whether the modules are coupled qualitatively based on the difference information, while this embodiment determines the coupling coefficient based on the difference information to quantitatively describe the coupling strength between the modules. Generally speaking, the difference information and the coupling coefficient are proportional. The greater the difference, the greater the coupling coefficient, and the smaller the difference, the smaller the coupling coefficient.

[0079] Continue to refer Figure 5 As shown, the method further includes steps S540-S560, as shown below:

[0080] Step S540: Compare the coupling coefficient with a second preset threshold.

[0081] Step S550: If the coupling coefficient is greater than a second preset threshold, determine that the first module and the second module are coupled.

[0082] Step S560: If the coupling coefficient is less than a second preset threshold, determine that the first module and the second module are uncoupled.

[0083] Specifically, the coupling coefficient can be compared with a second preset threshold. If it is greater than the second preset threshold, it is determined that the first module and the second module are coupled; if it is less than the second preset threshold, it is determined that the first module and the second module are uncoupled.

[0084] As an optional embodiment, the second preset threshold can be set manually, or correspond to the first module and the second module whose coupling relationship is to be determined, and is determined based on at least one of the following autonomous driving information: autonomous driving scene information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

[0085] Specifically, like the preset condition or the first preset threshold, the second preset threshold is closely related to input conditions such as the autonomous driving scenario and the autonomous driving level, and is usually obtained through experiments under specified conditions. In different modules, the second preset threshold is generally different, and the present disclosure does not impose any restrictions on this.

[0086] The method for determining the coupling relationship provided in this embodiment determines the coupling coefficient between the first module and the second module according to the difference information, and the coupling coefficient is used to represent the coupling strength between the first module and the second module; that is, this embodiment determines the coupling coefficient between each autonomous driving function module by the difference information between the output results before and after the decoupling of the autonomous driving function module, so as to quantitatively describe the coupling strength between each autonomous driving function module.

[0087] Based on the above embodiments, Figure 6 is a flowchart of another method for determining a coupling relationship according to an exemplary embodiment, which is applied to Figure 2 The autonomous driving function software system shown in the figure. Figure 6 As shown, the following steps are included.

[0088] In step S610, each module in the software system is traversed to determine the coupling relationship between each module and other modules.

[0089] In step S620, the autonomous driving function category corresponding to the first module is determined, and the autonomous driving function category corresponding to the first module corresponds to multiple modules including the first module.

[0090] In step S630, if it is determined that at least one module among the multiple modules is uncoupled from the second module, it is determined that the autonomous driving function category corresponding to the first module is uncoupled from the autonomous driving function category corresponding to the second module.

[0091] The difference from the above embodiment is that this embodiment further defines a specific implementation method for determining the coupling relationship between the automatic driving function categories. In this embodiment, each module in the software system is traversed to determine the coupling relationship between each module and other modules; the automatic driving function category corresponding to the first module is determined, and the automatic driving function category corresponding to the first module corresponds to multiple modules including the first module; if it is determined that at least one module in the multiple modules is not coupled with the second module, then it is determined that the automatic driving function category corresponding to the first module is not coupled with the automatic driving function category corresponding to the second module.

[0092] Specifically, the autonomous driving function software system includes multiple modules. For each module in the software system, steps S310-S330 can be executed to determine the coupling relationship between each module and other modules, so as to determine the coupling relationship between each module under the autonomous driving function category to which the first module belongs and the second module; if it is found that at least one module under the autonomous driving function category to which the first module belongs is uncoupled with the second module, it can be determined that the autonomous driving function category to which the first module belongs and the autonomous driving function category to which the second module belongs are uncoupled, and the two autonomous driving function categories can be decoupled.

[0093] As an optional embodiment, if it is determined that each module in the multiple modules has a program crash without being based on the second module, it is determined that the autonomous driving function category corresponding to the first module is coupled with the autonomous driving function category corresponding to the second module.

[0094] Specifically, the program crash situations of each module under the autonomous driving function category to which the first module belongs without being based on the second module are counted; if all modules have program crashes, it is determined that the autonomous driving function category to which the first module belongs and the autonomous driving function category to which the second module belongs are coupled and cannot be decoupled; conversely, if there is a module that has not had a program crash, it is possible to continue to determine whether they are coupled based on the difference information between the output results of the module that has not had a program crash and the second module.

[0095] The method for determining the coupling relationship provided in the present embodiment determines the autonomous driving function category corresponding to the first module, and the autonomous driving function category corresponding to the first module corresponds to multiple modules including the first module; if it is determined that at least one module among the multiple modules is not coupled with the second module, then it is determined that the autonomous driving function category corresponding to the first module is not coupled with the autonomous driving function category corresponding to the second module; that is, the present embodiment realizes the coupling judgment between autonomous driving function categories by traversing the coupling relationship between each module under the autonomous driving function category and other modules in the software system.

[0096] In order to further understand the embodiments of the present disclosure, Figure 7 is a flowchart of another method for determining a coupling relationship according to an exemplary embodiment, which is applied to Figure 1 or Figure 2 In the autonomous driving function software system shown in the figure, Figure 7 , the embodiments of the present disclosure are described in detail.

[0097] To determine Figure 1 or Figure 2 Any two modules (i.e. Figure 7Take the coupling relationship between the first module and the second module in as an example.

[0098] First, the preset decoupling conditions are determined based on the demand information of the autonomous driving solution (scenario information, autonomous driving level information, etc.). Then, two groups of processes are set, where the first group of processes is the original process in the software system, that is, the input of the first module includes the output of the second module and other input sources, and in the second group of processes, the input of the first module only includes other input sources, and the first group of processes is exactly the same as the other input sources in the second group of processes. Then, determine whether the first module in the second group of processes has a program crash. If so, it is concluded that the first module and the second module cannot be decoupled. If there is no program crash, the difference in the output results of the first module of the two groups of processes is obtained. Then, determine whether the difference meets the preset decoupling conditions. If not, it is concluded that the first module and the second module cannot be decoupled; if it is, it is concluded that the first module and the second module can be decoupled, and the decoupling operation is performed.

[0099] To determine Figure 2 Any two autonomous driving function categories (in Figure 7 The first module in the figure represents the first autonomous driving function category, referred to as the first category, and the second module represents the second autonomous driving function category, referred to as the second category) as an example of the coupling relationship between them.

[0100] First, the preset decoupling conditions are determined according to the demand information of the autonomous driving solution (scenario information, autonomous driving level information, etc.). Then, two groups of processes are set, where the first group of processes is the original process in the software system, that is, the input of the first category includes the output of the second category and other input sources, and in the second group of processes, the input of the first category only includes other input sources, and the first group of processes is exactly the same as the other input sources in the second group of processes. Then, the functional modules in the first category are traversed, that is, for each module in the first category, both groups of processes need to be executed at least once at the same time, and the execution results are counted to complete the traversal of all modules in the first category. Then, the crash of all modules under the first category in the second process is counted. If all modules under the first category have program crashes, it is concluded that the two categories cannot be decoupled; conversely, if one module in the first category does not crash, it is necessary to calculate the difference information of the output results of the module that did not crash in the first process and the second process; if the difference information of any module meets the preset decoupling conditions, it is concluded that the two categories can be decoupled and the decoupling action is completed; otherwise, it is concluded that the two categories cannot be decoupled.

[0101] In summary, the coupling relationship determination method provided in the embodiments of the present disclosure can complete the logical sorting of the relationships between all autonomous driving function modules, facilitate the decomposition of autonomous driving business processes into modular processes, and provide a technical basis for the development of modular autonomous driving function software systems, so that the subsequent design and development work from modules to the overall autonomous driving solution can be completed more conveniently, simply and quickly, shortening the development cycle of the autonomous driving solution.

[0102] Figure 8 is a block diagram of a coupling relationship determination device according to an exemplary embodiment, the device is applied to an automatic driving function software system, the software system includes at least a first module and a second module, the first module and the second module are respectively used to implement the corresponding automatic driving function. Figure 8 , the device 800 includes a first unit 810, a second unit 820 and a determining unit 830.

[0103] The first unit 810 is used to determine that the output result of the first module is the first result based on the second module; the second unit 820 is used to determine that the output result of the first module is the second result without being based on the second module; the determination unit 830 is used to determine the difference information between the first result and the second result, and determine the coupling relationship between the first module and the second module according to the difference information.

[0104] As an optional embodiment of the present disclosure, the determining unit 830 is specifically configured to determine whether the first module and the second module are coupled according to whether the difference information satisfies a preset condition.

[0105] As an optional embodiment of the present disclosure, the preset condition includes a first preset threshold; the determination unit 830 is specifically used to: compare the difference information value corresponding to the difference information with the first preset threshold; if the difference information value is greater than the first preset threshold, determine that the first module and the second module are coupled; if the difference information value is less than the first preset threshold, determine that the first module and the second module are not coupled.

[0106] As an optional embodiment of the present disclosure, the determining unit 830 is specifically used to: determine a coupling coefficient between the first module and the second module according to the difference information, wherein the coupling coefficient is used to represent the coupling strength between the first module and the second module.

[0107] As an optional embodiment of the present disclosure, the determination unit 830 is further used to: compare the coupling coefficient with a second preset threshold; if the coupling coefficient is greater than the second preset threshold, determine that the first module and the second module are coupled; if the coupling coefficient is less than the second preset threshold, determine that the first module and the second module are not coupled.

[0108] As an optional embodiment of the present disclosure, the second unit 820 is further used to: determine whether the first module has a program crash without relying on the second module; if so, the determination unit 830 is used to determine the coupling relationship between the first module and the second module; if not, the determination unit 830 is used to determine the coupling relationship between the first module and the second module based on the difference information.

[0109] As an optional embodiment of the present disclosure, the device is also used to: traverse each module in the software system to determine the coupling relationship between each module and other modules.

[0110] As an optional embodiment of the present disclosure, the determination unit 830 is further used to: determine the autonomous driving function category corresponding to the first module, the autonomous driving function category corresponding to the first module corresponds to multiple modules including the first module; if it is determined that at least one module among the multiple modules is uncoupled with the second module, then it is determined that the autonomous driving function category corresponding to the first module is uncoupled with the autonomous driving function category corresponding to the second module.

[0111] As an optional embodiment of the present disclosure, the second unit 820 is also used for: if it is determined that each of the multiple modules has a program crash without being based on the second module, the determination unit 830 is used to determine that the autonomous driving function category corresponding to the first module is coupled with the autonomous driving function category corresponding to the second module.

[0112] As an optional embodiment of the present disclosure, the first result is a preset output result of the first module based on the second module; or, the first result is a real-time output result of the first module based on the second module.

[0113] As an optional embodiment of the present disclosure, the preset condition corresponds to the first module and the second module whose coupling relationship is to be determined, and is determined based on at least one of the following autonomous driving information: autonomous driving scene information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

[0114] As an optional embodiment of the present disclosure, the second preset threshold corresponds to the first module and the second module whose coupling relationship is to be determined, and is determined based on at least one of the following autonomous driving information: autonomous driving scene information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

[0115] As an optional embodiment of the present disclosure, the difference information includes at least one of the following: vector distance, cosine distance, chi-square distance, and information entropy.

[0116] The implementation principle and technical effect of the device for determining a coupling relationship provided in the embodiment of the present disclosure are similar to those of the above-mentioned method embodiment, and the relevant description of the method embodiment can be inherited.

[0117] Fig. 9 1 is a block diagram of an electronic device 900 according to an exemplary embodiment. The electronic device 900 may be a vehicle controller, a vehicle terminal, a vehicle computer or other types of electronic devices.

[0118] Reference Fig. 9 , the electronic device 900 may include at least one processor 910 and a memory 920. The processor 910 may execute instructions stored in the memory 920. The processor 910 is communicatively connected to the memory 920 via a data bus. In addition to the memory 920, the processor 910 may also be communicatively connected to an input device 930, an output device 940, and a communication device 950 via a data bus.

[0119] The processor 910 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System on Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.

[0120] The memory 920 may be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0121] In the embodiment of the present disclosure, executable instructions are stored in the memory 920, and the processor 910 can read the executable instructions from the memory 920 and execute the instructions to implement all or part of the steps of the method for determining the coupling relationship described in any of the above exemplary embodiments.

[0122] In addition to the above methods and devices, the exemplary embodiments of the present disclosure may also be a computer program product or a computer-readable storage medium storing the computer program product. The computer product includes computer program instructions that can be executed by a processor to implement all or part of the steps described in any method in the above exemplary embodiments.

[0123] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and also conventional procedural programming languages, such as "C" language or similar programming languages ​​and scripting languages ​​(e.g., Python). The program code may be executed entirely on the user computing device, partially on the user computing device, as an independent software package, partially on the user computing device and partially on the remote computing device, or entirely on the remote computing device or server.

[0124] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of readable storage media include: a static random access memory (SRAM) with one or more wires electrically connected, an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk or an optical disk, or any suitable combination of the above.

[0125] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0126] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for determining a coupling relationship, characterized in that: Applied to an autonomous driving function software system, the software system includes at least a first module and a second module, the first module and the second module are respectively used to implement corresponding autonomous driving functions, the method includes: Based on the second module, determining the output result of the first module as a first result; Without being based on the second module, determining that the output result of the first module is the second result; Determine difference information between the first result and the second result, and determine a coupling relationship between the first module and the second module according to the difference information; Herein, “based on the second module” means that the input of the first module includes the output of the second module and other input sources, and “not based on the second module” means that the input of the first module only includes other input sources.

2. The method for determining a coupling relationship according to claim 1, characterized in that: The determining the coupling relationship between the first module and the second module according to the difference information includes: Whether the first module and the second module are coupled is determined according to whether the difference information meets a preset condition.

3. The method for determining a coupling relationship according to claim 2, characterized in that: The preset condition includes a first preset threshold; and determining whether the first module and the second module are coupled according to whether the difference information satisfies the preset condition includes: Comparing the difference information value corresponding to the difference information with the first preset threshold; If the difference information value is greater than the first preset threshold, determining that the first module and the second module are coupled; If the difference information value is less than the first preset threshold, it is determined that the first module and the second module are uncoupled.

4. The method for determining a coupling relationship according to claim 1, characterized in that: The determining the coupling relationship between the first module and the second module according to the difference information includes: A coupling coefficient between the first module and the second module is determined according to the difference information, where the coupling coefficient is used to represent the coupling strength between the first module and the second module.

5. The method for determining a coupling relationship according to claim 4, characterized in that: The method further comprises: Comparing the coupling coefficient with a second preset threshold; If the coupling coefficient is greater than a second preset threshold, determining that the first module and the second module are coupled; If the coupling coefficient is less than a second preset threshold, it is determined that the first module and the second module are uncoupled.

6. The method for determining a coupling relationship according to any one of claims 1 to 5, characterized in that: The method further comprises: Determine whether the first module crashes without relying on the second module; If so, determining that the first module and the second module are coupled; If not, determining the coupling relationship between the first module and the second module according to the difference information.

7. The method for determining a coupling relationship according to any one of claims 1 to 5, characterized in that: The method further comprises: Each module in the software system is traversed to determine the coupling relationship between each module and other modules.

8. The method for determining a coupling relationship according to claim 7, characterized in that: The method further comprises: Determine an autonomous driving function category corresponding to the first module, where the autonomous driving function category corresponding to the first module corresponds to a plurality of modules including the first module; If it is determined that at least one module among the multiple modules is uncoupled from the second module, it is determined that the autonomous driving function category corresponding to the first module is uncoupled from the autonomous driving function category corresponding to the second module.

9. The method for determining a coupling relationship according to claim 8, characterized in that: The method further comprises: If it is determined that each of the multiple modules has a program crash without being based on the second module, it is determined that the autonomous driving function category corresponding to the first module is coupled with the autonomous driving function category corresponding to the second module.

10. The method for determining a coupling relationship according to any one of claims 1 to 5, characterized in that: The first result is a preset output result of the first module based on the second module; Alternatively, the first result is a real-time output result of the first module based on the second module.

11. The method for determining a coupling relationship according to claim 2 or 3, characterized in that: The preset condition corresponds to the first module and the second module of the coupling relationship to be determined, and is determined according to at least one of the following automatic driving information: Autonomous driving scenario information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

12. The method for determining a coupling relationship according to claim 5, characterized in that: The second preset threshold corresponds to the first module and the second module of the coupling relationship to be determined, and is determined according to at least one of the following automatic driving information: Autonomous driving scenario information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

13. The method for determining a coupling relationship according to any one of claims 1 to 5, characterized in that: The difference information includes at least one of the following: Vector distance, cosine distance, chi-square distance, information entropy.

14. A device for determining a coupling relationship, characterized in that: The device is applied to an automatic driving function software system, the software system includes at least a first module and a second module, the first module and the second module are respectively used to implement corresponding automatic driving functions, and the device includes: A first unit, configured to determine, based on the second module, that an output result of the first module is a first result; A second unit, configured to determine, without relying on the second module, that an output result of the first module is a second result; a determining unit, configured to determine difference information between the first result and the second result, and determine a coupling relationship between the first module and the second module according to the difference information; Herein, “based on the second module” means that the input of the first module includes the output of the second module and other input sources, and “not based on the second module” means that the input of the first module only includes other input sources.

15. The coupling relationship determination device according to claim 14, characterized in that: The determining unit is specifically configured to: Whether the first module and the second module are coupled is determined according to whether the difference information meets a preset condition.

16. The coupling relationship determination device according to claim 15, characterized in that: The preset condition includes a first preset threshold; the determining unit is specifically configured to: Comparing the difference information value corresponding to the difference information with the first preset threshold; If the difference information value is greater than the first preset threshold, determining that the first module and the second module are coupled; If the difference information value is less than the first preset threshold, it is determined that the first module and the second module are uncoupled.

17. The device for determining a coupling relationship according to claim 14, characterized in that: The determining unit is specifically configured to: A coupling coefficient between the first module and the second module is determined according to the difference information, where the coupling coefficient is used to represent the coupling strength between the first module and the second module.

18. The device for determining a coupling relationship according to claim 17, characterized in that: The determining unit is further configured to: Comparing the coupling coefficient with a second preset threshold; If the coupling coefficient is greater than a second preset threshold, determining that the first module and the second module are coupled; If the coupling coefficient is less than a second preset threshold, it is determined that the first module and the second module are uncoupled.

19. The device for determining a coupling relationship according to any one of claims 14 to 18, characterized in that: The second unit is further used for: Determine whether the first module crashes without relying on the second module; If yes, the determining unit is used to determine that the first module and the second module are coupled; If not, the determining unit is used to determine the coupling relationship between the first module and the second module according to the difference information.

20. The device for determining a coupling relationship according to any one of claims 14 to 18, characterized in that: The device is also used for: Each module in the software system is traversed to determine the coupling relationship between each module and other modules.

21. The device for determining a coupling relationship according to claim 20, characterized in that: The determining unit is further configured to: Determine an autonomous driving function category corresponding to the first module, where the autonomous driving function category corresponding to the first module corresponds to a plurality of modules including the first module; If it is determined that at least one module among the multiple modules is uncoupled from the second module, it is determined that the autonomous driving function category corresponding to the first module is uncoupled from the autonomous driving function category corresponding to the second module.

22. The device for determining a coupling relationship according to claim 21, characterized in that: The second unit is further used for: If it is determined that each of the multiple modules has a program crash without being based on the second module, the determination unit is used to determine that the autonomous driving function category corresponding to the first module is coupled with the autonomous driving function category corresponding to the second module.

23. The device for determining a coupling relationship according to any one of claims 14 to 18, characterized in that: The first result is a preset output result of the first module based on the second module; Alternatively, the first result is a real-time output result of the first module based on the second module.

24. The device for determining a coupling relationship according to claim 15 or 16, characterized in that: The preset condition corresponds to the first module and the second module of the coupling relationship to be determined, and is determined according to at least one of the following automatic driving information: Autonomous driving scenario information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

25. The device for determining a coupling relationship according to claim 18, characterized in that: The second preset threshold corresponds to the first module and the second module of the coupling relationship to be determined, and is determined according to at least one of the following automatic driving information: Autonomous driving scenario information, autonomous driving level information, autonomous driving performance information, and other preset requirement information.

26. The device for determining a coupling relationship according to any one of claims 14 to 15, characterized in that: The difference information includes at least one of the following: Vector distance, cosine distance, chi-square distance, information entropy.

27. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method for determining the coupling relationship described in any one of claims 1-13.

28. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method for determining a coupling relationship described in any one of claims 1 to 13 are implemented.

Images