An automatic parking method

Abstract

The application provides an automatic parking method, comprising the following steps: a domain controller receives an externally input parking instruction; the domain controller acquires 4D point cloud data, image data and positioning data according to the parking instruction; the domain controller performs fusion processing on the 4D point cloud data, the image data and the positioning data to obtain environmental data of a surrounding area of an automatic driving vehicle; the domain controller performs judgment according to the environmental data and a preset judgment condition; when the domain controller determines that the environmental data meets the preset judgment condition, target parking space data is determined according to the environmental data; the domain controller calls a preset simultaneous localization and mapping (SLAM) algorithm to perform route planning processing on the 4D point cloud data, the image data, the positioning data and the target parking space data to obtain parking route planning data; and the domain controller controls the vehicle to enter a parking space corresponding to the target parking space data according to the parking route planning data.

Description

Technical Field

[0001] This invention relates to the field of automotive driving control technology, and in particular to an automatic parking method. Background Technology

[0002] In recent years, with the progress of the automotive industry, the number of cars on the road has continued to rise. Given the limited number of parking spaces available, poor driving skills and bad parking habits often lead to vehicles deviating from their designated spaces or occupying multiple spaces, making it more difficult for other vehicles to park and potentially causing collisions or other accidents. To address these issues, various intelligent parking assistance systems have emerged. Parking is especially challenging for those with less-than-stellar driving skills, making automatic parking technology even more crucial for solving these parking difficulties. Summary of the Invention

[0003] The present invention aims to at least partially solve one of the technical problems in the related art.

[0004] Therefore, the purpose of this invention is to propose an automatic parking method to automatically park a car in a parking space, thereby solving the technical problem of parking difficulties in the prior art.

[0005] To achieve the above objectives, embodiments of the present invention propose an automatic parking method, the method comprising:

[0006] The domain controller receives parking commands from external input;

[0007] The domain controller acquires 4D point cloud data, image data, and positioning data according to the parking command;

[0008] The domain controller performs fusion processing based on the 4D point cloud data, the image data, and the positioning data to obtain environmental data around the autonomous vehicle.

[0009] The domain controller makes a determination based on the environmental data and preset judgment conditions. When the domain controller determines that the environmental data meets the preset judgment conditions, it determines the target parking space data based on the environmental data.

[0010] The domain controller invokes a preset Simultaneous Localization and Mapping (SLAM) algorithm to perform route planning processing on the 4D point cloud data, the image data, the positioning data, and the target parking space data to obtain parking route planning data.

[0011] The domain controller controls the vehicle to drive into the parking space corresponding to the target parking space data based on the parking route planning data.

[0012] Optionally, after the domain controller makes a determination based on the environmental data and preset determination conditions, the method further includes:

[0013] When the domain controller determines that the environmental data does not meet the preset judgment conditions, it performs parking space search route planning based on the environmental data to obtain parking space search route data.

[0014] The domain controller operates based on the parking space search route data and acquires the 4D point cloud data, the image data, and the positioning data in real time.

[0015] The domain controller makes a determination based on the environmental data and preset judgment conditions. When the domain controller determines that the environmental data meets the preset judgment conditions, it determines the target parking space data based on the environmental data.

[0016] The domain controller processes the 4D point cloud data, the image data, the positioning data, and the target parking space data by calling the preset SLAM algorithm to obtain parking route planning data.

[0017] The domain controller controls the autonomous vehicle to drive into the parking space corresponding to the target parking space data based on the parking route planning data.

[0018] Further optionally, the domain controller acquires 4D point cloud data, image data, and positioning data according to the parking command, specifically including:

[0019] The domain controller acquires the 4D point cloud data fed back by the radar sensor according to the parking command;

[0020] The domain controller acquires the image data collected by the image acquisition device according to the parking command;

[0021] The domain controller acquires the positioning data from the positioning sensor based on the parking command.

[0022] Alternatively, the number of radar sensors may be four.

[0023] Further optionally, the domain controller acquiring the 4D point cloud data fed back by the radar sensor according to the parking command specifically includes:

[0024] The radar sensor senses the surrounding environment of the autonomous vehicle according to a first preset frequency and generates first 4D point cloud data.

[0025] The radar data processing module of the domain controller fuses the four first 4D point cloud data to obtain the 4D point cloud data.

[0026] Alternatively, the image acquisition device may be a camera; wherein the number of cameras is four.

[0027] Further optionally, the domain controller acquiring the image data acquired by the image acquisition device according to the parking command specifically includes:

[0028] The camera acquires images of the surrounding environment of the autonomous vehicle at a second preset frequency, and generates first image data;

[0029] The image processing module of the domain controller performs fusion processing on the four first image data to generate the image data.

[0030] Further optionally, the image processing module of the domain controller performs fusion processing on the four first image data to generate the image data, specifically including:

[0031] The image processing module performs distortion restoration processing on the four first images respectively to obtain four first distortion restored image data;

[0032] The image processing module performs viewpoint transformation processing on the four first distortion-restored image data to obtain four first viewpoint transformed image data.

[0033] The image processing module performs image stitching processing on the four first-view transformed image data to generate the image data.

[0034] Optionally, the domain controller obtains the positioning data from the positioning sensor according to the parking instruction by: the positioning sensor collecting the location information of the autonomous vehicle at a third preset frequency to generate the positioning data; wherein the positioning data includes the longitude and latitude of the autonomous vehicle.

[0035] Further optionally, the domain controller controlling the autonomous vehicle to drive into the parking space corresponding to the target parking space data based on the parking route planning data specifically includes:

[0036] The brake actuator controls the braking system of the autonomous vehicle based on the parking route planning data;

[0037] The accelerator actuator controls the acceleration system of the autonomous vehicle based on the parking route planning data;

[0038] The steering actuator controls the steering system of the autonomous vehicle based on the parking route planning data.

[0039] This invention provides an automatic parking method that, upon receiving a user's parking command, automatically executes the command via a domain controller. It controls the autonomous vehicle's radar sensors, image acquisition device, and positioning sensors to perceive and capture images of the surrounding environment. The acquired 4D point cloud data and image data are analyzed and processed to determine available parking spaces. A preset algorithm is then used to generate parking route planning data, and finally, the vehicle is controlled to park in the identified available space according to the parking route planning data. This automatic parking method alleviates the parking difficulties faced by drivers of autonomous vehicles, greatly facilitating the operation of autonomous vehicles and significantly improving the user experience.

[0040] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0041] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0042] Figure 1 A flowchart of an automatic parking method provided in an embodiment of the present invention;

[0043] Figure 2 A flowchart of another automatic parking method provided in this embodiment of the invention. Detailed Implementation

[0044] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0045] An automatic parking method according to an embodiment of the present invention is described below with reference to the accompanying drawings. Figure 1 A flowchart of an automatic parking method provided in an embodiment of the present invention is shown below. Figure 1 As shown, the method includes the following steps:

[0046] Step 101: The domain controller receives a parking command from an external source.

[0047] Specifically, the domain controller is the core of each functional domain in an autonomous vehicle. It mainly consists of three parts: the domain master processor, the operating system, and application software and algorithms. Relying on the high-performance domain master processor, abundant hardware interface resources, and powerful software features, the domain controller can integrate the core functions that originally required many ECUs to achieve, control the various system modules of the vehicle, and control the autonomous vehicle.

[0048] In this embodiment of the invention, the parking instruction is generated by receiving user input instructions from a device communicatively connected to the domain controller. For example, it is generated by receiving parking instructions input by the driver through a human-machine interface (HMI) connected to the domain controller.

[0049] Step 102: The domain controller acquires 4D point cloud data, image data, and positioning data based on the parking command.

[0050] Specifically, when the domain controller receives a parking command, it acquires 4D point cloud data, image data, and positioning data based on the parking command.

[0051] In this embodiment of the invention, acquiring 4D point cloud data according to parking instructions specifically involves the domain controller acquiring 4D point cloud data fed back by radar sensors based on parking instructions. The radar sensors are devices installed on the vehicle to perceive obstacles and other conditions in the surrounding environment. In a preferred embodiment of the invention, the autonomous vehicle is equipped with four radar sensors, i.e., the total number of radar sensors is 4.

[0052] In the preferred embodiment of this invention, the domain controller acquiring the 4D point cloud data fed back by the radar sensor according to the parking command specifically includes the following steps:

[0053] First, the radar sensor perceives the surrounding environment of the autonomous vehicle according to a first preset frequency, generating first 4D point cloud data. The first preset frequency is the frequency at which the radar sensor perceives the surrounding environment of the autonomous vehicle; it is a reliable frequency value obtained after multiple tests before the vehicle rolls off the production line. For example, in a preferred embodiment of this invention, the radar sensor is a millimeter-wave angular radar with a frequency range of 76-79 GHz.

[0054] Secondly, the radar data processing module of the domain controller fuses the four first 4D point cloud data sets to obtain the 4D point cloud data. That is, the domain controller fuses the four first 4D point cloud data sets using a preset point cloud data processing algorithm to obtain the 4D point cloud data.

[0055] In this embodiment of the invention, acquiring image data according to a parking instruction specifically involves the domain controller acquiring image data collected by an image acquisition device based on the parking instruction. The image acquisition device is a camera used to capture images of the vehicle's surrounding environment. In a preferred embodiment of the invention, the camera is a high-definition camera, and the autonomous vehicle is equipped with a total of four cameras; that is, the number of cameras is 4.

[0056] In a preferred embodiment of the present invention, the domain controller acquiring image data acquired by the image acquisition device according to the parking command specifically includes the following steps:

[0057] First, the camera acquires images of the surrounding environment of the autonomous vehicle according to a second preset frequency, generating first image data. The second frequency is the frequency at which the camera captures images of the autonomous vehicle's surroundings, obtained after multiple tests before the vehicle rolls off the production line. In a preferred embodiment of the invention, the camera's acquisition frequency is 2.5MHz.

[0058] Secondly, the domain controller's image processing module fuses the four first image data to generate image data. That is, the domain controller uses an image processing algorithm to fuse the four first image data to generate image data. In the preferred embodiment of this invention, the fusion processing of the four first image data by the domain controller's image processing module to generate image data specifically includes: First, the image processing module performs distortion restoration processing on each of the four first images to obtain four first distortion-restored image data. Then, the image processing module performs viewpoint transformation processing on the four first distortion-restored image data to obtain four first viewpoint-transformed image data. Finally, the image processing module performs image stitching processing on the four first viewpoint-transformed image data to generate image data.

[0059] In this embodiment of the invention, the domain controller obtains the positioning data from the positioning sensor according to the parking command as follows: the positioning sensor collects the location information of the autonomous vehicle at a third preset frequency and generates positioning data. The positioning data includes the longitude and latitude of the autonomous vehicle.

[0060] Step 103: The domain controller performs fusion processing on the 4D point cloud data, image data and positioning data to obtain the environmental data around the autonomous vehicle.

[0061] Specifically, the domain controller in an autonomous vehicle invokes a pre-defined fusion processing algorithm to fuse 4D point cloud data, image data, and positioning data, ultimately obtaining processed data of the autonomous vehicle's surrounding environment, referred to here as environmental data. This includes obstacle data, parking space data, and distance data between obstacles in the vehicle's surrounding environment.

[0062] Step 104: The domain controller makes a determination based on the environmental data and preset judgment conditions. When the domain controller determines that the environmental data meets the preset judgment conditions, it determines the target parking space data based on the environmental data.

[0063] Specifically, the preset judgment data includes vehicle dimensions, parking space size thresholds, and other data. The domain controller makes judgments based on environmental data and preset judgment conditions. When the environmental data meets the preset judgment conditions, it indicates that there is parking space data in the environmental data that meets the parking requirements. This means that a suitable vacant parking space for this autonomous vehicle has been found. At this time, the domain controller determines the target parking space data based on the environmental data.

[0064] Step 105: The domain controller calls the preset Simultaneous Localization and Mapping (SLAM) algorithm to perform route planning processing on the 4D point cloud data, image data, positioning data and target parking space data to obtain parking route planning data.

[0065] Specifically, autonomous vehicles are pre-installed with a SLAM algorithm for route planning. At this point, the domain controller invokes the pre-installed SLAM algorithm to process 4D point cloud data, image data, localization data, and target parking space data to obtain parking route planning data. In other words, it calculates the route the autonomous vehicle will take to park in the target parking space, generating parking route planning data.

[0066] Step 106: The domain controller controls the vehicle to drive into the parking space corresponding to the target parking space data based on the parking route planning data.

[0067] Specifically, in this embodiment of the invention, the domain controller controls the autonomous vehicle to drive into the parking space corresponding to the target parking space data according to the parking route planning data, which includes: a brake actuator controlling the braking system of the autonomous vehicle according to the parking route planning data; an acceleration actuator controlling the acceleration system of the autonomous vehicle according to the parking route planning data; and a steering actuator controlling the steering system of the autonomous vehicle according to the parking route planning data.

[0068] The above is an embodiment of the present invention providing an automatic parking method. This method is used when the driver drives the autonomous vehicle to the vicinity of an empty parking space, and it can automatically park the autonomous vehicle in the corresponding empty parking space.

[0069] This invention also provides a solution for situations where the driver has not yet driven the autonomous vehicle into a nearby vacant parking space. Figure 2 A flowchart of another automatic parking method provided in an embodiment of the present invention, combined with Figure 2As shown in the figure, the implementation steps of this method also include the following steps after step 103 and before step 104:

[0070] Step 1031: The domain controller makes a judgment based on the environmental data and preset judgment conditions. When the domain controller determines that the environmental data does not meet the preset judgment conditions, it plans the parking space search route based on the environmental data to obtain the parking space search route data.

[0071] Specifically, the preset judgment data includes vehicle dimensions, parking space size thresholds, and other data. The domain controller makes judgments based on environmental data and preset judgment conditions. When it is determined that the environmental data does not meet the preset judgment conditions, it means that there are no parking spaces in the environmental data that meet the parking requirements. This means that no suitable vacant parking space has been found for the autonomous vehicle. At this time, the domain controller calls a preset SLAM algorithm to process the 4D point cloud data, image data, and positioning data to determine the driving route in order to continue searching for a suitable vacant parking space for the autonomous vehicle. This driving route is referred to here as the parking space search route data.

[0072] Step 1032: The domain controller drives according to the parking space search route data and acquires 4D point cloud data, image data and positioning data in real time.

[0073] Specifically, the domain controller operates based on parking space search data and acquires new 4D point cloud data, image data, and positioning data in real time.

[0074] In this embodiment of the invention, the domain controller continuously executes steps 1031 and 1032 until it can execute step 104 and subsequent steps after step 1032. That is, the autonomous vehicle makes judgments based on environmental data and preset judgment conditions while driving, specifically determining whether there are vacant parking spaces (target parking spaces) in the surrounding area that meet the conditions. Once it is determined that a vacant parking space meeting the conditions exists in the surrounding environmental data, the system proceeds to step 104 and subsequent steps to park the autonomous vehicle in the searched target parking space.

[0075] This invention provides an automatic parking method that, upon receiving a user's parking command, automatically executes the command via a domain controller. It controls the autonomous vehicle's radar sensors, image acquisition device, and positioning sensors to perceive and capture images of the surrounding environment. The acquired 4D point cloud data and image data are analyzed and processed to determine available parking spaces. A preset algorithm is then used to generate parking route planning data, and finally, the vehicle is controlled to park in the identified available space according to the parking route planning data. This automatic parking method alleviates the parking difficulties faced by drivers of autonomous vehicles, greatly facilitating the operation of autonomous vehicles and significantly improving the user experience.

[0076] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0077] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, the terms "first" and "second" are limited to this specific context.

[0078] The "second" feature may explicitly or implicitly include at least one of those features. In the description of this invention,

[0079] "Multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0080] Any process or method description in the flowchart or otherwise herein may be understood as a table.

[0081] The invention includes modules, segments, or portions of executable instructions comprising one or more steps for implementing custom logic functions or processes, and the scope of preferred embodiments of the invention includes additional implementations.

[0082] The functions may be performed in a manner not shown or discussed in the order described, including in a substantially simultaneous manner or in the reverse order, depending on the functions involved, as will be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0083] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, which can be specifically implemented in any computation.

[0084] This is intended for use in a machine-readable medium by an instruction execution system, apparatus, or device (such as a computer-based system, a processor-based system, or other system that can fetch and execute instructions from or in connection with such an instruction execution system, apparatus, or device). For the purposes of this specification,

[0085] "Computer-readable medium" can be any means that can contain, store, communicate, propagate or transmit programs for use in conjunction with an instruction execution system, apparatus or device.

[0086] More specific examples (a non-exhaustive list) of computer-readable media include the following: electrical connections having one or more wires (electronic devices), portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory).

[0087] High-speed memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Additionally, computer-readable media can even be paper or other suitable media on which the program can be printed, because...

[0088] The program can be obtained electronically, for example, by optically scanning paper or other media, followed by editing, interpreting, or otherwise processing as appropriate, and then stored in a computer memory.

[0089] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0090] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0091] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0092] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

[0093] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0094] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An automatic parking method, applied to autonomous vehicles, characterized in that, The method includes: The domain controller receives parking commands from external input; The domain controller acquires 4D point cloud data, image data, and positioning data according to the parking command; The domain controller performs fusion processing based on the 4D point cloud data, the image data, and the positioning data to obtain environmental data around the autonomous vehicle. The domain controller makes a determination based on the environmental data and preset judgment conditions. When the domain controller determines that the environmental data meets the preset judgment conditions, it determines the target parking space data based on the environmental data. The domain controller invokes a preset simultaneous localization and mapping (SLAM) algorithm to perform route planning processing on the 4D point cloud data, the image data, the positioning data, and the target parking space data to obtain parking route planning data. The domain controller controls the vehicle to drive into the parking space corresponding to the target parking space data based on the parking route planning data. The method further includes, after the domain controller makes a determination based on the environmental data and preset judgment conditions: When the domain controller determines that the environmental data does not meet the preset judgment conditions, it performs parking space search route planning based on the environmental data to obtain parking space search route data. The domain controller operates based on the parking space search route data and acquires the 4D point cloud data, the image data, and the positioning data in real time. The domain controller makes a determination based on the environmental data and preset judgment conditions. When the domain controller determines that the environmental data meets the preset judgment conditions, it determines the target parking space data based on the environmental data. The domain controller processes the 4D point cloud data, the image data, the positioning data, and the target parking space data by calling the preset Simultaneous Localization and Mapping (SLAM) algorithm to obtain parking route planning data. The domain controller controls the autonomous vehicle to drive into the parking space corresponding to the target parking space data based on the parking route planning data.

2. The automatic parking method according to claim 1, characterized in that, The domain controller acquires 4D point cloud data, image data, and positioning data based on the parking command, specifically including: The domain controller acquires the 4D point cloud data fed back by the radar sensor according to the parking command; The domain controller acquires the image data collected by the image acquisition device according to the parking command; The domain controller acquires the positioning data from the positioning sensor based on the parking command.

3. The automatic parking method according to claim 2, characterized in that, The number of radar sensors is 4.

4. The automatic parking method according to claim 3, characterized in that, The domain controller acquires the 4D point cloud data fed back by the radar sensor according to the parking command, specifically including: The radar sensor senses the surrounding environment of the autonomous vehicle according to a first preset frequency and generates first 4D point cloud data. The radar data processing module of the domain controller fuses the four first 4D point cloud data to obtain the 4D point cloud data.

5. The automatic parking method according to claim 2, characterized in that, The image acquisition device is a camera; the number of cameras is 4.

6. The automatic parking method according to claim 5, characterized in that, The domain controller obtains the image data acquired by the image acquisition device according to the parking command, specifically including: The camera acquires images of the surrounding environment of the autonomous vehicle at a second preset frequency, and generates first image data; The image processing module of the domain controller performs fusion processing on the four first image data to generate the image data.

7. The automatic parking method according to claim 6, characterized in that, The image processing module of the domain controller performs fusion processing on the four first image data to generate the image data, specifically including: The image processing module performs distortion restoration processing on the four first images respectively to obtain four first distortion restored image data; The image processing module performs viewpoint transformation processing on the four first distortion-restored image data to obtain four first viewpoint transformed image data. The image processing module performs image stitching processing on the four first-view transformed image data to generate the image data.

8. The automatic parking method according to claim 2, characterized in that, The domain controller obtains the positioning data from the positioning sensor according to the parking command by: the positioning sensor collecting the location information of the autonomous vehicle at a third preset frequency and generating the positioning data; wherein, the positioning data includes the longitude and latitude of the autonomous vehicle.

9. The automatic parking method according to claim 1, characterized in that, The domain controller controls the autonomous vehicle to drive into the parking space corresponding to the target parking space data based on the parking route planning data, specifically including: The brake actuator controls the braking system of the autonomous vehicle based on the parking route planning data; The accelerator actuator controls the acceleration system of the autonomous vehicle based on the parking route planning data; The steering actuator controls the steering system of the autonomous vehicle based on the parking route planning data.

Images