CN110716529A - Automatic generation method and device for automatic driving test case - Google Patents
Automatic generation method and device for automatic driving test case Download PDFInfo
- Publication number
- CN110716529A CN110716529A CN201910913474.8A CN201910913474A CN110716529A CN 110716529 A CN110716529 A CN 110716529A CN 201910913474 A CN201910913474 A CN 201910913474A CN 110716529 A CN110716529 A CN 110716529A
- Authority
- CN
- China
- Prior art keywords
- factors
- automatic driving
- factor
- scene
- driving
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides an automatic generation method and device of an automatic driving test case, which comprises the following steps: based on the weight of each factor in the typical scene of automatic driving, reselecting and arranging the factors to generate an optimal test scene case; and generating a visual scene animation based on the optimal test scene case. On one hand, testing factors, factor extraction and classification are carried out on typical scene data of natural driving, the weight values of the factors are calculated, optimal combination of the factors and the factors is carried out at the same time, and the testing scene is output, and on the other hand, the testing scene is described in a visual description mode, so that testing understanding and management are facilitated.
Description
Technical Field
The invention relates to the field of automatic driving, in particular to an automatic generation method and device of an automatic driving test case.
Background
With the gradual trend of the flow ceiling of the mobile internet, the digital fusion of the internet and the traditional industries such as agriculture, industry, building industry and service industry becomes a new trend, and the technology of combining the industrial internet with 5G, cloud computing and the like can accelerate the economic transformation of the entity. The automobile serves as an indispensable intelligent mobile device in an industrial internet scene, and with the innovation of new-generation automobile technical revolution such as new energy, intelligent internet and automatic driving, a reproducible and circular business mode closed loop is created by combining different landing scenes.
The automatic driving means that the intelligent automobile senses the driving environment around the automobile by installing sensor equipment (including 2D (two-dimensional) photographing visual sensing, laser radar, millimeter wave radar and the like) arranged on the automobile, fast operation and analysis are carried out by combining a navigation high-precision map, potential road condition environments are continuously simulated and deeply learned and judged, the optimal or most suitable driving route and mode of the automobile are further planned by means of an algorithm, and then the optimal or most suitable driving route and mode are fed back to a control system through a chip to carry out actual operation actions such as braking and steering wheel control.
At present, automatic driving is in a high-speed development stage, and the development and testing of the corresponding system are rapidly developed, but the industry has not agreed how to perform safety testing in the real world. In a real road, because unknown scenes are difficult to exhaust, the number of scenes in a test scene in a limited range is extremely large because of a plurality of combinations of roads, environments and traffic participants, and investigation finds that existing software or platforms in the industry at present do not optimize the use cases of the test scene and output a relatively intuitive scene description. There are still significant limitations to software simulation or real vehicle testing.
Automatic driving has been developed to various degrees worldwide, and the automatic driving has reached the level of L4 and the accumulated test mileage has exceeded 2000 kilometers in the example of Google, whereas the industry considers that the automatic driving needs 160 kilometers accumulated when landing, so there is a long way to reach this goal in view of the prior art and the development limitations of the industry.
The time required to achieve this goal is also very long, how to verify the new code in the shortest possible time to improve driving safety, and the construction of a scene library is essential in an automated driving process.
Based on different kinds of permutation and combination of traffic participants, the generated test scene library is endless and cannot be tested one by one at all, and based on the current technical development condition of automatic driving, it is completely unnecessary to carry out coverage test on all actual driving scenes.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide an automatic driving test case generation method and apparatus that overcome the above problems or at least partially solve the above problems.
According to a first aspect of the embodiments of the present invention, there is provided an automatic generation method for an automatic driving test case, including:
and acquiring the weight of each factor and factor in the actual driving data of the automatic driving, and reordering the factors and factors based on a Pairwise algorithm to obtain an optimal test scene case.
Preferably, the obtaining of the weight of each factor in the automatic driving actual driving data specifically includes:
acquiring automatic driving actual driving data, and classifying and extracting factors and factors in the automatic driving actual driving data; and acquiring the weight of each factor based on an entropy method.
Preferably, the obtaining of the weight of each factor based on the entropy method specifically includes:
obtaining the discrete degree of each factor and factor based on an entropy method, and representing the maximum combination quantity by using matrixes A and N M of N factors and M factors:
in the above formula, i is 1,2, …, n; j is 1,2, …, m; xijIs the value of the ith row and the jth column in the matrix A; obtaining the specific gravity of the ith factor under the j-th index:
formula of entropy value of j-th index:
formula for coefficient of difference for j-th index:
gj＝1-ej
get the weight of the jth index:
preferably, the factors include objects, road conditions, environment, and behavior in a typical scenario of automatic driving;
the factor is parameter information or attribute information of each factor.
Preferably, the objects include other persons or vehicles present in the typical scene of autonomous driving, as well as other objects or animals that influence driving decisions or that are all autonomously movable;
the road condition is the characteristics of a road and the characteristics of traffic control;
the environment is an environment factor which can be changed in a typical scene of automatic driving and is transmitted to an automatic driving automobile in real time by the outside;
the behavior is the driving behavior of the autonomous vehicle itself.
Preferably, the factors and the factors are reordered based on a Pairwise algorithm, and the reordering specifically includes:
formulating a test scene exclusion rule based on a preset automatic driving rule, recombining the factors and the factors based on a Pairwise algorithm, performing unreasonable scene exclusion based on a preset unreasonable scene exclusion rule, and optimally screening the combined test scene case based on the weight of the factors to obtain an optimal test scene case.
According to a second aspect of the embodiments of the present invention, there is provided an automatic driving test case generation apparatus, including a screening module and an optimal test scenario case generation module;
the screening module is used for acquiring the weight of each factor in the actual driving data of the automatic driving;
and the optimal test scene case generation module is used for reordering the factors and the factors based on a Pairwise algorithm to obtain an optimal test scene case.
According to a third aspect of the embodiments of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the automatic driving test case generation method provided in any one of the various possible implementations of the first aspect when executing the program.
According to a fourth aspect of embodiments of the present invention, there is provided a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the automated driving test case automatic generation method as provided by any one of the various possible implementations of the first aspect.
According to the automatic generation method and device for the automatic driving test case, provided by the embodiment of the invention, on one hand, the principle of high-speed automatic driving priority in the current industry is selected to perform data analysis based on the traveling data of the company, on the other hand, the factor is extracted based on the traveling data to obtain the weight, and the optimal combination of the test scenes is obtained based on the Pairwise algorithm, so that the test scenes which are verified in the shortest time and are more effective are achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from these without inventive effort.
Fig. 1 is a schematic flow chart of an automatic generation method of an automatic driving test case according to an embodiment of the present invention;
fig. 2 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The scene is a very important ring in the automatic driving test system, and the diversity, the coverage, the typicality and the like of the test scene can influence the accuracy of the test result, so that the safety and the quality of automatic driving are ensured.
The scene refers to a combination of a driving occasion and a driving scene, and is deeply influenced by a driving environment, such as road, traffic, weather, illumination and other factors, which jointly form a whole scene concept. The scene is the comprehensive reflection of the environment and the driving behavior in a certain time and space range, and describes the external states of roads, traffic facilities, meteorological conditions, traffic participants and the like and the information of driving tasks, states and the like of the own vehicle. From the view of scene architecture, different driving occasions such as highways, country roads, urban working conditions, airports, docks, closed parks and the like exist; in this case, how to drive, the driving task, the driving speed, the driving mode, and the like together constitute a three-dimensional framework of the entire scene.
Automatic driving has been developed to various degrees worldwide, and the automatic driving has reached the level of L4 and the accumulated test mileage has exceeded 2000 kilometers in the example of Google, whereas the industry considers that the automatic driving needs 160 kilometers accumulated when landing, so there is a long way to reach this goal in view of the prior art and the development limitations of the industry. The time required to achieve this goal is also very long, how to verify the new code in the shortest possible time to improve driving safety, and the construction of a scene library is essential in an automated driving process. Based on different kinds of permutation and combination of traffic participants, the generated test scene library is endless and cannot be tested one by one at all, and based on the current technical development condition of automatic driving, it is completely unnecessary to carry out coverage test on all actual driving scenes.
Therefore, according to the automatic generation method and device for the automatic driving test case provided by the embodiment of the invention, on one hand, the principle of high-speed automatic driving priority in the current industry is selected to perform data analysis based on the traveling data of the company of nearly millions of kilometers, on the other hand, the factor is extracted based on the traveling data to obtain the weight, and the optimal combination of the test scenes is obtained based on the Pairwise algorithm, so that the test scenes which are verified in a short time as much as possible and are effective are achieved. The following description and description will proceed with reference being made to various embodiments.
As shown in fig. 1, an embodiment of the present invention provides an automatic driving test case generation method, including:
and acquiring the weight of each factor and factor in the actual driving data of the automatic driving, and reordering the factors and factors based on a Pairwise algorithm to obtain an optimal test scene case.
Based on the fact that the physical performance test evaluation system of the traditional automobile is obviously different from the physical performance test evaluation system of the traditional automobile in test evaluation content and form, the automatic driving automobile fundamentally changes on the basis of the traditional automobile test, wherein the traditional automobile test emphasizes the performance of an evaluation machine in command execution, and the automatic driving test emphasizes the evaluation of the matching of multiple sensors of the whole automobile and the sensing, judging and decision-making capability of the fusion output of the sensors; the traditional test scene has a fixed mode and a fixed situation, but the test scene of the automatic driving automobile needs to have the characteristics of diversity, typicality and the like, and needs to cover all complex special scenes as far as possible; the software system and hardware equipment of the automatic driving test are changed in a skyward and overland mode.
At present, safety accidents frequently occur in the field of automatic driving, safety becomes an essential problem to be solved in the field of automatic driving, the industry and the society need an automatic driving technology with higher reliability to tamp the development foundation, and the excavation of a test scene, enrichment and improvement of the test technology are very important steps for improving the safety performance of automatic driving.
In this embodiment, as a preferred implementation manner, on one hand, a principle of high-speed automatic driving priority in the current industry is selected to perform data analysis based on traveling data of the company of approximately millions of kilometers, and on the other hand, factor extraction is performed based on the traveling data to obtain weights, and an optimal combination of test scenarios is obtained based on a Pairwise algorithm, so that a test scenario with as many verifications and effectiveness as short as possible is achieved.
On the basis of the above embodiment, acquiring the weight of each factor in the automatic driving actual running data specifically includes:
acquiring automatic driving actual driving data, and classifying and extracting factors and factors in the automatic driving actual driving data; and acquiring the weight of each factor based on an entropy method.
In the present embodiment, as a preferred embodiment, scene factor classification extraction is performed using a python pandas module based on the automatic driving actual running data and weights are automatically calculated.
In this embodiment, as a preferred embodiment, the automated driving actual driving data is counted by using a tool, and the statistical result is classified according to OpenCRG, openscene, and OpenDriver protocols to summarize and extract factors and factors.
On the basis of the above embodiments, the obtaining of the weight of each factor based on the entropy method specifically includes:
obtaining the discrete degree of each factor and factor based on an entropy method, and representing the maximum combination quantity by using matrixes A and N M of N factors and M factors:
in the above formula, i is 1,2, …, n; j is 1,2, …, m; xijIs the value of the ith row and the jth column in the matrix A; obtaining the specific gravity of the ith factor under the j-th index:
formula of entropy value of j-th index:
in the above formula, k is more than 0, ln is a natural number, and the constant k is related to the sample number n, so that e is more than or equal to 0 and less than or equal to 1; for the j index, index value XijThe larger the difference is, the larger the evaluation effect on the scheme is, and the smaller the entropy value is;
formula for coefficient of difference for j-th index:
gj＝1-ej
get the weight of the jth index:
an entropy value method is used for judging the dispersion degree of each factor, and the judgment principle is that the larger the information quantity is, the smaller the uncertainty is, and the smaller the entropy is; the smaller the amount of information, the greater the uncertainty and the greater the entropy.
On the basis of the above embodiments, the factors include objects, road conditions, environments and behaviors in the typical scene of automatic driving;
the factor is parameter information or attribute information of each factor.
The automatic driving automobile is faced with various complicated and intricate environments when driving on the road, and a test system cannot exhaust one of the environments, so that various test scenes can be classified according to a certain classification method.
On the basis of the above embodiments, the objects include other people or vehicles present in the typical scene of automatic driving, and other objects or animals that influence the driving decision or all autonomous movement;
the road condition is the characteristics of a road and the characteristics of traffic control;
the environment is an environment factor which can be changed in a typical scene of automatic driving and is transmitted to an automatic driving automobile in real time by the outside;
the behavior is the driving behavior of the autonomous vehicle itself.
On the basis of the above embodiments, the objects include other people or vehicles present in the typical scene of automatic driving, and other objects or animals that influence the driving decision or all autonomous movement;
the road condition is the characteristics of a road and the characteristics of traffic control;
the environment is an environment factor which can be changed in a typical scene of automatic driving and is transmitted to an automatic driving automobile in real time by the outside;
the behavior is the driving behavior of the autonomous vehicle itself.
In the present embodiment, as a preferred embodiment, the objects are defined as other people or vehicles present in the scene (typical scene of automatic driving), and other objects or animals that influence the driving decision or all possible autonomous movements. On the one hand, the method mainly depends on various sensors for automatic driving, including millimeter wave radar, a camera, an ultrasonic probe, a laser radar and the like, and meanwhile, a large amount of real-time calculation is also carried out to predict the advancing direction of the other party in the next second.
The factor is specific parameter information or attribute information of each factor, such as:
object type factor: such as street lamps, garbage bins, signboards, etc.;
object movement speed factor: stationary, moving at low speed (e.g., cyclists), moving at high speed (e.g., flying cars);
object movement direction factor: what the relative angle of movement is on the left or right of the autonomous vehicle;
number of objects factor: if a plurality of police cars stop at the roadside or a group of ducks cross the road, the speed needs to be reduced;
environmental awareness: for a living subject, the autonomous vehicle also needs to determine whether the subject is carefully watching the road, such as a driver of a drunk driver, a child aged 5, or a young person walking while watching a mobile phone.
In this embodiment, as a preferred implementation, the road condition factors are defined as the characteristics of the road and the characteristics of traffic control, and will not change with the environmental change, and the autonomous driving vehicle can predict in advance, and is mainly autonomously located by a map drawn in advance.
The factor is specific parameter information or attribute information of each factor, for example:
design factors of the intersection are as follows: crossroads, T-shaped intersections, Y-shaped intersections;
traffic control mode factors: traffic light patterns, stop boards and avoidance boards;
lane number factor: single lane, 4 lanes;
lane line factors: a parting line is present and not present;
lane type factor: a bicycle lane, a bus lane, a passing lane;
the speed limiting factor is as follows: 25mph, business district speed limit, residential district speed limit;
road type factor: high speed, common path, minor path;
angle factors: uphill, downhill, jolting;
regional factors: school district, hospital district, mountain area, construction area.
The environment is an essential element of a scene, and determines whether an autonomous automobile can get on the road to a great extent. In the embodiment, as a preferred implementation, the environment is defined as all possible changing environmental factors, and much data of the environment needs to be transmitted to the automatic driving automobile in real time depending on the outside.
The factor is specific parameter information or attribute information of each factor, such as:
weather factors: rainfall, wind speed, temperature, visibility;
the lighting factor is as follows: cloudy day, sunrise and sunset time, sun angle;
road surface factors: freezing, water accumulation and construction;
signal factors are as follows: 5G signal strength (signal in tunnel may be very poor);
noise factors: ambient noise can affect pedestrians or other vehicles from hearing the signal from an autonomous automobile.
In the present embodiment, as a preferred embodiment, the behavior is defined as the behavior of the autonomous vehicle itself, and the data in this respect mainly depends on the path planning.
The factor is specific parameter information or attribute information of each factor, such as:
driving direction factors: straight going, backing, U-shaped turning around, left turning, right turning, arc, leaving lane, merging lane;
the speed factor: static, low-speed running and high-speed running;
acceleration factor: accelerating, decelerating and keeping constant speed;
signal factors are as follows: visual signals and sound signals emitted by the automatic driving automobile, and the like.
On the basis of the above embodiments, the factors and factors are reordered based on the Pairwise algorithm, which specifically includes:
formulating a test scene exclusion rule based on a preset automatic driving rule, recombining the factors and the factors based on a Pairwise algorithm, performing unreasonable scene exclusion based on a preset unreasonable scene exclusion rule, and optimally screening the combined test scene case based on the weight of the factors to obtain an optimal test scene case.
In this embodiment, as a preferred embodiment, after acquiring N factors, F1 and F2 … Fn are used to represent that each factor has Li different states, each use case contains N factors, and any factor acquires any state (level) in the factor, so that the combination of Li, P and Lj, Q (Li, P indicates that of factor i) appears in at least one group of test cases.
And (4) eliminating the inconsistent scene formulation rule according to the actual driving experience, namely automatically generating an optimal test scene which is consistent with the expectation.
And (3) formulating a driving scene which is not in accordance with the normalcy based on the actual driving experience:
#
when the speed is 0, the vehicle cannot be accelerated, decelerated or steered
#
if [ speed of obstacle A ] ═ stationary "
THEN [ obstacle vehicle behavior a ] < > "deceleration" AND [ obstacle vehicle motion direction a ] ═ hold "AND [ road ahead change a ] ═ hold";
#
speed # equals high speed (120km/h), cannot be accelerated
#
if [ obstacle vehicle speed a ] ═ high speed (120km/h) "THEN [ obstacle vehicle behavior a ] < >" acceleration ";
#
no left doubling of # passing lane and no right doubling of emergency lane
#
if [ lane a where the obstacle vehicle is located ] ═ in the passing lane "THEN [ obstacle vehicle motion direction a ] < >" left parallel line ";
if [ lane a where the obstacle vehicle is located ] ═ emergency lane "THEN [ obstacle vehicle moving direction a ] < >" right parallel line ";
in this embodiment, as a preferred embodiment, the permutation and combination of the factors and factors are compared by using a Pairwise algorithm and an orthogonal analysis method, for example, the factors and factors extracted in the first step:
(1) case number of orthogonal analysis: 720 pieces (a)
(2) Only the number of cases after the exclusion rule is used: 228 pieces (A)
(3) Case number after using rule of exclusion and Pairwise algorithm: 120 pieces
(4) And (4) sorting the cases according to the weight of the factor and the step (3): and the 22 pieces of files automatically generate an export document by using a python openpyxl module to perform excel reading and writing operation according to the final combination result.
According to a second aspect of the embodiments of the present invention, an automatic driving test case automatic generation apparatus is provided, based on the automatic driving test case automatic generation method in each of the above embodiments, including a screening module and an optimal test scenario case generation module;
the screening module is used for acquiring the weight of each factor in the actual driving data of the automatic driving;
and the optimal test scene case generation module is used for reordering the factors and the factors based on a Pairwise algorithm to obtain an optimal test scene case.
An embodiment of the present invention provides an electronic device, as shown in fig. 2, the device including: a processor (processor)501, a communication Interface (Communications Interface)502, a memory (memory)503, and a communication bus 504, wherein the processor 501, the communication Interface 502, and the memory 503 are configured to communicate with each other via the communication bus 504. The processor 501 may call a computer program running on the memory 503 and on the processor 501 to execute the automatic driving test case generation method provided by the foregoing embodiments, for example, the method includes:
and acquiring the weight of each factor and factor in the actual driving data of the automatic driving, and reordering the factors and factors based on a Pairwise algorithm to obtain an optimal test scene case.
In addition, the logic instructions in the memory 503 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
An embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to execute the automatic driving test case generation method provided in the foregoing embodiments, for example, the method includes:
and acquiring the weight of each factor and factor in the actual driving data of the automatic driving, and reordering the factors and factors based on a Pairwise algorithm to obtain an optimal test scene case.
In summary, the method and the device for automatically generating the automatic driving test case provided in the embodiments of the present invention select the principle of high-speed automatic driving priority in the current industry to perform data analysis based on the traveling data of the company of nearly millions kilometers, and perform factor extraction to obtain the weight based on the traveling data and obtain the optimal combination of the test scenarios based on the Pairwise algorithm, thereby achieving the purpose of short time verification as much as possible and effective test scenarios.
The above-described embodiments of the electronic device and the like are merely illustrative, and units illustrated as separate components may or may not be physically separate, and components displayed 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute the various embodiments or some parts of the methods of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. An automatic generation method of an automatic driving test case is characterized by comprising the following steps:
and acquiring the weight of each factor and factor in the actual driving data of the automatic driving, and reordering the factors and factors based on a Pairwise algorithm to obtain an optimal test scene case.
2. The automatic generation method of the automatic driving test case according to claim 1, wherein the obtaining of the weight of each factor in the automatic driving actual driving data specifically includes:
acquiring automatic driving actual driving data, and classifying and extracting factors and factors in the automatic driving actual driving data; and acquiring the weight of each factor based on an entropy method.
3. The automatic generation method of the automatic driving test case according to claim 2, wherein the obtaining of the weight of each factor based on the entropy method specifically includes:
obtaining the discrete degree of each factor and factor based on an entropy method, and representing the maximum combination quantity by using matrixes A and N M of N factors and M factors:
in the above formula, i is 1,2, …, n; j is 1,2, …, m; xijIs the value of the ith row and the jth column in the matrix A; obtaining the specific gravity of the ith factor under the j-th index:
formula of entropy value of j-th index:
formula for coefficient of difference for j-th index:
gj＝1-ej
get the weight of the jth index:
4. the method for automatically generating the automatic driving test case according to claim 2, wherein the factors include objects, road conditions, environments and behaviors in an automatic driving typical scene;
the factor is parameter information or attribute information of each factor.
5. The method for automatically generating the auto-driving test case according to claim 4, wherein the objects comprise other people or vehicles appearing in the auto-driving typical scene and other objects or animals affecting driving decisions or all autonomous moving;
the road condition is the characteristics of a road and the characteristics of traffic control;
the environment is an environment factor which can be changed in a typical scene of automatic driving and is transmitted to an automatic driving automobile in real time by the outside;
the behavior is the driving behavior of the autonomous vehicle itself.
6. The automatic generation method of the automatic driving test case according to claim 2, wherein the factors and the factors are reordered based on a Pairwise algorithm, and specifically comprises:
formulating a test scene exclusion rule based on a preset automatic driving rule, recombining the factors and the factors based on a Pairwise algorithm, performing unreasonable scene exclusion based on a preset unreasonable scene exclusion rule, and optimally screening the combined test scene case based on the weight of the factors to obtain an optimal test scene case.
7. An automatic generation device for an automatic driving test case is characterized by comprising a screening module and an optimal test scene case generation module;
the screening module is used for acquiring the weight of each factor in the actual driving data of the automatic driving;
and the optimal test scene case generation module is used for reordering the factors and the factors based on a Pairwise algorithm to obtain an optimal test scene case.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 6 are implemented when the processor executes the program.
9. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910913474.8A CN110716529A (en) | 2019-09-25 | 2019-09-25 | Automatic generation method and device for automatic driving test case |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910913474.8A CN110716529A (en) | 2019-09-25 | 2019-09-25 | Automatic generation method and device for automatic driving test case |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110716529A true CN110716529A (en) | 2020-01-21 |
Family
ID=69210909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910913474.8A Pending CN110716529A (en) | 2019-09-25 | 2019-09-25 | Automatic generation method and device for automatic driving test case |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110716529A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611175A (en) * | 2020-06-01 | 2020-09-01 | 深圳裹动智驾科技有限公司 | Automatic driving software development method, server side and client side |
| CN111679991A (en) * | 2020-06-23 | 2020-09-18 | 武汉光庭信息技术股份有限公司 | Method and system for generating test case by utilizing big data |
| CN111831570A (en) * | 2020-07-23 | 2020-10-27 | 深圳慕智科技有限公司 | Test case generation method oriented to automatic driving image data |
| CN111881032A (en) * | 2020-07-23 | 2020-11-03 | 深圳慕智科技有限公司 | Distributed fuzzy test method for laser radar of automatic driving software system |
| CN112328477A (en) * | 2020-11-02 | 2021-02-05 | 东软睿驰汽车技术（沈阳）有限公司 | Method and device for generating test case of automatic driving algorithm and electronic equipment |
| CN112629881A (en) * | 2020-12-16 | 2021-04-09 | 北京航空航天大学 | Method for extracting automatic driving simulation test element |
| CN112835790A (en) * | 2021-01-22 | 2021-05-25 | 北京罗克维尔斯科技有限公司 | Test method, device, equipment and medium for automatic driving software |
| CN113589798A (en) * | 2021-08-12 | 2021-11-02 | 上海裹动科技有限公司 | Automatic test behavior generation method and server |
| CN113760752A (en) * | 2021-08-18 | 2021-12-07 | 一汽奔腾轿车有限公司 | Real vehicle testing method and device of driver state monitoring system |
| CN113804451A (en) * | 2020-06-11 | 2021-12-17 | 上海汽车集团股份有限公司 | Automatic simulation test method and device for intelligent driving of automobile |
| CN114185330A (en) * | 2021-12-12 | 2022-03-15 | 蜂联智能（深圳）有限公司 | Control method and control device based on multi-scene interaction |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU166823U1 (en) * | 2016-06-22 | 2016-12-10 | Юрий Александрович Борисов | APPARATUS FOR CHECKING THE HELICOPTER AUTOPILOT |
| CN107704381A (en) * | 2017-08-31 | 2018-02-16 | 电子科技大学 | A kind of Generation of software test case method of combination of two |
| CN108765235A (en) * | 2018-05-09 | 2018-11-06 | 公安部交通管理科学研究所 | Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case |
| CN109900494A (en) * | 2019-02-25 | 2019-06-18 | 上海机动车检测认证技术研究中心有限公司 | A kind of generation method of test case |
| CN110232257A (en) * | 2019-07-02 | 2019-09-13 | 吉林大学 | A kind of construction method and its degree-of-difficulty factor calculation method of automatic Pilot test scene |
-
2019
- 2019-09-25 CN CN201910913474.8A patent/CN110716529A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU166823U1 (en) * | 2016-06-22 | 2016-12-10 | Юрий Александрович Борисов | APPARATUS FOR CHECKING THE HELICOPTER AUTOPILOT |
| CN107704381A (en) * | 2017-08-31 | 2018-02-16 | 电子科技大学 | A kind of Generation of software test case method of combination of two |
| CN108765235A (en) * | 2018-05-09 | 2018-11-06 | 公安部交通管理科学研究所 | Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case |
| CN109900494A (en) * | 2019-02-25 | 2019-06-18 | 上海机动车检测认证技术研究中心有限公司 | A kind of generation method of test case |
| CN110232257A (en) * | 2019-07-02 | 2019-09-13 | 吉林大学 | A kind of construction method and its degree-of-difficulty factor calculation method of automatic Pilot test scene |
Non-Patent Citations (3)
| Title |
|---|
| 李诗隽 等: "城市化与房地产繁荣度动态耦合协调关系研究", 《中国房地产》 * |
| 范莉莉 等: "基于熵值法的钢铁企业低碳竞争力评价", 《软科学》 * |
| 韩兴勇 等: "我国渔业台风灾害风险评价及区划研究", 《海洋开发与管理》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611175B (en) * | 2020-06-01 | 2023-05-26 | 深圳安途智行科技有限公司 | Automatic driving software development method, server and client |
| CN111611175A (en) * | 2020-06-01 | 2020-09-01 | 深圳裹动智驾科技有限公司 | Automatic driving software development method, server side and client side |
| CN113804451A (en) * | 2020-06-11 | 2021-12-17 | 上海汽车集团股份有限公司 | Automatic simulation test method and device for intelligent driving of automobile |
| CN111679991B (en) * | 2020-06-23 | 2021-04-13 | 武汉光庭信息技术股份有限公司 | Method and system for generating test case by utilizing big data |
| CN111679991A (en) * | 2020-06-23 | 2020-09-18 | 武汉光庭信息技术股份有限公司 | Method and system for generating test case by utilizing big data |
| CN111881032A (en) * | 2020-07-23 | 2020-11-03 | 深圳慕智科技有限公司 | Distributed fuzzy test method for laser radar of automatic driving software system |
| CN111831570A (en) * | 2020-07-23 | 2020-10-27 | 深圳慕智科技有限公司 | Test case generation method oriented to automatic driving image data |
| CN112328477A (en) * | 2020-11-02 | 2021-02-05 | 东软睿驰汽车技术（沈阳）有限公司 | Method and device for generating test case of automatic driving algorithm and electronic equipment |
| CN112328477B (en) * | 2020-11-02 | 2023-08-15 | 东软睿驰汽车技术（沈阳）有限公司 | Method and device for generating test case of automatic driving algorithm and electronic equipment |
| CN112629881A (en) * | 2020-12-16 | 2021-04-09 | 北京航空航天大学 | Method for extracting automatic driving simulation test element |
| CN112835790A (en) * | 2021-01-22 | 2021-05-25 | 北京罗克维尔斯科技有限公司 | Test method, device, equipment and medium for automatic driving software |
| CN113589798A (en) * | 2021-08-12 | 2021-11-02 | 上海裹动科技有限公司 | Automatic test behavior generation method and server |
| CN113760752A (en) * | 2021-08-18 | 2021-12-07 | 一汽奔腾轿车有限公司 | Real vehicle testing method and device of driver state monitoring system |
| CN114185330A (en) * | 2021-12-12 | 2022-03-15 | 蜂联智能（深圳）有限公司 | Control method and control device based on multi-scene interaction |
| CN114185330B (en) * | 2021-12-12 | 2024-06-11 | 深圳市集智创新信息技术有限公司 | Control method and control device based on multi-scene interaction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110716529A (en) | Automatic generation method and device for automatic driving test case | |
| CN110688311A (en) | Test case management method and device for automatic driving typical scene | |
| US11554785B2 (en) | Driving scenario machine learning network and driving environment simulation | |
| RU2733015C1 (en) | Real-time vehicle control | |
| RU2734744C1 (en) | Operational control of autonomous vehicle, including operation of model instance of partially observed markov process of decision making | |
| RU2725920C1 (en) | Control of autonomous vehicle operational control | |
| RU2734732C1 (en) | Traffic network blocking tracking during operational control of autonomous vehicle | |
| WO2022206942A1 (en) | Laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field | |
| US10127466B2 (en) | Lateral sign placement determination | |
| CN111178402B (en) | Scene classification method and device for road test of automatic driving vehicle | |
| CN110688943A (en) | Method and device for automatically acquiring image sample based on actual driving data | |
| CN111797001A (en) | Method for constructing automatic driving simulation test model based on SCANeR | |
| Niranjan et al. | Deep learning based object detection model for autonomous driving research using carla simulator | |
| CN106198049A (en) | Real vehicles is at ring test system and method | |
| CN113935441B (en) | Method and device for selecting automobile automatic driving function test road and storage medium | |
| CN110675476A (en) | Method and device for visually conveying definition of automatic driving scene | |
| CN110232335A (en) | Driving Scene classification method and electronic equipment | |
| CN115048972B (en) | Traffic scene deconstruction classification method and virtual-real combined automatic driving test method | |
| CN111477030B (en) | Vehicle collaborative risk avoiding method, vehicle end platform, cloud end platform and storage medium | |
| CN115098079B (en) | Radar detection model determination method, system, electronic device and readable storage medium | |
| CN116457800A (en) | Architecture for map change detection in an autonomous vehicle | |
| CN113511204A (en) | Vehicle lane changing behavior identification method and related equipment | |
| CN115165387A (en) | Control method, device and system for testing performance of automatic driving whole vehicle | |
| Fazekas et al. | ANN-based classification of urban road environments from traffic sign and crossroad data | |
| CN114771576A (en) | Behavior data processing method, control method of automatic driving vehicle and automatic driving vehicle |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200121 |
|
| RJ01 | Rejection of invention patent application after publication |