A vehicle and a functional difference layer acquisition and automatic driving method and device thereof
By acquiring driving data from road test vehicles to construct functional difference layers and generate blacklists and whitelists, the safety hazards of advanced intelligent driving functions in complex scenarios are resolved, ensuring the safety of autonomous driving.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NINGBO GEELY AUTOMOBILE RES & DEV CO LTD
- Filing Date
- 2023-04-24
- Publication Date
- 2026-05-12
Smart Images
Figure CN116501821B_ABST
Abstract
Description
Technical Field
[0001] This application relates to vehicle control technology, and more particularly to a method and apparatus for acquiring vehicle and its functional difference layers and for autonomous driving. Background Technology
[0002] With the continuous development of technology, intelligent driving has increasingly become a key research and development direction for major automakers. While seeking higher levels (L3+) of intelligent driving functions, automakers are also paying increasing attention to intelligent driving safety. Ideally, high-level (L3+) intelligent driving functions, supported by numerous perception sensors and software, can effectively ensure driving safety.
[0003] However, in reality, under complex road and traffic conditions, intelligent driving functions often cannot guarantee 100% driving safety. Furthermore, limited by the current level of development of intelligent technology, intelligent driving functions cannot safely handle all road and traffic scenarios, which can lead to corresponding driving safety issues. Summary of the Invention
[0004] This application provides a method and apparatus for acquiring vehicle and its functional difference layers and for autonomous driving, which can help the autonomous driving function of the vehicle to deactivate or degrade in a timely manner to ensure driving safety.
[0005] This application provides a method for obtaining a functional difference layer, the method including:
[0006] Activate the autonomous driving function of test vehicles on real roads covered by high-precision maps;
[0007] Acquire the driving data of the test vehicle on the real road; the driving data includes the first abnormal point data marked when the autonomous driving function malfunctions;
[0008] The driving process is reconstructed on the constructed electronic horizon road model based on the driving data. Based on the first anomaly data, the second anomaly data is marked accordingly in the reconstructed driving process, and the corresponding model data is obtained. The model data includes the second anomaly data.
[0009] A functional difference layer corresponding to the current road scene type is generated based on the model data; the functional difference layer includes a blacklist or whitelist of driving segments of the real road generated based on the second anomaly point data.
[0010] In an exemplary embodiment of this application, obtaining the driving data of the road test vehicle on the real road may include:
[0011] During the driving of the test vehicle on the real road, road information is acquired, and the time and location of the abnormality of the autonomous driving function are marked as the first abnormality point data.
[0012] The electronic horizon message data containing the road information and the first anomaly point data is captured and used as the driving data.
[0013] In an exemplary embodiment of this application, the step of reconstructing the driving process on the constructed electronic horizon road model based on the driving data may include:
[0014] The electronic horizon message data is loaded using a preset map visualization tool, the electronic horizon road model is constructed, and the electronic horizon road model is displayed as a base map in the map visualization tool.
[0015] The electronic horizon message data is replayed on the electronic horizon road model, and the location of the test vehicle at different times on the real road is simulated and displayed on the base map of the map visualization tool, and each piece of road information in the electronic horizon message data is displayed.
[0016] In an exemplary embodiment of this application, both the first abnormal point data and the second abnormal point data may include: the time and location when the autonomous driving function malfunctions;
[0017] The step of marking the second anomaly data accordingly based on the first anomaly data during the reconstructed driving process may include:
[0018] By comparing the first anomaly data with the real-time location of the road test vehicle played back in the map visualization tool, the second anomaly data is marked in the map visualization tool, and the location attribute values related to the second anomaly data are automatically written to a preset format annotation file.
[0019] In an exemplary embodiment of this application, generating a functional difference layer corresponding to the current road scene type based on the model data may include:
[0020] The annotation file is read, the annotation file is classified into the current road scene type, a functional difference layer file corresponding to the current road scene type is generated by city, and the functional difference layer is obtained based on the functional difference layer file.
[0021] In an exemplary embodiment of this application, each of the road scene types may include a road scene switch;
[0022] The road scene switch is configured to, when in the on state, activate the road scene and control the electronic horizon road module under the road scene to send the electronic horizon message data; when in the off state, deactivate the road scene and control the electronic horizon road module under the road scene not to send the electronic horizon message data.
[0023] In an exemplary embodiment of this application, the blacklist may include: road segment information corresponding to the abnormal driving segments when the number of abnormal driving segments in a real road scenario is less than the number of normal driving segments;
[0024] The whitelist may include: road segment information corresponding to the normally performing driving segments when there are more abnormal driving segments than normal driving segments in real road scenarios;
[0025] The road segment information may include: road identification ID, lane ID and / or lane number data.
[0026] This application embodiment also provides a functional difference layer acquisition device, which may include a first processor and a first memory. The first memory stores a first instruction, and when the first instruction is executed by the first processor, the functional difference layer acquisition method is implemented.
[0027] This application also provides an autonomous driving method, which may include:
[0028] Retrieve the functional difference layer corresponding to the current driving road; the functional difference layer is obtained according to the functional difference layer acquisition method described above.
[0029] Automated driving is performed based on the retrieved functional difference layer.
[0030] In an exemplary embodiment of this application, the step of performing autonomous driving based on the retrieved functional difference layer may include:
[0031] Determine the road scene type corresponding to the functional difference layer;
[0032] When the number of abnormal driving segments in the identified road scene type is less than the number of normal driving segments, the preset road scene switch is set to the on state, and the blacklist and whitelist flags corresponding to the road scene type are marked as blacklisted, so that the vehicle can perform autonomous driving function on the driving segments on the current driving road other than the blacklisted segments, and stop the autonomous driving function on the driving segments corresponding to the blacklisted segments.
[0033] When the number of abnormal driving segments in the identified road scene type exceeds the number of normal driving segments, the road scene switch is set to the off state, and the blacklist and whitelist flags are marked as whitelisted. This causes the vehicle to stop the autonomous driving function on driving segments other than those on the whitelist on the current driving road, and to perform the autonomous driving function on driving segments corresponding to the whitelist.
[0034] This application also provides an autonomous driving device, which may include a second processor and a second memory. The second memory stores a second instruction, and when the second instruction is executed by the second processor, the autonomous driving method is implemented.
[0035] This application also provides a vehicle that may include the aforementioned functional difference layer acquisition device and the aforementioned autonomous driving device.
[0036] This application embodiment may include: activating the autonomous driving function of a test vehicle on a real road covered by a high-precision map; acquiring driving data of the test vehicle on the real road; the driving data including first anomaly point data marked when the autonomous driving function malfunctions; reconstructing the driving process on a constructed electronic horizon road model based on the driving data, marking second anomaly point data accordingly based on the first anomaly point data in the reconstructed driving process, and acquiring corresponding model data; the model data including the second anomaly point data; generating a functional difference layer corresponding to the current road scene type based on the model data; the functional difference layer including a blacklist or whitelist of driving segments on the real road generated based on the second anomaly point data. Through this embodiment, the autonomous driving function of the vehicle can be deactivated or downgraded in a timely manner, ensuring driving safety.
[0037] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the application. Other advantages of this application can be realized and obtained by means of the solutions described in the description and the accompanying drawings. Attached Figure Description
[0038] The accompanying drawings are used to provide an understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.
[0039] Figure 1 This is a flowchart illustrating the method for obtaining the functional difference layer according to an embodiment of this application;
[0040] Figure 2 This is a schematic diagram illustrating the method for obtaining the functional difference layer according to an embodiment of this application;
[0041] Figure 3 This is a schematic diagram illustrating the first relationship between data such as road scene type, road scene switch, blacklist / whitelist flags, blacklist, and whitelist in an embodiment of this application.
[0042] Figure 4 This is a schematic diagram illustrating the first relationship between data such as road scene type, road scene switch, blacklist / whitelist flags, blacklist, and whitelist in an embodiment of this application.
[0043] Figure 5 This is a block diagram of the functional difference layer acquisition device according to an embodiment of this application;
[0044] Figure 6 This is a flowchart of an autonomous driving method according to an embodiment of this application;
[0045] Figure 7 This is a block diagram of the autonomous driving device according to an embodiment of this application;
[0046] Figure 8 This is a block diagram of the vehicle components according to an embodiment of this application. Detailed Implementation
[0047] This application describes several embodiments, but these descriptions are exemplary and not restrictive, and it will be apparent to those skilled in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with, or may replace, any feature or element of any other embodiment.
[0048] This application includes and contemplates combinations of features and elements known to those skilled in the art. The embodiments, features, and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive scheme as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive schemes to form another unique inventive scheme as defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in this application may be implemented individually or in any suitable combination. Therefore, the embodiments are not limited except by the limitations imposed by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.
[0049] Furthermore, in describing representative embodiments, the specification may have presented methods and / or processes as a specific sequence of steps. However, the method or process should not be limited to the specific order of steps described herein, to the extent that it does not depend on such a specific order. As will be understood by those skilled in the art, other sequences of steps are also possible. Therefore, the specific order of steps set forth in the specification should not be construed as a limitation of the claims. Moreover, the claims concerning the method and / or process should not be limited to the steps performed in the written order, and those skilled in the art will readily understand that these orders can be varied and still remain within the spirit and scope of the embodiments of this application.
[0050] This application provides a method for obtaining a functional difference layer, such as... Figure 1 As shown, the method may include steps S101-S104:
[0051] S101. Activate the autonomous driving function of the test vehicle on real roads covered by high-precision maps;
[0052] S102. Obtain the driving data of the test vehicle on the real road; the driving data includes the first abnormal point data marked when the autonomous driving function is abnormal;
[0053] S103. Reconstruct the driving process on the constructed electronic horizon road model based on the driving data, mark the second anomaly data in the reconstructed driving process according to the first anomaly data, and obtain the corresponding model data; the model data includes the second anomaly data;
[0054] S104. Generate a functional difference layer corresponding to the current road scene type based on the model data; the functional difference layer includes a blacklist or whitelist of driving segments of the real road generated based on the second anomaly point data.
[0055] In an exemplary embodiment of this application, a functional difference layer can be created independently of the high-precision map manufacturer, based on high-precision map data and the actual performance of the vehicle's intelligent driving function (i.e., autonomous driving function). The electronic horizon road module (EHP, EHR) can match the data of the functional difference layer to determine whether it is necessary to send the high-precision map electronic horizon to the intelligent driving function, thereby determining whether the intelligent driving function should be discontinued.
[0056] In an exemplary embodiment of this application, obtaining the driving data of the road test vehicle on the real road may include:
[0057] During the driving of the test vehicle on the real road, road information is acquired, and the time and location of the abnormality of the autonomous driving function are marked as the first abnormality point data.
[0058] The electronic horizon message data containing the road information and the first anomaly point data is captured and used as the driving data.
[0059] In exemplary embodiments of this application, as Figure 2 As shown, a test vehicle equipped with intelligent driving capabilities can be used to activate the intelligent driving function on roads covered by high-precision maps. Data is collected and recorded via a data recording program. When encountering areas where the intelligent driving function malfunctions, the test vehicle records the time and location of the problem (i.e., the first anomaly point data). The recorded data includes electronic horizon messages from the vehicle's original electronic horizon road module (EHP, EHR). The recorded high-precision map electronic horizon messages can be stored using data packet formats (including but not limited to pcap).
[0060] In an exemplary embodiment of this application, the step of reconstructing the driving process on the constructed electronic horizon road model based on the driving data may include:
[0061] The electronic horizon message data is loaded using a preset map visualization tool, the electronic horizon road model is constructed, and the electronic horizon road model is displayed as a base map in the map visualization tool.
[0062] The electronic horizon message data is replayed on the electronic horizon road model, and the location of the test vehicle at different times on the real road is simulated and displayed on the base map of the map visualization tool, and each piece of road information in the electronic horizon message data is displayed.
[0063] In an exemplary embodiment of this application, the data packets of the Electronic Horizon Message can be parsed in a laboratory and the Electronic Horizon Message Data Packets can be loaded on a high-precision map visualization tool to reconstruct the road model.
[0064] In an exemplary embodiment of this application, both the first abnormal point data and the second abnormal point data may include: the time and location when the autonomous driving function malfunctions;
[0065] The step of marking the second anomaly data accordingly based on the first anomaly data during the reconstructed driving process may include:
[0066] By comparing the first anomaly data with the real-time location of the road test vehicle played back in the map visualization tool, the second anomaly data is marked in the map visualization tool, and the location attribute values related to the second anomaly data are automatically written to a preset format annotation file.
[0067] In an exemplary embodiment of this application, the location attribute value may include, but is not limited to: city code, road ID (identity identifier), lane ID, lane number, scene type flag, etc.
[0068] In an exemplary embodiment of this application, electronic horizon message data packets can be replayed on a high-precision map visualization tool, and annotations can be made on the electronic horizon road model of the high-precision map visualization tool by comparing the time points of abnormal performance of intelligent driving functions recorded in road tests.
[0069] In an exemplary embodiment of this application, generating a functional difference layer corresponding to the current road scene type based on the model data may include:
[0070] The annotation file is read, the annotation file is classified into the current road scene type, a functional difference layer file corresponding to the current road scene type is generated by city, and the functional difference layer is obtained based on the functional difference layer file.
[0071] In an exemplary embodiment of this application, a functional difference layer may refer to a layer with different functional differences. These functional differences may include, but are not limited to, the following complex road scenarios with functional abnormalities, which may be referred to as road scenario types: urban expressway on-ramps and off-ramps, highway on-ramps and off-ramps, connecting ramps, highway traffic lights, urban expressway traffic lights, and other road scenarios where intelligent driving functions are poorly performed as discovered during road tests.
[0072] In an exemplary embodiment of this application, the functional difference layer files for different road scene types may contain their respective functional performance anomaly annotation data.
[0073] In an exemplary embodiment of this application, the annotation data of the map visualization tool is processed, and a functional difference layer can be generated in a format that can be recognized by the Electronic Horizon Road Module (EHP, EHR). The functional difference layer can contain road scene switches and blacklists / whitelists for each road scene type, so as to facilitate differentiated management of different road scene types.
[0074] In an exemplary embodiment of this application, the functional difference layer file data structure may include, but is not limited to:
[0075] High-precision map version (for easy matching with in-vehicle high-precision maps), difference layer version, road scene type, road scene switch, blacklist / whitelist flags, blacklist, and whitelist; the blacklist and whitelist contain road ID, lane ID, and lane number. Functional difference layer files include, but are not limited to, those using the following formats: json, protocol buffer, and xml.
[0076] In an exemplary embodiment of this application, each of the road scene types may include a road scene switch;
[0077] The road scene switch is configured to, when in the on state, activate the road scene and control the electronic horizon road module under the road scene to send the electronic horizon message data; when in the off state, deactivate the road scene and control the electronic horizon road module under the road scene not to send the electronic horizon message data.
[0078] In an exemplary embodiment of this application, the road scene switch corresponding to each road scene type can control whether the electronic horizon road module (EHP, EHR) can send electronic horizon message data to the intelligent driving function module under that road scene type.
[0079] In an exemplary embodiment of this application, each road scenario type includes a blacklist and a whitelist, and each road scenario type has a flag indicating whether to use the blacklist or the whitelist under that road scenario type, denoted as the blacklist / whitelist flag. The blacklist / whitelist contains information such as the road ID, lane ID, and lane number data marked during road testing.
[0080] In an exemplary embodiment of this application, the blacklist may include: road segment information corresponding to the abnormal driving segments when the number of abnormal driving segments in a real road scenario is less than the number of normal driving segments;
[0081] The whitelist may include: road segment information corresponding to the normally performing driving segments when there are more abnormal driving segments than normal driving segments in real road scenarios;
[0082] The road segment information may include: road identification ID, lane ID and / or lane number data.
[0083] In exemplary embodiments of this application, as Figure 3 , Figure 4 As shown, the relationships between data such as road scene type, road scene switch, blacklist / whitelist flags, blacklist, and whitelist include:
[0084] If a vehicle's intelligent driving function generally behaves abnormally on most roads except for a few exceptions in a certain road scenario, the road scenario switch can be configured to be off. This means that in this scenario, the Electronic Horizon Road Module (EHP, EHR) does not need to send Electronic Horizon message data to the intelligent driving function module by default, thereby indirectly controlling the intelligent driving function to be turned off. The blacklist / whitelist flag can be configured to use the whitelist, indicating that roads in the whitelist are exceptions. When the vehicle is driving on these exception roads, the Electronic Horizon Road Module (EHP, EHR) can send Electronic Horizon message data to the intelligent driving function module, so the vehicle can normally activate the intelligent driving function on these roads.
[0085] If the vehicle's intelligent driving function generally performs normally on most roads except for a few exceptions in a certain road scenario, the road scenario switch can be configured to be on. This means that in this scenario, the Electronic Horizon Road Module (EHP, EHR) needs to send Electronic Horizon message data to the intelligent driving function module by default, thereby indirectly controlling the activation of the intelligent driving function. Configuring the blacklist / whitelist flag to use the blacklist indicates that roads on the blacklist are exceptions. When the vehicle is traveling on these exception roads, the Electronic Horizon Road Module (EHP, EHR) cannot send Electronic Horizon message data to the intelligent driving function module, so the intelligent driving function needs to be turned off on these roads.
[0086] In an exemplary embodiment of this application, the blacklist and whitelist may not contain road data, meaning there are no exceptions. Additionally, the blacklist and whitelist flags can be configured so that neither is used in either category.
[0087] In an exemplary embodiment of this application, the blacklist and whitelist of the same road scene type cannot contain the same road data at the same time.
[0088] In an exemplary embodiment of this application, the solution of this application is based on the intelligent driving performance of actual road test vehicles on the road, and marks the places with abnormal functional performance and generates a functional difference layer. This layer can be applied to all intelligent driving vehicles, helping the intelligent driving function of the vehicle to exit or degrade in a timely manner, thus ensuring driving safety.
[0089] This application embodiment also provides a functional difference layer acquisition device 1, such as... Figure 5 As shown, it may include a first processor 11 and a first memory 12. The first memory 12 stores a first instruction. When the first instruction is executed by the first processor 11, the functional difference layer acquisition method is implemented.
[0090] In the exemplary embodiments of this application, any of the embodiments in the foregoing embodiments of the functional difference layer acquisition method are applicable to this device embodiment, and will not be described in detail here.
[0091] This application also provides an autonomous driving method, such as... Figure 6 As shown, the method may include steps S101-S102:
[0092] S101. Retrieve the functional difference layer corresponding to the current driving road; the functional difference layer is obtained according to the functional difference layer acquisition method.
[0093] S102. Perform automatic driving based on the retrieved functional difference layer.
[0094] In an exemplary embodiment of this application, the step of performing autonomous driving based on the retrieved functional difference layer may include:
[0095] Determine the road scene type corresponding to the functional difference layer;
[0096] When the number of abnormal driving segments in the identified road scene type is less than the number of normal driving segments, the preset road scene switch is set to the on state, and the blacklist and whitelist flags corresponding to the road scene type are marked as blacklisted, so that the vehicle can perform autonomous driving function on the driving segments on the current driving road other than the blacklisted segments, and stop the autonomous driving function on the driving segments corresponding to the blacklisted segments.
[0097] When the number of abnormal driving segments in the identified road scene type exceeds the number of normal driving segments, the road scene switch is set to the off state, and the blacklist and whitelist flags are marked as whitelisted. This causes the vehicle to stop the autonomous driving function on driving segments other than those on the whitelist on the current driving road, and to perform the autonomous driving function on driving segments corresponding to the whitelist.
[0098] This application also provides an autonomous driving device 2, such as... Figure 7 As shown, it may include a second processor 21 and a second memory 22. The second memory 22 stores a second instruction. When the second instruction is executed by the second processor 22, the autonomous driving method is implemented.
[0099] In the exemplary embodiments of this application, any of the embodiments in the foregoing autonomous driving method embodiments are applicable to the device embodiments, and will not be described in detail here.
[0100] This application also provides a vehicle 3, such as... Figure 8As shown, it may include the functional difference layer acquisition device 1 and the autonomous driving device 2.
[0101] In the exemplary embodiments of this application, any of the embodiments in the foregoing embodiments of the functional difference layer acquisition method and the autonomous driving method are applicable to this vehicle embodiment, and will not be described in detail here.
[0102] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.
Claims
1. A method for obtaining functional difference layers, characterized in that, The method includes: Activate the autonomous driving function of test vehicles on real roads with map coverage; Acquire the driving data of the test vehicle on the real road; the driving data includes the first abnormal point data marked when the autonomous driving function malfunctions; The driving process is reconstructed on the constructed electronic horizon road model based on the driving data. Based on the first anomaly data, the second anomaly data is marked accordingly in the reconstructed driving process, and the corresponding model data is obtained. The model data includes the second anomaly data. A functional difference layer corresponding to the current road scene type is generated based on the model data; the functional difference layer includes a blacklist or whitelist of driving segments of the real road generated based on the second anomaly data; The blacklist includes: road segment information corresponding to the abnormal driving segments when the number of abnormal driving segments in real road scenarios is less than the number of normal driving segments; The whitelist includes: road segment information corresponding to the normally performing driving segments when there are more abnormal driving segments than normal driving segments in real road scenarios; The road segment information includes: road identification ID, lane ID and / or lane number data.
2. The method for obtaining functional difference layers according to claim 1, characterized in that, The acquisition of the driving data of the test vehicle on the real road includes: During the driving of the test vehicle on the real road, road information is acquired, and the time and location of the abnormality of the autonomous driving function are marked as the first abnormality point data. The electronic horizon message data containing the road information and the first anomaly point data is captured and used as the driving data.
3. The method for obtaining functional difference layers according to claim 2, characterized in that, The process of reconstructing the driving process on the constructed electronic horizon road model based on the driving data includes: The electronic horizon message data is loaded using a preset map visualization tool, the electronic horizon road model is constructed, and the electronic horizon road model is displayed as a base map in the map visualization tool. The electronic horizon message data is replayed on the electronic horizon road model, and the location of the test vehicle at different times on the real road is simulated and displayed on the base map of the map visualization tool, and each piece of road information in the electronic horizon message data is displayed.
4. The method for obtaining functional difference layers according to claim 3, characterized in that, Both the first anomaly data and the second anomaly data include: the time and location when the autonomous driving function malfunctioned; The step of marking the second anomaly data accordingly based on the first anomaly data in the reconstructed driving process includes: By comparing the first anomaly data with the real-time location of the road test vehicle played back in the map visualization tool, the second anomaly data is marked in the map visualization tool, and the location attribute values related to the second anomaly data are automatically written to a preset format annotation file.
5. The method for obtaining functional difference layers according to claim 4, characterized in that, The step of generating a functional difference layer corresponding to the current road scene type based on the model data includes: The annotation file is read, the annotation file is classified into the current road scene type, a functional difference layer file corresponding to the current road scene type is generated by city, and the functional difference layer is obtained based on the functional difference layer file.
6. The method for obtaining functional difference layers according to claim 5, characterized in that, Each of the aforementioned road scene types includes a road scene switch; The road scene switch is configured to, when in the on state, activate the road scene and control the electronic horizon road module under the road scene to send the electronic horizon message data; when in the off state, deactivate the road scene and control the electronic horizon road module under the road scene not to send the electronic horizon message data.
7. A functional difference layer acquisition device, comprising a first processor and a first memory, wherein the first memory stores a first instruction, characterized in that, When the first instruction is executed by the first processor, the method for obtaining the functional difference layer as described in any one of claims 1-6 is implemented.
8. An autonomous driving method, characterized in that, The method includes: Retrieve the functional difference layer corresponding to the current driving road; the functional difference layer is obtained by the method for obtaining the functional difference layer according to any one of claims 1-6; Automated driving is performed based on the retrieved functional difference layer.
9. The autonomous driving method according to claim 8, characterized in that, The automatic driving based on the retrieved functional difference layer includes: Determine the road scene type corresponding to the functional difference layer; When the number of abnormal driving segments in the identified road scene type is less than the number of normal driving segments, the preset road scene switch is set to the on state, and the blacklist and whitelist flags corresponding to the road scene type are marked as blacklisted, so that the vehicle can perform autonomous driving function on the driving segments on the current driving road other than the blacklisted segments, and stop the autonomous driving function on the driving segments corresponding to the blacklisted segments. When the number of abnormal driving segments in the identified road scene type exceeds the number of normal driving segments, the road scene switch is set to the off state, and the blacklist and whitelist flags are marked as whitelisted. This causes the vehicle to stop the autonomous driving function on driving segments other than those on the whitelist on the current driving road, and to perform the autonomous driving function on driving segments corresponding to the whitelist.
10. An autonomous driving device, comprising a second processor and a second memory, wherein the second memory stores second instructions, characterized in that, When the second instruction is executed by the second processor, the autonomous driving method as described in claim 8 or 9 is implemented.
11. A vehicle, characterized in that, It includes the functional difference layer acquisition device as described in claim 7 and the autonomous driving device as described in claim 10.