Output path planning method and apparatus, and electronic device

Abstract

An output path planning method and apparatus, an electronic device, and a computer-readable storage medium. The method comprises: acquiring current positioning pose data of a vehicle and environment data (S1); compiling the positioning pose data and the environment data into a description text (S2); and compiling the description text into a visual language text, and obtaining a path planning output result on the basis of the visual language text (S3). According to the method, the visual language text is directly output as the path planning output result. In this way, path planning calculation can be realized in multiple dimensions, thereby improving the accuracy of path planning.

Description

Method, device and electronic device for outputting path planning Technical Field

[0001] The embodiments of the present application relate to the field of intelligent driving technology, and in particular to a method, device, and electronic device for outputting path planning. Background Art

[0002] At present, the intelligent driving technology of vehicles has been developing rapidly. Some vehicles can already realize intelligent driving in simple road environments, such as intelligent driving on highways with fewer vehicles.

[0003] Summary of the Invention

[0004] The present application provides a method, device and electronic device for outputting path planning.

[0005] In a first aspect, the present application provides a method for outputting path planning, the method comprising: obtaining the current positioning posture data and environmental data of a vehicle, wherein the environmental data includes at least high-precision map data and navigation data; compiling the positioning posture data and the environmental data into a description text, wherein the description text is text data describing the current surrounding environment of the vehicle; compiling the description text into a visual language text; and obtaining a path planning output result based on the visual language text.

[0006] Based on this method, visual language text can be directly used as the path planning output result, thereby realizing the calculation of path planning in multiple dimensions, thereby improving the accuracy of path planning.

[0007] In an optional embodiment, the positioning posture data and the environmental data are compiled into a description text, including: extracting posture keywords representing the current posture of the vehicle from the positioning posture data, and using the posture keywords as target words; extracting position keywords representing the current position of the vehicle from the high-precision map data, and using the position keywords as map words; extracting navigation keywords containing the destination of the vehicle from the navigation data, and using the navigation keywords as the navigation words; and text-arranging the target words, the map words, and the navigation words to generate the description text.

[0008] In an optional embodiment, the description text is compiled into a visual language text, including: performing visual language compilation on the target words, the map words, and the navigation words to obtain environment words, behavior words, and result words, respectively, wherein the environment words are used to describe the environment currently surrounding the vehicle, the behavior words are used to describe the current behavior of the vehicle, and the result words are used to describe the relationship between the environment words and the behavior words; and performing text arrangement on the environment words, the behavior words, and the result words to generate the visual language text consisting of the environment words, the behavior words, and the result words.

[0009] In an optional embodiment, a path planning output result is obtained based on the visual language text, including: calculating the attention between different types of words in the visual language text through an attention algorithm; rewriting and arranging different types of words in the visual language text based on the attention between different types of words to obtain an output language text, and using the output language text as the path planning output result.

[0010] In an optional embodiment, each type of word in the visual language text is rewritten and arranged based on the attention between each type of word to obtain an output language text, including: generating a pattern text corresponding to the current driving mode of the vehicle; based on the attention between each type of word and the pattern text, each type of word in the visual language text is rewritten and arranged to obtain an output language text containing the pattern text.

[0011] In the second aspect, the present application provides a device for outputting path planning, which includes: an acquisition unit for acquiring the vehicle's current positioning posture data and environmental data, wherein the environmental data includes high-precision map data and navigation data; a description text compilation unit for compiling the positioning posture data and the environmental data into a description text, wherein the description text is text data describing the vehicle's current surrounding environment; a processing unit for compiling the description text into a visual language text, and obtaining a path planning output result based on the visual language text.

[0012] In an optional embodiment, the description text compilation unit is used to: extract posture keywords representing the current posture of the vehicle from the positioning posture data, and use the posture keywords as target words; extract position keywords representing the current position of the vehicle from the high-precision map data, and use the position keywords as map words; extract navigation keywords containing the destination of the vehicle from the navigation data, and use the navigation keywords as navigation words; and perform text arrangement on the target words, the map words, and the navigation words to generate the description text.

[0013] In an optional embodiment, the processing unit is used to: calculate the attention between different types of words in the visual language text through an attention algorithm; rewrite and arrange different types of words in the visual language text based on the attention between different types of words to obtain output language text, and use the output language text as the path planning output result.

[0014] In a third aspect, the present application provides an electronic device comprising: a memory for storing a computer program; and a processor for implementing the method steps of outputting a path planning as described in any of the above methods when executing the computer program stored in the memory.

[0015] In a fourth aspect, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps of outputting path planning described in any of the above methods are implemented.

[0016] For each of the above-mentioned aspects from the second to the fourth aspects and the technical effects that may be achieved by each of the aspects, please refer to the above-mentioned description of the technical effects that can be achieved by the first aspect or various possible solutions in the first aspect, and no further details will be given here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 is a flow chart of a method for outputting path planning provided in an embodiment of the present application.

[0018] FIG2 is a schematic diagram of the architecture of a path planning output system provided in an embodiment of the present application.

[0019] FIG3 is a schematic diagram of a path planning display interface provided in an embodiment of the present application.

[0020] FIG4 is a schematic diagram of the structure of a device for outputting path planning provided in an embodiment of the present application.

[0021] FIG5 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail with reference to the accompanying drawings. The specific operating methods in the method embodiments can also be applied to device embodiments or system embodiments. It should be noted that in the description of the present application, "multiple" is understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. A is connected to B, which can represent the following two situations: A is directly connected to B and A is connected to B through C. In addition, in the description of the present application, words such as "first" and "second" are only used to distinguish the purpose of description, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0023] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0024] At present, the intelligent driving technology of vehicles has been developing rapidly. Some vehicles can already realize intelligent driving in simple road environments, such as intelligent driving on highways with fewer vehicles.

[0025] In intelligent driving scenarios, various sensors and processors are combined to perceive and calculate the vehicle's surroundings. Path planning is then implemented using environmental perception data, navigation data, and positioning and posture data. Currently, the mainstream path planning approach uses post-processing algorithms to select a single planned path from among multiple planned paths. This selected path can be globally optimal, maximize probability, or maximize safety. However, current path planning methods rely on post-processing algorithms, which utilize fewer dimensions and result in inaccurate results.

[0026] In order to solve the above technical problems, an embodiment of the present application provides a method for outputting path planning. In this method, the current positioning posture data and environmental data of the vehicle are first obtained, the positioning posture data and environmental data are compiled into a description text, the description text is compiled into a visual language text, and the path planning output result is obtained based on the visual language text. This method can perform path planning calculations in multiple dimensions such as vehicle data, positioning posture data, and environmental data, thereby ensuring that the final output path planning output result displayed in text form is more accurate.

[0027] FIG1 is a flow chart of a method for outputting path planning provided in an embodiment of the present application. As shown in FIG1 , the method includes steps S1 to S3 .

[0028] Step S1, obtaining the vehicle's current positioning posture data and environmental data.

[0029] The method for outputting path planning provided in the embodiment of the present application can be applied to the system architecture shown in FIG2 . The system architecture includes: a description text generation module 210 , a text analysis module (not shown in FIG2 ), and a visual language text compilation module 220 .

[0030] The text analysis module is configured to analyze the input data and extract different words from the input data. The words extracted by the text analysis module can be input into the description text generation module 210, which encodes the words extracted by the text analysis module to generate description text. The visual language text compilation module 220 is configured to receive the description text generated by the description text generation module 210 and compile the description text into visual language text.

[0031] Specifically, the text analysis module first obtains input data, which includes the vehicle's current positioning data and environmental data of the vehicle's current location. The environmental data may include high-precision map data and navigation data (such as the standard navigation map shown in Figure 2). The high-precision map data may be a local high-precision map vector segment, through which the local high-precision map around the vehicle's current location can be determined.

[0032] In some embodiments, in addition to high-precision map data and navigation data, the environmental data may also include the vehicle's current 3D occupied area data, which can accurately determine the vehicle's current location and area occupancy status.

[0033] In addition, in the embodiment of the present application, in addition to the high-precision map data, navigation data, and 3D occupied area data introduced above, other relevant data of the vehicle at the current moment can also be added to the environmental data, which will not be illustrated one by one here.

[0034] Step S2: compile the positioning posture data and environmental data into a description text.

[0035] In an embodiment of the present application, after obtaining positioning posture data and environmental data, language analysis is first performed on the positioning posture data and environmental data. A posture keyword representing the vehicle's current posture is then extracted from the positioning posture data. The posture keyword can be a single word or multiple words, and this is not limited here. The posture keyword is then used as a target word. The target word describes the vehicle's current posture state.

[0036] By performing linguistic analysis on the high-precision map data within the environmental data, location keywords representing the vehicle's current location are extracted from this high-precision map data. This keyword extraction can be based on existing text recognition methods or through a neural network model for keyword extraction. The extracted location keywords are then used as map words, which describe the vehicle's current map data. For example, the vehicle's current map data includes information such as the presence of nearby vehicles, the presence of nearby pedestrians, the distance to surrounding vehicles, and the distance to pedestrians.

[0037] By performing linguistic analysis on the navigation data, navigation keywords containing the vehicle's departure and destination are extracted from the navigation data. Navigation keywords can be extracted based on the navigation data input by the user. For example, based on the user-entered information such as the starting point and destination, navigation keywords are extracted and navigation path data is generated. The navigation keywords are then used as navigation words, which represent navigation-related information about the vehicle at the current moment, such as the vehicle's starting location, end location, and current travel path. It should be noted that the navigation words can include multiple keywords, and the content of the navigation words is not limited here.

[0038] The above-mentioned target words, map words and navigation words describe the driving status of the vehicle and the surrounding environment status at the current moment, such as the vehicle's position, direction, speed, lane, nearby vehicles, nearby pedestrians, etc.

[0039] In addition to performing language analysis on positioning data, high-precision map data, and navigation data, the text analysis module can also perform language analysis on other data to obtain other words. Other words can include the vehicle's current driving mode, operating status, etc.

[0040] After obtaining the target word, map word, and navigation word through the text analysis module, the target word, map word, and navigation word can be input into the description text generation module 210. The description text generation module 210 first determines the relevance between the target word, map word, and navigation word, which can be specifically obtained by calculating the relevance between the words; then, based on the result of the relevance calculation, the target word, map word, and navigation word are rearranged to generate a description text. Of course, conjunctions will be added during the arrangement process to ensure that a complete description text is formed. In an embodiment, the description text generated based on the target word, map word, and navigation word can be: "There is an intersection 200 meters ahead, and there are currently two cars around, which are 10 meters and 50 meters away from me, respectively. The rest is an open area, and there is a dotted line on the ground that indicates a changeable lane." In this way, a description text of the vehicle's surroundings can be accurately obtained.

[0041] Step S3: compile the description text into visual language text, and obtain the path planning output result according to the visual language text.

[0042] Referring to the system architecture shown in FIG2 , after the description text generation module 210 generates the description text, the description text is imported into the visual language text compilation module 220. The visual language text compilation module 220 then recompiles the target words, map words, and navigation words in the description text into environment words, behavior words, and result words. In FIG2 , the environment words and behavior words can be collectively referred to as state words.

[0043] The visual language text compilation module 220 is further used to rearrange the texts of various words, thereby arranging the environment words, behavior words and result words into another text, which is the visual language text.

[0044] It should be noted here that environmental words are used to describe the environment around the vehicle at the current moment, behavioral words are used to describe the current behavior of the vehicle, and result words are used to describe the relationship between environmental words and behavioral words. Therefore, the visual language text is composed of environmental words, behavioral words, and result words. In an embodiment of the present application, the visual language text can be directly output as the path planning output result. In this way, the calculation of path planning can be achieved through multiple dimensions, thereby improving the accuracy of path planning.

[0045] In some embodiments, the above-mentioned output path planning method mainly performs language analysis and processing on the data, and the process can be completed by the GPU (English full name: Graphic Processing Unit, Chinese name: Graphics Processing Unit). There is no need to copy the data from the GPU to the CPU to complete the subsequent processing process, that is, the CPU is no longer required to perform calculations, thereby eliminating the data transmission between the CPU and the GPU, realizing efficient on-chip computing under the full GPU, and reducing the text of data transmission.

[0046] In some embodiments, the above-described output path planning method can be executed by a vehicle control system, such as a controller on the vehicle. In some embodiments, the above-described output path planning method can be executed by a GPU in a vehicle control system, such as a GPU in a controller on the vehicle. In some embodiments, the output path planning method can be executed by a server on the vehicle. For example, after obtaining the path planning data result, the server sends the path planning output result to the vehicle, so that the path planning output result can be output by the vehicle's voice system.

[0047] In the embodiment of the present application, the system architecture shown in FIG2 also includes an attention calculation module 230. In addition to outputting the path planning results, the attention mechanism algorithm can also obtain the vehicle's current and expected behavior data, vehicle speed signal, and corner signal. Of course, the specific signals to be obtained can be set according to the actual application scenario, and no further examples will be given here.

[0048] In an embodiment of the present application, in order to improve the accuracy of the final output path planning result, after the visual language text compilation module 220 obtains the visual language text, the visual language text can be output to the attention calculation module 230. The attention calculation module 230 can decompose the various types of words in the visual language text, and then calculate the attention between the various types of words in the visual language text through the attention mechanism algorithm. The attention represents the correlation between the words.

[0049] The attention calculation module 230 can output the attention between each type of words in the visual language text to the visual language text compilation module 220. The visual language text compilation module 220 rewrites and arranges each type of words in the visual language text based on the attention between each type of words to obtain the output language text, and uses the output language text as the path planning output result.

[0050] That is to say, the attention mechanism can determine the correlation between words, and then the order between words can be determined through this correlation, so as to rearrange the words in the visual language text and obtain the final output result.

[0051] For example, as shown in Figure 3, vehicle A is the current vehicle, vehicle B is another road user, and the gray areas on the ground represent high-precision map and standard map points. Taking the current moment as an example, the final path planning output can be described as follows: "The vehicle is currently at an intersection, and the standard map navigation tells me to go straight. There is a vehicle ahead, traveling at 30 km / h. There is also a vehicle on the left, also traveling at 30 km / h. Lane changes are not allowed on the right. If recommended for safety, the vehicle recommends following the vehicle at 25 km / h."

[0052] As can be seen from the above examples, after analyzing and processing positioning pose data, navigation data, and map data, the final output is a path planning result for visual language text. Furthermore, by incorporating the attention mechanism into the analysis and processing, the correlation between each word is increased, making the final path planning result more accurate.

[0053] In an embodiment of the present application, when calculating the attention between different types of words through the attention mechanism, other information about the vehicle at the current moment, such as the vehicle's driving mode, can also be added. Therefore, after obtaining the vehicle's driving mode at the current moment, a pattern text corresponding to the driving mode is generated, such as: aggressive mode, steady mode, safe mode, etc. Based on the attention between different types of words and the pattern text, the different types of words in the visual language text are rewritten and arranged to obtain an output language text containing the pattern text. In this way, other information can be added to the final path planning output result, so that the final path planning output result is more in line with the driver's driving habits and improves the driver's experience.

[0054] The text analysis module, description text generation module, visual language text compilation module and attention module in the embodiments of the present application can be implemented by computer executable instructions.

[0055] Based on the same inventive concept, an embodiment of the present application further provides a device for outputting a path plan. FIG4 is a schematic structural diagram of an apparatus for outputting a path plan in an embodiment of the present application, the apparatus comprising:

[0056] An acquisition unit 401 is configured to acquire the vehicle's current positioning data and environmental data, wherein the environmental data includes high-precision map data and navigation data;

[0057] A description text compiling unit 402 is configured to compile the positioning posture data and the environment data into a description text, wherein the description text is text data describing the current surrounding environment of the vehicle;

[0058] The processing unit 403 is configured to compile the description text into a visual language text, and obtain a path planning output result according to the visual language text.

[0059] In an optional embodiment, the description text compiling unit 402 is specifically configured to

[0060] Extracting posture keywords representing the current posture of the vehicle from the positioning posture data, and using the posture keywords as target words;

[0061] extracting a location keyword representing the current location of the vehicle from the high-precision map data, and using the location keyword as a map word;

[0062] extracting a navigation keyword containing the destination of the vehicle from the navigation data, and using the navigation keyword as a navigation word;

[0063] The target word, the map word, and the navigation word are arranged into text to generate the description text.

[0064] In an optional embodiment, the processing unit 403 is specifically configured to calculate the attention between different types of words in the visual language text by using an attention algorithm;

[0065] The various types of words in the visual language text are rewritten and arranged based on the attention between the various types of words to obtain an output language text, and the output language text is used as the path planning output result.

[0066] Based on the same inventive concept, an embodiment of the present application further provides an electronic device that can implement the functions of the aforementioned device for outputting a path plan. Referring to FIG5 , the electronic device includes:

[0067] At least one processor 501, and a memory 502 connected to at least one processor 501. The specific connection medium between the processor 501 and the memory 502 is not limited in the embodiments of the present application. FIG5 takes the connection between the processor 501 and the memory 502 via the bus 500 as an example. The bus 500 is represented by a bold line in FIG5. The connection method between other components is only for schematic illustration and is not intended to be limiting. The bus 500 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, FIG5 only uses a bold line to represent it, but this does not mean that there is only one bus or one type of bus. Alternatively, the processor 501 can also be called a controller, and there is no limitation on the name.

[0068] In this embodiment of the present application, memory 502 stores instructions executable by at least one processor 501. At least one processor 501 can execute the method for outputting a path plan discussed above by executing the instructions stored in memory 502. Processor 501 can implement the functions of each module in the apparatus shown in FIG4.

[0069] Among them, the processor 501 is the control center of the device, which can use various interfaces and lines to connect the various parts of the entire control device, and monitor the device as a whole by running or executing instructions stored in the memory 502 and calling data stored in the memory 502, the various functions of the device and processing data.

[0070] In one possible design, processor 501 may include one or more processing units. Processor 501 may integrate an application processor and a modem processor. The application processor primarily processes the operating system, user interface, and application programs, while the modem processor primarily processes wireless communications. It is understood that the modem processor may not be integrated into processor 501. In some embodiments, processor 501 and memory 502 may be implemented on the same chip. In some embodiments, they may also be implemented on separate chips.

[0071] The processor 501 can be a general-purpose processor, such as a central processing unit, a graphics processing unit (GPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method for outputting path planning disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0072] The memory 502 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 502 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. The memory 502 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 502 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0073] By programming the processor 501, the code corresponding to the method for outputting a path plan described in the aforementioned embodiment can be embedded in the chip, enabling the chip to execute the steps of the method for outputting a path plan in the embodiment shown in FIG1 during operation. Designing and programming the processor 501 is well known to those skilled in the art and will not be further described here.

[0074] Based on the same inventive concept, an embodiment of the present application further provides a storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer executes a method for outputting path planning discussed above.

[0075] In some possible implementations, various aspects of a method for outputting path planning provided by the present application may also be implemented in the form of a program product, which includes program code. When the program product is run on an apparatus, the program code is used to enable the control device to execute the steps of a method for outputting path planning according to various exemplary implementations of the present application described above in this specification.

[0076] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0077] The present application is described with reference to the flow chart and / or block diagram of the method, device (system), and computer program product according to the embodiment of the present application. It should be understood that each flow process and / or box in the flow chart and / or block diagram and the combination of the flow process and / or box in the flow chart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processing machine or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one flow chart flow or multiple flows and / or one box or multiple boxes of the block diagram.

[0078] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0080] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for outputting path planning, comprising: Acquire the current positioning posture data and environmental data of the vehicle, wherein the environmental data includes high-precision map data and navigation data; Compiling the positioning posture data and the environment data into a description text, wherein the description text is text data describing the current surrounding environment of the vehicle; Compiling the description text into visual language text; and A path planning output result is obtained according to the visual language text.

2. The method according to claim 1, characterized in that Compiling the positioning posture data and the environment data into a description text includes: Extracting posture keywords representing the current posture of the vehicle from the positioning posture data, and using the posture keywords as target words; Extracting a location keyword representing the current location of the vehicle from the high-precision map data, and using the location keyword as a map word; extracting a navigation keyword including the destination of the vehicle from the navigation data, and using the navigation keyword as a navigation word; The target word, the map word, and the navigation word are arranged into text format to generate the description text.

3. The method according to claim 2, characterized in that Compiling the description text into visual language text, including: Performing visual language compilation on the target word, the map word, and the navigation word to obtain environment words, behavior words, and result words, respectively, wherein the environment words are used to describe the environment currently surrounding the vehicle, the behavior words are used to describe the current behavior of the vehicle, and the result words are used to describe the relationship between the environment words and the behavior words; The environment words, the behavior words and the result words are arranged into text format to generate the visual language text containing the environment words, the behavior words and the result words.

4. The method according to claim 1, characterized in that Obtaining a path planning output result according to the visual language text includes: Calculating the attention between different types of words in the visual language text by using an attention algorithm; Rewrite and arrange the words of each type in the visual language text based on the attention between the words of each type to obtain an output language text; and The output language text is used as the path planning output result.

5. The method according to claim 4, characterized in that Rewriting and arranging each type of word in the visual language text based on the attention between each type of word to obtain an output language text, including: generating a mode text corresponding to a current driving mode of the vehicle; Based on the attention between the various types of words and the pattern text, the various types of words in the visual language text are rewritten and arranged to obtain an output language text containing the pattern text.

6. A device for outputting path planning, comprising: An acquisition unit, used to acquire the current positioning posture data and environmental data of the vehicle, wherein the environmental data includes high-precision map data and navigation data; A description text compiling unit, used to compile the positioning posture data and the environment data into a description text, wherein the description text is text data describing the current surrounding environment of the vehicle; A processing unit is used to compile the description text into a visual language text and obtain a path planning output result according to the visual language text.

7. The device according to claim 6, characterized in that The description text compilation unit is used for: Extracting posture keywords representing the current posture of the vehicle from the positioning posture data, and using the posture keywords as target words; Extracting a location keyword representing the current location of the vehicle from the high-precision map data, and using the location keyword as a map word; extracting a navigation keyword including the destination of the vehicle from the navigation data, and using the navigation keyword as a navigation word; The target word, the map word, and the navigation word are arranged into text format to generate the description text.

8. The device according to claim 6, characterized in that The processing unit is used for: Calculating the attention between different types of words in the visual language text by using an attention algorithm; Rewrite and arrange the words of different types in the visual language text based on the attention between the words of different types to obtain an output language text; and The output language text is used as the path planning output result.

9. An electronic device, comprising: Memory, used to store computer programs; A processor, configured to implement the method steps of any one of claims 1 to 5 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method steps described in any one of claims 1 to 5.

Images