CN111611711B - Automatic driving data processing method and device and electronic equipment - Google Patents
Automatic driving data processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN111611711B CN111611711B CN202010436745.8A CN202010436745A CN111611711B CN 111611711 B CN111611711 B CN 111611711B CN 202010436745 A CN202010436745 A CN 202010436745A CN 111611711 B CN111611711 B CN 111611711B
- Authority
- CN
- China
- Prior art keywords
- data
- scene
- defect
- automatic driving
- vehicle
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
Abstract
The application discloses an automatic driving data processing method and device and electronic equipment, and relates to the field of automatic driving. The specific implementation scheme is as follows: acquiring initial scene data of an automatic driving vehicle running an automatic driving system when the automatic driving vehicle runs in a real environment, wherein the initial scene data comprises data of a defect scene; cutting out the data of the defect scene from the initial scene data; inputting the data of the defect scene into a simulation platform, and operating the updated automatic driving system by the simulation platform based on the data of the defect scene to obtain an operation result of the updated automatic driving system in the defect scene. The scene data obtained by the method can greatly improve the reproduction degree of the simulation platform to the real defect scene.
Description
Technical Field
The embodiment of the application relates to the technical field of automatic driving in data processing technology, in particular to an automatic driving data processing method, an automatic driving data processing device and electronic equipment.
Background
In the iterative development process of an automatic driving system, the role of scene data, especially the data of a defect scene, is particularly important. A defective scene refers to a scene when an autonomous vehicle exhibits unreasonable driving behavior on a real road. For example, when an autonomous vehicle runs straight at an intersection, there is a risk of collision with a vehicle ahead, and the scene where the autonomous vehicle is located is a defective scene. The data of the defective scene may include data corresponding to various scene elements such as pedestrians, obstacles, and the like involved in the defective scene. The data of the defect scene plays an important role in regression testing and effect improvement of the automatic driving system. And a tester can judge whether the automatic driving system still has certain defects according to the operation result of the automatic driving system in the defect scene. And the research and development personnel judge whether the found defects are solved according to the operation result of the automatic driving system in the defect scene.
In the iterative development of the autopilot system, a simulation platform can be utilized for testing. At present, the simulation platform cannot perform fully intelligent simulation on scene data, especially data of a defect scene. Therefore, how to obtain data close to the real defect scene based on the capability of the current simulation platform is a problem to be solved.
Disclosure of Invention
The embodiment of the application provides an automatic driving data processing method, an automatic driving data processing device and electronic equipment, which are used for obtaining data close to a real defect scene.
In a first aspect, an embodiment of the present application provides an autopilot data processing method, including:
acquiring initial scene data of an automatic driving vehicle running an automatic driving system when the automatic driving vehicle runs in a real environment, wherein the initial scene data comprises data of a defect scene, and the defect scene is a scene where the vehicle is in a driving behavior which is inconsistent with an expected one;
cutting out the data of the defect scene from the initial scene data;
inputting the data of the defect scene into a simulation platform, and operating the updated automatic driving system by the simulation platform based on the data of the defect scene to obtain an operation result of the updated automatic driving system in the defect scene.
In a second aspect, an embodiment of the present application provides an autopilot data processing apparatus, including:
the processing module is used for acquiring initial scene data of an automatic driving vehicle running an automatic driving system when the automatic driving vehicle runs in a real environment, wherein the initial scene data comprises data of a defect scene, and the defect scene is a scene where the vehicle is in a driving behavior which is inconsistent with an expected one; the method comprises the steps of,
cutting out the data of the defect scene from the initial scene data;
the input module is used for inputting the data of the defect scene into the simulation platform, and the simulation platform operates the updated automatic driving system based on the data of the defect scene to obtain the operation result of the updated automatic driving system in the defect scene.
In a third aspect, an embodiment of the present application provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect described above.
In a fourth aspect, embodiments of the present application provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product comprising: a computer program stored in a readable storage medium, from which it can be read by at least one processor of an electronic device, the at least one processor executing the computer program causing the electronic device to perform the method of the first aspect.
One embodiment of the above application has the following advantages or benefits:
and cutting out the data of a defect scene with defects from the initial scene data obtained by the actual drive test of the vehicle, and inputting the data of the defect scene into a simulation platform. Because the data of the defect scene is cut from the real scene data, the data of the defect scene can reproduce the drive test defect, and therefore, after the data of the defect scene is input into the simulation platform, the simulation platform can embody the actual operation result based on the operation result obtained after the automatic driving system is operated by the data of the defect scene, thereby greatly improving the reproduction degree of the simulation platform to the real defect scene.
Other effects of the above alternative will be described below in connection with specific embodiments.
Drawings
The drawings are for better understanding of the present solution and do not constitute a limitation of the present application. Wherein:
FIG. 1 is an exemplary system architecture diagram of an autopilot data processing method of an embodiment of the present application;
fig. 2 is a flow chart of an automatic driving data processing method according to an embodiment of the present application;
FIG. 3 is an example diagram of scene durations identified by a plurality of candidate data;
FIG. 4 is a schematic diagram of selecting data of a defect scene from a plurality of candidate data;
FIG. 5 is a schematic diagram of a flow of performing simulation test on data of a cut-out defect scene in an embodiment of the present application;
FIG. 6 is a block diagram of an autopilot data processing apparatus according to an embodiment of the present application;
fig. 7 is a block diagram of an electronic device of a method of automated driving data processing according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The embodiment of the application can be applied to a scene of testing an automatic driving system by using a simulation platform. In the development process of the automatic driving system, continuous verification tests are required to be carried out on the automatic driving system under various scenes so as to ensure that the safety of the automatic driving vehicle can be higher than the operation safety of a human driver. In the case where the function of the automatic driving system is not stable yet, if the test is performed by directly using the real drive test, there may be a problem of insufficient safety or the like. Therefore, the test of the autopilot system by using the simulation platform becomes an important means for testing the autopilot system. The simulation platform is required to simulate real road scenes and record the running conditions of the automatic driving system under the scenes. Especially for the defect scenes, as the vehicle is defective under the scenes, the higher the reproduction degree of the simulation platform to the defect scenes is, the more the automatic driving system can identify whether the defect occurring under the defect scenes is solved. However, the current simulation platform cannot perform fully intelligent simulation on the data of the defect scene.
Based on the above problems, the embodiment of the application provides an automatic driving data processing method, which is based on scene data during automatic driving vehicle driving, cuts and selects to generate defect scene data capable of reproducing drive test defects, and operates an automatic driving system by a simulation platform based on the defect scene data, so that the reproduction degree of the simulation platform to a real defect scene is greatly improved.
FIG. 1 is an exemplary system architecture diagram of an autopilot data processing method of an embodiment of the present application, as shown in FIG. 1, involving an autopilot vehicle, electronics that generate data for a defective scene, and a simulation platform. The electronic equipment is respectively in communication connection with the automatic driving vehicle and the simulation platform. The autonomous vehicle performs drive tests daily, i.e. travels in a real environment. During driving, the autonomous vehicle may record scene data, such as sensor data, obstacle information, lanes in which the vehicle is located, etc., in real time. If a defect occurs, the autonomous vehicle also records the time at which the defect occurred. The electronic device generating the data of the defect scene uses the method of the embodiment of the application to intercept and select the data of the defect scene which can reproduce the drive test defect, and inputs the data to the simulation platform. The simulation platform operates the automatic driving system after the developer modifies the defects based on the data of the defect scene to obtain operation results, and the developer or the tester uses the operation results to perform subsequent analysis and other operations according to respective needs.
It should be noted that, in the implementation process, the device where the simulation platform is located may be the same physical device as the electronic device that generates the data of the defect scene in fig. 1, or may be a different physical device, which is not limited in particular in the embodiment of the present application.
For convenience of description, the following embodiments of the present application will simply refer to an autonomous vehicle as a vehicle.
Fig. 2 is a flow chart of an automatic driving data processing method according to an embodiment of the present application, and an execution subject of the method is the above-mentioned electronic device for generating the data of the defect scene, which is hereinafter referred to as an electronic device. As shown in fig. 2, the method includes:
s201, acquiring initial scene data of an automatic driving vehicle running an automatic driving system when the automatic driving vehicle runs in a real environment, wherein the initial scene data comprises data of a defect scene, and the defect scene is a scene where the vehicle is in a driving behavior which is inconsistent with an expected one.
In the iterative development process of the automatic driving system, a new automatic driving system is obtained through a certain iteration, and the automatic driving vehicle can install the new automatic driving system and conduct real road test. In the real drive test process, the automatic driving vehicle records scene data in real time. If a defect occurs, the autonomous vehicle also records the time at which the defect occurred. All or part of the scene data recorded by the automatic driving vehicle in one drive test can be used as the initial scene data. It should be understood that if it is partial scene data, the partial scene data includes data of a defective scene.
By way of example, the scene data may include: sensor data, messages sent and/or received by the autopilot system, information about the obstacle (e.g., type of obstacle, location of the obstacle, distance of the obstacle from the vehicle, speed of travel of the obstacle, etc.), lanes in which the vehicle is located, speed of the vehicle, status of traffic lights, map information, etc.
The scene data can be recorded at various moments in the running process of the vehicle. Therefore, when the driving behavior of the vehicle does not match the expected driving behavior, that is, when the driving defect occurs, scene data of a period of time before and a period of time after the occurrence of the driving defect is also recorded.
S202, cutting out the data of the defect scene from the initial scene data.
Illustratively, if the vehicle is drive tested at 9:00 to 11:00 of a day, the vehicle may record scene data at various times between 9:00 to 11:00 points. At 10:00, the vehicle is defective. For example, there is a risk of collision with a preceding vehicle, the electronic device may truncate scene data at the time of occurrence of such a defect as data of a defective scene. For example, scene data between 9:55 and 10:05 is truncated as data of a defective scene.
It should be understood that a vehicle defect is associated with a scene of a period of time, and thus, the scene in which the vehicle is defective includes not only the scene at one time when the defect occurs but also the scenes of a period of time before and after the defect occurs.
S203, inputting the data of the defect scene into a simulation platform, and operating the updated automatic driving system by the simulation platform based on the data of the defect scene to obtain an operation result of the updated automatic driving system in the defect scene.
Optionally, the updated autopilot system is a system that corrects for defects relative to an autopilot system installed when the vehicle is routed. Illustratively, when a vehicle is routed, a certain version of the automatic driving system is installed, a defect occurs, and a developer corrects the defect to obtain an updated automatic driving system. Further, the updated autopilot system may be input to a simulation platform. The simulation platform triggers the updated automatic driving system to operate in the defect scene based on the received data of the defect scene and the updated automatic driving system, and obtains an updated operation result in the defect scene. The operation results may include, for example: no collision, running in the rightmost lane, performing a right turn operation, etc.
The operation result can be used by a developer or a tester. Three examples of using the above-described running results are listed below:
1. the developer uses the running results to conduct regression testing.
The developer corrects the automatic driving system aiming at the defects in the driving process, and the simulation platform triggers the automatic driving system to operate under the defect scene. By analyzing the operation result, a developer can know whether the defect occurring in the specific defect scene is solved.
2. And the tester uses the operation result to perform system quality test.
And a tester can judge whether the automatic driving system still has the defects in the defect scene by analyzing the operation result.
3. And measuring the updated automatic driving system.
By way of example, a metrology subsystem may be included in the simulation platform that is run through the defect scene playback data and that, based on the categories of the defect scenes, may measure recall rates for recalling metrics for each of the problem scene categories, thereby guiding optimization of the metrology strategy of the metrology system.
According to the operation result of the automatic driving system in the defect scene, whether the automatic driving system still has certain defects can be judged. And the research and development personnel judge whether the found defects are solved according to the operation result of the automatic driving system in the defect scene.
In this embodiment, data of a defect scene with a defect is cut out from initial scene data obtained by actual drive test of a vehicle, and the data of the defect scene is input into a simulation platform. Because the data of the defect scene is cut from the real scene data, the data of the defect scene can reproduce the drive test defect, and therefore, after the data of the defect scene is input into the simulation platform, the simulation platform can embody the actual operation result based on the operation result obtained after the automatic driving system is operated by the data of the defect scene, thereby greatly improving the reproduction degree of the simulation platform to the real defect scene.
The method of the electronic device to extract the data of the defect scene from the initial scene data in the above step S202 is described below.
As described above, the scene in which the defect occurs in the vehicle includes not only the scene at the moment when the defect occurs but also the scene for a period of time before and after the defect occurs. Exemplary, the vehicle is at 10:00 is at risk of collision, then the scenario of this defect should include 10:00 a period of time before and after this time to optimize the effect of scene reproduction. When the data of the defect scene is intercepted from the initial scene data, if the duration of the intercepted defect scene is too long, when the simulation platform runs the updated automatic driving system based on the data of the defect scene, the difference of the running results between the simulation vehicle and the drive test real vehicle is larger and larger, the scene is intercepted in advance, and therefore the defect of the drive test cannot be better reproduced. If the length of the intercepted defect scene is too short, the actual defect can be reproduced with a high probability, but the whole process of the defect cannot be completely displayed.
Based on the above consideration, when the data of the defect scene is selected in the step S202, as an alternative implementation manner, the electronic device may select a plurality of pieces of data to be selected from the initial scene data based on the time when the driving behavior of the vehicle is inconsistent with the expected driving behavior, and select the data of the defect scene from the plurality of pieces of data to be selected according to the simulation test result of the plurality of pieces of data to be selected.
In one example, the time at which the defect occurs when the vehicle is manually taken over may be taken as the time at which the driving behavior of the vehicle that is inconsistent with the expectation occurs. For example, when a vehicle is at risk of collision with a preceding vehicle and an in-vehicle person presses an in-vehicle button to take over the vehicle, the time at which the button is pressed is the time at which the vehicle exhibits driving behavior that is inconsistent with the expectation.
Based on the moment, the electronic device can select a plurality of pieces of data to be selected, perform simulation test based on the pieces of data to be selected, and know which piece of data to be selected in the plurality of pieces of data to be selected is most suitable as data of a defect scene according to the result of the simulation test, namely which piece of data to be selected is optimal scene data, so that the data of the selected defect scene can keep a certain scene, and actual problems on the road can be better reproduced.
As an alternative implementation manner, based on the moment when the vehicle has driving behavior which is inconsistent with expected driving behavior, the scene ending moments identified by the selected plurality of candidate data are the same, and the scene duration identified by each candidate data is different from one another.
Scene data before the occurrence of a defect is more important for the effect of reproducing a scene, while once the defect occurs, the effect of subsequent scenes on reproducing a scene becomes smaller. Therefore, in this embodiment, the end moments of the selected plurality of candidate data are the same, and at the same time, the duration of the scenes identified by the candidate data is different, so that the scenes with different start moments and the same end moment can be selected, and the optimal scene data which can not only keep a certain scene, but also better reproduce the actual problem on the road can be covered in the scenes.
As an optional implementation manner, the scene end time identified by each candidate data in the plurality of candidate data is after the time when the driving behavior inconsistent with the expected behavior occurs, and is different from the time when the driving behavior inconsistent with the expected behavior occurs by a preset duration.
As described above, scene data before occurrence of a defect is more important for the effect of reproducing a scene, and once the defect occurs, the effect of subsequent scenes on reproducing a scene becomes smaller. Therefore, the scene end time identified by each candidate data is selected to be a certain time after the time when the defect occurs. The starting time of the scenes marked by the data to be selected is different, so that the scenes can contain the optimal scene data which can keep a certain scene and better reproduce the actual problems on the road.
Fig. 3 is an example diagram of scene durations identified by a plurality of candidate data, and as shown in fig. 3, assuming that a time when a driving behavior of a vehicle inconsistent with an expectation is a t1 time, the electronic device may select a t2 time 5 seconds after the t1 time as a scene end time of each candidate data based on the t1 time, and at the same time, each time from 5 seconds before the t1 time as a scene start time of each candidate data. For example, t3 is the scene start time of the first candidate data, t4 is the scene start time of the second candidate data, and so on.
For example, the electronic device may start 5 seconds before the time t1 and end 100 seconds, that is, 96 pieces of candidate data may be selected, where the start time of the 96 pieces of candidate data is a time before the time t1, and the end time is a time t2 5 seconds after the time t 1.
On the basis of selecting a plurality of data to be selected, the electronic equipment selects data of a defect scene from the plurality of data to be selected according to simulation test results of the data to be selected.
As an optional implementation manner, the electronic device determines similarity between the driving data corresponding to each piece of data to be selected and the actual driving data of the vehicle in the defect scene, where the driving data corresponding to the piece of data to be selected is the driving data obtained by the simulation platform running the automatic driving system based on the piece of data to be selected, and further, the piece of data to be selected with the highest similarity and the shortest identified scene duration is used as the data of the defect scene.
The simulation platform is used for running the automatic driving system when the road is operated based on the data to be selected, and the driving data are obtained. And carrying out similarity detection on the running data and actual running data during actual driving of the vehicle, so that the similarity of the running data and the actual running data can be obtained. The travel data may include, for example: travel track, travel speed, etc.
The method for performing similarity detection may be, for example, log sim scene detection or log2world scene detection.
After the similarity between each piece of data to be selected and the actual running data is obtained, the electronic equipment takes the data to be selected, which has the highest similarity and the shortest scene duration, as the data of the defect scene.
In one example, if one candidate data with highest similarity exists in the plurality of candidate data, the candidate data is directly used as the data of the defect scene. And if a plurality of candidate data with the same similarity or the difference smaller than a certain threshold value exist, taking the candidate data with the shortest duration in the candidate data as the data of the defect scene.
Fig. 4 is a schematic diagram of selecting data of a defect scene from a plurality of pieces of data to be selected, as shown in fig. 4, for N pieces of data to be selected, each piece of data to be selected has two pieces of information of similarity and scene duration, and based on these pieces of information, the electronic device may select the data to be selected that has the highest similarity and has the shortest scene duration as the data of the defect scene.
In this embodiment, the simulation test is performed based on each piece of the candidate data, so that it can be known which piece of the candidate data corresponds to the running data most similar to the actual running data of the vehicle, that is, which piece of the candidate data can reproduce the defect scene most, and meanwhile, by combining the duration of the candidate data, the optimal scene data which can not only maintain a certain scene but also reproduce the actual problem on the road better can be selected.
In a specific implementation process, various types of defects may occur in the vehicle during driving, and thus, corresponding defect scenes may have corresponding types. By way of example, the categories of defect scenes may include: collision with the front vehicle, lane change error, untimely deceleration and the like. The data of the defect scene of the same class can be used for testing the problem of the class. Thus, as an alternative, the electronic device may divide the data of defect scenes belonging to the same category into the same scene data set, i.e. one scene data set may correspond to one problem category.
Accordingly, as an optional implementation manner, after the electronic device cuts out the data of the defect scene through the foregoing method, the data of the defect scene may be added to the scene data set corresponding to the type according to the type of the defect scene.
For example, if the type of the defect scene is that the defect scene collides with the front vehicle, the data of the defect scene is added to the scene data set of the collision of the front vehicle.
By the method, data of each type of defect scene can be more abundant, and then the effect in simulation test is better.
Accordingly, the electronic device may input a set of scene data for each category into the simulation platform. When the updated automatic driving system is operated, the simulation platform can verify the running condition of the updated automatic driving system under various defect scenes of the category, so that as many defect scenes as possible can be covered, and the simulation test effect is better.
As an optional implementation manner, when the electronic device adds the data of the defect scene to the scene data set, it may first determine whether there is previous scene data that is repeated with the data of the defect scene in the scene data set corresponding to the category, and if not, add the data of the defect scene to the scene data set corresponding to the category.
In this way, the repeated data in the scene data set can be avoided, and the purity of the scene data set is ensured.
Alternatively, when the data of the defective scene and the previous scene data satisfy the following condition, the data of the defective scene may be considered to be repeated with the previous scene data:
the vehicle identification is the same and the moment when the vehicle appears to be in unexpected driving behaviour is the same.
That is, defects that occur at the same time in the same vehicle can be considered to be the same defects, and the repeated addition to the scene data set is not required.
Fig. 5 is a schematic flow chart of cutting out data of a defect scene and performing a simulation test in the embodiment of the present application, as shown in fig. 5, initial scene data during road collection is collected by a vehicle, an electronic device performs scene cutting out based on the initial scene data, creates a scene data set, and inputs the created scene data set to a simulation platform, where regression test, system quality test, system measurement and the like can be completed.
The specific implementation process refers to the foregoing embodiments, and will not be described herein.
Fig. 6 is a block diagram of an autopilot data processing apparatus according to an embodiment of the present application, and as shown in fig. 6, the apparatus 600 includes:
the processing module 601 is configured to obtain initial scene data of an autopilot vehicle running an autopilot system when the autopilot vehicle runs in a real environment, where the initial scene data includes data of a defective scene, and the defective scene is a scene in which the autopilot vehicle has driving behaviors that are inconsistent with expected behavior; and cutting out the data of the defect scene from the initial scene data.
The input module 602 is configured to input the data of the defect scene into a simulation platform, and the simulation platform operates the updated autopilot system based on the data of the defect scene, so as to obtain an operation result of the updated autopilot system in the defect scene.
As an alternative embodiment, the processing module 601 is specifically configured to:
based on the moment when the driving behavior of the vehicle is inconsistent with the expected driving behavior, a plurality of data to be selected are cut out from the initial scene data; and selecting the data of the defect scene from the data to be selected according to the simulation test result of the data to be selected.
As an optional implementation manner, the scene end time identified by each candidate data in the plurality of candidate data is the same, and the scene duration identified by each candidate data is different from each other.
As an alternative embodiment, the scene end time identified by each candidate data is after the time of occurrence of the driving behavior which is inconsistent with the expectation, and is different from the time of occurrence of the driving behavior which is inconsistent with the expectation by a preset time length.
As an alternative embodiment, the processing module 601 is specifically configured to:
respectively determining the similarity between the running data corresponding to each piece of data to be selected and the actual running data of the vehicle in the defect scene, wherein the running data corresponding to the data to be selected is the running data obtained by the simulation platform for running an automatic driving system based on the data to be selected; and taking the candidate data which has the highest similarity and the shortest identified scene duration as the data of the defect scene.
As an alternative embodiment, the processing module 601 is further configured to:
and adding the data of the defect scene into a scene data set corresponding to the category according to the category of the defect scene.
As an alternative embodiment, the input module 602 is specifically configured to: the input module is specifically used for:
the scene data set is input to the simulation platform.
As an alternative embodiment, the processing module 601 is specifically configured to:
and if the scene data set corresponding to the category does not have the previous scene data which is repeated with the data of the defect scene, adding the data of the defect scene into the scene data set corresponding to the category.
As an alternative embodiment, the data of the defect scene and the previous scene data are repeated when the data of the defect scene and the previous scene data satisfy the following conditions:
the vehicle identification is the same and the moment when the vehicle appears to be in unexpected driving behaviour is the same.
According to embodiments of the present application, an electronic device and a readable storage medium are also provided.
According to an embodiment of the present application, there is also provided a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of an electronic device can read, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any one of the embodiments described above.
As shown in fig. 7, a block diagram of an electronic device according to a method of automated driving data processing according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the application described and/or claimed herein.
As shown in fig. 7, the electronic device includes: one or more processors 701, memory 702, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple electronic devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 701 is illustrated in fig. 7.
Memory 702 is a non-transitory computer-readable storage medium provided herein. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of automated driving data processing provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the method of automated driving data processing provided by the present application.
The memory 702 is used as a non-transitory computer readable storage medium for storing non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules (e.g., the processing module 701 and the input module 703 shown in fig. 7) corresponding to the method of automatic driving data processing in the embodiments of the present application. The processor 701 executes various functional applications of the server and data processing, i.e., a method of implementing the automated driving data processing in the above-described method embodiment, by running non-transitory software programs, instructions, and modules stored in the memory 702.
Memory 702 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created from the use of the electronic device processed from the autopilot data, and the like. In addition, the memory 702 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 702 may optionally include memory located remotely from processor 701, which may be connected to the autopilot data processing electronics via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the method of automatic driving data processing may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected by a bus or otherwise, in fig. 7 by way of example.
The input device 703 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic device for automated driving data processing, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointer stick, one or more mouse buttons, a track ball, a joystick, and the like. The output device 704 may include a display apparatus, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASIC (application specific integrated circuit), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
These computing programs (also referred to as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions disclosed in the present application can be achieved, and are not limited herein.
The above embodiments do not limit the scope of the application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application are intended to be included within the scope of the present application.
Claims (11)
1. An automatic driving data processing method, characterized by comprising:
acquiring initial scene data of an automatic driving vehicle running an automatic driving system when the automatic driving vehicle runs in a real environment, wherein the initial scene data comprises data of a defect scene, and the defect scene is a scene where the vehicle is in a driving behavior which is inconsistent with an expected one;
based on the moment when the driving behavior of the vehicle is inconsistent with the expected driving behavior, a plurality of data to be selected are cut out from the initial scene data;
selecting the data of the defect scene from the data to be selected according to the simulation test result of the data to be selected;
inputting the data of the defect scene into a simulation platform, and operating the updated automatic driving system by the simulation platform based on the data of the defect scene to obtain an operation result of the updated automatic driving system in the defect scene.
2. The method of claim 1, wherein the scene end time identified by each candidate data in the plurality of candidate data is the same, and the scene duration identified by each candidate data is different from each other.
3. The method of claim 2, wherein the scene end time identified by each candidate data is after the time of occurrence of the driving behavior that is inconsistent with the expectation, and differs from the time of occurrence of the driving behavior that is inconsistent with the expectation by a preset period of time.
4. A method according to any one of claims 1-3, wherein selecting the data of the defect scene from the data to be selected according to the result of the simulation test on the data to be selected comprises:
respectively determining the similarity between the running data corresponding to each piece of data to be selected and the actual running data of the vehicle in the defect scene, wherein the running data corresponding to the data to be selected is the running data obtained by the simulation platform for running an automatic driving system based on the data to be selected;
and taking the data to be selected which has the highest similarity and the shortest identified scene duration as the data of the defect scene.
5. A method according to any one of claims 1-3, wherein after said intercepting said defect scene data from said initial scene data, further comprising:
and adding the data of the defect scene into a scene data set corresponding to the category according to the category of the defect scene.
6. The method of claim 5, wherein inputting the data of the defect scene into a simulation platform comprises:
the scene data set is input to the simulation platform.
7. The method according to claim 6, wherein adding the data of the defect scene to the scene data set corresponding to the category according to the category of the defect scene comprises:
and if the scene data set corresponding to the category does not have the previous scene data which is repeated with the data of the defect scene, adding the data of the defect scene into the scene data set corresponding to the category.
8. The method of claim 7, wherein the data of the defect scene and the prior scene data are repeated when the data of the defect scene and the prior scene data satisfy the following condition:
the vehicle identification is the same and the moment when the vehicle appears to be in unexpected driving behaviour is the same.
9. An automatic driving data processing apparatus, comprising:
the processing module is used for acquiring initial scene data of an automatic driving vehicle running an automatic driving system when the automatic driving vehicle runs in a real environment, wherein the initial scene data comprises data of a defect scene, and the defect scene is a scene where the vehicle is in a driving behavior which is inconsistent with an expected one; the method comprises the steps of,
based on the moment when the driving behavior of the vehicle is inconsistent with the expected driving behavior, a plurality of data to be selected are cut out from the initial scene data; selecting the data of the defect scene from the data to be selected according to the simulation test result of the data to be selected;
the input module is used for inputting the data of the defect scene into the simulation platform, and the simulation platform operates the updated automatic driving system based on the data of the defect scene to obtain the operation result of the updated automatic driving system in the defect scene.
10. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
11. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010436745.8A CN111611711B (en) | 2020-05-21 | 2020-05-21 | Automatic driving data processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010436745.8A CN111611711B (en) | 2020-05-21 | 2020-05-21 | Automatic driving data processing method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111611711A CN111611711A (en) | 2020-09-01 |
| CN111611711B true CN111611711B (en) | 2023-06-20 |
Family
ID=72199500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010436745.8A Active CN111611711B (en) | 2020-05-21 | 2020-05-21 | Automatic driving data processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111611711B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307642B (en) * | 2020-11-17 | 2022-09-16 | 苏州智加科技有限公司 | Data processing method, device, system, computer equipment and storage medium |
| CN112329152B (en) * | 2020-11-24 | 2023-04-07 | 苏州智加科技有限公司 | Driving data searching method, device and equipment |
| CN112528477B (en) * | 2020-12-03 | 2024-03-08 | 安徽江淮汽车集团股份有限公司 | Road scene simulation method, equipment, storage medium and device |
| 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 |
| CN112965466B (en) * | 2021-02-18 | 2022-08-30 | 北京百度网讯科技有限公司 | Reduction test method, device, equipment and program product of automatic driving system |
| CN113779791B (en) * | 2021-09-08 | 2024-02-06 | 广东博智林机器人有限公司 | Simulation system, simulation method, simulation device and electronic equipment |
| CN115167374A (en) * | 2022-08-09 | 2022-10-11 | 科大国创合肥智能汽车科技有限公司 | Automatic driving sensor recharging virtual simulation test method and system thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106134A (en) * | 2011-11-10 | 2013-05-15 | 阿里巴巴集团控股有限公司 | Detecting method, device and system for performance deficiency |
| WO2017130550A1 (en) * | 2016-01-29 | 2017-08-03 | 富士フイルム株式会社 | Defect inspection device, method, and program |
| CN107341096A (en) * | 2017-06-28 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | The generation method and device of journal file, computer equipment and storage medium |
| DE102018211984A1 (en) * | 2017-07-21 | 2019-01-24 | Denso Corporation | VEHICLE CONTROL SYSTEM |
| CN110174274A (en) * | 2019-05-28 | 2019-08-27 | 初速度（苏州）科技有限公司 | A kind of modification method and device of intelligent driving algorithm |
| CN110188482A (en) * | 2019-05-31 | 2019-08-30 | 初速度（苏州）科技有限公司 | A kind of test scene creation method and device based on intelligent driving |
| CN110619528A (en) * | 2019-09-29 | 2019-12-27 | 武汉极意网络科技有限公司 | Behavior verification data processing method, behavior verification data processing device, behavior verification equipment and storage medium |
| CN111090927A (en) * | 2019-11-15 | 2020-05-01 | 苏州浪潮智能科技有限公司 | Method and device for testing automatic driving model |
| CN111177887A (en) * | 2019-12-09 | 2020-05-19 | 武汉光庭信息技术股份有限公司 | Method and device for constructing simulation track data based on real driving scene |
-
2020
- 2020-05-21 CN CN202010436745.8A patent/CN111611711B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106134A (en) * | 2011-11-10 | 2013-05-15 | 阿里巴巴集团控股有限公司 | Detecting method, device and system for performance deficiency |
| WO2017130550A1 (en) * | 2016-01-29 | 2017-08-03 | 富士フイルム株式会社 | Defect inspection device, method, and program |
| CN107341096A (en) * | 2017-06-28 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | The generation method and device of journal file, computer equipment and storage medium |
| DE102018211984A1 (en) * | 2017-07-21 | 2019-01-24 | Denso Corporation | VEHICLE CONTROL SYSTEM |
| CN110174274A (en) * | 2019-05-28 | 2019-08-27 | 初速度（苏州）科技有限公司 | A kind of modification method and device of intelligent driving algorithm |
| CN110188482A (en) * | 2019-05-31 | 2019-08-30 | 初速度（苏州）科技有限公司 | A kind of test scene creation method and device based on intelligent driving |
| CN110619528A (en) * | 2019-09-29 | 2019-12-27 | 武汉极意网络科技有限公司 | Behavior verification data processing method, behavior verification data processing device, behavior verification equipment and storage medium |
| CN111090927A (en) * | 2019-11-15 | 2020-05-01 | 苏州浪潮智能科技有限公司 | Method and device for testing automatic driving model |
| CN111177887A (en) * | 2019-12-09 | 2020-05-19 | 武汉光庭信息技术股份有限公司 | Method and device for constructing simulation track data based on real driving scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111611711A (en) | 2020-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111611711B (en) | Automatic driving data processing method and device and electronic equipment | |
| KR102487336B1 (en) | Method, electronic device and storage medium for testing autonomous driving system | |
| CN111310934B (en) | Model generation method and device, electronic equipment and storage medium | |
| KR102601534B1 (en) | Scene reproduction test method, apparatus, device and program of autonomous driving system | |
| US10176079B2 (en) | Identification of elements of currently-executing component script | |
| CN111625950B (en) | Automatic driving simulation scene reconstruction method, device, equipment and medium | |
| US10761963B2 (en) | Object monitoring in code debugging | |
| CN114415628A (en) | Automatic driving test method and device, electronic equipment and storage medium | |
| CN112527748B (en) | Method, device, equipment and storage medium for analyzing user operation behavior | |
| US20150242380A1 (en) | Checking testing coverage | |
| CN111652153B (en) | Scene automatic identification method and device, unmanned vehicle and storage medium | |
| CN111984476A (en) | Test method and device | |
| CN111371862B (en) | Unmanned vehicle debugging method, device, server and medium | |
| CN111597707B (en) | Method, device, equipment and storage medium for processing simulation scene | |
| KR20190135074A (en) | Ui testing automation method using deep learning algorithem and tree and appratus for the same | |
| CN112149828A (en) | Operator precision detection method and device based on deep learning framework | |
| CN112486817A (en) | Evaluation method, device, equipment and storage medium for data updating | |
| CN111242455A (en) | Method and device for evaluating voice function of electronic map, electronic equipment and storage medium | |
| CN111340976B (en) | Method and device for debugging automatic driving vehicle module and electronic equipment | |
| CN111599174B (en) | Traffic index abnormity detection method and electronic equipment | |
| CN114861321A (en) | Problem scene extraction method, device, equipment and medium for traffic flow simulation | |
| CN111767651B (en) | Index prediction model construction method, index prediction method and device | |
| CN111597940B (en) | Rendering model evaluation method and device, electronic equipment and readable storage medium | |
| CN110796024B (en) | Automatic driving visual perception test method and device for failure sample | |
| CN116166530A (en) | Automatic driving simulation method and device, electronic equipment and storage medium |
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 |