A parking mapping and operation method, device and electronic equipment

Abstract

This invention provides a parking mapping operation method, apparatus, and electronic device. The method includes the following steps: when the main state machine receives a wake-up command, it starts a pre-created scheduled node in the mapping through a scheduling function pre-added to the autonomous driving operation framework. The scheduled node includes a mapping node and a positioning node; the mapping node obtains a first feedback signal indicating that the scheduled node has been started, wherein when the main state machine obtains the first feedback signal, the mapping node receives configuration data from the data collection node to complete a new mapping based on the configuration data; the mapping node obtains a second feedback signal indicating that the new mapping is successful; based on the second feedback signal, the vehicle is controlled to complete memory parking according to the new mapping, and the scheduled node is shut down after memory parking is completed. This improves the problem of excessive CPU computing resources being consumed and reducing the stability of the mapping function during memory parking mapping operation.

Description

Technical Field

[0001] This invention belongs to the field of artificial intelligence technology, specifically relating to a parking mapping and operation method, device, and electronic equipment. Background Technology

[0002] With the rapid development of artificial intelligence, various technologies that use AI to assist or even replace human labor have been proposed and are constantly being improved, with autonomous driving being an important one. In the field of autonomous driving, parking is one of its most important functions, and memory parking is a key feature.

[0003] Parking environments in natural scenarios are complex and ever-changing. Current infrastructure cannot provide a high-precision map for every parking scenario. Even if a 3D map is created beforehand for a parking scenario, changes will occur over time. Therefore, memory parking, which flexibly constructs scenario maps and plans parking routes, will be a frequently used automatic parking function. However, map building, a core component of memory parking, requires extensive computation and consumes significant CPU resources during operation. Therefore, reducing CPU usage and improving the stability of the map building function are paramount for memory parking. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a parking mapping operation method, apparatus and electronic device to solve the problem that the mapping function of memory parking consumes a lot of CPU computing resources and reduces the stability of the mapping function during operation.

[0005] The present invention solves the above-mentioned technical problems through the following technical means:

[0006] In a first aspect, embodiments of this application provide a parking mapping and operation method, applied to the main state machine of a vehicle, the method comprising:

[0007] When the master state machine receives a wake-up command, it starts the pre-created scheduled nodes in the mapping through a scheduling function pre-added to the autonomous driving operation framework. The scheduled nodes include mapping nodes and positioning nodes.

[0008] The mapping node obtains a first feedback signal indicating that the scheduled node has been started. When the main state machine obtains the first feedback signal, the mapping node receives configuration data from the data collection node to complete a new mapping based on the configuration data.

[0009] A second feedback signal representing the success of the new mapping is obtained through the mapping node;

[0010] Based on the second feedback signal, the vehicle is controlled to complete memory parking according to the new map, and the scheduled node is closed through the scheduling function after memory parking is completed.

[0011] In conjunction with the first aspect, in some optional embodiments, before the master state machine receives the wake-up command, the method further includes:

[0012] Write a scheduling function and add it to the autonomous driving operation framework. Then call the scheduling function through a subroutine, where the subroutine is the program of all nodes.

[0013] In conjunction with the first aspect, in some optional implementations, the mapping node is also used to load pre-stored configuration items in the mapping node when the autonomous driving operation framework invokes the mapping node, and then send a suspension command. After receiving the suspension command, the subroutine is used to listen for wake-up commands and stop receiving signals from other nodes.

[0014] In conjunction with the first aspect, in some optional implementations, scheduling nodes in a pre-created graph are initiated by pre-added scheduling functions within the autonomous driving operation framework, including:

[0015] After receiving the wake-up command, the master state machine executes the scheduling function of the autonomous driving operation framework. The master state machine is equipped with a flag bit for repeated calling throughout the entire vehicle operation cycle. The flag bit and the wake-up command judgment statement work together to call the scheduled node once in the same mapping cycle.

[0016] In conjunction with the first aspect, in some optional implementations, the method further includes the steps of obtaining a second feedback signal indicating the success of the new mapping through the mapping node and, based on the second feedback signal, controlling the vehicle to complete memory parking according to the new mapping, and closing the scheduling between the scheduled nodes through the scheduling function after completing memory parking.

[0017] The execution status of the mapping is obtained from the second feedback signal returned by the mapping node, and it is determined whether to reset the flag bit. The flag bit includes a flag indicating whether mapping is being performed. When it is determined to reset the flag bit, the flag bit is reset. Then, the simultaneous action of the flag bit and the wake-up command is used to determine the execution steps. The scheduled node in the pre-created mapping is started by the scheduling function pre-added in the autonomous driving operation framework.

[0018] In conjunction with the first aspect, in some alternative implementations, the new mapping includes feature point mapping and semantic mapping.

[0019] In conjunction with the first aspect, in some optional implementations, after completing the new mapping, the mapping node continues to suspend itself and waits for the next call of the main state machine.

[0020] Secondly, embodiments of this application also provide a parking mapping and operation device, comprising:

[0021] The wake-up unit is used to start the pre-created scheduled nodes in the mapping by means of the scheduling function pre-added to the autonomous driving operation framework when the main state machine receives a wake-up command. The scheduled nodes include mapping nodes and positioning nodes.

[0022] A mapping unit is used to obtain a first feedback signal representing the activation of the scheduled node through the mapping node, wherein when the main state machine obtains the first feedback signal, the mapping node receives configuration data from the data collection node to complete a new mapping based on the configuration data;

[0023] The feedback unit is used to obtain a second feedback signal representing the success of the new mapping through the mapping node;

[0024] An execution unit is configured to control the vehicle to complete memory parking based on the second feedback signal and the new mapping, and to close the scheduled node through the scheduling function after completing memory parking.

[0025] Thirdly, embodiments of this application also provide an electronic device, which includes a processor and a memory coupled to each other, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the electronic device performs the above-described method.

[0026] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the methods described above.

[0027] The present invention has the following advantages:

[0028] When a vehicle needs to remember its parking space during autonomous driving, it first sends a wake-up command (map start signal) to the main state machine. Upon receiving the map start signal, the main state machine uses a scheduling function to start the scheduled node. After successfully starting the scheduled node, it sends a first feedback signal indicating that the scheduled node has been started to the main state machine. Then, the electronic devices receive configuration data through the data collection node and complete a new map based on the configuration data. The second feedback signal indicating that the new map has been successfully built is then sent to the main state machine. The main state machine then controls the vehicle to complete the memory parking based on the new map. Finally, it shuts down the scheduled node through the scheduling function, waiting for the next use. By defining the scheduling of mapping nodes separately within the autonomous driving framework, the operation of other nodes is not affected during runtime. Simultaneously, when the master state machine does not receive a wake-up command, the mapping node does not receive signals from other nodes, but only listens to the master state machine's instructions, reducing the average CPU utilization. Furthermore, the master state machine receives and determines the timing of mapping scheduling and introduces a flag for the mapping state to avoid repeated calls within the same cycle. Scheduling mapping nodes through the master state machine allows the system to know when the CPU load will increase, thereby dynamically planning CPU usage and improving system stability. Attached Figure Description

[0029] The present invention can be further illustrated by the non-limiting embodiments given in the accompanying drawings:

[0030] Figure 1 This is a schematic flowchart of a parking mapping and operation method provided by an embodiment of the present invention;

[0031] Figure 2 This is a block diagram of a parking mapping and operation device provided in this invention.

[0032] Icons: 200 - Wake-up unit; 210 - Mapping unit; 220 - Feedback unit; 230 - Execution unit. Detailed Implementation

[0033] The present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that similar or identical parts are referred to by the same reference numerals in the drawings or description. Implementations not shown or described in the drawings are forms known to those skilled in the art. In the description of this application, terms such as "first" and "second" are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0034] This application provides an electronic device. The electronic device includes a processor and a memory coupled together. The memory stores a computer program, and when the computer program is executed by the processor, the electronic device is able to perform corresponding steps in a parking mapping operation method described below.

[0035] Electronic devices can be, but are not limited to, the main state machine of a vehicle. The processor and memory are electrically connected; the processor executes the computer program stored in the memory. Both the processor and memory are existing hardware modules, so they will not be described in detail here.

[0036] like Figure 1 As shown, this application also provides a parking mapping and operation method, which can be applied to the aforementioned electronic device, and the electronic device executes or implements the various steps of the method. That is, the parking mapping and operation method can be applied to the vehicle's main state machine, and the method may include the following steps:

[0037] Step 100: When the master state machine receives the wake-up command, it starts the pre-created scheduled nodes in the mapping through the scheduling function pre-added to the autonomous driving operation framework. The scheduled nodes include mapping nodes and positioning nodes.

[0038] Step 110: Obtain the first feedback signal representing the start of the scheduled node through the mapping node. When the mapping node obtains the first feedback signal in the main state machine, it receives configuration data from the data collection node to complete the new mapping according to the configuration data.

[0039] Step 120: Obtain the second feedback signal representing the success of new map construction through the map construction nodes;

[0040] Step 130: Based on the second feedback signal, control the vehicle to complete memory parking according to the new map, and shut down the scheduled node through the scheduling function after completing memory parking.

[0041] The following is a detailed explanation of each step in the parking mapping and operation method:

[0042] In step 100, when the master state machine receives a wake-up command, it starts the scheduled nodes in the pre-created mapping by using the scheduling function pre-added to the autonomous driving operation framework. In this embodiment, the scheduled nodes include mapping nodes and positioning nodes. The wake-up command refers to the vehicle sending a signal to the master state machine to start mapping.

[0043] In this embodiment, before the main state machine receives the wake-up command, it first uses an electronic device to write a scheduling function and adds the scheduling function to the autonomous driving operation framework. The scheduling function is called through a subroutine, where the subroutine is any node program; for example, any node program generated using the autonomous driving operation framework can be called a subroutine. Additionally, the mapping node is also used to load pre-stored configuration items when the autonomous driving operation framework invokes the mapping node. Then, it sends a suspend command through the electronic device. Upon receiving the suspend command, the subroutine listens for the wake-up command and stops receiving signals from other nodes, thus serving only the wake-up command and reducing CPU usage. In this embodiment, the configuration items are conventional configuration items, so they will not be described in detail here.

[0044] For example, a scheduling function is a function defined in the autonomous driving operation framework and used in the program. Its function is to start and stop the scheduling program.

[0045] After receiving the wake-up command, the main state machine executes the scheduling function of the autonomous driving operation framework. The main state machine is equipped with a flag bit for repeated calling throughout the entire vehicle operation cycle. The flag bit and the wake-up command judgment statement work together to call the scheduled node once in the same mapping cycle. This can improve the problem of the large amount of CPU computing resources consumed and the reduced stability of the mapping function during the operation of the memory parking mapping function.

[0046] In this embodiment, repeated calls refer to the entire vehicle operation cycle, which is the period from power-on to power-off; a single call refers to a single mapping cycle. For example, if the mapping node is in a busy state, it will not respond even if an external signal to start mapping is input, because mapping is in progress. Therefore, the signal to start mapping and the wake-up command judgment statement need to act simultaneously to ensure that the node is called only once in the same mapping cycle.

[0047] In step 110, the master state machine obtains a first feedback signal representing the start of the scheduled node through the mapping node. When the master state machine obtains the first feedback signal, the electronic device receives configuration data from the data collection node to complete the new mapping based on the configuration data.

[0048] In this embodiment, the new graph construction includes feature point graph construction and semantic graph construction. After the graph construction node completes the new graph construction, the graph construction node will continue to be suspended and wait for the next call of the main state machine. The first feedback signal includes a signal indicating that the scheduled node has been successfully started. In this embodiment, feature point graph construction and semantic graph construction are two types of graph construction. Both feature point graph construction and semantic graph construction are existing technologies, so they will not be described in detail here.

[0049] In step 120, the master state machine obtains a second feedback signal representing the success of the new graph construction through the graph construction node.

[0050] In this embodiment, the main state machine obtains the mapping execution status from the second feedback signal returned by the mapping node and determines whether to reset the flag bit. The flag bit includes a flag indicating whether mapping has been completed, and the second feedback signal includes a signal indicating successful mapping. In this embodiment, when it is determined that the flag bit should be reset, the flag bit is reset. Then, the simultaneous action of the flag bit and the wake-up command is determined, and the execution steps are initiated by the scheduling function pre-added to the autonomous driving operation framework, activating the pre-created scheduled node in the mapping process.

[0051] In step 130, the master state machine, based on the second feedback signal, controls the vehicle to complete memory parking according to the new map, and after completing memory parking, shuts down the scheduled node through the scheduling function to reduce the CPU usage.

[0052] In this embodiment, each time a parking memory is used, the vehicle must first send a wake-up command to the main state machine, then use the scheduling function to start the scheduled node, then input configuration data into the map to complete the new map construction, then the main state machine controls the vehicle to complete the parking memory according to the new map construction, and finally use the scheduling function to shut down the scheduled node and wait for the next use.

[0053] This application also provides a parking mapping and operation device, which includes at least one software function module stored in a storage module or embedded in an operating system in the form of software or firmware. A processor is used to execute the executable module stored in the storage module, such as the software function module and computer program included in the parking mapping and operation device.

[0054] like Figure 2 As shown, the parking mapping and operation device includes a wake-up unit 200, a mapping unit 210, a feedback unit 220, and an execution unit 230. The functions of each unit are as follows:

[0055] The wake-up unit 200 is used to start the pre-created scheduled nodes in the mapping through the scheduling function pre-added to the autonomous driving operation framework when the main state machine receives the wake-up command. The scheduled nodes include mapping nodes and positioning nodes.

[0056] The mapping unit 210 is used to obtain a first feedback signal representing the start of the scheduled node through the mapping node. When the mapping node obtains the first feedback signal in the main state machine, it receives configuration data from the data collection node to complete the new mapping according to the configuration data.

[0057] Feedback unit 220 is used to obtain a second feedback signal representing the success of new mapping through mapping nodes;

[0058] The execution unit 230 is used to control the vehicle to complete memory parking based on the second feedback signal and the new map, and to close the scheduled node through the scheduling function after the memory parking is completed.

[0059] Optionally, the parking mapping operation device may also include a programming addition unit. Before the main state machine receives a wake-up command, the programming addition unit is used to: write a scheduling function and add the scheduling function to the autonomous driving operation framework, and call the scheduling function through subroutines, where the subroutines are all node programs; the mapping node is also used to send a suspension command after the mapping node has completed loading the relevant configuration items when the framework operation calls the mapping node, and the subroutines, after receiving the suspension command, are used to listen for wake-up commands and stop receiving signals from other nodes.

[0060] Optionally, the wake-up unit 200 can be used to: after the main state machine receives the wake-up command, execute the scheduling function of the autonomous driving operation framework, wherein the main state machine is set with a flag bit for repeated calling throughout the entire vehicle operation cycle, the flag bit acts simultaneously with the wake-up command judgment statement, so as to call the scheduled node once in the same mapping cycle.

[0061] Optionally, the mapping unit 210 can be used to: create new maps including feature point mapping and semantic mapping.

[0062] Optionally, the parking mapping operation device may further include a judgment unit. The feedback unit 220 obtains a second feedback signal indicating successful new mapping through the mapping node, and the execution unit 230, based on the second feedback signal, controls the vehicle to complete memory parking according to the new mapping. After completing memory parking, the scheduled node is closed via a scheduling function. The judgment unit is used to: obtain the mapping execution status from the second feedback signal returned by the mapping node, and determine whether to reset the flag bit, where the flag bit includes a flag indicating whether mapping has been completed. When it is determined that the flag bit should be reset, the flag bit is reset. Then, the simultaneous action of the flag bit and the wake-up command judgment statement, along with the execution steps, activates the scheduled node in the pre-created mapping through a scheduling function pre-added to the autonomous driving operation framework.

[0063] Optionally, the execution unit 230 can be used to: after a mapping node completes a new mapping, continue to suspend the mapping node and wait for the next call of the main state machine.

[0064] This application also provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to execute the parking mapping method described in the above embodiments.

[0065] Based on the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by hardware or by using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This software product can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, control device, or network device, etc.) to execute the methods described in the various implementation scenarios of this application.

[0066] In summary, this application provides a parking mapping operation method, apparatus, and electronic device. In this solution, when a vehicle needs to remember a parking space during autonomous driving, the vehicle first sends a wake-up command (map start signal) to the main state machine. Upon receiving the map start signal, the main state machine uses a scheduling function to start the scheduled node. After successfully starting the scheduled node, a first feedback signal indicating the node's activation is sent to the main state machine. Subsequently, the electronic device receives configuration data through a data collection node and completes a new map based on the configuration data. Then, a second feedback signal indicating successful new map construction is sent to the main state machine. The main state machine then controls the vehicle to complete the parking memory operation based on the new map. Finally, the scheduled node is shut down through the scheduling function, awaiting its next use. By defining the scheduling of mapping nodes separately within the autonomous driving framework, the operation of other nodes is not affected during runtime. Simultaneously, when the master state machine does not receive a wake-up command, the mapping node does not receive signals from other nodes, but only listens to the master state machine's instructions, reducing the average CPU utilization. Furthermore, the master state machine receives and determines the timing of mapping scheduling and introduces a flag for the mapping state to avoid repeated calls within the same cycle. Scheduling mapping nodes through the master state machine allows the system to know when the CPU load will increase, thereby dynamically planning CPU usage and improving system stability.

[0067] In the embodiments provided in this application, it should be understood that the disclosed apparatus, devices, and methods can also be implemented in other ways. The apparatus, devices, and methods embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which includes one or more executable instructions for implementing a specified logical function. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0068] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A parking mapping and operation method, characterized in that, The method, applied to the main state machine of a vehicle, includes: When the master state machine receives a wake-up command, it starts the pre-created scheduled nodes in the mapping through a scheduling function pre-added to the autonomous driving operation framework. The scheduled nodes include mapping nodes and positioning nodes. The mapping node obtains a first feedback signal indicating that the scheduled node has been started. When the main state machine obtains the first feedback signal, the mapping node receives configuration data from the data collection node to complete a new mapping based on the configuration data. A second feedback signal representing the success of the new mapping is obtained through the mapping node; Based on the second feedback signal, the vehicle is controlled to complete memory parking according to the new map, and the scheduled node is closed through the scheduling function after memory parking is completed.

2. The method according to claim 1, characterized in that, Before the main state machine receives the wake-up command, the method further includes: Write a scheduling function and add it to the autonomous driving operation framework. Then call the scheduling function through a subroutine, where the subroutine is the program of all nodes.

3. The method according to claim 2, characterized in that, The mapping node is also used to load pre-stored configuration items when the autonomous driving operation framework calls the mapping node, and then send a suspension command. After receiving the suspension command, the subroutine is used to listen for wake-up commands and stop receiving signals from other nodes.

4. The method according to claim 1, characterized in that, By pre-adding scheduling functions to the autonomous driving operation framework, the scheduled nodes in the pre-created graph are started, including: After receiving the wake-up command, the master state machine executes the scheduling function of the autonomous driving operation framework. The master state machine is equipped with a flag bit for repeated calling throughout the entire vehicle operation cycle. The flag bit and the wake-up command judgment statement work together to call the scheduled node once in the same mapping cycle.

5. The method according to claim 4, characterized in that, The method further includes the steps of obtaining a second feedback signal indicating the success of the new mapping through the mapping node, and controlling the vehicle to complete memory parking based on the second feedback signal and the new mapping, and closing the scheduling between the scheduled nodes through the scheduling function after completing memory parking. The execution status of the mapping is obtained from the second feedback signal returned by the mapping node, and it is determined whether to reset the flag bit. The flag bit includes a flag indicating whether mapping is being performed. When it is determined to reset the flag bit, the flag bit is reset. Then, the simultaneous action of the flag bit and the wake-up command is used to determine the execution steps. The scheduled node in the pre-created mapping is started by the scheduling function pre-added in the autonomous driving operation framework.

6. The method according to claim 1, characterized in that, The new mapping includes feature point mapping and semantic mapping.

7. The method according to claim 1, characterized in that, After completing the new graph construction, the graph construction node continues to suspend itself and waits for the next call of the main state machine.

8. A parking mapping and operation device, characterized in that, include: The wake-up unit is used to start the pre-created scheduled nodes in the mapping by means of the scheduling function pre-added to the autonomous driving operation framework when the main state machine receives a wake-up command. The scheduled nodes include mapping nodes and positioning nodes. A mapping unit is used to obtain a first feedback signal representing the activation of the scheduled node through the mapping node, wherein when the main state machine obtains the first feedback signal, the mapping node receives configuration data from the data collection node to complete a new mapping based on the configuration data; The feedback unit is used to obtain a second feedback signal representing the success of the new mapping through the mapping node; An execution unit is configured to control the vehicle to complete memory parking based on the second feedback signal and the new mapping, and to close the scheduled node through the scheduling function after completing memory parking.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory coupled together, the memory storing a computer program that, when executed by the processor, causes the electronic device to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when run on a computer, causes the computer to perform the method as described in any one of claims 1-7.

Images