A parking path mapping method and device, and a parking method and device

Abstract

The embodiments of the present application disclose a parking path mapping method and apparatus, as well as a parking method and apparatus. The parking path mapping method includes: marking multiple different timestamps during the vehicle's driving towards the target parking space, and recording the vehicle operation information corresponding to each timestamp; detecting whether there is a repeated path during the driving process according to the vehicle operation information corresponding to the timestamp; when there is no repeated path, taking the path traveled by the vehicle during the entire driving process as the parking planning path; when there is a repeated path, identifying the section corresponding to the repeated path, re-planning the path for this section, and combining the non-repeated path with the re-planned path as the parking planning path; saving the parking planning path as map data to complete the parking path mapping. Through the solution of this embodiment, the optimization of useless paths is achieved, the cruise on useless paths during parking is avoided, and the use efficiency of the automatic parking function and the user experience are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to automatic parking technology, and particularly to a method and device for building a parking path map and a method and device for parking. Background Art

[0002] The valet parking system creates a map of the route to the parking space through the vehicle camera, lidar, RTK (Real-Time Kinematic) module, and IMU (Inertial Measurement Unit) module. The valet parking system can assist the driver in controlling the accelerator, brake, and steering wheel, and help the driver automatically cruise to the parking space according to the established map route in the indoor underground same-level parking lot and park in the parking space, which is an intelligent driving assistance system. Summary of the Invention

[0003] The embodiments of the present application provide a method and device for building a parking path map and a method and device for parking, which can optimize useless paths such as the meeting vehicle reverse path and the wrong-way U-turn path in the parking path, avoid cruising on useless paths during parking, and improve the use efficiency of the automatic parking function and the user experience.

[0004] The embodiments of the present application provide a method for building a parking path map, and the method may include:

[0005] Marking multiple different timestamps during the vehicle's driving process towards the target parking space, and recording the vehicle operation information corresponding to each timestamp; the vehicle operation information includes any one or more of the following: driving scene images and data, target parking space information, odometer information, vehicle coordinate information, vehicle speed information, vehicle gear information, and vehicle body attitude information; the driving scene images and data include any one or more of the following: scene images, obstacle images, obstacle distances, and road widths;

[0006] Detecting whether there is a repeated path during the entire driving process according to the vehicle operation information corresponding to multiple different timestamps;

[0007] When it is detected that there is no repeated path during the entire driving process, taking the path traveled by the vehicle during the entire driving process as the parking planning path; when it is detected that there is a repeated path during the entire driving process, identifying the section corresponding to the repeated path, re-planning the path for the section, and combining the non-repeated path during the entire driving process with the re-planned path as the parking planning path;

[0008] Saving the parking planning path as map data to complete the construction of the parking path map.

[0009] In an exemplary embodiment of the present application, the vehicle operation information may include: odometer information and vehicle coordinate information;

[0010] Detecting whether there is a repeated path during the entire driving process based on the vehicle operation information corresponding to multiple different timestamps may include:

[0011] Calculating whether the path between the two timestamps is a repeated path according to the odometer information and the vehicle coordinate information corresponding to any two timestamps;

[0012] When the path between any two timestamps during the entire driving process is a repeated path, it is determined that there is a repeated path during the entire driving process; when the path between any two timestamps during the entire driving process is a non-repeated path, it is determined that there is no repeated path during the entire driving process.

[0013] In an exemplary embodiment of the present application, calculating whether the path between the two timestamps is a repeated path according to the odometer information and the vehicle coordinate information corresponding to any two timestamps includes:

[0014] Subtracting the odometer information corresponding to any two timestamps to obtain the mileage distance between the two timestamps;

[0015] Subtracting the vehicle coordinate information corresponding to any two timestamps to obtain the coordinate distance between the two timestamps;

[0016] When the mileage distance is greater than or equal to the sum of the coordinate distance and the preset calibration distance, it is confirmed that the path between the two timestamps is a repeated path;

[0017] When the mileage distance is less than the sum of the coordinate distance and the preset calibration distance, it is confirmed that the path between the two timestamps is a non-repeated path.

[0018] In an exemplary embodiment of the present application, identifying the section corresponding to the repeated path may include:

[0019] Obtaining each two timestamps confirmed as repeated paths during the entire driving process of the vehicle and the corresponding mileage distance for each two timestamps;

[0020] Detecting whether all the obtained timestamps are continuous;

[0021] When all the obtained timestamps are continuous, obtaining a continuous timestamp segment, and determining the section corresponding to the repeated path according to the start and end timestamps of the continuous timestamp segment and / or according to the mileage distance;

[0022] When all the obtained timestamps are not continuous, dividing all the obtained timestamps into different continuous timestamp segments according to the breakpoints, and for different continuous timestamp segments, respectively determining the section corresponding to the repeated path according to the start and end timestamps of each continuous timestamp segment and / or according to the mileage distance.

[0023] In an exemplary embodiment of the present application, determining the section corresponding to the repeated path according to the mileage distance may include:

[0024] Comparing the obtained mileage distances to find the one with the largest value;

[0025] Regarding the section between the two timestamps corresponding to the mileage distance with the largest value as the section corresponding to the repeated path.

[0026] In an exemplary embodiment of the present application, before combining the non-repeated path in the entire driving process with the re-planned path as the parking planning path, the method may further include: obtaining the non-repeated path in the entire driving process.

[0027] In an exemplary embodiment of the present application, obtaining the non-repeated path in the entire driving process may include:

[0028] Creating a set composed of all timestamps and the vehicle operation information corresponding to the all timestamps, denoted as the first set;

[0029] Creating a set composed of the timestamps corresponding to the repeated path and the vehicle operation information corresponding to the timestamps corresponding to the repeated path, denoted as the second set;

[0030] Subtracting the second set from the first set to obtain a third set; the third set is a set composed of the timestamps corresponding to the non-repeated path and the vehicle operation information corresponding to the timestamps corresponding to the non-repeated path;

[0031] Regarding the path corresponding to any continuous timestamps in the third set as the non-repeated path.

[0032] In an exemplary embodiment of the present application, obtaining the non-repeated path in the entire driving process may include:

[0033] When the path between any two timestamps in the entire driving process is a non-repeated path, recording the timestamps corresponding to the non-repeated path;

[0034] Creating a set composed of the timestamps corresponding to the non-repeated path and the vehicle operation information corresponding to the timestamps corresponding to the non-repeated path, denoted as the fourth set;

[0035] Regarding the path corresponding to any continuous timestamps in the fourth set as the non-repeated path.

[0036] An embodiment of the present application further provides a parking path mapping device, which is characterized in that the device includes: a camera, a positioning device, an object detection device, a vehicle state detection device, a first processor, and a first computer-readable storage medium. A first instruction is stored in the first computer-readable storage medium. When the first instruction is executed by the first processor, the parking path mapping method described above is implemented.

[0037] An embodiment of the present application further provides a parking method, which may include:

[0038] Retrieve the parking planning path obtained according to the parking path mapping method described above;

[0039] Park according to the parking planning path.

[0040] An embodiment of the present application further provides a parking device, which may include: a second processor and a second computer-readable storage medium. A second instruction is stored in the second computer-readable storage medium. When the second instruction is executed by the second processor, the parking method described above is implemented.

[0041] Compared with the related art, an embodiment of the present application may include: marking a plurality of different timestamps during the vehicle's driving process towards the target parking space, and recording the vehicle operation information corresponding to each of the timestamps; detecting whether there is a repeated path during the entire driving process according to the vehicle operation information corresponding to the plurality of different timestamps; when it is detected that there is no repeated path during the entire driving process, taking the path traveled by the vehicle during the entire driving process as the parking planning path; when it is detected that there is a repeated path during the entire driving process, identifying the section corresponding to the repeated path, re-planning the path for the section, and combining the non-repeated path during the entire driving process with the re-planned path as the parking planning path; saving the parking planning path as map data to complete the parking path mapping. Through the solution of this embodiment, it is possible to optimize useless paths such as passing and reversing paths and wrong-way turning paths that appear in the parking path, avoid cruising on useless paths during parking, and improve the usage efficiency of the automatic parking function and the user experience.

[0042] Other features and advantages of the present application will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present application. Other advantages of the present application can be realized and obtained through the solutions described in the specification and the drawings. Description of the Drawings

[0043] The drawings are used to provide an understanding of the technical solution of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application, and do not constitute a limitation to the technical solution of the present application.

[0044] Figure 1 Flow chart of the parking path mapping method according to the embodiment of the present application;

[0045] Figure 2 Flow chart of the method for detecting whether there is a repeated path during the entire driving process according to the vehicle operation information corresponding to multiple different timestamps in the embodiment of the present application;

[0046] Figure 3 Flow chart of the method for calculating whether the path between two timestamps is a repeated path according to the odometer information and vehicle coordinate information corresponding to any two timestamps in the embodiment of the present application;

[0047] Figure 4 Schematic diagram of the parking planning path including the section to be re-planned according to the embodiment of the present application;

[0048] FIG. 5(a) is a schematic diagram of the repeated path in the first form according to the embodiment of the present application;

[0049] FIG. 5(b) is a schematic diagram of the repeated path in the second form according to the embodiment of the present application;

[0050] FIG. 5(c) is a schematic diagram of the repeated path in the third form according to the embodiment of the present application;

[0051] FIG. 5(d) is a schematic diagram of the repeated path in the fourth form according to the embodiment of the present application;

[0052] Figure 6 Schematic diagram of set M, set D, and set K according to the embodiment of the present application;

[0053] Figure 7 Block diagram of the parking path mapping device according to the embodiment of the present application;

[0054] Figure 8 Flow chart of the parking method according to the embodiment of the present application;

[0055] Figure 9 Block diagram of the parking device according to the embodiment of the present application. Detailed implementation manners

[0056] This application describes multiple embodiments, but the description is exemplary rather than restrictive, and it will be apparent to those of ordinary skill in the art that there can be more embodiments and implementation solutions within the scope covered by the embodiments described in this application. Although many possible feature combinations are shown in the drawings and discussed in the detailed description, many other combination ways of the disclosed features are also possible. Unless specifically restricted, any feature or element of any embodiment can be combined with any other feature or element in any other embodiment, or can replace any other feature or element in any other embodiment.

[0057] This application includes and contemplates combinations with features and elements known to those of ordinary skill in the art. The embodiments, features, and elements already disclosed in this application can also be combined with any conventional features or elements to form unique inventive solutions defined by the claims. Any feature or element of any embodiment can also be combined with features or elements from other inventive solutions to form another unique inventive solution defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in this application can be implemented alone or in any suitable combination. Therefore, the embodiments are not subject to other limitations except those made in accordance with the appended claims and their equivalents. In addition, various modifications and changes can be made within the scope of the appended claims.

[0058] In addition, when describing representative embodiments, the specification may have presented the method and / or process as a specific sequence of steps. However, to the extent that the method or process does not depend on the specific order of the steps described herein, the method or process should not be limited to the specific order of steps described. As will be understood by those of ordinary skill in the art, other step orders are possible. Therefore, the specific order of steps set forth in the specification should not be construed as a limitation on the claims. In addition, the claims directed to the method and / or process should not be limited to performing their steps in the order written, and those skilled in the art can easily understand that these orders can be varied and still remain within the spirit and scope of the embodiments of this application.

[0059] The embodiments of this application provide a parking path mapping method, as Figure 1 shown, the method may include steps S101 - S104:

[0060] S101. Mark multiple different timestamps during the vehicle's driving process towards the target parking space, and record the vehicle running information corresponding to each of the timestamps;

[0061] S102. Detect whether there is a repeated path during the entire driving process according to the vehicle running information corresponding to multiple different timestamps;

[0062] S103. When it is detected that there is no repeated path during the entire driving process, the path traveled by the vehicle during the entire driving process is used as the parking planning path; when it is detected that there is a repeated path during the entire driving process, identify the road section corresponding to the repeated path, re-plan the path for the road section, and combine the non-repeated path during the entire driving process with the re-planned path as the parking planning path;

[0063] S104. Save the parking planning path as map data to complete the parking path mapping.

[0064] In an exemplary embodiment of the present application, the solution of the embodiment of the present application can be applied to, but not limited to, daily automatic parking scenarios and valet parking scenarios.

[0065] In an exemplary embodiment of the present application, the vehicle operation information may include any one or more of the following: driving scene images and data, target parking space information, vehicle coordinate information, odometer information, vehicle speed information, vehicle gear information, and vehicle body attitude information; the driving scene images and data may include any one or more of the following: scene images, obstacle images, obstacle distances, and road widths.

[0066] In an exemplary embodiment of the present application, devices such as cameras, positioning devices (such as real-time kinematic RTK modules, inertial measurement unit IMU modules), object detection devices, and vehicle state detection devices may be provided on the vehicle to collect the vehicle operation information.

[0067] In an exemplary embodiment of the present application, the driving scene images and data can be obtained by using on-vehicle cameras. For example, it may include, but not limited to, cameras installed at the front end of the vehicle, and on-vehicle driving recorders, etc.

[0068] In an exemplary embodiment of the present application, the target parking space information can be associated by a vehicle controller (or called a processor) with an associated system (such as a parking space system), and after obtaining an idle parking space through data sharing, perform a parking space selection operation (such as random selection, sequential selection, selection according to a preset algorithm, etc.) to obtain.

[0069] In an exemplary embodiment of the present application, the vehicle coordinate information can be obtained by positioning the vehicle. The positioning technologies that the vehicle can adopt may include, but not limited to, satellite positioning, base station positioning, radar positioning, millimeter wave positioning, etc. The positioning device can be set accordingly according to the adopted positioning technology.

[0070] In an exemplary embodiment of the present application, for example, the selected positioning device may include: a real-time kinematic RTK module.

[0071] In an exemplary embodiment of the present application, the object detection techniques that the vehicle can adopt may include, but are not limited to, infrared detection technology, radar detection technology, vision detection technology, ultrasonic detection technology, etc. The object detection device can be correspondingly set according to the adopted object detection technology.

[0072] In an exemplary embodiment of the present application, for example, the selected object detection device may include: a lidar and a vision detection device (such as a camera).

[0073] In an exemplary embodiment of the present application, information such as odometer information, vehicle speed information, vehicle gear information, and vehicle body attitude information can be obtained through a vehicle state detection device, which may include, but is not limited to, an odometer, a speed sensor, an acceleration sensor, a gear sensor, a pose sensor, an angle sensor, a gyroscope, etc., and an integrated vehicle state detection device can also be directly adopted.

[0074] In an exemplary embodiment of the present application, the vehicle state detection device may include: an inertial measurement unit (IMU) module; the vehicle body attitude information can be judged through the IMU module.

[0075] In an exemplary embodiment of the present application, the vehicle operation information obtained during the vehicle driving process can be synchronized with a set timestamp, that is, the vehicle operation information corresponding to the timestamp is recorded at each timestamp (for example, it can be the vehicle operation information from the previous timestamp to the current timestamp), and can be marked on the parking planning path on the map. For example, a timestamp sequence is formed on the parking planning path on the map with continuous timestamps, such as: t1, t2, …, tn, where n is a positive integer; the first set M = {t1 (driving scene images and data, target parking space information, vehicle coordinate information, odometer information, vehicle speed information, vehicle gear information, vehicle body attitude information, etc.), t2 (driving scene images and data, target parking space information, vehicle coordinate information, odometer information, vehicle speed information, vehicle gear information, vehicle body attitude information, etc.), ……, tn (driving scene images and data, target parking space information, vehicle coordinate information, odometer information, vehicle speed information, vehicle gear information, vehicle body attitude information, etc.)} can be formed by the timestamp and its corresponding vehicle operation information. Among them, for the starting timestamp t1, the odometer information, vehicle speed information, etc. can all be 0.

[0076] In an exemplary embodiment of the present application, each timestamp t1, t2, …, tn can be marked on the driving path.

[0077] In an exemplary embodiment of the present application, during the process of parking path mapping, various situations may occur during the vehicle operation, such as meeting another vehicle, taking the wrong route, making a U-turn, etc. When meeting another vehicle, there may be a reverse path, resulting in a repeated path. Repeated paths may also occur when taking the wrong route or making a U-turn. These repeated paths are all useless paths in the parking planning path. Therefore, the useless path can be optimized in the parking planning path. Before optimization, it is necessary to first detect whether there is a repeated path during the vehicle driving process.

[0078] In an exemplary embodiment of the present application, when the vehicle operation information may include: odometer information and vehicle coordinate information; as Figure 2 shown, detecting whether there is a repeated path during the entire driving process according to the vehicle operation information corresponding to multiple different timestamps may include steps S201 - S202:

[0079] S201. Calculate whether the path between the two timestamps is a repeated path according to the odometer information and the vehicle coordinate information corresponding to any two timestamps.

[0080] In an exemplary embodiment of the present application, as Figure 3 shown, calculating whether the path between the two timestamps is a repeated path according to the odometer information and the vehicle coordinate information corresponding to any two timestamps includes steps S301 - S304:

[0081] S301. Subtract the odometer information corresponding to any two timestamps to obtain the mileage distance d1 between the two timestamps;

[0082] S302. Subtract the vehicle coordinate information corresponding to any two timestamps to obtain the coordinate distance d2 between the two timestamps;

[0083] S303. When the mileage distance d1 is greater than or equal to the sum of the coordinate distance d2 and the preset calibration distance d3, confirm that the path between the two timestamps is a repeated path;

[0084] S304. When the mileage distance d1 is less than the sum of the coordinate distance d2 and the preset calibration distance d3, confirm that the path between the two timestamps is a non - repeated path.

[0085] In an exemplary embodiment of the present application, the mileage distance d1 and the coordinate distance d2 between any two timestamps can be calculated. Since when there is a repeated route, the mileage distance of the vehicle must be much greater than the coordinate distance d2, it is possible to determine whether the path between the two timestamps is a repeated path according to the magnitudes of the mileage distance d1 and the coordinate distance d2.

[0086] In an exemplary embodiment of the present application, the determination of the repeated path can be added with a calibration distance d3, which can be a preset value for leaving an error threshold. For example, if a section of the path has no repeated path, but the mileage distance d1 caused by the tortuous path is much greater than the coordinate distance d2, without the calibration distance d3, it is easy to cause misjudgment. The calibration distance d3 can be set to different values according to different application scenarios, and can make a pre-judgment on the road conditions or driving scenarios based on information such as driving scenario images and data, vehicle speed information, vehicle gear information, and vehicle body attitude information, so as to determine the value of the calibration distance d3 according to the pre-judgment result.

[0087] In an exemplary embodiment of the present application, after determining whether the path between two timestamps (such as timestamp t5 and t6) is a repeated path through the above scheme, the judgment result can be verified by the vehicle operation information corresponding to t6 (that is, the vehicle operation information from t5 to t6, such as driving scenario images, vehicle coordinate information, vehicle body attitude information, etc.) to improve the judgment accuracy.

[0088] In an exemplary embodiment of the present application, if the judgment result is consistent with the verification result, the judgment result can be recorded as the final result. If the judgment result is inconsistent with the verification result, an inquiry message can be sent to verify with the driver whether there is a repeated path between t5 and t6.

[0089] S202. When the path between any two timestamps during the entire driving process is a repeated path, it is determined that there is a repeated path during the entire driving process; when the path between any two timestamps during the entire driving process is a non-repeated path, it is determined that there is no repeated path during the entire driving process.

[0090] In an exemplary embodiment of the present application, as long as a repeated path is detected during the entire driving process, it can be determined that there is a repeated path during the entire driving process, otherwise it is determined that there is no repeated path during the entire driving process.

[0091] In an exemplary embodiment of the present application, if it is detected that there is no repeated path during the entire driving process, it means that the current path planning is relatively smooth, and the path traveled during the driving process can be directly used as the parking planning path. If it is detected that there is a repeated path during the entire driving process, it means that the current path planning needs to be further optimized, and the repeated path can be processed to optimize the planned path. Specifically, it can be processed according to a preset strategy, and finally a parking planning path is determined according to this driving process.

[0092] In an exemplary embodiment of the present application, the determination of the parking planning path according to the preset strategy may include:

[0093] Identify the road section corresponding to the repeated path;

[0094] Re-plan the path for the road section, and combine the non-repeated path in the entire driving process with the re-planned path as the parking planning path. Alternatively, mark the road section as a road section to be re-planned, and combine the non-repeated path in the entire driving process with the road section to be re-planned as the parking planning path; wherein the road section to be re-planned is used to indicate that when the vehicle drives to the road section to be re-planned during parking according to the parking planning path, the vehicle re-plans the path for the road section to be re-planned.

[0095] In an exemplary embodiment of the present application, the preset strategy may include two solutions: On the one hand, the path of the road section where the repeated path is located can be re-planned (which can be implemented by using a preset path planning algorithm), so that the re-planned path is used as the planned path of the road section where the repeated path is located, and combined with the path corresponding to the non-repeated path as a complete parking planning path. By recommending a new path to the driver, the driver can determine whether to use the new path to replace the original repeated path, avoiding the user from cruising on useless paths when using valet parking, and improving the use efficiency of the valet parking function and the user experience. On the other hand, the path of this road section can no longer be re-planned, that is, there is no planned path for this road section, and this road section is marked to indicate that there is no planned path for this road section, which can be used as a road section to be re-planned, and the mark is combined with the path corresponding to the non-repeated path to temporarily serve as a complete parking planning path. If the driving path of this road section can be obtained later, it can be supplemented to the corresponding road section of this parking planning path. It is also possible that when the driver adopts this parking planning path and drives to the corresponding road section, he can re-plan the path or navigate by himself, obtain the driving path of this road section, and continue to automatically park according to the original parking planning path after passing through this road section. This solution can be used for special situations such as temporary control and temporary maintenance of repeated paths. If a new path is re-planned, it may be a long detour, and the road section where the repeated path is located may be the optimal path or the shortest path. Since it is caused by temporary control and maintenance and other situations, the road section may be unobstructed during the next parking. Therefore, for this situation, it can be temporarily marked as a road section to be re-planned, and when driving to this road section to be re-planned according to the parking planning path next time, it may directly pass through this road section after re-navigation. At this time, the path of this section can be used as the navigation path of this road section to be re-planned and added to the parking planning path, so as to complete and improve the parking planning path.

[0096] In an exemplary embodiment of the present application, such as Figure 4As shown, in the entire parking planning path, the section between timestamp ta and timestamp tb is the section to be re-planned, while the sections between timestamp t1 and ta, and between timestamp tb and tn are normal parking planning paths. Then, the vehicle can park automatically along the section between t1 and ta. After reaching ta, it re-plans the path for the section between ta and tb by itself. After completing the driving of this section according to the re-planned path and reaching tb, the vehicle continues to drive along the original parking planning path for the section between tb and tn until parking is completed. Or after reaching ta, it can directly re-plan the path from ta to the target parking space and run along the re-planned path until it reaches the target parking space.

[0097] In an exemplary embodiment of the present application, before implementing the above two solutions, the section where the repeated path is located can be identified first, and this section can be one or more sections.

[0098] In an exemplary embodiment of the present application, identifying the section corresponding to the repeated path may include:

[0099] Obtain every two timestamps confirmed as repeated paths during the entire driving process of the vehicle and the mileage distances corresponding to the every two timestamps;

[0100] Detect whether all the obtained timestamps are continuous;

[0101] When all the obtained timestamps are continuous, obtain a continuous timestamp segment, and determine the section corresponding to the repeated path according to the start and end timestamps of the continuous timestamp segment and / or according to the mileage distance;

[0102] When all the obtained timestamps are not continuous, divide all the obtained timestamps into different continuous timestamp segments according to the breakpoints. For different continuous timestamp segments, determine the section corresponding to the repeated path respectively according to the start and end timestamps of each continuous timestamp segment and / or according to the mileage distance.

[0103] In an exemplary embodiment of the present application, when it is confirmed that the path between any two timestamps is a repeated path, the two timestamps and the corresponding mileage distances are recorded; for example, if it is recognized that the path between timestamp t3 and t4 is a repeated path, the path between timestamp t4 and t5 is a repeated path, the path between timestamp t8 and t9 is a repeated path, and the path between timestamp t9 and t10 is a repeated path, then the timestamps t3 and t4 and the corresponding mileage distance d1_4, the timestamps t4 and t5 and the corresponding mileage distance d1_5, the timestamps t8 and t9 and the corresponding mileage distance d1_9, and the timestamps t9 and t10 and the corresponding mileage distance d1_10 can be recorded respectively; hereinafter, it can be detected whether the timestamps t3, t4, t5, t6, t8, t9, and t10 are consecutive, that is, it can be detected whether the identifiers (such as serial numbers) 3, 4, 5, 6, 8, 9, and 10 of the timestamps are consecutive. Among them, 3, 4, 5, and 6 are consecutive respectively, and 8, 9, and 10 are consecutive respectively. Therefore, the timestamps t3, t4, t5, and t6 are consecutive respectively, and the timestamps t8, t9, and t10 are consecutive respectively. Thus, two consecutive timestamp segments are obtained, including consecutive timestamp segment 1 (from t3 to t6) and consecutive timestamp segment 2 (from t8 to t10).

[0104] In an exemplary embodiment of the present application, after obtaining one or more consecutive timestamp segments, the road segments corresponding to each consecutive timestamp segment can be used as the road segments corresponding to the repeated path, that is, the road segment between the start and end timestamps of the consecutive timestamp segment is used as the road segment corresponding to the repeated path.

[0105] In an exemplary embodiment of the present application, the road segments corresponding to the repeated path can also be determined respectively within each consecutive timestamp segment according to the mileage distance.

[0106] In an exemplary embodiment of the present application, the determination of the road segments corresponding to the repeated path according to the mileage distance may include:

[0107] Comparing the numerically largest mileage distance from all the obtained mileage distances;

[0108] The road segment between the two timestamps corresponding to the numerically largest mileage distance is used as the road segment corresponding to the repeated path.

[0109] In an exemplary embodiment of the present application, since within a consecutive timestamp segment, the repeated path may repeat in any shape, as shown in FIGS. 5(a), 5(b), 5(c), and 5(d), and among the repeated paths in any shape, only the two timestamps with the largest mileage distance (such as t3 and t6, and t8 and t10 in the above embodiment) can represent the road segment corresponding to the repeated path. Therefore, the recorded multiple mileage distances can be compared to determine the two timestamps corresponding to the largest mileage distance, and the road segment between these two timestamps is used as the road segment corresponding to the repeated path.

[0110] In an exemplary embodiment of the present application, before combining the non-repeating path during the entire driving process with the re-planned path as the parking planning path, the method may further include: obtaining the non-repeating path during the entire driving process.

[0111] In an exemplary embodiment of the present application, the obtaining the non-repeating path during the entire driving process may include:

[0112] Create a set composed of all timestamps and the vehicle running information corresponding to the all timestamps, denoted as the first set (i.e., the aforementioned set M);

[0113] Create a set composed of the timestamps corresponding to the repeating path and the vehicle running information corresponding to the timestamps corresponding to the repeating path, denoted as the second set (which can be denoted as set D);

[0114] Subtract the second set from the first set to obtain a third set (which can be denoted as set K); the third set is a set composed of the timestamps corresponding to the non-repeating path and the vehicle running information corresponding to the timestamps corresponding to the non-repeating path;

[0115] Take the path corresponding to any consecutive timestamps in the third set as the non-repeating path.

[0116] In an exemplary embodiment of the present application, as Figure 6 shown, is a schematic diagram of set M, set D, and set K.

[0117] In an exemplary embodiment of the present application, the obtaining the non-repeating path during the entire driving process may further include:

[0118] When the path between any two timestamps during the entire driving process is a non-repeating path, record the timestamps corresponding to the non-repeating path;

[0119] Create a set composed of the timestamps corresponding to the non-repeating path and the vehicle running information corresponding to the timestamps corresponding to the non-repeating path, denoted as the fourth set (which can be denoted as set K);

[0120] Take the path corresponding to any consecutive timestamps in the fourth set as the non-repeating path.

[0121] In an exemplary embodiment of the present application, after determining the non-repeating path through the above-described embodiment solution, the parking planning path under the condition of the existence of a repeating path can be obtained according to the two solutions given by the preset strategy in the foregoing solution. Finally, the obtained parking planning path can be generated into map data, thereby creating a parking map.

[0122] In an exemplary embodiment of the present application, during the process of constructing a parking path map for a vehicle, auxiliary devices such as a vehicle camera, lidar, IMU, or wheel speed sensor are used to create a driving path. Automated annotations are made on the driving path, marking multiple timestamps (each timestamp corresponding to a set of vehicle operation information). Based on these timestamps, duplicate paths can be identified, the duplicate paths can be optimized, and the starting and ending points (which can be identified by the starting point timestamp and the ending point timestamp) of the duplicate paths can be identified. For the corresponding sections of the road, a new path is planned and recommended to the driver, and the driver can determine whether to use the new path to replace the original duplicate path, avoiding the user from cruising on useless paths when using automatic parking, and improving the usage efficiency of the automatic parking function and the user experience.

[0123] An embodiment of the present application also provides a parking path mapping device 1, as Figure 7 shown. The device includes: a camera 11, a positioning device 12, an object detection device 13, a vehicle state detection device 14, a first processor 15, and a first computer-readable storage medium 16. The first computer-readable storage medium 16 stores a first instruction, and when the first instruction is executed by the first processor 15, the parking path mapping method described above is implemented.

[0124] In an exemplary embodiment of the present application, any of the above-described embodiments of the parking path mapping method is applicable to this device embodiment, and will not be elaborated here one by one.

[0125] An embodiment of the present application also provides a parking method, as Figure 8 shown. The method may include steps S401 - S402:

[0126] S401. Retrieve the parking planning path obtained according to the above-described parking path mapping method;

[0127] S402. Park the vehicle according to the parking planning path.

[0128] In an exemplary embodiment of the present application, any of the above-described embodiments of the parking path mapping method is applicable to this parking method embodiment, and will not be elaborated here one by one.

[0129] In an exemplary embodiment of the present application, based on the solution of marking the section to be re-planned in the parking path mapping method, the following solution can be executed during parking.

[0130] In an exemplary embodiment of the present application, before parking according to the parking planning path, the method may further include:

[0131] Detect whether the parking planning path contains a mark of the section to be re-planned;

[0132] When the mark exists, abandon parking according to the parking planning path, and park according to a parking path different from the parking planning path used historically; or, select to park according to the parking planning path;

[0133] When the mark does not exist, select to park according to the parking planning path.

[0134] In an exemplary embodiment of the present application, the parking according to the parking planning path may include:

[0135] When the mark does not exist, drive along the parking planning path to complete parking;

[0136] When the mark exists, for the path in the parking planning path where the section to be re-planned is not marked, drive along this path, and when reaching the section to be re-planned during driving, perform path planning on the section to be re-planned, and drive along the planned path to complete the section to be re-planned until parking is completed.

[0137] An embodiment of the present application also provides a parking device 2, as Figure 9 shown, the device may include: a second processor 21 and a second computer-readable storage medium 22. Second instructions are stored in the second computer-readable storage medium 22, and when the second instructions are executed by the second processor 21, the parking method described above is implemented.

[0138] In an exemplary embodiment of the present application, any of the foregoing embodiments of the parking method is applicable to the embodiment of this parking device, and will not be elaborated here one by one.

[0139] Those of ordinary skill in the art will understand that all or some of the steps in the methods disclosed above, and the functional modules / units in systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof. In the hardware implementation, the division of functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be executed by several physical components in cooperation. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

Claims

1. A parking path mapping method, characterized in that, The method includes: Marking a plurality of different timestamps during the vehicle's driving towards the target parking space, and recording the vehicle running information corresponding to each of the timestamps, where the vehicle running information includes: odometer information and vehicle coordinate information; Detecting whether there is a repeated path during the entire driving process according to the vehicle running information corresponding to a plurality of different timestamps, including: calculating whether the path between two timestamps is a repeated path according to the odometer information and the vehicle coordinate information corresponding to any two timestamps; when the path between any two timestamps during the entire driving process is a repeated path, determining that there is a repeated path during the entire driving process; when the path between any two timestamps during the entire driving process is a non-repeated path, determining that there is no repeated path during the entire driving process; When it is detected that there is no repeated path during the entire driving process, taking the path traveled by the vehicle during the entire driving process as the parking planning path; when it is detected that there is a repeated path during the entire driving process, identifying the section corresponding to the repeated path, re-planning the path for this section, and combining the non-repeated path during the entire driving process with the re-planned path as the parking planning path; Saving the parking planning path as map data to complete the construction of the parking path map.

2. The parking path mapping method according to claim 1, wherein The calculating whether the path between two timestamps is a repeated path according to the odometer information and the vehicle coordinate information corresponding to any two timestamps includes: Subtracting the odometer information corresponding to any two timestamps to obtain the mileage distance between the two timestamps; Subtracting the vehicle coordinate information corresponding to any two timestamps to obtain the coordinate distance between the two timestamps; When the mileage distance is greater than or equal to the sum of the coordinate distance and the preset calibration distance, confirming that the path between the two timestamps is a repeated path; When the mileage distance is less than the sum of the coordinate distance and the preset calibration distance, confirming that the path between the two timestamps is a non-repeated path.

3. The parking path mapping method according to claim 2, wherein Identifying the section corresponding to the repeated path includes: Obtaining each two timestamps confirmed as repeated paths during the entire driving process of the vehicle and the corresponding mileage distance for each two timestamps; Detecting whether all the obtained timestamps are continuous; When all the obtained timestamps are continuous, obtaining a continuous timestamp segment, and determining the section corresponding to the repeated path according to the start and end timestamps of the continuous timestamp segment and / or according to the mileage distance; When all the obtained timestamps are not continuous, dividing all the obtained timestamps into different continuous timestamp segments according to the breakpoints, and for different continuous timestamp segments, respectively determining the section corresponding to the repeated path according to the start and end timestamps of each continuous timestamp segment and / or according to the mileage distance.

4. The parking path mapping method according to claim 2, characterized in that Before combining the non-repeated path during the entire driving process with the re-planned path as the parking planning path, the method further includes: obtaining the non-repeated path during the entire driving process.

5. The parking path mapping method according to claim 4, wherein, The obtaining the non-repeated path during the entire driving process includes: Creating a set composed of all the timestamps and the vehicle running information corresponding to all the timestamps, denoted as the first set; Create a set composed of the timestamps corresponding to the repeated paths and the vehicle operation information corresponding to the timestamps corresponding to the repeated paths, denoted as the second set; Subtract the second set from the first set to obtain a third set; the third set is a set composed of the timestamps corresponding to the non-repeated paths and the vehicle operation information corresponding to the timestamps corresponding to the non-repeated paths; Take the paths corresponding to any consecutive timestamps in the third set as the non-repeated paths.

6. The parking path mapping method according to claim 4, wherein, The obtaining of the non-repeated paths in the entire driving process includes: When the path between any two timestamps in the entire driving process is a non-repeated path, record the timestamps corresponding to the non-repeated path; Create a set composed of the timestamps corresponding to the non-repeated paths and the vehicle operation information corresponding to the timestamps corresponding to the non-repeated paths, denoted as the fourth set; Take the paths corresponding to any consecutive timestamps in the fourth set as the non-repeated paths.

7. A parking path mapping device, characterized in that, The device includes: a camera, a positioning device, an object detection device, a vehicle state detection device, a first processor, and a first computer-readable storage medium. The first computer-readable storage medium stores a first instruction. When the first instruction is executed by the first processor, the parking path mapping method described in any one of claims 1-6 is implemented.

8. A parking method, characterized in that, The method includes: Retrieve the parking planning path obtained according to the parking path mapping method described in any one of claims 1-6; Park the vehicle according to the parking planning path.

9. A parking device, characterized in that, The device includes: a second processor and a second computer-readable storage medium. The second computer-readable storage medium stores a second instruction. When the second instruction is executed by the second processor, the parking method described in claim 8 is implemented.

Images