Parking path optimization method, system and vehicle

Abstract

The present application provides a parking path optimization method, system and vehicle; the parking path optimization method includes: after obtaining a parking signal, first obtaining the initial coordinates of the target obstacle vehicle and its corresponding preset key points; then correcting the initial coordinates according to the body specification parameters of the current vehicle to obtain the corrected coordinates; further determining whether the target obstacle vehicle has an associated parking space, and if so, obtaining the target coordinates according to the parking space coordinates of the associated parking space and the corrected coordinates; if not, directly using the corrected coordinates as the target coordinates; and finally optimizing the parking path based on the target coordinates. The present application can more accurately calculate the parking path, improve the accuracy and safety of parking; and also improve the efficiency and convenience of parking; in addition, it can also effectively eliminate the impact of the shadow of the obstacle vehicle on parking planning.

Description

Technical Field

[0001] The present application relates to the field of assisted driving technology, and in particular to a parking path optimization method, system and vehicle. Background Art

[0002] At present, automatic parking is a standard feature or rigid demand in the automobile market. The development of automatic parking can enable drivers to complete parking operations more easily in busy parking lots or small spaces. However, the presence of obstacle vehicles will have a greater impact on the performance and accuracy of automatic parking, resulting in the inability of automatic parking to plan accurate parking paths and precise parking, and may even make parking impossible.

[0003] The existing parking planning method only has an obstacle recognition method, but does not have a method for eliminating the shadow of the obstacle vehicle, resulting in insufficient parking accuracy or too many parking steps, which in turn affects the user experience. Summary of the invention

[0004] The present application aims to solve the technical problem that there is no method for eliminating the shadow of an obstructing vehicle in the prior art, resulting in insufficient parking accuracy and a poor parking experience, and provides a parking path optimization method, system and vehicle.

[0005] Specifically, the present application provides a parking path optimization method, comprising the following steps:

[0006] S100: In response to a parking signal, obtaining initial coordinates of a target obstacle vehicle and its corresponding preset key points.

[0007] S200: Acquire body specification parameters of the current vehicle, and correct the initial coordinates according to the body specification parameters to obtain corrected coordinates.

[0008] S300: Determine whether the target obstacle vehicle has an associated parking space. If so, obtain the parking space coordinates of the associated parking space, and obtain the target coordinates according to the parking space coordinates and the corrected coordinates; otherwise, use the corrected coordinates as the target coordinates.

[0009] S400: Optimizing a parking path based on the target coordinates.

[0010] In the above technical solution, by obtaining the body specification parameters of the current vehicle and correcting the initial coordinates, the parking path can be calculated more accurately, thereby improving the accuracy and safety of parking. If the target obstacle vehicle has an associated parking space, the target coordinates can be obtained based on the parking space coordinates and the corrected coordinates of the associated parking space, thereby further optimizing the parking path and improving the efficiency and convenience of parking. Based on the target coordinates, the parking path can be optimized, including the length of the path, the turning radius, and the safe distance between the vehicle and the obstacle, thereby making parking smoother, more efficient, and safer. In addition, the parking path optimization method can effectively eliminate the influence of the shadow of the obstacle vehicle on the parking planning.

[0011] Furthermore, obtaining the target obstacle vehicle in step S100 includes:

[0012] S101: Acquire a parking planning state in real time, so as to identify obstacles in real time when the parking planning state is a parking space search state.

[0013] S102: Determine whether the identified obstacle is a vehicle. If so, use the vehicle as a preparatory obstacle vehicle; otherwise, return to step S101.

[0014] In the above technical solution, by identifying obstacles in real time when the parking planning state is the parking space search state, the information of the target obstacle vehicle can be obtained in time, so that the change of obstacles can be responded to more quickly, and the real-time and adaptability of the parking system can be improved; by judging whether the identified obstacle is a vehicle, the real vehicle can be used as a preparatory obstacle vehicle, so as to plan and optimize the parking path more accurately, and avoid misjudging other objects as vehicles and generating an erroneous parking path.

[0015] Furthermore, the step S100 of acquiring the target obstacle vehicle further includes:

[0016] The color of the prepared obstacle vehicle is obtained, and it is determined whether the color is a preset color.

[0017] If so, the prepared obstacle vehicle is used as the target obstacle vehicle; otherwise, the obstacle coordinates of the prepared obstacle vehicle are obtained, and the obstacle coordinates are used as the target coordinates.

[0018] In the above technical solution, by obtaining the color of the prepared obstacle vehicle and determining whether it is the preset color, the accuracy of identifying the target obstacle vehicle can be improved, the possibility of parking path planning errors can be reduced, and the parking accuracy can be further improved; if the color of the prepared obstacle vehicle is not the preset color, the coordinates of the prepared obstacle vehicle can be obtained and the obstacle coordinates can be used as the target coordinates to further optimize the parking path.

[0019] Furthermore, the step S200 includes:

[0020] S201: Acquire body specification parameters of the target obstacle vehicle according to the initial coordinates.

[0021] S202: Obtain the difference between the body specification parameters of the target obstacle vehicle and the body specification parameters of the current vehicle, and determine whether the difference is greater than a preset threshold. If so, obtain the corrected coordinates based on the difference and the initial coordinates; otherwise, use the initial coordinates as the target coordinates.

[0022] In the above technical solution, by obtaining the body specification parameters of the target obstacle vehicle according to the initial coordinates, the corrected coordinates can be calculated more accurately, so that the parking path planning is more accurate and adaptable to the needs of different vehicles; by comparing the difference between the body specification parameters of the target obstacle vehicle and the body specification parameters of the current vehicle, and judging whether it exceeds the preset threshold, it can be adaptively determined whether correction is needed. If the difference exceeds the threshold, the corrected coordinates are obtained based on the difference and the initial coordinates to further optimize the parking path; by considering the difference between the body specification parameters of the target obstacle vehicle and the current vehicle, the corrected coordinates can be calculated more accurately, thereby improving the accuracy and adaptability of parking path planning.

[0023] Furthermore, the step S300 of acquiring the target coordinates according to the parking space coordinates and the corrected coordinates includes:

[0024] The lateral translation coordinates and the longitudinal translation coordinates are calculated according to the parking space coordinates and the corrected coordinates, so as to obtain the target coordinates based on the lateral translation coordinates, the longitudinal translation coordinates and the corrected coordinates.

[0025] In the above technical solution, by calculating the lateral translation coordinates and the longitudinal translation coordinates according to the parking space coordinates and the corrected coordinates, the target coordinates can be obtained more accurately, avoiding parking path planning errors caused by parking space position or corrected coordinate errors, thereby further optimizing the parking path.

[0026] Based on the same concept, the present application also provides a parking path optimization system, the system comprising:

[0027] The first acquisition module is used to acquire a target obstacle vehicle in response to a parking signal.

[0028] The second acquisition module is used to acquire the initial coordinates of the preset key points corresponding to the target obstacle vehicle.

[0029] The third acquisition module is used to acquire the body specification parameters of the current vehicle, and to correct the initial coordinates according to the body specification parameters to obtain corrected coordinates.

[0030] Judgment module: used to judge whether the target obstacle vehicle has an associated parking space, so as to enter the fourth acquisition module when there is an associated parking space, and to enter the fifth acquisition module when there is no associated parking space.

[0031] The fourth acquisition module is used to acquire the parking space coordinates of the associated parking space, and acquire the target coordinates according to the parking space coordinates and the corrected coordinates.

[0032] The fifth acquisition module is used to use the corrected coordinates as target coordinates.

[0033] Optimization module: used for optimizing the parking path based on the target coordinates.

[0034] In the above technical solution, the system can obtain necessary information such as the target obstacle vehicle, the initial coordinates of preset key points, the body specification parameters of the current vehicle, etc., so as to fully obtain the required data for parking path optimization; by obtaining the body specification parameters of the current vehicle and correcting the initial coordinates to obtain the corrected coordinates, it can adapt to the sizes and shapes of different vehicles to improve the accuracy and safety of the parking path; when there is an associated parking space, the parking space coordinates of the associated parking space can be obtained, and the final target coordinates can be obtained based on the parking space coordinates and the corrected coordinates to further optimize the parking path; when the target obstacle vehicle has no associated parking space, the system can directly use the corrected coordinates as the target coordinates, thereby simplifying the system logical structure and improving the real-time and efficiency of the system.

[0035] Furthermore, the first acquisition module includes:

[0036] Identification unit: used for acquiring the parking planning state in real time, so as to identify obstacles in real time when the parking planning state is a parking space search state.

[0037] The first judgment unit is used to judge whether the identified obstacle is a car, so that if the obstacle is a car, the car is used as a preparatory obstacle car and transferred to the second judgment unit; and if it is not a car, it returns to the identification unit.

[0038] The second judgment unit is used to obtain the color of the prepared obstacle vehicle and judge whether the color is a preset color, so as to use the prepared obstacle vehicle as the target obstacle vehicle if the color is the preset color; and to transfer to the first acquisition unit if the color is not the preset color.

[0039] The first acquisition unit is used to acquire the obstacle coordinates of the obstacle-prepared vehicle and use the obstacle coordinates as the target coordinates.

[0040] In the above technical solution, the parking planning status can be obtained in real time and obstacles in the scene can be identified, which helps to respond to changes in the parking scene in a timely manner and improve the accuracy and safety of parking path planning; by judging whether the identified obstacle is a vehicle, and further judging whether the color of the prepared obstacle vehicle meets the preset conditions, it helps to accurately screen out target obstacle vehicles that meet the requirements, avoid misidentification or selection of inappropriate vehicles as correction targets, and thus ensure the optimization effect and accuracy of the parking path.

[0041] Furthermore, the third acquisition module includes:

[0042] The second acquisition unit is used to acquire the body specification parameters of the target obstacle vehicle according to the initial coordinates.

[0043] The third judgment unit is used to obtain the difference between the body specification parameters of the target obstacle vehicle and the body specification parameters of the current vehicle, and to judge whether the difference is greater than a preset threshold, so as to transfer to the correction unit when the difference is greater than the preset threshold; and to transfer to the third acquisition unit when the difference is less than or equal to the preset threshold.

[0044] Correction unit: used for obtaining corrected coordinates based on the difference and the initial coordinates.

[0045] The third acquisition unit is used to use the initial coordinates as target coordinates.

[0046] In the above technical solution, by obtaining the body specification parameters of the obstacle vehicle, it is helpful to predict and calculate the position of the target obstacle vehicle and the range that affects the parking of the current vehicle; the coordinates are corrected based on the parameter difference between the target obstacle vehicle and the current vehicle, which can adapt to different vehicles and has high flexibility and scalability; and when the difference is less than or equal to the preset threshold, the initial coordinates are directly used as the target coordinates, which improves the real-time and efficiency of the system.

[0047] Furthermore, the fourth acquisition module includes:

[0048] Calculation unit: used for calculating the lateral translation coordinates and the longitudinal translation coordinates according to the parking space coordinates and the correction coordinates.

[0049] The fourth acquisition unit is used to acquire the target coordinates based on the lateral translation coordinates, the longitudinal translation coordinates and the corrected coordinates.

[0050] In the above technical solution, by translating the corrected relevant coordinates of the obstacle vehicle, high-precision calculation of the coordinates of the target obstacle vehicle can be achieved, thereby improving the accuracy of parking path planning; at the same time, the system can adapt to a variety of different scenarios, thereby improving the adaptability and flexibility of the system.

[0051] Based on the same concept, the present application provides a vehicle, wherein the vehicle is equipped with a parking path optimization system, and the system uses the parking path optimization method to optimize the parking path to plan an optimal parking path.

[0052] Compared with the prior art, the technical effects of this application are:

[0053] After obtaining the parking signal, the present application first obtains the initial coordinates of the target obstacle vehicle and its corresponding preset key points; then the initial coordinates are corrected according to the body specification parameters of the current vehicle to obtain the corrected coordinates; then it is further determined whether the target obstacle vehicle has an associated parking space, and if so, the target coordinates are obtained according to the parking space coordinates of the associated parking space and the corrected coordinates; if not, the corrected coordinates are directly used as the target coordinates; finally, the parking path is optimized based on the target coordinates. The present application can calculate the parking path more accurately, improve the accuracy and safety of parking; and also improve the efficiency and convenience of parking; in addition, it can effectively eliminate the impact of the shadow of the obstacle vehicle on parking planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a flow chart of the parking path optimization method described in this application.

[0055] Figure 2 for Figure 1 System framework diagram of the parking path optimization method. DETAILED DESCRIPTION

[0056] The present application provides a parking path optimization method, system and vehicle to solve the technical problem that there is no method for eliminating the shadow of an obstacle vehicle in the prior art, resulting in insufficient parking accuracy and poor user experience.

[0057] A parking path optimization method, system and vehicle of the present application are further described in detail below in conjunction with specific embodiments and drawings.

[0058] Embodiment 1:

[0059] See also Figure 1 The present application provides a parking path optimization method, comprising the following steps:

[0060] S100: In response to a parking signal, obtaining initial coordinates of a target obstacle vehicle and its corresponding preset key points.

[0061] Furthermore, obtaining the target obstacle vehicle in step S100 includes:

[0062] S101: Acquire a parking planning state in real time, so as to identify obstacles in real time when the parking planning state is a parking space search state.

[0063] In this embodiment, the front-view camera, surround-view camera and / or ultrasonic radar identify the surrounding environment information of the current vehicle in real time, and transmit the surrounding environment information to the OD recognition module, which performs feature extraction and target detection on the surrounding environment information to determine whether there are obstacles based on the processing results.

[0064] Among them, the OD recognition module refers to the Object Detection module, which is a visual recognition module based on machine learning and deep learning technology. It is used to detect and identify different objects and areas in images or videos, and output their coordinates, categories and other information.

[0065] Specifically, the OD recognition module usually includes a feature extractor and a target detector; the feature extractor first preprocesses and extracts features of the input surrounding environment information, and converts the surrounding environment information into a vector or matrix representation with distinguishable features; then the feature vector or matrix is ​​input into the target detector for detection and classification, and the target objects and areas in the surrounding environment information are identified, and their coordinates, categories and other information are output.

[0066] S102: Determine whether the identified obstacle is a vehicle. If so, use the vehicle as a preparatory obstacle vehicle; otherwise, return to step S101.

[0067] In this embodiment, it is determined whether the obstacle is a vehicle based on the category output by the target detector. If so, the vehicle is determined as a preliminary obstacle vehicle; if not, the obstacle identification continues.

[0068] In the above technical solution, by identifying obstacles in real time when the parking planning state is the parking space search state, the information of the target obstacle vehicle can be obtained in time, so that the change of obstacles can be responded to more quickly, and the real-time and adaptability of the parking system can be improved; by judging whether the identified obstacle is a vehicle, the real vehicle can be used as a preparatory obstacle vehicle, so as to plan and optimize the parking path more accurately, and avoid misjudging other objects as vehicles and generating an erroneous parking path.

[0069] Furthermore, the step S100 of acquiring the target obstacle vehicle further includes:

[0070] The color of the prepared obstacle vehicle is obtained, and it is determined whether the color is a preset color.

[0071] In this embodiment, the OD recognition module continues to perform feature extraction and target detection on the identified prepared obstacle vehicle to obtain the color of the prepared obstacle vehicle; and then determines whether the obtained color is black or gray.

[0072] If so, the prepared obstacle vehicle is used as the target obstacle vehicle; otherwise, the obstacle coordinates of the prepared obstacle vehicle are obtained, and the obstacle coordinates are used as the target coordinates.

[0073] In this embodiment, if the acquired color is black or gray, the acquired vehicle is determined to be the target obstacle vehicle; if it is not black or gray, the coordinates acquired in the previous sequence are directly output and used as the target coordinates for subsequent use in parking path planning.

[0074] In the above technical solution, by obtaining the color of the prepared obstacle vehicle and determining whether it is the preset color, the accuracy of identifying the target obstacle vehicle can be improved, the possibility of parking path planning errors can be reduced, and the parking accuracy can be further improved; if the color of the prepared obstacle vehicle is not the preset color, the coordinates of the prepared obstacle vehicle can be obtained and the obstacle coordinates can be used as the target coordinates to further optimize the parking path.

[0075] S200: Acquire body specification parameters of the current vehicle, and correct the initial coordinates according to the body specification parameters to obtain corrected coordinates.

[0076] Furthermore, the step S200 includes:

[0077] S201: Acquire body specification parameters of the target obstacle vehicle according to the initial coordinates.

[0078] In this embodiment, the OD recognition module further acquires the length and width of the target obstacle vehicle, ie, the vehicle body specification parameters, according to the acquired initial coordinates.

[0079] The initial coordinates are the coordinates of the four key points around the target obstacle vehicle, with the center of the vehicle body as the origin, the right side of the vehicle as the positive direction of the X axis, and the front side as the positive direction of the Y axis; assuming the output initial coordinates P1(x1,y1), P2(x2,y2), P3(x3,y3), P4(x4,y4), we can get

[0080]

[0081] S202: Obtain the difference between the body specification parameters of the target obstacle vehicle and the body specification parameters of the current vehicle, and determine whether the difference is greater than a preset threshold. If so, obtain the corrected coordinates based on the difference and the initial coordinates; otherwise, use the initial coordinates as the target coordinates.

[0082] Furthermore, the length and width of the current vehicle are obtained. Assume that the length obtained is 当前 and width 当前 , and then calculate the length 障碍and length 当前 The difference between 障碍 and width 当前 The difference is used to determine whether the length and width of the target obstacle vehicle are significantly greater than the length and width of the current vehicle. If so, the algorithm module needs to correct the initial coordinates of the target obstacle vehicle.

[0083] Assuming that the length and width differences are X and Y respectively, let the length correction amount be dx and the width correction amount be dy, then: dx=X / 2, dy=Y / 2.

[0084] Then the corrected coordinates P1`(x1-X / 2,y1-Y / 2), P2`(x2-X / 2,y2-Y / 2), P3`(x3+X / 2,y3+Y / 2), and P4`(x4+X / 2,y4+Y / 2) are obtained.

[0085] If the difference between the length and width of the target obstacle vehicle and the length and width of the current vehicle is not greater than the preset threshold, the initial coordinates are directly used as the target coordinates.

[0086] In the above technical solution, by obtaining the body specification parameters of the target obstacle vehicle according to the initial coordinates, the corrected coordinates can be calculated more accurately, so that the parking path planning is more accurate and adaptable to the needs of different vehicles; by comparing the difference between the body specification parameters of the target obstacle vehicle and the body specification parameters of the current vehicle, and judging whether it exceeds the preset threshold, it can be adaptively determined whether correction is needed. If the difference exceeds the threshold, the corrected coordinates are obtained based on the difference and the initial coordinates to further optimize the parking path; by considering the difference between the body specification parameters of the target obstacle vehicle and the current vehicle, the corrected coordinates can be calculated more accurately, thereby improving the accuracy and adaptability of parking path planning.

[0087] S300: Determine whether the target obstacle vehicle has an associated parking space. If so, obtain the parking space coordinates of the associated parking space, and obtain the target coordinates according to the parking space coordinates and the corrected coordinates; otherwise, use the corrected coordinates as the target coordinates.

[0088] Furthermore, the step S300 of acquiring the target coordinates according to the parking space coordinates and the corrected coordinates includes:

[0089] The lateral translation coordinates and the longitudinal translation coordinates are calculated according to the parking space coordinates and the corrected coordinates, so as to obtain the target coordinates based on the lateral translation coordinates, the longitudinal translation coordinates and the corrected coordinates.

[0090] Among them, the lateral translation coordinate is equal to the sum of the lateral coordinate of the parking space coordinate and the lateral offset of the corrected coordinate, and the longitudinal translation coordinate is equal to the sum of the ordinate of the parking space coordinate and the longitudinal offset of the corrected coordinate; the lateral coordinate of the target coordinate is the lateral translation coordinate, and the ordinate is the longitudinal translation coordinate.

[0091] In this embodiment, the parking space recognition module will detect whether there is an associated parking space for the target obstacle vehicle through a visual recognition algorithm. If so, the parking space recognition module will obtain the coordinates of the associated parking space, that is, the parking space coordinates, through feature extraction and target detection; then, the value of the correction coordinates will be translated based on the parking space coordinates to obtain the target coordinates.

[0092] If the parking space recognition module does not recognize that the target obstacle vehicle has an associated parking space, the corrected coordinates obtained in the previous sequence are directly used as the target coordinates.

[0093] In the above technical solution, by calculating the lateral translation coordinates and the longitudinal translation coordinates according to the parking space coordinates and the corrected coordinates, the target coordinates can be obtained more accurately, avoiding parking path planning errors caused by parking space position or corrected coordinate errors, thereby further optimizing the parking path.

[0094] S400: Optimizing a parking path based on the target coordinates.

[0095] In this embodiment, the parking planning module obtains the target coordinates to plan the parking path according to the target coordinates. The target coordinates at this time have higher accuracy and can more accurately plan the optimal path and the corresponding number of parking steps, thereby improving the accuracy, efficiency and safety of parking and enhancing the user experience.

[0096] Embodiment 2:

[0097] See also Figure 2 The present application also provides a parking path optimization system, the system comprising:

[0098] The first acquisition module is used to acquire a target obstacle vehicle in response to a parking signal.

[0099] Furthermore, the first acquisition module includes:

[0100] Identification unit: used for acquiring the parking planning state in real time, so as to identify obstacles in real time when the parking planning state is a parking space search state.

[0101] The first judgment unit is used to judge whether the identified obstacle is a car, so that if the obstacle is a car, the car is used as a preparatory obstacle car and transferred to the second judgment unit; and if it is not a car, it returns to the identification unit.

[0102] The second judgment unit is used to obtain the color of the prepared obstacle vehicle and judge whether the color is a preset color, so as to use the prepared obstacle vehicle as the target obstacle vehicle if the color is the preset color; and to transfer to the first acquisition unit if the color is not the preset color.

[0103] The first acquisition unit is used to acquire the obstacle coordinates of the obstacle-prepared vehicle and use the obstacle coordinates as the target coordinates.

[0104] In the above technical solution, the parking planning status can be obtained in real time and obstacles in the scene can be identified, which helps to respond to changes in the parking scene in a timely manner and improve the accuracy and safety of parking path planning; by judging whether the identified obstacle is a vehicle, and further judging whether the color of the prepared obstacle vehicle meets the preset conditions, it helps to accurately screen out target obstacle vehicles that meet the requirements, avoid misidentification or selection of inappropriate vehicles as correction targets, and thus ensure the optimization effect and accuracy of the parking path.

[0105] The second acquisition module is used to acquire the initial coordinates of the preset key points corresponding to the target obstacle vehicle.

[0106] The third acquisition module is used to acquire the body specification parameters of the current vehicle, and to correct the initial coordinates according to the body specification parameters to obtain corrected coordinates.

[0107] Furthermore, the third acquisition module includes:

[0108] The second acquisition unit is used to acquire the body specification parameters of the target obstacle vehicle according to the initial coordinates.

[0109] The third judgment unit is used to obtain the difference between the body specification parameters of the target obstacle vehicle and the body specification parameters of the current vehicle, and to judge whether the difference is greater than a preset threshold, so as to transfer to the correction unit when the difference is greater than the preset threshold; and to transfer to the third acquisition unit when the difference is less than or equal to the preset threshold.

[0110] Correction unit: used for obtaining corrected coordinates based on the difference and the initial coordinates.

[0111] The third acquisition unit is used to use the initial coordinates as target coordinates.

[0112] In the above technical solution, by obtaining the body specification parameters of the obstacle vehicle, it is helpful to predict and calculate the position of the target obstacle vehicle and the range that affects the parking of the current vehicle; the coordinates are corrected based on the parameter difference between the target obstacle vehicle and the current vehicle, which can adapt to different vehicles and has high flexibility and scalability; and when the difference is less than or equal to the preset threshold, the initial coordinates are directly used as the target coordinates, which improves the real-time and efficiency of the system.

[0113] Judgment module: used to judge whether the target obstacle vehicle has an associated parking space, so as to enter the fourth acquisition module when there is an associated parking space, and to enter the fifth acquisition module when there is no associated parking space.

[0114] The fourth acquisition module is used to acquire the parking space coordinates of the associated parking space, and acquire the target coordinates according to the parking space coordinates and the corrected coordinates.

[0115] Furthermore, the fourth acquisition module includes:

[0116] Calculation unit: used for calculating the lateral translation coordinates and the longitudinal translation coordinates according to the parking space coordinates and the correction coordinates.

[0117] The fourth acquisition unit is used to acquire the target coordinates based on the lateral translation coordinates, the longitudinal translation coordinates and the corrected coordinates.

[0118] In the above technical solution, by translating the corrected relevant coordinates of the obstacle vehicle, high-precision calculation of the coordinates of the target obstacle vehicle can be achieved, thereby improving the accuracy of parking path planning; at the same time, the system can adapt to a variety of different scenarios, thereby improving the adaptability and flexibility of the system.

[0119] The fifth acquisition module is used to use the corrected coordinates as target coordinates.

[0120] Optimization module: used for optimizing the parking path based on the target coordinates.

[0121] Embodiment three:

[0122] The present application provides a vehicle, wherein the vehicle is equipped with a parking path optimization system, and the system optimizes the parking path using the parking path optimization method to plan an optimal parking path.

[0123] In summary, the present application provides a parking path optimization method, system and vehicle; after obtaining the parking signal, first obtain the initial coordinates of the target obstacle vehicle and its corresponding preset key points; then correct the initial coordinates according to the body specification parameters of the current vehicle to obtain the corrected coordinates; then further determine whether the target obstacle vehicle has an associated parking space, and if so, obtain the target coordinates according to the parking space coordinates of the associated parking space and the corrected coordinates; if not, directly use the corrected coordinates as the target coordinates; finally optimize the parking path based on the target coordinates. The present application can more accurately calculate the parking path, improve the accuracy and safety of parking; and also improve the efficiency and convenience of parking; in addition, it can effectively eliminate the impact of the shadow of the obstacle vehicle on parking planning.

[0124] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application to this. Those of ordinary skill in the art may make various changes and modifications therein without departing from the scope and spirit of the present application. All these changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0125] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0127] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some modules according to the embodiments of the present application. The application can also be implemented as a device program (e.g., computer program and computer program product) for executing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0128] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0129] Although the description of the present application is carried out in conjunction with the above specific embodiments, it is obvious that those skilled in the art can make many substitutions, modifications and changes based on the above content. Therefore, all such substitutions, improvements and changes are included in the spirit and scope of the appended claims.

Claims

1. A parking path optimization method, characterized in that: The following steps are involved: S100: In response to a parking signal, obtaining initial coordinates of a target obstacle vehicle and its corresponding preset key points; S200: Acquire body specification parameters of the current vehicle, and correct the initial coordinates according to the body specification parameters to obtain corrected coordinates; Wherein, the step S200 includes: S201: Acquire body specification parameters of the target obstacle vehicle according to the initial coordinates; S202: Obtain the difference between the body specification parameters of the target obstacle vehicle and the body specification parameters of the current vehicle, and determine whether the difference is greater than a preset threshold value. If so, obtain the corrected coordinates based on the difference and the initial coordinates; otherwise, use the initial coordinates as the target coordinates; S300: Determine whether the target obstacle vehicle has an associated parking space. If so, obtain the parking space coordinates of the associated parking space, and obtain the target coordinates according to the parking space coordinates and the corrected coordinates; otherwise, use the corrected coordinates as the target coordinates; Wherein, acquiring the target coordinates according to the parking space coordinates and the corrected coordinates in step S300 includes: calculating the lateral translation coordinates and the longitudinal translation coordinates according to the parking space coordinates and the corrected coordinates, so as to acquire the target coordinates based on the lateral translation coordinates, the longitudinal translation coordinates and the corrected coordinates; S400: Optimizing a parking path based on the target coordinates.

2. The parking path optimization method according to claim 1, characterized in that: The step S100 of obtaining the target obstacle vehicle includes: S101: acquiring a parking planning state in real time, so as to identify obstacles in real time when the parking planning state is a parking space search state; S102: Determine whether the identified obstacle is a vehicle. If so, use the vehicle as a preparatory obstacle vehicle; otherwise, return to step S101.

3. The parking path optimization method according to claim 2, characterized in that: The step S100 of acquiring the target obstacle vehicle further includes: Obtaining the color of the prepared obstacle vehicle and determining whether the color is a preset color; If so, the prepared obstacle vehicle is used as the target obstacle vehicle; otherwise, the obstacle coordinates of the prepared obstacle vehicle are obtained, and the obstacle coordinates are used as the target coordinates.

4. A system using the parking path optimization method according to any one of claims 1 to 3, characterized in that: The system comprises: A first acquisition module: used for acquiring a target obstacle vehicle in response to a parking signal; The second acquisition module is used to obtain the initial coordinates of the preset key points corresponding to the target obstacle vehicle; A third acquisition module: used for acquiring body specification parameters of the current vehicle, and correcting the initial coordinates according to the body specification parameters to obtain corrected coordinates; A judgment module: used to judge whether the target obstacle vehicle has an associated parking space, so as to enter the fourth acquisition module when there is an associated parking space, and to enter the fifth acquisition module when there is no associated parking space; The fourth acquisition module is used to acquire the parking space coordinates of the associated parking space, and acquire the target coordinates according to the parking space coordinates and the corrected coordinates; A fifth acquisition module: used for taking the corrected coordinates as target coordinates; Optimization module: used for optimizing the parking path based on the target coordinates.

5. The system according to claim 4, characterized in that The first acquisition module includes: Identification unit: used for obtaining the parking planning state in real time, so as to identify obstacles in real time when the parking planning state is a parking space search state; The first judgment unit is used to judge whether the identified obstacle is a car, so that if the obstacle is a car, the car is used as a preparatory obstacle car and transferred to the second judgment unit; and if it is not a car, it returns to the identification unit; The second judgment unit is used to obtain the color of the prepared obstacle vehicle and judge whether the color is a preset color, so as to use the prepared obstacle vehicle as the target obstacle vehicle if the color is the preset color; and to transfer to the first acquisition unit if the color is not the preset color; The first acquisition unit is used to acquire the obstacle coordinates of the obstacle-prepared vehicle and use the obstacle coordinates as the target coordinates.

6. The system according to claim 5, characterized in that The third acquisition module includes: A second acquisition unit: used for acquiring the body specification parameters of the target obstacle vehicle according to the initial coordinates; The third judgment unit is used to obtain the difference between the body specification parameters of the target obstacle vehicle and the body specification parameters of the current vehicle, and judge whether the difference is greater than a preset threshold, so as to transfer to the correction unit when the difference is greater than the preset threshold; and transfer to the third acquisition unit when the difference is less than or equal to the preset threshold; Correction unit: used for obtaining corrected coordinates based on the difference and the initial coordinates; The third acquisition unit is used to use the initial coordinates as target coordinates.

7. The system according to claim 6, characterized in that The fourth acquisition module includes: Calculation unit: used for calculating the lateral translation coordinates and the longitudinal translation coordinates according to the parking space coordinates and the correction coordinates; The fourth acquisition unit is used to acquire the target coordinates based on the lateral translation coordinates, the longitudinal translation coordinates and the corrected coordinates.

8. A vehicle, characterized in that: The vehicle is equipped with a parking path optimization system, and the system optimizes the parking path using the parking path optimization method according to any one of claims 1 to 3 to plan an optimal parking path.

Images