Motor vehicle auxiliary parking method and device and computer readable storage medium

Abstract

The embodiment of the invention provides a motor vehicle auxiliary parking method and device and a computer readable storage medium, and the method comprises the steps: fusing the positioning data of a combined navigation positioning system and odometer information to form latitude and longitude coordinates; converting the latitude and longitude coordinates into vehicle poses, and determining initial vehicle poses and initial latitude and longitude coordinates; a three-dimensional scene map and a two-dimensional scene map are constructed in combination with image information and vehicle poses in the driving process of the motor vehicle; selecting a target parking space; based on the latitude and longitude coordinates of the current position and the initial latitude and longitude coordinates, a coarse positioning pose is obtained through calculation, matching search within a preset range is carried out in a two-dimensional scene map with the coarse positioning pose as the center to correct the coarse positioning pose, and three-dimensional matching is carried out according to the corrected coarse positioning pose to obtain a fine positioning pose; calculating and generating a target parking path based on the two-dimensional scene map; and controlling the motor vehicle to drive into the target parking space based on the parking path and the fine positioning pose. According to the embodiment, the positioning precision can be effectively improved.

Description

Technical Field

[0001] This invention relates to the field of motor vehicle assisted parking technology, and in particular to a motor vehicle assisted parking method, device and computer-readable storage medium. Background Technology

[0002] As motor vehicles become increasingly automated, car manufacturers are starting to equip them with valet parking systems at the factory to enable automatic parking. In practice, valet parking systems need to use SLAM (Simultaneous Localization and Mapping) technology to build parking maps of the parking area.

[0003] Currently, several methods are commonly used to locate vehicles in the process of building parking maps: localization based on vehicle wheel speed odometer and onboard image fusion, localization based on monocular camera visual scene, and localization based on image feature point matching of onboard images. However, the first method has a large pose error when the wheels slip; the second method can lead to localization errors in similar scenarios; and the third method relies on image features, which affects localization accuracy in poor lighting conditions. Therefore, existing localization methods all have some shortcomings. Summary of the Invention

[0004] The technical problem to be solved by the embodiments of the present invention is to provide a method for assisting parking of motor vehicles, which can effectively improve positioning accuracy.

[0005] A further technical problem to be solved by the embodiments of the present invention is to provide a motor vehicle auxiliary parking device that can effectively improve positioning accuracy.

[0006] A further technical problem to be solved by the embodiments of the present invention is to provide a computer-readable storage medium that can effectively improve positioning accuracy.

[0007] To address the aforementioned technical problems, the present invention first provides the following technical solution: a method for assisted parking of a motor vehicle, comprising the following steps: The system integrates positioning data from the vehicle's combined navigation and positioning system with the vehicle's latitude and longitude coordinates output from the vehicle's odometer information. The combined navigation and positioning system and the vehicle camera are calibrated using an external parameter matrix. The latitude and longitude coordinates are transformed to the vehicle coordinate system, and the initial vehicle pose and initial latitude and longitude coordinates of the vehicle at the origin of the vehicle coordinate system are determined. During the driving process of a motor vehicle, image information extracted from video images captured and transmitted by the vehicle-mounted camera and the vehicle's pose are combined to construct a three-dimensional scene map and a two-dimensional scene map. Select the target parking space from the two-dimensional scene map; Based on the current latitude and longitude coordinates of the vehicle and the initial latitude and longitude coordinates, the coarse positioning pose of the vehicle is calculated. In the two-dimensional scene map, a matching search is performed within a predetermined range with the coarse positioning pose as the center to correct the coarse positioning pose. Then, according to the corrected coarse positioning pose, three-dimensional matching is performed in the three-dimensional scene map to obtain the fine positioning pose of the vehicle. Based on the two-dimensional scene map, a target parking path is calculated and generated for a motor vehicle to drive from its current location into the target parking space; and Based on the target parking path and the precise positioning and pose of the vehicle, the vehicle is controlled to drive into the target parking space.

[0008] Furthermore, the step of constructing a three-dimensional scene map and a two-dimensional scene map by combining image information extracted from video images captured and transmitted from the vehicle-mounted camera and the vehicle's pose during vehicle operation specifically includes: The first image frame and the second image frame are obtained from the images extracted from the video images captured and transmitted by the vehicle-mounted camera, respectively. A 3D scene map is constructed by fusing the odometer information and image feature information extracted from the first image frame, and then performing tracking and nonlinear optimization; and The vehicle's pose is finely corrected, and a two-dimensional scene map is established by integrating the finely corrected vehicle pose with parking guidance information extracted from the second image frame. The parking guidance information includes at least lane lines, parking spaces, guidance signs, and parking space lines.

[0009] Furthermore, the ORB algorithm model is used to extract ORB feature information from the first image frame as the image feature information; and a pre-trained deep learning neural network model is used to extract the parking guidance information from the second image frame.

[0010] Furthermore, the first image frame is a front view image obtained by extracting images from video images captured by the vehicle-mounted front-view camera and correcting distortion; the second image frame is a panoramic surround view image obtained by stitching together images extracted from video images captured by various vehicle-mounted cameras installed around the vehicle body.

[0011] Furthermore, the step of calculating and generating a target parking path for a motor vehicle to enter the target parking space based on the two-dimensional scene map specifically includes: Based on the two-dimensional scene map, a global path planning algorithm model is used to calculate and generate the optimal path for the vehicle to enter the target parking space, and the optimal path is then smoothed; and A deep learning algorithm model is used to generate a drivable area containing lane lines from the first image frame. Based on the drivable area, the optimal path is optimized using a local path planning algorithm model to obtain a target parking path containing several path planning points.

[0012] Furthermore, the global path planning algorithm model is a path planning algorithm model that combines the A* algorithm with Clothoid curve fitting.

[0013] Furthermore, the local path planning algorithm model is a path planning algorithm model that combines B-spline curve fitting and D* search algorithm.

[0014] Furthermore, the LQR control algorithm model is used to control the vehicle to drive into the target parking space based on each path planning point in the target parking path and the vehicle's precise positioning and pose.

[0015] Furthermore, when performing 3D matching on the 3D scene map based on the corrected coarse positioning pose, if 3D matching fails, the corrected coarse positioning pose will be used as the fine positioning pose of the vehicle.

[0016] On the other hand, in order to solve the above-mentioned further technical problems, the present invention provides the following technical solution: a motor vehicle auxiliary parking device, which is connected to a combined navigation and positioning system and an on-board camera installed on a motor vehicle, respectively. The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the motor vehicle auxiliary parking method as described in any of the above claims.

[0017] Furthermore, in order to solve the aforementioned technical problems, the present invention provides the following technical solution: a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the motor vehicle assisted parking method as described in any of the above claims.

[0018] After adopting the above technical solution, the embodiments of the present invention have at least the following beneficial effects: The embodiments of the present invention output latitude and longitude coordinates reflecting the absolute positioning coordinates of a motor vehicle by fusing positioning data and odometer information from a combined navigation and positioning system. The vehicle pose can be obtained by converting the latitude and longitude coordinates into the vehicle coordinate system. During mapping, a three-dimensional scene map and a two-dimensional scene map are constructed by combining image information from the images collected from the vehicle-mounted camera and the vehicle pose, resulting in high mapping efficiency. Furthermore, after selecting a target parking space from the two-dimensional scene map, a coarse positioning pose of the motor vehicle is first calculated based on the latitude and longitude coordinates of the motor vehicle at its current position and the initial latitude and longitude coordinates at the origin of the coordinate system. Then, a matching search is performed within a predetermined range centered on the coarse positioning pose in the two-dimensional scene map to correct the coarse positioning pose. The corrected coarse positioning pose is then matched in three dimensions in the three-dimensional scene map to obtain the fine positioning pose of the motor vehicle, thereby improving the positioning accuracy. This facilitates the subsequent calculation and generation of a preferred target parking path and the control of the motor vehicle to accurately enter the target parking space based on the parking path and the fine positioning pose of the motor vehicle. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of an optional embodiment of the motor vehicle assisted parking method of the present invention.

[0020] Figure 2 The flowchart below shows a specific step S3 of an optional embodiment of the motor vehicle assisted parking method of the present invention.

[0021] Figure 3 The flowchart below shows a specific step S6 of an optional embodiment of the motor vehicle assisted parking method of the present invention.

[0022] Figure 4 This is a schematic diagram of an optional embodiment of the motor vehicle auxiliary parking device of the present invention.

[0023] Figure 5 This is a functional block diagram of an optional embodiment of the motor vehicle auxiliary parking device of the present invention. Detailed Implementation

[0024] The present application will now be described in further detail with reference to the accompanying drawings and specific embodiments. It should be understood that the following illustrative embodiments and descriptions are only used to explain the present invention and are not intended to limit the present invention. Moreover, the embodiments and features in the embodiments of the present application can be combined with each other unless otherwise specified.

[0025] like Figure 1 As shown, an optional embodiment of the present invention provides a method for assisted parking of a motor vehicle, comprising the following steps: S1: The positioning data from the vehicle's integrated navigation and positioning system (P-Box) 1, combined with the vehicle's latitude and longitude coordinates output from the vehicle's odometer information. S2: Perform extrinsic parameter matrix calibration on the combined navigation and positioning system 1 and the vehicle camera 2, transform the latitude and longitude coordinates to the vehicle coordinate system, and determine the initial vehicle pose and initial latitude and longitude coordinates of the motor vehicle at the origin of the vehicle coordinate system. S3: During the driving process of the motor vehicle, the image information extracted from the video images collected and transmitted from the vehicle-mounted camera and the vehicle's position and pose are combined to construct a three-dimensional scene map and a two-dimensional scene map. S4: Select the target parking space from the two-dimensional scene map; S5: Based on the current latitude and longitude coordinates of the vehicle and the initial latitude and longitude coordinates, calculate the coarse positioning pose of the vehicle. Perform a matching search within a predetermined range (e.g., a radius of 10m) in the two-dimensional scene map with the coarse positioning pose as the center to correct the coarse positioning pose. Then, perform three-dimensional matching in the three-dimensional scene map according to the corrected coarse positioning pose to obtain the fine positioning pose of the vehicle. S6: Based on the two-dimensional scene map, calculate and generate a target parking path for a motor vehicle to enter the target parking space from its current location; and S7: Based on the target parking path and the precise positioning and pose of the vehicle, control the vehicle to drive into the target parking space.

[0026] This invention, through the fusion of positioning data and odometer information from the integrated navigation and positioning system 1, outputs latitude and longitude coordinates reflecting the absolute positioning coordinates of a motor vehicle. The vehicle's pose can be obtained by converting these coordinates into the vehicle coordinate system. During mapping, a three-dimensional scene map and a two-dimensional scene map are constructed by combining image information from images captured by the onboard camera and the vehicle's pose, resulting in high mapping efficiency. Furthermore, after selecting a target parking space from the two-dimensional scene map, a coarse positioning pose is first calculated based on the vehicle's current latitude and longitude coordinates and the initial latitude and longitude coordinates at the origin. Then, a matching search is performed within a predetermined range centered on the coarse positioning pose in the two-dimensional scene map to correct it. Finally, the corrected coarse positioning pose is used for three-dimensional matching in the three-dimensional scene map to obtain the vehicle's fine positioning pose, thereby improving positioning accuracy. This facilitates subsequent calculations to generate a preferred target parking path and, based on the parking path and the vehicle's fine positioning pose, controls the vehicle to accurately enter the target parking space.

[0027] It is understandable that the positioning accuracy of the integrated navigation and positioning system 1 depends on IMU data, RTK signal and odometer information to achieve positioning. When the vehicle is in a location with strong RTK signal, the positioning accuracy of the integrated navigation and positioning system 1 can be in the centimeter range; when the vehicle is in a location with relatively weak RTK signal, such as underground (e.g., underground parking lot), the positioning accuracy of the integrated navigation and positioning system 1 can be in the meter range.

[0028] In an optional embodiment of the present invention, such as Figure 2 As shown, step S3 specifically includes: S31: Obtain the first image frame and the second image frame respectively from the images extracted from the video images captured and transmitted by the vehicle-mounted camera 2; S32: A three-dimensional scene map is established by fusing the odometer information and image feature information extracted from the first image frame, and then performing tracking and nonlinear optimization; and S33: Finely correct the vehicle pose of the motor vehicle, and integrate the finely corrected vehicle pose with the parking guidance information extracted from the second image frame to establish a two-dimensional scene map. The parking guidance information includes at least lane lines, parking spaces, guidance signs, and parking space lines.

[0029] In this embodiment, a three-dimensional scene map is established by fusing the odometer information and the image feature information extracted from the first image frame. A two-dimensional scene map is established by finely correcting the vehicle pose and fusing the finely corrected vehicle pose with the parking guidance information extracted from the second image frame. This method is efficient and facilitates subsequent vehicle positioning.

[0030] In an optional embodiment of the present invention, the ORB (Oriented FAST and Rotated BRIEF) algorithm model is used to extract ORB feature information from the first image frame as the image feature information; a pre-trained deep learning neural network model is used to extract the parking guidance information from the second image frame. In this embodiment, the ORB algorithm model is used to extract ORB feature information from the image as image feature information for 3D scene map construction, which has fast extraction speed and high robustness; while the pre-trained deep learning neural network model is used to extract parking guidance information, which has higher extraction efficiency and accuracy.

[0031] In an optional embodiment of the present invention, the first image frame is a front view image obtained by distortion correction of an image extracted from a video image captured by a vehicle-mounted front-view camera; the second image frame is a panoramic surround view image obtained by image stitching of images extracted from video images captured by various vehicle-mounted cameras 2 installed around the vehicle body. In this embodiment, a three-dimensional scene map is constructed using feature information from the front view image. Vehicle-mounted front-view cameras typically have a long focal length, which can clearly capture details of distant objects and has a better effect on the geometric reconstruction of distant objects in a three-dimensional map. A two-dimensional scene map is constructed using relevant image information from the panoramic surround view image because the panoramic surround view image makes it easier to capture ground markings, such as lane lines and parking space lines.

[0032] In an optional embodiment of the present invention, such as Figure 3 As shown, step S6 specifically includes: S61: Based on the two-dimensional scene map, a global path planning algorithm model is used to calculate and generate the optimal path for the motor vehicle to enter the target parking space, and the optimal path is smoothed; and S62: A drivable (free space) region containing lane lines is generated from the first image frame using a deep learning algorithm model. Based on the drivable region, the optimal path is optimized using a local path planning algorithm model to obtain a target parking path containing several path planning points.

[0033] In this embodiment, global path planning is first used to determine the optimal path, and then local path planning is performed in the drivable area containing lane lines. The local path planning algorithm provides multiple collision-free reference points to avoid collisions during driving.

[0034] In an optional embodiment of the present invention, the global path planning algorithm model is a path planning algorithm model that combines the A* algorithm with Clothoid (Euler spiral) curve fitting; the local path planning algorithm model is a path planning algorithm model that combines B-spline curve fitting and D* search algorithm. In this embodiment, the combination of the A* algorithm and Clothoid curve fitting achieves kinematically feasible and curvature-continuous path planning, which is particularly suitable for the motion characteristics of vehicles and has high path planning efficiency; while the combination of B-spline curve fitting and D* search algorithm for local path planning specifically involves approximating the reference points using the B-spline curve fitting algorithm, given multiple (e.g., 6) collision-free reference points, i.e., uniformly sampling a set of points along the curve and moving laterally to obtain collision-free reference points, and then using the D* algorithm on these reference points to find new reference paths, wherein the cost function must include the deviation from the global path and the minimum distance to the obstacle.

[0035] In an optional embodiment of the present invention, an LQR (Least Square Linear Quadratic Regulator) control algorithm model is used to control the vehicle to enter the target parking space based on each path planning point in the target parking path and the vehicle's precise positioning pose. In this embodiment, the LQR control algorithm model is a classic optimal control algorithm, typically used for vehicle trajectory tracking, which can accurately control the vehicle to enter the target parking space based on the planned path planning points and the vehicle's precise positioning pose.

[0036] In an optional embodiment of the present invention, when performing 3D matching on the 3D scene map based on the corrected coarse positioning pose, if 3D matching fails, the corrected coarse positioning pose will be used as the fine positioning pose of the vehicle. In this embodiment, if 3D matching cannot be achieved with the 2D positioning pose, the system directly uses the corrected coarse positioning pose (i.e., the 2D positioning pose) as the fine positioning pose of the vehicle, thereby avoiding getting stuck in a local unsolvable situation and ensuring the stability of the system.

[0037] In an optional embodiment of the present invention, the two-dimensional scene map is displayed in a human-computer interaction interface, and the target parking space is selected from the two-dimensional scene map based on the selection command input through the human-computer interaction interface; or, an available parking space is automatically selected from the two-dimensional scene map as the target parking space. In this embodiment, a two-dimensional scene map can be displayed in the human-computer interaction interface, allowing the user to select the target parking space; alternatively, the system can automatically select an available parking space for parking through image recognition.

[0038] On the other hand, such as Figure 4 As shown, this embodiment of the invention provides a motor vehicle assisted parking device 3, which is connected to a combined navigation and positioning system 1 and an on-board camera 2 installed on a motor vehicle. The 3 includes a processor 30, a memory 32, and a computer program stored in the memory 32 and configured to be executed by the processor 30. When the processor 30 executes the computer program, it implements the motor vehicle assisted parking method as described in any of the above embodiments.

[0039] For example, the computer program can be divided into one or more modules / units, which are stored in the memory 32 and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the vehicle parking assistance device 3. For example, the computer program can be divided into... Figure 5The functional modules in the motor vehicle auxiliary parking device 3 include latitude and longitude acquisition module 41, coordinate transformation module 42, mapping module 43, parking space selection module 44, positioning module 45, route planning module 46, and vehicle control module 47, which respectively perform the above steps S1-S7.

[0040] The vehicle parking assistance device 3 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The vehicle parking assistance device 3 may include, but is not limited to, a processor 30 and a memory 32. Those skilled in the art will understand that the schematic diagram is merely an example of the vehicle parking assistance device 3 and does not constitute a limitation on the vehicle parking assistance device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, the vehicle parking assistance device 3 may also include input / output devices, network access devices, buses, etc.

[0041] The processor 30 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 30 is the control center of the vehicle parking assistance device 3, connecting all parts of the vehicle parking assistance device 3 via various interfaces and lines.

[0042] The memory 32 can be used to store the computer program and / or modules. The processor 30 implements various functions of the vehicle parking assistance device 3 by running or executing the computer program and / or modules stored in the memory 32 and calling the data stored in the memory 32. The memory 32 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as image recognition function, image overlay function, etc.), etc.; the data storage area may store data created according to the use of the control device (such as image data, etc.). In addition, the memory 32 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0043] If the functions described in the embodiments of the present invention are implemented in the form of software functional modules or units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the embodiments of the present invention can implement all or part of the processes in the methods described above, or they can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 30, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0044] In another aspect, embodiments of the present invention provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the motor vehicle assisted parking method as described in any of the above embodiments.

[0045] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0046] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the scope of protection of the present invention.

Claims

1. A method for assisting parking a motor vehicle, characterized in that, The method includes the following steps: The system integrates positioning data from the vehicle's combined navigation and positioning system with the vehicle's latitude and longitude coordinates output from the vehicle's odometer information. The combined navigation and positioning system and the vehicle camera are calibrated using an external parameter matrix. The latitude and longitude coordinates are transformed to the vehicle coordinate system, and the initial vehicle pose and initial latitude and longitude coordinates of the vehicle at the origin of the vehicle coordinate system are determined. During the driving process of a motor vehicle, image information extracted from video images captured and transmitted by the vehicle-mounted camera and the vehicle's pose are combined to construct a three-dimensional scene map and a two-dimensional scene map. Select the target parking space from the two-dimensional scene map; Based on the current latitude and longitude coordinates of the vehicle and the initial latitude and longitude coordinates, the coarse positioning pose of the vehicle is calculated. In the two-dimensional scene map, a matching search is performed within a predetermined range with the coarse positioning pose as the center to correct the coarse positioning pose. Then, according to the corrected coarse positioning pose, three-dimensional matching is performed in the three-dimensional scene map to obtain the fine positioning pose of the vehicle. Based on the two-dimensional scene map, a target parking path is calculated and generated for a motor vehicle to drive from its current location into the target parking space; and Based on the target parking path and the precise positioning and pose of the vehicle, the vehicle is controlled to drive into the target parking space.

2. The motor vehicle assisted parking method as described in claim 1, characterized in that, The process of constructing a 3D scene map and a 2D scene map by combining image information extracted from video images captured and transmitted from the vehicle-mounted camera and the vehicle's pose during vehicle operation specifically includes: The first image frame and the second image frame are obtained from the images extracted from the video images captured and transmitted by the vehicle-mounted camera, respectively. A 3D scene map is constructed by fusing the odometer information and image feature information extracted from the first image frame, and then performing tracking and nonlinear optimization; and The vehicle's pose is finely corrected, and a two-dimensional scene map is established by integrating the finely corrected vehicle pose with parking guidance information extracted from the second image frame. The parking guidance information includes at least lane lines, parking spaces, guidance signs, and parking space lines.

3. The motor vehicle assisted parking method as described in claim 2, characterized in that, The ORB algorithm model is used to extract ORB feature information from the first image frame as the image feature information; the pre-trained deep learning neural network model is used to extract the parking guidance information from the second image frame.

4. The motor vehicle assisted parking method as described in claim 2 or 3, characterized in that, The first image frame is a front view image obtained by extracting images from video images captured by a vehicle-mounted front-view camera and correcting for distortion; the second image frame is a panoramic surround view image obtained by stitching together images extracted from video images captured by various vehicle-mounted cameras installed around the vehicle body.

5. The motor vehicle assisted parking method as described in claim 1, characterized in that, The specific steps of calculating and generating a target parking path for a motor vehicle to enter the target parking space based on the two-dimensional scene map include: Based on the two-dimensional scene map, a global path planning algorithm model is used to calculate and generate the optimal path for the vehicle to enter the target parking space, and the optimal path is then smoothed; and A deep learning algorithm model is used to generate a drivable area containing lane lines from the first image frame. Based on the drivable area, the optimal path is optimized using a local path planning algorithm model to obtain a target parking path containing several path planning points.

6. The motor vehicle assisted parking method as described in claim 5, characterized in that, The global path planning algorithm model is a path planning algorithm model that combines the A* algorithm with Clothoid curve fitting; the local path planning algorithm model is a path planning algorithm model that combines B-spline curve fitting and D* search algorithm.

7. The motor vehicle assisted parking method as described in claim 5, characterized in that, The LQR control algorithm model is used to control the vehicle to drive into the target parking space based on each path planning point in the target parking path and the precise positioning and pose of the vehicle.

8. The motor vehicle assisted parking method as described in claim 1, characterized in that, If a 3D matching fails when performing 3D matching on the 3D scene map based on the corrected coarse positioning pose, the corrected coarse positioning pose will be used as the fine positioning pose of the vehicle.

9. A motor vehicle auxiliary parking device, connected to a combined navigation and positioning system and an on-board camera installed on a motor vehicle, characterized in that, The apparatus includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the motor vehicle assisted parking method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the motor vehicle assisted parking method as described in any one of claims 1 to 8.

Images