A data processing method, apparatus, device, and storage medium for autonomous driving

Abstract

This application discloses a data processing method, apparatus, device, and storage medium for autonomous driving. The method includes: acquiring test information and operational design configuration information; the test information includes test data corresponding to multiple driving scenarios, and the test data includes semantic information and test result information corresponding to the driving scenarios; based on the test result information, obtaining first test information and second test information, where the first test information includes test data corresponding to driving scenarios that passed the test, and the second test information includes test data corresponding to driving scenarios that failed the test; obtaining operational design information based on the semantic information and operational design configuration information in the first test information; obtaining reference operational design information based on the second test information; and obtaining target operational design information based on the operational design information and the reference operational design information. The technical solution provided by this application can optimize autonomous driving systems, thereby improving the safety of autonomous driving systems.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a data processing method, apparatus, device, and storage medium for autonomous driving. Background Technology

[0002] Whether an autonomous driving system can continuously perform lateral or longitudinal motion control of the vehicle in dynamic driving tasks within its corresponding operational design domain (ODD), and whether it has the ability to detect and respond to targets and events that are compatible with the lateral or longitudinal motion control it performs, are important criteria for classifying driving automation.

[0003] As the algorithms for autonomous driving systems continue to be developed, the design operating domain that autonomous driving systems can cover is constantly changing. In existing technologies, road test results or limited simulation results are often used to determine whether an autonomous driving system meets the design operating range. However, the above methods for determining whether an autonomous driving system meets the design operating range may result in omissions or incorrect judgments.

[0004] Therefore, an improved data processing technology is needed to solve the problems existing in the above-mentioned technologies. Summary of the Invention

[0005] To address the problems of the prior art, this application provides a technical solution for a data processing method, apparatus, device, and storage medium for autonomous driving, as described below:

[0006] On the one hand, a data processing method for autonomous driving is provided, the method comprising:

[0007] Acquire test information and operation design configuration information. The test information includes test data corresponding to multiple driving scenarios. The test data includes semantic information and test result information corresponding to the driving scenarios. The operation design configuration information represents the driving environment information of autonomous driving.

[0008] Based on the test results, first test information and second test information are obtained. The first test information includes test data corresponding to driving scenarios that passed the test, and the second test information includes test data corresponding to driving scenarios that failed the test.

[0009] Based on the semantic information in the first test information and the operation design configuration information, the operation design information is obtained;

[0010] Based on the second test information, the reference operating design information is obtained;

[0011] Based on the operational design information and the reference operational design information, the target operational design information is obtained.

[0012] Further, obtaining the runtime design information based on the semantic information in the first test information and the runtime design configuration information includes:

[0013] The semantic information in the first test information is matched with the operation design configuration information to obtain the first semantic information that matches the operation design configuration information;

[0014] The first semantic information that matches the runtime design configuration information is determined as the runtime design information.

[0015] Further, obtaining the reference operating design information based on the second test information includes:

[0016] The semantic information in the second test information is matched with the operation design configuration information to obtain the second semantic information that matches the operation design configuration information;

[0017] The second semantic information that matches the runtime design configuration information is determined as the reference runtime design information.

[0018] Further, obtaining the target operation design information based on the operation design information and the reference operation design information includes:

[0019] Compare the operational design information with the reference operational design information;

[0020] If there is identical operational information in the operational design information and the reference operational design information, delete the operational information that is identical to the reference operational design information from the operational design information to obtain the remaining operational design information;

[0021] The remaining operational design information is determined as the target operational design information.

[0022] Furthermore, the method also includes:

[0023] If there is no identical operational information between the operational design information and the reference operational design information, the operational design information shall be determined as the target operational design information.

[0024] Furthermore, prior to the steps of obtaining test information and running the design configuration information, the following steps are also included:

[0025] Acquire test data for driving scenarios under multiple preset function items;

[0026] The test information is determined based on the test data corresponding to the driving scenario under multiple preset function items.

[0027] Furthermore, determining the test information based on the test data corresponding to the driving scenario under multiple preset functional items includes:

[0028] If the test data corresponding to the driving scenario under multiple preset function items all indicate that the test has passed, then the test information corresponding to the driving scenario is that the test has passed.

[0029] On the other hand, a data processing apparatus for autonomous driving is provided, the apparatus comprising:

[0030] Information acquisition module: used to acquire test information and operation design configuration information. The test information includes test data corresponding to multiple driving scenarios. The test data includes semantic information and test result information corresponding to the driving scenarios. The operation design configuration information represents the driving environment information of autonomous driving.

[0031] Test information determination module: used to obtain first test information and second test information based on the test result information, wherein the first test information includes test data corresponding to driving scenarios that pass the test, and the second test information includes test data corresponding to driving scenarios that fail the test;

[0032] Runtime design information determination module: used to obtain runtime design information based on the semantic information in the first test information and the runtime design configuration information;

[0033] Reference operating design information determination module: used to obtain reference operating design information based on the second test information;

[0034] Target operation design information determination module: used to obtain target operation design information based on the operation design information and the reference operation design information.

[0035] On the other hand, a data processing device for autonomous driving is provided, the data processing device including a processor and a memory, the memory storing at least one instruction, at least one program, code data or instruction data, the at least one instruction, the at least one program, the code data or instruction data being loaded and executed by the processor to implement the data processing method for autonomous driving as described above.

[0036] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction, at least one program, code data, or instruction data is stored in the storage medium, wherein the at least one instruction, the at least one program, the code data, or instruction data is loaded and executed by a processor to implement the data processing method for autonomous driving as described above.

[0037] This application provides a data processing method, apparatus, device, and storage medium for autonomous driving, which has the following technical advantages:

[0038] This application first obtains test information and operational design configuration information. The test information includes test data corresponding to multiple driving scenarios, and the test data includes semantic information and test result information corresponding to the driving scenarios. The operational design configuration information represents the driving environment information of autonomous driving. The test result information is used to indicate whether a driving scenario passes or fails the test, so as to determine the test data corresponding to the driving scenarios that pass the test and the test data corresponding to the driving scenarios that fail the test. Next, based on the test result information, first test information and second test information are determined. Then, based on the semantic information and operational design configuration information in the first test information, operational design information is obtained. Based on the second test information, reference operational design information is obtained. Finally, based on the operational design information and reference operational design information, target operational design information is obtained. The technical solution provided by this application can optimize the autonomous driving system, thereby improving the safety of the autonomous driving system. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A flowchart illustrating a data processing method for autonomous driving provided in an embodiment of this application;

[0041] Figure 2 A flowchart illustrating the method for determining operational design information provided in an embodiment of this application;

[0042] Figure 3 A flowchart illustrating the method for determining reference operating design information provided in the embodiments of this application;

[0043] Figure 4 A flowchart illustrating the method for determining target operational design information provided in this application embodiment;

[0044] Figure 5 This application provides a schematic diagram of the structure of a data processing device for autonomous driving.

[0045] Figure 6 A schematic diagram of the structure of the operation design information determination module provided in the embodiments of this application;

[0046] Figure 7 A schematic diagram of the reference operating design information determination module provided in the embodiments of this application;

[0047] Figure 8 A schematic diagram of the target operation design information determination module provided in the embodiments of this application;

[0048] Figure 9 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0050] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in sequences other than those illustrated or described herein.

[0051] Please see Figure 1 The diagram shown is a flowchart illustrating a data processing method for autonomous driving provided in an embodiment of this application. The following is a summary of the process. Figure 1 The technical solution of this application is described in detail. It should be noted that this specification provides the method operation steps as shown in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operation steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many steps and does not represent the only execution order. The method specifically includes the following steps:

[0052] S101: Obtain test information and operation design configuration information. The test information includes test data corresponding to multiple driving scenarios. The test data includes semantic information and test result information corresponding to the driving scenarios. The operation design configuration information represents the driving environment information of autonomous driving.

[0053] In this embodiment, semantic information is a set of semantics corresponding to a driving scenario. This can be understood as describing the driving scenario according to preset semantics, so that each scenario information within the driving scenario is represented using semantics, thereby obtaining a driving scenario characterized by semantic information. This facilitates the extraction of semantics belonging to the operational design domain definition from the semantic information. Test result information is used to indicate whether a driving scenario passes or fails the test; that is, it is used to indicate whether the semantic information corresponding to the driving scenario passes or fails the test, so that test data corresponding to driving scenarios that pass the test and test data corresponding to driving scenarios that fail the test can be determined based on the test result information.

[0054] In one specific embodiment, the operation design configuration information includes the operation design domain corresponding to the autonomous vehicle. The operation design domain is the operating environment specifically designed for the driving automation system or its functions, including but not limited to environmental, geographical and time constraints, and / or the presence or absence of certain traffic or road features. It should be noted that for the autonomous vehicle to drive normally in the driving scenario, it is necessary to comprehensively consider various types of roads, road markings, traffic signs and environmental information to ensure that the autonomous vehicle performs adequately in its predetermined operating environment. The adequate performance of the autonomous vehicle in its predetermined operating environment is a key part of the verification of the autonomous driving system.

[0055] In simple terms, the operational design domain defines the specific operating environments in which autonomous driving is possible. Outside of these environments, autonomous driving cannot function reliably. Every autonomous vehicle must operate within a defined environment. This environment can be broad or precise, determining the driving scenarios the vehicle can handle. For example, an autonomous driving system might only function on highways, automatically maintaining lane position, overtaking, following other vehicles, yielding, navigating ETC lanes, and entering / exiting ramps. However, it cannot operate fully autonomously in urban areas. To ensure comprehensive testing and validation of autonomous driving, it's essential to guarantee that all scenarios within the operational design domain pass, thus ensuring the safe operation of the autonomous driving system.

[0056] In practical applications, driving scenarios refer to the driving scenarios that autonomous vehicles need to deal with. Driving scenarios consist of road information and target perception environment information. By acquiring comprehensive and extensive driving scenarios that autonomous vehicles may encounter during driving, a relatively complete driving scenario for autonomous vehicles can be generated, thereby improving the safety performance of autonomous vehicles.

[0057] In an optional implementation, prior to step S101, the method further includes:

[0058] S1011: Obtain test data for driving scenarios under multiple preset function items.

[0059] S1012: Determine test information based on test data corresponding to multiple preset function items under the driving scenario.

[0060] In an optional implementation, step S1012 may include:

[0061] S10121: If the test data for a driving scenario under multiple preset function items all indicate that the test has passed, then the test information for the driving scenario is "test passed".

[0062] In this embodiment, the test data is the functional item test data corresponding to the functional items required for the driving scenario. Based on the functional item test data, test data corresponding to multiple test scenarios in the driving scenario is determined. Then, based on the test data corresponding to multiple test scenarios, test information corresponding to the driving scenario is determined. Here, the test scenario is a specific scenario in the driving scenario. For example, when the speed limit in the driving scenario includes a minimum speed limit and a maximum speed limit, the test scenario is the driving scenario corresponding to a specific speed information between the minimum speed limit and the maximum speed limit. It should be noted that the driving scenario corresponding to a specific speed information includes not only speed information, but also obstacle information or weather information, etc., to constitute a complete driving scenario. In this driving scenario, apart from the speed information, other information can be completely the same, so as to eliminate the influence of speed information on the test results and ensure that safe driving can be achieved within this speed range.

[0063] In practical applications, each functional item can be determined by one or more performance indicators. Then, based on the test data corresponding to the performance indicators of each functional item, the test data for each functional item in the test scenario can be determined, thereby determining the test information corresponding to the driving scenario. This allows for the identification of driving scenarios that pass the test and those that fail. For example, the correspondence between the test information for the driving scenario, the test data for the test scenario, and the test data for the functional item is shown in Table 1. Table 1 is as follows:

[0064]

[0065] As shown in Table 1, if all performance indicators for a functional item indicate a pass, then the functional item in the test scenario is considered to have passed the test. Conversely, if any performance indicator for a functional item indicates a fail, then the functional item in the test scenario is considered to have failed the test. Similarly, if all test data for a driving scenario indicates a pass, then the driving scenario is considered to have passed the test. Conversely, if any test data for a driving scenario indicates a fail, then the driving scenario is considered to have failed the test. It should be noted that in Table 1, "pass" represents a successful test and "fail" represents a failed test.

[0066] S102: Based on the test results, obtain first test information and second test information. The first test information includes test data corresponding to driving scenarios that passed the test, and the second test information includes test data corresponding to driving scenarios that failed the test.

[0067] In this embodiment of the application, based on the test result information, the test data corresponding to the driving scenario is divided into test data corresponding to the driving scenario that passed the test and test data corresponding to the driving scenario that failed the test. In order to determine the operation design information corresponding to the driving scenario that passed the test based on the semantic information corresponding to the driving scenario that failed the test, and to determine the reference operation design information corresponding to the driving scenario that passed the test based on the semantic information corresponding to the driving scenario that failed the test, thereby optimizing the target operation design information in the autonomous driving system and improving the safety of the autonomous driving system.

[0068] S103: Obtain the runtime design information based on the semantic information and runtime design configuration information in the first test information.

[0069] In one alternative implementation, such as Figure 2 As shown, it is a flowchart illustrating the method for determining operational design information provided in an embodiment of this application. Step S103 may include:

[0070] S1031: Match the semantic information in the first test information with the runtime design configuration information to obtain the first semantic information that matches the runtime design configuration information.

[0071] S1032: The first semantic information that matches the runtime design configuration information is determined as the runtime design information.

[0072] In this embodiment, the first test information is the test data corresponding to the driving scenario that passed the test. Then, the semantic information and operation design configuration information in the first test information can be matched to obtain the semantic information belonging to the operation design domain definition corresponding to the driving scenario that passed the test, that is, the operation design information corresponding to the driving scenario that passed the test. This forms an operation design information table corresponding to the driving scenario. The operation design information table may include operation design information and its corresponding test result information, etc., thereby determining the operation design information that the autonomous driving system can handle, so as to verify the operation design information of the autonomous driving system and improve the safety performance of the autonomous driving system.

[0073] S104: Based on the second test information, obtain the reference operating design information.

[0074] In one alternative implementation, such as Figure 3 As shown, it is a flowchart illustrating the reference operating design information determination method provided in an embodiment of this application. Step S104 may include:

[0075] S1041: Match the semantic information in the second test information with the runtime design configuration information to obtain the second semantic information that matches the runtime design configuration information.

[0076] S1042: The second semantic information that matches the runtime design configuration information is determined as the reference runtime design information.

[0077] In this embodiment, the second test information is the test data corresponding to the driving scenario that failed the test. Then, the semantic information and operation design configuration information in the second test information can be matched to obtain the semantic information belonging to the operation design domain definition corresponding to the driving scenario that failed the test, that is, the reference operation design information corresponding to the driving scenario that failed the test. This forms a reference operation design information table corresponding to the driving scenario. The reference operation design information table may include reference operation design information and its corresponding test result information, etc., thereby identifying the reference operation design information that the autonomous driving system cannot handle. This facilitates the comparison between the operation design information and the reference operation design information to verify the operation design information, ensuring the completeness of the verification of the operation design information, avoiding missed detections, and thus optimizing the autonomous driving system, thereby improving the safety and accuracy of the autonomous driving system.

[0078] It should be noted that for driving scenarios that fail the test, the specific information of the failure should be located so that the developers of the autonomous driving system can improve the location information to ensure that it can cope with more driving scenarios.

[0079] S105: Obtain the target operation design information based on the operation design information and the reference operation design information.

[0080] In one alternative implementation, such as Figure 4 As shown, it is a flowchart illustrating the method for determining target operational design information provided in an embodiment of this application. Step S105 may include:

[0081] S1051: Compare the operational design information with the reference operational design information.

[0082] S1052: If there is the same running information in the running design information and the reference running design information, delete the running information that is the same as the reference running design information from the running design information to obtain the remaining running design information.

[0083] S1053: Determine the remaining runtime design information as the target runtime design information.

[0084] In an optional implementation, the method further includes:

[0085] S1054: If there is no identical operating information between the operating design information and the reference operating design information, the operating design information shall be determined as the target operating design information.

[0086] In this embodiment, by deleting the same operation information as the reference operation design information from the operation design information, the operation design information is verified, which facilitates real-time updates to the operation design information and ensures that the autonomous driving system can fully cope with the target operation design information. This optimizes the operation design information in the autonomous driving system and improves the safety of the autonomous driving system.

[0087] In another specific embodiment, if there is no identical operational information in the operational design information and the reference operational design information, then there is no need to update the operational design information, which also indicates that the autonomous driving system can cope with all the acquired operational design information, that is, the autonomous vehicle can drive safely in the autonomous driving system.

[0088] In another alternative implementation, the method further includes:

[0089] S201: Based on the test results, obtain third test information and fourth test information, wherein the third test information includes test data corresponding to the road information that passed the test, and the fourth test information includes test data corresponding to the road information that failed the test.

[0090] S202: Based on the semantic information and runtime design configuration information in the third test information, obtain the first runtime design information.

[0091] S203: Based on the fourth test information, the first reference operating design information is obtained.

[0092] S204: Based on the first operational design information and the first reference operational design information, the first target operational design information is obtained.

[0093] In this embodiment, test data corresponding to road information in multiple driving scenarios are extracted to determine first operational design information and first reference operational design information based on road information as a classification standard. This allows for the determination of first target operational design information that the road information can fully handle, thereby ensuring that the autonomous driving system can fully handle the first target operational design information. This optimizes the first operational design information in the autonomous driving system and improves the safety of the autonomous driving system.

[0094] In practical applications, the third test information consists of test data corresponding to road information that passed the test. This data can then be matched with the semantic information and operational design configuration information within the third test information to obtain the semantic information belonging to the operational design domain defined for the road information that passed the test. This results in the first operational design information corresponding to the road information, forming a first operational design information table. This first operational design information table can include the first operational design information and its corresponding test results. The fourth test information consists of test data corresponding to road information that failed the test. This data can then be matched with the semantic information and operational design configuration information within the fourth test information to obtain the semantic information belonging to the operational design domain defined for the road information that failed the test. This results in the first reference operational design information corresponding to the road information, forming a first reference operational design information table. This first reference operational design information table can include the first reference operational design information and its corresponding test results. This process helps determine the first operational design information that the autonomous driving system can handle, facilitating a comparison between the first operational design information and the first reference operational design information to verify the first operational design information and ensure the completeness of the verification process.

[0095] It should be noted that the embodiments of this application can also extract test data corresponding to information other than road information in the driving scenario, so as to determine the target operation design information based on the extracted information as the classification standard, and ensure the integrity of the operation design information corresponding to the extracted information.

[0096] As can be seen from the above technical solutions of the embodiments of this application, the following technical effects are achieved:

[0097] This application first obtains test information and operational design configuration information. The test information includes test data corresponding to multiple driving scenarios, and the test data includes semantic information and test result information corresponding to the driving scenarios. The operational design configuration information represents the driving environment information of autonomous driving. The test result information is used to indicate whether a driving scenario passes or fails the test, so as to determine the test data corresponding to the driving scenarios that pass the test and the test data corresponding to the driving scenarios that fail the test. Next, based on the test result information, first test information and second test information are determined. Then, based on the semantic information and operational design configuration information in the first test information, operational design information is obtained. Based on the second test information, reference operational design information is obtained. Finally, based on the operational design information and reference operational design information, target operational design information is obtained. The technical solution provided by this application can optimize the autonomous driving system, thereby improving the safety of the autonomous driving system.

[0098] This application also provides a data processing device for autonomous driving, such as... Figure 5 As shown, this is a schematic diagram of a data processing device for autonomous driving provided in an embodiment of this application. The device specifically includes:

[0099] Information acquisition module 10: used to acquire test information and operation design configuration information. The test information includes test data corresponding to multiple driving scenarios. The test data includes semantic information and test result information corresponding to the driving scenarios. The operation design configuration information represents the driving environment information of autonomous driving.

[0100] Test information determination module 20: used to obtain first test information and second test information based on test result information. The first test information includes test data corresponding to driving scenarios that pass the test, and the second test information includes test data corresponding to driving scenarios that fail the test.

[0101] Runtime design information determination module 30: used to obtain runtime design information based on the semantic information and runtime design configuration information in the first test information.

[0102] Reference operating design information determination module 40: used to obtain reference operating design information based on the second test information.

[0103] Target operation design information determination module 50: used to obtain target operation design information based on operation design information and reference operation design information.

[0104] Preferred, such as Figure 6 As shown, this is a structural schematic diagram of the runtime design information determination module provided in an embodiment of this application. Specifically, the runtime design information determination module 30 may include:

[0105] First semantic information determination submodule 301: is used to match the semantic information in the first test information with the operation design configuration information to obtain the first semantic information that matches the operation design configuration information.

[0106] Runtime design information determination submodule 302: used to determine the first semantic information that matches the runtime design configuration information as runtime design information.

[0107] Preferred, such as Figure 7 As shown, this is a structural schematic diagram of the reference operating design information determination module provided in an embodiment of this application. Specifically, the reference operating design information determination module 40 may include:

[0108] Second semantic information determination submodule 401: is used to match the semantic information in the second test information with the operation design configuration information to obtain the second semantic information that matches the operation design configuration information.

[0109] Reference Operation Design Information Determination Submodule 402: Used to determine the second semantic information that matches the operation design configuration information as the reference operation design information.

[0110] Preferred, such as Figure 8 As shown, this is a structural schematic diagram of the target operation design information determination module provided in an embodiment of this application. Specifically, the target operation design information determination module 50 may include:

[0111] Comparison Submodule 501: Used to compare the runtime design information with the reference runtime design information.

[0112] Remaining Operation Design Information Determination Submodule 502: When there is identical operation information in the operation design information and the reference operation design information, the operation information identical to the reference operation design information is deleted from the operation design information to obtain the remaining operation design information.

[0113] First target operation design information determination submodule 503: used to determine the remaining operation design information as target operation design information.

[0114] Preferably, the device further includes:

[0115] Second target operation design information determination submodule 504: used to determine the operation design information as the target operation design information when there is no identical operation information in the operation design information and the reference operation design information.

[0116] Preferably, the device further includes:

[0117] Test data acquisition module 60: Used to acquire test data corresponding to multiple preset function items in driving scenarios.

[0118] The test information determination module 70 corresponding to the driving scenario is used to determine the test information based on the test data corresponding to the driving scenario under multiple preset function items.

[0119] Preferably, the test information determination module 70 corresponding to the driving scenario may include:

[0120] Test module 701: If the test data corresponding to multiple preset function items for a driving scenario all indicate that the test has passed, then the test information corresponding to the driving scenario is "test passed".

[0121] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0122] This application provides a data processing device for autonomous driving. The data processing device for autonomous driving includes a processor and a memory. The memory stores at least one instruction, at least one program, code data, or instruction data. The at least one instruction, the at least one program, the code data, or the instruction data is loaded and executed by the processor to implement the data processing method for autonomous driving as provided in the above method embodiments.

[0123] Memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. Memory can primarily include a program storage area and a data storage area. The program storage area can store the operating system, application programs required for the functions, etc.; the data storage area can store data created based on the use of the device, etc. Furthermore, memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory can also include a memory controller to provide the processor with access to the memory.

[0124] The data processing device for autonomous driving can be a server. This application embodiment also provides a schematic diagram of a server structure. Please refer to [link / reference]. Figure 9The server 900 is used to implement the data processing method provided in the above embodiments. The server 900 can vary significantly due to different configurations or performance, and may include one or more processors 910 (e.g., one or more processors) and memory 930, and one or more storage media 920 (e.g., one or more mass storage devices) for storing application programs 923 or data 922. The memory 930 and storage media 920 can be temporary or persistent storage. The program stored in the storage media 920 may include one or more modules, each module including a series of instruction operations on the server. Furthermore, the processor 910 may be configured to communicate with the storage media 920 and execute the series of instruction operations in the storage media 920 on the server 900. The server 900 may also include one or more power supplies 960, one or more wired or wireless network interfaces 950, one or more input / output interfaces 940, and / or one or more operating systems 921, such as Windows Server™, Mac OSX™, Unix™, Linux™, FreeBSD™, etc.

[0125] Embodiments of this application also provide a computer-readable storage medium, which can be disposed in a server to store at least one instruction, at least one program segment, code data, or instruction data related to implementing a data processing method for autonomous driving in the method embodiments. The at least one instruction, the at least one program segment, the code data, or the instruction data is loaded and executed by the processor to implement the data processing for autonomous driving provided in the above method embodiments.

[0126] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system and server embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0127] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A data processing method for automatic driving, characterized by, The method includes: Acquire test data corresponding to multiple preset function items for a driving scenario. The test data is the function item test data corresponding to the function items required for the driving scenario. Based on the test data corresponding to the driving scenario under multiple preset function items, determine the test information; The test information and operation design configuration information are obtained. The test information includes test data corresponding to multiple driving scenarios. The test data includes semantic information and test result information corresponding to the driving scenarios. The operation design configuration information represents the driving environment information of autonomous driving. The semantic information is a semantic set corresponding to the driving scenarios. The test result information is used to indicate whether the driving scenarios have passed or failed the test. Based on the test results, first test information and second test information are obtained. The first test information includes test data corresponding to driving scenarios that passed the test, and the second test information includes test data corresponding to driving scenarios that failed the test. Based on the semantic information in the first test information and the operation design configuration information, the operation design information is obtained; Based on the second test information, the reference operating design information is obtained; The operation design information is compared with the reference operation design information; if there is the same operation information in the operation design information and the reference operation design information, the operation information that is the same as the reference operation design information is deleted from the operation design information to obtain the remaining operation design information; the remaining operation design information is determined as the target operation design information.

2. The data processing method according to claim 1, characterized in that, The step of obtaining the runtime design information based on the semantic information in the first test information and the runtime design configuration information includes: The semantic information in the first test information is matched with the operation design configuration information to obtain the first semantic information that matches the operation design configuration information; The first semantic information that matches the runtime design configuration information is determined as the runtime design information.

3. The data processing method of claim 1, wherein, The step of obtaining reference operating design information based on the second test information includes: The semantic information in the second test information is matched with the operation design configuration information to obtain the second semantic information that matches the operation design configuration information; The second semantic information that matches the runtime design configuration information is determined as the reference runtime design information.

4. The data processing method of claim 1, wherein, The method further includes: If there is no identical operational information between the operational design information and the reference operational design information, the operational design information shall be determined as the target operational design information.

5. The data processing method of claim 1, wherein, The step of determining the test information based on test data corresponding to multiple preset function items in the driving scenario includes: If the test data corresponding to the driving scenario under multiple preset function items all indicate that the test has passed, then the test information corresponding to the driving scenario is that the test has passed.

6. A data processing apparatus for automatic driving, characterized by, The device includes: Test data acquisition module: used to acquire test data corresponding to multiple preset function items in a driving scenario. The test data is the function item test data corresponding to the function items required for the driving scenario. The test information determination module corresponding to the driving scenario is used to determine the test information based on the test data corresponding to the driving scenario under multiple preset function items. Information acquisition module: used to acquire test information and operation design configuration information. The test information includes test data corresponding to multiple driving scenarios. The test data includes semantic information and test result information corresponding to the driving scenario. The operation design configuration information represents the driving environment information of autonomous driving. The semantic information is a semantic set corresponding to the driving scenario. The test result information is used to indicate whether the driving scenario has passed the test or failed the test. Test information determination module: used to obtain first test information and second test information based on the test result information, wherein the first test information includes test data corresponding to driving scenarios that pass the test, and the second test information includes test data corresponding to driving scenarios that fail the test; Runtime design information determination module: used to obtain runtime design information based on the semantic information in the first test information and the runtime design configuration information; Reference operating design information determination module: used to obtain reference operating design information based on the second test information; Comparison submodule: used to compare the runtime design information with the reference runtime design information; Remaining Operation Design Information Determination Submodule: When there is identical operation information in the operation design information and the reference operation design information, delete the operation information that is identical to the reference operation design information from the operation design information to obtain the remaining operation design information; The first target operation design information determination submodule is used to determine the remaining operation design information as the target operation design information.

7. A data processing device for automatic driving, characterized by, The data processing device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program segment, code data, or instruction data, and the at least one instruction, the at least one program segment, the code data, or the instruction data is loaded and executed by the processor to implement the data processing method for autonomous driving as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction or at least one program segment, which is loaded and executed by a processor to implement the data processing method for autonomous driving as described in any one of claims 1 to 5.

Images