CN112328477B - Method and device for generating test case of automatic driving algorithm and electronic equipment - Google Patents
Method and device for generating test case of automatic driving algorithm and electronic equipment Download PDFInfo
- Publication number
- CN112328477B CN112328477B CN202011206729.6A CN202011206729A CN112328477B CN 112328477 B CN112328477 B CN 112328477B CN 202011206729 A CN202011206729 A CN 202011206729A CN 112328477 B CN112328477 B CN 112328477B
- Authority
- CN
- China
- Prior art keywords
- test case
- test
- derived
- test cases
- cases
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3684—Test management for test design, e.g. generating new test cases
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method and a device for generating an autopilot algorithm test case and electronic equipment, wherein the method comprises the following steps: acquiring a basic test case of an automatic driving algorithm; executing the following generation process of the effective test cases: randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases; carrying out validity evaluation on each derived test case so as to determine valid test cases; judging whether the generation process of the effective test case meets a preset termination condition or not; if the test result is not satisfied, taking the effective test case as a basic test case, and returning to the step of executing the random derivative test case on the basis of the basic test case; and if the test result is met, taking the obtained basic test case and the obtained effective test case as target test cases of an automatic driving algorithm. The method can automatically generate the target test cases, greatly improves the generation efficiency of the target test cases, and finally obtains the target test cases more abundantly and variously.
Description
Technical Field
The application relates to the technical field of automatic driving test verification, in particular to a method and a device for generating an automatic driving algorithm test case and electronic equipment.
Background
Computer simulation of an automatic driving system is a basic key technology for testing and testing of an automatic driving vehicle, and is also a basic tool for defining relevant development and admission technical standards of the automatic driving vehicle in the future industry. The simulation test supplements with the automatic driving vehicle test under the real physical environment, and the main purpose of the automatic driving simulation technology is to determine possible problems in the automatic driving process by simulating the real environment and constructing a vehicle model. Compared with a real environment test, the automatic driving simulation test has the advantages of low cost, high parallelism, high speed, compressible time, easy scene reproduction, debugging and the like, and particularly for a planning function part (specifically, an automatic driving algorithm) of an automatic driving system, the feasibility of the planning algorithm can be verified in a large quantity in a short time, and the feasibility of functional regression verification is greatly improved.
In the prior art, when generating test cases of an automatic driving algorithm, there are generally the following two ways: the test case is generated manually, and the test case generated by the method has high accuracy and typical scene, but has the technical problems of low efficiency and time waste; the other is to generate test cases based on a random parameter mode, and the test cases generated by the mode are too continuous and lack of diversity (namely, the scene does not change greatly, but only the motion state of a certain obstacle object in the scene is changed).
In summary, the existing method for generating test cases of the automatic driving algorithm has the technical problems of low efficiency and lack of diversity of the generated test cases.
Disclosure of Invention
In view of the above, the present application aims to provide a method, a device and an electronic device for generating test cases of an autopilot algorithm, so as to solve the technical problems of low efficiency and lack of diversity of the generated test cases of the existing test cases of the autopilot algorithm.
In a first aspect, the present application provides a method for generating test cases of an autopilot algorithm, applied to a test case generating system, where the method includes:
acquiring a basic test case of an automatic driving algorithm, wherein the basic test case is a test case generated manually;
executing the following generation process of the effective test cases:
randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases;
carrying out validity assessment on each derived test case in the plurality of derived test cases, and determining valid test cases in the plurality of derived test cases according to assessment results;
judging whether the generation process of the effective test case meets a preset termination condition or not;
if not, the effective test case is used as the basic test case, and the step of executing the test case randomly derived on the basis of the basic test case is returned;
and if so, taking the obtained basic test case and the obtained effective test case as target test cases of the automatic driving algorithm.
Further, randomly deriving test cases based on the basic test cases includes:
and randomly increasing and decreasing obstacle objects on the basis of the basic test cases, and setting the motion parameters of the obstacle objects so as to obtain the plurality of derivative test cases, wherein the obstacle objects are objects except for the target simulation vehicle controlled by the automatic driving algorithm.
Further, performing validity evaluation on each of the plurality of derived test cases includes:
judging whether each derived test case meets a preset validity condition or not, wherein the preset validity condition at least comprises: the method comprises the steps that an obstacle object except a target simulation vehicle controlled by an automatic driving algorithm in a derived test case can influence the target simulation vehicle controlled by the automatic driving algorithm, an effective path exists in the derived test case so that the target simulation vehicle reaches a preset destination, the obstacle object does not exist in a preset safety range of an initial position of the target simulation vehicle in the derived test case, and under the condition that the target simulation vehicle is not controlled, the target simulation vehicle can finish running according to a preset route, and no direct or potential non-responsibility collision condition exists between the target simulation vehicle and the obstacle object in the derived test case;
if the preset validity condition is met, determining the derived test case as the valid test case;
and if the preset validity condition is not met, determining the derived test case as an invalid test case.
Further, the preset termination condition includes any one of the following: the number of times of executing the generation process of the valid test cases reaches a first preset threshold, the number of the basic test cases and the valid test cases obtained after executing the generation process of the valid test cases, and the number of times of executing the generation process of the valid test cases reach a second preset threshold.
Further, after obtaining the target test case of the autopilot algorithm, the method further includes:
and executing the target test case in a simulation system to test the automatic driving algorithm.
Further, the obstacle object includes: static obstacle objects and dynamic obstacle objects.
In a second aspect, an embodiment of the present application further provides a device for generating a test case of an autopilot algorithm, which is applied to a test case generating system, where the device includes:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring a basic test case of an automatic driving algorithm, wherein the basic test case is a test case generated manually;
the effective test case generating unit is used for executing the following effective test case generating process:
randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases;
carrying out validity assessment on each derived test case in the plurality of derived test cases, and determining valid test cases in the plurality of derived test cases according to assessment results;
the judging unit is used for judging whether the generation process of the effective test case meets the preset termination condition or not;
returning to an execution unit, if the test result is not satisfied, taking the effective test case as the basic test case, and returning to the step of executing the test case randomly derived on the basis of the basic test case;
and the setting unit is used for taking the obtained basic test case and the obtained effective test case as target test cases of the automatic driving algorithm if the basic test case and the effective test case are met.
Further, the valid test case generating unit is further configured to:
and randomly increasing and decreasing obstacle objects on the basis of the basic test cases, and setting the motion parameters of the obstacle objects so as to obtain the plurality of derivative test cases, wherein the obstacle objects are objects except for the target simulation vehicle controlled by the automatic driving algorithm.
In a third aspect, an embodiment of the present application further provides an electronic device, including a memory, and a processor, where the memory stores a computer program executable on the processor, and the processor implements the steps of the method according to any one of the first aspects when the processor executes the computer program.
In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium storing machine-executable instructions which, when invoked and executed by a processor, cause the processor to perform the method of any one of the first aspects.
In the embodiment of the application, a method for generating test cases of an automatic driving algorithm is provided, and the method is applied to a test case generating system and comprises the following steps: acquiring a basic test case of an automatic driving algorithm; then executing the following generation process of the valid test cases: randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases; furthermore, validity evaluation is carried out on each derived test case in the derived test cases, and valid test cases are determined in the derived test cases according to the evaluation results; then judging whether the generation process of the effective test case meets the preset termination condition or not; if the test result is not satisfied, taking the effective test case as a basic test case, and returning to the step of executing the random derivative test case on the basis of the basic test case; and if the test result is met, taking the obtained basic test case and the obtained effective test case as target test cases of an automatic driving algorithm. According to the method, the target test cases can be automatically generated, the generation efficiency of the target test cases is greatly improved, the plurality of derived test cases obtained by randomly deriving the test cases on the basis of the basic test cases are more diversified, and therefore the effective test cases are determined to be more diversified in the plurality of derived test cases, namely the finally obtained target test cases are more abundant and various, and the technical problems that the existing automatic driving algorithm test case generation method is low in efficiency and the generated test cases lack of diversity are solved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for generating an autopilot algorithm test case according to an embodiment of the present application;
FIG. 2 is a flowchart of a method for evaluating the validity of each of a plurality of derived test cases according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a device for generating test cases of an autopilot algorithm according to an embodiment of the present application;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions of the present application will be clearly and completely described in connection with the embodiments, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
At present, when a test case of an automatic driving algorithm is generated, an obstacle object is increased or decreased in a test case generation system in a manual mode, and under the condition that the obstacle object is increased, the motion parameters of the obstacle object are set, so that a new test case is obtained, and the mode is low in efficiency and time-consuming; the other is to obtain the basic test case (generated by a manual mode) and then randomly change the motion parameters of each obstacle object in the basic test case so as to obtain a new test case.
Based on the above, the embodiment provides a method for generating the test cases of the automatic driving algorithm, which can automatically generate the target test cases, greatly improves the generation efficiency of the target test cases, and finally obtains the target test cases more abundantly and variously, thereby solving the technical problems of low efficiency and lack of diversity of the generated test cases of the existing automatic driving algorithm test cases.
Embodiments of the present application are further described below with reference to the accompanying drawings.
Embodiment one:
according to an embodiment of the present application, there is provided an embodiment of a method for generating an autopilot algorithm test case, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different from that herein.
FIG. 1 is a flowchart of a method for generating test cases of an autopilot algorithm according to an embodiment of the present application, as shown in FIG. 1, the method being applied to a test case generating system, and comprising the steps of:
step S102, acquiring a basic test case of an automatic driving algorithm, wherein the basic test case is a test case generated manually;
in the embodiment of the application, the basic test case is a test case generated manually. When the test case is generated manually, the following two methods can be included: one is that a traffic accident occurs in a real physical environment, and the traffic accident is typical and has reference significance, so that a scene corresponding to the traffic accident can be represented in a test case generating system. Specifically, in the test case system, an obstacle object is set on a simulated road in a manual mode, and the motion parameters of the obstacle object are set, so that when the finally obtained test case containing the obstacle object operates, the test case corresponds to the traffic accident, and the test case is generated in a manual mode; and the other is that a developer sets an obstacle object on a simulated road in a manual mode according to imagination and sets the motion parameters of the obstacle object, so that the generation of the test case is completed.
It should be noted that, the basic test case is used for discovering the problem existing in the autopilot algorithm, that is, the basic test case is used for detecting the autopilot algorithm, and after detecting the problem of the autopilot algorithm, the developer perfects the autopilot algorithm.
Step S104, randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases;
compared with the test cases generated based on the random parameter mode, the derived test cases obtained by the method are more abundant and diversified, and after the automatic driving algorithm is detected according to the diversified test cases, more possible problems of the automatic driving algorithm can be found, so that the automatic driving algorithm after final completion is more accurate and stable.
Hereinafter, the process of randomly deriving the test case will be described in detail, and will not be described in detail.
Step S106, carrying out validity assessment on each derived test case in the derived test cases, and determining valid test cases in the derived test cases according to assessment results;
the process of validity assessment is described in detail below and is not described in detail here.
Step S108, judging whether the generation process of the effective test case meets the preset termination condition;
in an embodiment of the present application, the preset termination condition includes any one of the following: the number of times of executing the generation process of the valid test cases reaches a first preset threshold, the number of the basic test cases and the valid test cases obtained after executing the generation process of the valid test cases and reaches a second preset threshold.
That is, the preset termination condition may be: the iteration times reach a first preset threshold value, and the sum of the number of the basic test cases and the number of the effective test cases obtained after the current iteration is performed reaches a second preset threshold value.
Step S110, if not, taking the effective test case as a basic test case, and returning to the step of executing the random derivative test case based on the basic test case;
and step S112, if the test result is met, taking the obtained basic test case and the obtained effective test case as target test cases of an automatic driving algorithm.
In the embodiment of the application, a method for generating test cases of an automatic driving algorithm is provided, and the method is applied to a test case generating system and comprises the following steps: acquiring a basic test case of an automatic driving algorithm; then executing the following generation process of the valid test cases: randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases; furthermore, validity evaluation is carried out on each derived test case in the derived test cases, and valid test cases are determined in the derived test cases according to the evaluation results; then judging whether the generation process of the effective test case meets the preset termination condition or not; if the test result is not satisfied, taking the effective test case as a basic test case, and returning to the step of executing the random derivative test case on the basis of the basic test case; and if the test result is met, taking the obtained basic test case and the obtained effective test case as target test cases of an automatic driving algorithm. According to the method, the target test cases can be automatically generated, the generation efficiency of the target test cases is greatly improved, the plurality of derived test cases obtained by randomly deriving the test cases on the basis of the basic test cases are more diversified, and therefore the effective test cases are determined to be more diversified in the plurality of derived test cases, namely the finally obtained target test cases are more abundant and various, and the technical problems that the existing automatic driving algorithm test case generation method is low in efficiency and the generated test cases lack of diversity are solved.
The foregoing briefly describes a method for generating an autopilot algorithm test case of the present application, and details related thereto are described in detail below.
In an alternative embodiment of the present application, step S104, a process for randomly deriving test cases based on basic test cases includes:
and randomly increasing or decreasing the obstacle objects on the basis of the basic test cases, and setting the motion parameters of the obstacle objects under the condition of increasing the obstacle objects so as to obtain a plurality of derivative test cases, wherein the obstacle objects are objects except for the target simulation vehicle controlled by the automatic driving algorithm.
In an embodiment of the present application, the obstacle object includes: static obstacle objects and dynamic obstacle objects. Specifically, the static obstacle object includes: static road conditions (e.g., road repair conditions), static persons, static vehicles, etc., and dynamic obstacle objects include: traveling vehicles (which may include, in particular, traveling automobiles, traveling bicycles, traveling buses, traveling electric vehicles, etc.) and pedestrians.
The generation of the derived test cases by randomly increasing or decreasing the obstacle objects can change the scene of the original basic test cases, so that the scene of the original basic test cases is greatly changed, and the generated derived test cases are more diversified.
The above describes the process of randomly deriving test cases in detail, and the process of evaluating the validity of derived test cases is described in detail below.
In an alternative embodiment of the present application, referring to fig. 2, step S106, a process for performing validity assessment on each of a plurality of derived test cases includes:
step S201, determining whether each derived test case meets a preset validity condition, where the preset validity condition at least includes: the method comprises the steps that obstacle objects except for a target simulation vehicle controlled by an automatic driving algorithm in a derived test case can influence the target simulation vehicle controlled by the automatic driving algorithm, an effective path exists in the derived test case so that the target simulation vehicle reaches a preset destination, no obstacle object exists in a preset safety range of an initial position of the target simulation vehicle in the derived test case, the target simulation vehicle can finish running according to a preset route under the condition that the target simulation vehicle is not controlled in the derived test case, and no direct or potential no-responsibility collision condition exists between the target simulation vehicle and the obstacle object in the derived test case;
for example: in the derived test cases, obstacle objects except for the target simulation vehicle controlled by the automatic driving algorithm can influence the target simulation vehicle controlled by the automatic driving algorithm. That is, there is an interactive obstacle object, that is, there is a vehicle that has an influence on the target simulation vehicle, for example, the vehicle speed is greater than the target simulation vehicle after the target simulation vehicle, and the vehicle speed is less than the target simulation vehicle before the target simulation vehicle;
and an effective path exists in the derived test case so that the target simulation vehicle reaches a preset destination. I.e. there is a valid path to reach the destination. If not blocked by other vehicles;
and deriving an object without obstacle in a preset safety range of the initial position of the target simulation vehicle in the test case. Namely, no other vehicle exists in the safety range of the initial position of the target simulation vehicle;
the target simulation vehicle can finish running according to a preset route under the condition that the target simulation vehicle is not controlled in the derived test cases. That is, if no control operation is performed in the whole running process of the target simulation vehicle, the running cannot be completed according to a preset line;
the derived test cases are free of direct or potential no-responsibility collision situations between the target simulation vehicle and the obstacle object. That is, the case where other vehicles hit the target simulation vehicle cannot occur.
Step S202, if a preset validity condition is met, determining that the derived test case is a valid test case;
step S203, if the preset validity condition is not satisfied, determining that the derived test case is an invalid test case.
In an alternative embodiment of the present application, after obtaining the target test case of the autopilot algorithm, the method further includes: and executing the target test case in the simulation system to test the automatic driving algorithm.
The method for generating the test cases of the automatic driving algorithm can automatically generate the target test cases, greatly improves the generation efficiency of the target test cases, and obtains more diversified multiple derived test cases by randomly deriving the test cases on the basis of the basic test cases, so that the effective test cases are determined to be more diversified in the multiple derived test cases, namely the finally obtained target test cases are more abundant and diversified.
Embodiment two:
the embodiment of the application also provides a device for generating the test case of the automatic driving algorithm, which is mainly used for executing the method for generating the test case of the automatic driving algorithm provided by the embodiment of the application, and the device for generating the test case of the automatic driving algorithm provided by the embodiment of the application is specifically introduced.
Fig. 3 is a schematic diagram of a device for generating an autopilot test case according to an embodiment of the present application, and as shown in fig. 3, the device for generating an autopilot test case is applied to a test case generating system, and mainly includes: an acquisition unit 10, a valid test case generation unit 20, a judgment unit 30, a return execution unit 40, and a setting unit 50, wherein:
the acquisition unit is used for acquiring basic test cases of an automatic driving algorithm, wherein the basic test cases are test cases generated manually;
the effective test case generating unit is used for executing the following effective test case generating process:
randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases;
carrying out validity evaluation on each derived test case in the derived test cases, and determining valid test cases in the derived test cases according to evaluation results;
the judging unit is used for judging whether the generation process of the effective test case meets the preset termination condition or not;
returning to the execution unit, if the test result is not satisfied, taking the effective test case as a basic test case, and returning to the step of executing the randomly derived test case on the basis of the basic test case;
and the setting unit is used for taking the obtained basic test case and the obtained effective test case as target test cases of the automatic driving algorithm if the basic test case and the effective test case are met.
In the embodiment of the application, a method for generating test cases of an automatic driving algorithm is provided, and the method is applied to a test case generating system and comprises the following steps: acquiring a basic test case of an automatic driving algorithm; then executing the following generation process of the valid test cases: randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases; furthermore, validity evaluation is carried out on each derived test case in the derived test cases, and valid test cases are determined in the derived test cases according to the evaluation results; then judging whether the generation process of the effective test case meets the preset termination condition or not; if the test result is not satisfied, taking the effective test case as a basic test case, and returning to the step of executing the random derivative test case on the basis of the basic test case; and if the test result is met, taking the obtained basic test case and the obtained effective test case as target test cases of an automatic driving algorithm. According to the method, the target test cases can be automatically generated, the generation efficiency of the target test cases is greatly improved, the plurality of derived test cases obtained by randomly deriving the test cases on the basis of the basic test cases are more diversified, and therefore the effective test cases are determined to be more diversified in the plurality of derived test cases, namely the finally obtained target test cases are more abundant and various, and the technical problems that the existing automatic driving algorithm test case generation method is low in efficiency and the generated test cases lack of diversity are solved.
Optionally, the valid test case generating unit is further configured to: and randomly increasing or decreasing obstacle objects on the basis of the basic test cases, and setting the motion parameters of the obstacle objects so as to obtain a plurality of derivative test cases, wherein the obstacle objects are objects except for a target simulation vehicle controlled by an automatic driving algorithm.
Optionally, the valid test case generating unit is further configured to: judging whether each derived test case meets a preset validity condition, wherein the preset validity condition at least comprises: the method comprises the steps that obstacle objects except for a target simulation vehicle controlled by an automatic driving algorithm in a derived test case can influence the target simulation vehicle controlled by the automatic driving algorithm, an effective path exists in the derived test case so that the target simulation vehicle reaches a preset destination, no obstacle object exists in a preset safety range of an initial position of the target simulation vehicle in the derived test case, the target simulation vehicle can finish running according to a preset route under the condition that the target simulation vehicle is not controlled in the derived test case, and no direct or potential no-responsibility collision condition exists between the target simulation vehicle and the obstacle object in the derived test case; if the preset validity condition is met, determining the derived test case as a valid test case; and if the preset validity condition is not met, determining the derived test case as an invalid test case.
Optionally, the preset termination condition includes any one of the following: the number of times of executing the generation process of the valid test cases reaches a first preset threshold, the number of the basic test cases and the valid test cases obtained after the generation process of the valid test cases is executed last time, and the number of times of executing the generation process of the valid test cases reaches a second preset threshold.
Optionally, the device is further configured to: and executing the target test case in the simulation system to test the automatic driving algorithm.
Optionally, the obstacle object includes: static obstacle objects and dynamic obstacle objects.
The device provided by the embodiment of the present application has the same implementation principle and technical effects as those of the foregoing method embodiment, and for the sake of brevity, reference may be made to the corresponding content in the foregoing method embodiment where the device embodiment is not mentioned.
As shown in fig. 4, an electronic device 600 provided in an embodiment of the present application includes: the system comprises a processor 601, a memory 602 and a bus, wherein the memory 602 stores machine-readable instructions executable by the processor 601, when the electronic device is running, the processor 601 communicates with the memory 602 through the bus, and the processor 601 executes the machine-readable instructions to execute the steps of the method for generating the test case of the autopilot algorithm.
Specifically, the memory 602 and the processor 601 can be general-purpose memories and processors, which are not limited herein, and the method for generating the test case of the autopilot algorithm can be executed when the processor 601 runs the computer program stored in the memory 602.
The processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 601 or instructions in the form of software. The processor 601 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but may also be a digital signal processor (Digital Signal Processing, DSP for short), application specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 602, and the processor 601 reads information in the memory 602 and performs the steps of the above method in combination with its hardware.
Corresponding to the method for generating the test case of the autopilot algorithm, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores machine executable instructions, and the computer executable instructions cause a processor to execute the steps of the method for generating the test case of the autopilot algorithm when the computer executable instructions are called and run by the processor.
The device for generating the test case of the automatic driving algorithm provided by the embodiment of the application can be specific hardware on equipment or software or firmware installed on the equipment and the like. The device provided by the embodiment of the present application has the same implementation principle and technical effects as those of the foregoing method embodiment, and for the sake of brevity, reference may be made to the corresponding content in the foregoing method embodiment where the device embodiment is not mentioned. It will be clear to those skilled in the art that, for convenience and brevity, the specific operation of the system, apparatus and unit described above may refer to the corresponding process in the above method embodiment, which is not described in detail herein.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
As another example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments provided in the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, or in a software product stored in a storage medium, including several instructions for causing an electronic device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method for generating an autopilot algorithm test case according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It should be noted that: like reference numerals and letters in the following figures denote like items, and thus once an item is defined in one figure, no further definition or explanation of it is required in the following figures, and furthermore, the terms "first," "second," "third," etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above examples are only specific embodiments of the present application, and are not intended to limit the scope of the present application, but it should be understood by those skilled in the art that the present application is not limited thereto, and that the present application is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit of the corresponding technical solutions. Are intended to be encompassed within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (7)
1. The method for generating the test case of the automatic driving algorithm is characterized by being applied to a test case generating system, and comprises the following steps:
acquiring a basic test case of an automatic driving algorithm, wherein the basic test case is a test case generated manually;
executing the following generation process of the effective test cases:
randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases;
carrying out validity assessment on each derived test case in the plurality of derived test cases, and determining valid test cases in the plurality of derived test cases according to assessment results;
judging whether the generation process of the effective test case meets a preset termination condition or not;
if not, the effective test case is used as the basic test case, and the step of executing the test case randomly derived on the basis of the basic test case is returned;
if yes, the obtained basic test case and the obtained effective test case are used as target test cases of the automatic driving algorithm;
the method comprises the following steps of:
randomly increasing and decreasing obstacle objects on the basis of the basic test cases, and setting the motion parameters of the obstacle objects under the condition of increasing the obstacle objects so as to obtain a plurality of derivative test cases, wherein the obstacle objects are objects except for a target simulation vehicle controlled by the automatic driving algorithm;
wherein the performing validity evaluation on each of the plurality of derived test cases includes:
judging whether each derived test case meets a preset validity condition or not, wherein the preset validity condition at least comprises: the method comprises the steps that an obstacle object except a target simulation vehicle controlled by an automatic driving algorithm in a derived test case can influence the target simulation vehicle controlled by the automatic driving algorithm, an effective path exists in the derived test case so that the target simulation vehicle reaches a preset destination, the obstacle object does not exist in a preset safety range of an initial position of the target simulation vehicle in the derived test case, and under the condition that the target simulation vehicle is not controlled, the target simulation vehicle can finish running according to a preset route, and no direct or potential non-responsibility collision condition exists between the target simulation vehicle and the obstacle object in the derived test case;
if the preset validity condition is met, determining the derived test case as the valid test case;
and if the preset validity condition is not met, determining the derived test case as an invalid test case.
2. The method of claim 1, wherein the preset termination condition comprises any one of: the number of times of executing the generation process of the valid test cases reaches a first preset threshold, the number of the basic test cases and the valid test cases obtained after executing the generation process of the valid test cases, and the number of times of executing the generation process of the valid test cases reach a second preset threshold.
3. The method of claim 1, wherein after obtaining the target test case for the autopilot algorithm, the method further comprises:
and executing the target test case in a simulation system to test the automatic driving algorithm.
4. The method of claim 1, wherein the obstacle object comprises: static obstacle objects and dynamic obstacle objects.
5. An automatic driving algorithm test case generating device, which is applied to a test case generating system, comprising:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring a basic test case of an automatic driving algorithm, wherein the basic test case is a test case generated manually;
the effective test case generating unit is used for executing the following effective test case generating process:
randomly deriving test cases on the basis of the basic test cases to obtain a plurality of derived test cases;
carrying out validity assessment on each derived test case in the plurality of derived test cases, and determining valid test cases in the plurality of derived test cases according to assessment results;
the judging unit is used for judging whether the generation process of the effective test case meets the preset termination condition or not;
returning to an execution unit, if the test result is not satisfied, taking the effective test case as the basic test case, and returning to the step of executing the test case randomly derived on the basis of the basic test case;
the setting unit is used for taking the obtained basic test case and the obtained effective test case as target test cases of the automatic driving algorithm if the basic test case and the effective test case are met;
the valid test case generation unit is further configured to: randomly increasing and decreasing obstacle objects on the basis of the basic test cases, and setting motion parameters of the obstacle objects so as to obtain a plurality of derivative test cases, wherein the obstacle objects are objects except for a target simulation vehicle controlled by the automatic driving algorithm;
the valid test case generation unit is further configured to: judging whether each derived test case meets a preset validity condition or not, wherein the preset validity condition at least comprises: the method comprises the steps that an obstacle object except a target simulation vehicle controlled by an automatic driving algorithm in a derived test case can influence the target simulation vehicle controlled by the automatic driving algorithm, an effective path exists in the derived test case so that the target simulation vehicle reaches a preset destination, the obstacle object does not exist in a preset safety range of an initial position of the target simulation vehicle in the derived test case, and under the condition that the target simulation vehicle is not controlled, the target simulation vehicle can finish running according to a preset route, and no direct or potential non-responsibility collision condition exists between the target simulation vehicle and the obstacle object in the derived test case; if the preset validity condition is met, determining the derived test case as the valid test case; and if the preset validity condition is not met, determining the derived test case as an invalid test case.
6. An electronic device comprising a memory, a processor, the memory having stored therein a computer program executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the method of any of the preceding claims 1 to 4.
7. A computer readable storage medium storing machine executable instructions which, when invoked and executed by a processor, cause the processor to perform the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011206729.6A CN112328477B (en) | 2020-11-02 | 2020-11-02 | Method and device for generating test case of automatic driving algorithm and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011206729.6A CN112328477B (en) | 2020-11-02 | 2020-11-02 | Method and device for generating test case of automatic driving algorithm and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112328477A CN112328477A (en) | 2021-02-05 |
| CN112328477B true CN112328477B (en) | 2023-08-15 |
Family
ID=74322951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011206729.6A Active CN112328477B (en) | 2020-11-02 | 2020-11-02 | Method and device for generating test case of automatic driving algorithm and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112328477B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107991898A (en) * | 2016-10-26 | 2018-05-04 | 法乐第(北京)网络科技有限公司 | A kind of automatic driving vehicle simulating test device and electronic equipment |
| CN110579359A (en) * | 2019-09-10 | 2019-12-17 | 武汉光庭信息技术股份有限公司 | Optimization method and system of automatic driving failure scene library, server and medium |
| CN110673590A (en) * | 2019-10-21 | 2020-01-10 | 安徽江淮汽车集团股份有限公司 | Method, device and equipment for judging reliability of automatic driving system and storage medium |
| CN110716529A (en) * | 2019-09-25 | 2020-01-21 | 武汉光庭信息技术股份有限公司 | Automatic generation method and device for automatic driving test case |
| CN110781069A (en) * | 2019-08-28 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Positioning module testing method, device and equipment for automatic driving vehicle |
| CN110955159A (en) * | 2019-11-28 | 2020-04-03 | 安徽江淮汽车集团股份有限公司 | Automatic driving simulation example compiling method and device, electronic equipment and storage medium |
| CN111199088A (en) * | 2018-10-31 | 2020-05-26 | 百度在线网络技术（北京）有限公司 | Method and device for reproducing scene data |
| CN111208798A (en) * | 2019-12-26 | 2020-05-29 | 深圳市优必选科技股份有限公司 | Robot testing method and device, electronic equipment and storage medium |
| CN111539087A (en) * | 2019-01-18 | 2020-08-14 | 上汽通用汽车有限公司 | Automatic driving system simulation test platform and automatic driving system evaluation method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7043785B2 (en) * | 2017-10-25 | 2022-03-30 | 株式会社Ihi | Information generator |
-
2020
- 2020-11-02 CN CN202011206729.6A patent/CN112328477B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107991898A (en) * | 2016-10-26 | 2018-05-04 | 法乐第(北京)网络科技有限公司 | A kind of automatic driving vehicle simulating test device and electronic equipment |
| CN111199088A (en) * | 2018-10-31 | 2020-05-26 | 百度在线网络技术（北京）有限公司 | Method and device for reproducing scene data |
| CN111539087A (en) * | 2019-01-18 | 2020-08-14 | 上汽通用汽车有限公司 | Automatic driving system simulation test platform and automatic driving system evaluation method |
| CN110781069A (en) * | 2019-08-28 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Positioning module testing method, device and equipment for automatic driving vehicle |
| CN110579359A (en) * | 2019-09-10 | 2019-12-17 | 武汉光庭信息技术股份有限公司 | Optimization method and system of automatic driving failure scene library, server and medium |
| CN110716529A (en) * | 2019-09-25 | 2020-01-21 | 武汉光庭信息技术股份有限公司 | Automatic generation method and device for automatic driving test case |
| CN110673590A (en) * | 2019-10-21 | 2020-01-10 | 安徽江淮汽车集团股份有限公司 | Method, device and equipment for judging reliability of automatic driving system and storage medium |
| CN110955159A (en) * | 2019-11-28 | 2020-04-03 | 安徽江淮汽车集团股份有限公司 | Automatic driving simulation example compiling method and device, electronic equipment and storage medium |
| CN111208798A (en) * | 2019-12-26 | 2020-05-29 | 深圳市优必选科技股份有限公司 | Robot testing method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 自动驾驶系统测试用例生成技术的实证研究;闫施违;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》(第2期);C035-382 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112328477A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111009153B (en) | Training method, device and equipment of trajectory prediction model | |
| Kim et al. | Testing autonomous vehicle software in the virtual prototyping environment | |
| CN109782730B (en) | Method and apparatus for autonomic system performance and rating | |
| CN112327806B (en) | Automatic driving test method and device, electronic equipment and storage medium | |
| CN113935143A (en) | Estimating collision probability by increasing severity level of autonomous vehicle | |
| CN115755869B (en) | Automatic parking test method and device, storage medium and equipment | |
| CN115099051A (en) | Automatic driving simulation test scene generation method and device, vehicle and storage medium | |
| Raffaelli et al. | Facing ADAS validation complexity with usage oriented testing | |
| CN113762406A (en) | Data mining method and device and electronic equipment | |
| CN113468678B (en) | Method and device for calculating accuracy of automatic driving algorithm | |
| CN112328477B (en) | Method and device for generating test case of automatic driving algorithm and electronic equipment | |
| CN111143424B (en) | Feature scene data mining method, device and terminal | |
| CN117197796A (en) | Vehicle shielding recognition method and related device | |
| CN111177878A (en) | Method, device and terminal for screening derivative simulation scenes | |
| KR20230144646A (en) | Generating unknown-unsafe scenarios, improving automated vehicles, computer systems | |
| CN113987751A (en) | Scheme screening method and device, electronic equipment and storage medium | |
| CN114368390A (en) | Method and apparatus for verifying KI-based information processing systems | |
| CN113642521A (en) | Traffic light identification quality evaluation method and device and electronic equipment | |
| Cao et al. | Application oriented testcase generation for validation of environment perception sensor in automated driving systems | |
| CN114580213B (en) | Multi-stage road side simulation method, device, equipment and storage medium | |
| EP3757904A1 (en) | Device and method for training a neural network | |
| CN116244932B (en) | Method for carrying out safety simulation on vehicle, electronic equipment and storage medium | |
| CN112907684B (en) | Humidity detection method, device, equipment and medium | |
| CN111597959B (en) | Behavior detection method and device and electronic equipment | |
| CN115267861B (en) | Automatic driving fusion positioning precision testing method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |