Method, device, apparatus, storage medium and program product for autonomous parking

Abstract

The disclosed embodiments relate to methods, devices, equipment, storage media and program products for autonomous parking, and relate to the field of autonomous parking. The method for autonomous parking includes determining a common area associated with one or more candidate parking routes of the vehicle based on the historical position of the vehicle in a first time period; obtaining one or more candidate parking routes of the vehicle based on one or more historical parking routes of the vehicle in the common area, wherein the one or more historical parking routes include at least one of a parking entry route and a parking exit route; and in response to determining that the vehicle is in a common area, providing the vehicle with the obtained one or more candidate parking routes for the vehicle to park in or out. In this way, the user can be exempted from the manual route setting process, lower the threshold for use, improve the user experience, and improve the practicality and usage rate of the autonomous parking function. Moreover, the pressure on the computing device can be reduced and the hardware cost can be reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous parking, and more particularly, to a method, apparatus, electronic device, computer storage medium, and computer program product for autonomous parking. Background Art

[0002] In the autonomous driving technology, autonomous parking can provide great convenience for users. Autonomous parking technology can help users complete the parking process automatically or semi-automatically without relying on user operation. The parking process can include a parking process or a parking process. The current parking process depends on the user's creation of a parking route. In other words, the user needs to drive to the starting point of the parking route to set the starting point, then drive to the end point of the parking route to set the end point, and finally wait for the parking route to be generated. Summary of the invention

[0003] According to an example embodiment of the present disclosure, a solution for autonomous parking is provided.

[0004] In a first aspect of the present disclosure, a method for autonomous parking is provided. The method includes: determining a common area associated with one or more candidate parking routes of the vehicle based on a historical position of the vehicle within a first time period; acquiring one or more candidate parking routes of the vehicle based on one or more historical parking routes of the vehicle in the common area, the one or more historical parking routes including at least one of a parking entry route and a parking exit route; and in response to determining that the vehicle is in the common area, providing the vehicle with the acquired one or more candidate parking routes for the vehicle to park in or out.

[0005] In a second aspect of the present disclosure, an apparatus for autonomous parking is provided. The apparatus includes a common area determination module configured to determine a common area associated with one or more candidate parking routes of the vehicle based on a historical position of the vehicle within a first time period; a candidate parking route acquisition module configured to acquire one or more candidate parking routes of the vehicle based on one or more historical parking routes of the vehicle in the common area, wherein the one or more historical parking routes include at least one of a parking entry route and a parking exit route; and a candidate parking route providing module configured to provide the vehicle with the acquired one or more candidate parking routes in response to determining that the vehicle is in the common area, for the vehicle to park in or out.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The electronic device includes one or more processors; and a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to the first aspect of the present disclosure.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0008] In a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, and when the computer program is executed by a processor, the computer program performs the method according to the first aspect of the present disclosure.

[0009] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] Figure 1 A schematic diagram illustrating an example environment in which various embodiments of the present disclosure can be implemented;

[0012] Figure 2 A flowchart showing a process for autonomous parking according to an embodiment of the present disclosure is shown;

[0013] Figure 3 A flowchart of obtaining a parking route for autonomous parking according to an embodiment of the present disclosure is shown;

[0014] Figure 4 A flowchart of obtaining a parking route for autonomous parking according to an embodiment of the present disclosure is shown;

[0015] Figure 5 A schematic block diagram showing an apparatus for determining a state of an object according to an embodiment of the present disclosure; and

[0016] Figure 6 A block diagram of a computing device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0019] As mentioned above, during the automatic parking process of a vehicle (preferably a smart driving vehicle), the user is required to drive to the starting point of the parking route to set the starting point, then drive to the end point of the parking route to set the end point, and finally wait for the parking route to be generated.

[0020] Traditionally, there are two solutions for the generation of autonomous parking routes. In one solution, the generation of parking routes requires the user to set the route starting point after driving to the parking route, and to perform simultaneous localization and mapping (SLAM) of the route while starting to drive the car to the end point of the route. The mapping is completed after the user sets the end point, and the route is saved and learned according to the route type and parking space type set by the user. As is well known to those skilled in the art, SLAM information is a method of tracking the position of a robot or vehicle in the world in real time and identifying the position of landmarks (such as buildings, obstacles, road signs and other object features).

[0021] In another solution, the background performs route training and saves according to the user's automatic mapping information.

[0022] However, no matter which of the above solutions is used, users are required to actively create routes, that is, users are required to actively inform the on-board computing device or cloud route information. Such technical means result in high user barriers and poor user experience. Moreover, driving the car to the end of the route while performing simultaneous positioning and mapping SLAM on the route requires high computing power of the computing device or system, which in turn increases hardware costs.

[0023] In order to at least partially solve the above problems and other potential problems, this paper proposes a solution for autonomous parking. In this solution, it is possible to determine the common areas based on the locations where the vehicle often appears, and autonomously learn the route after the vehicle enters the common area. After the path is determined by autonomous learning and verified, when the vehicle enters the common area again, the verified route is actively recommended to the vehicle for the vehicle to autonomously park in or out. Moreover, when obtaining the surrounding environment information of the garage, it can be obtained without relying on or not completely relying on the on-board camera. In this way, the user can be exempted from the manual route setting process, lower the threshold of use, improve the user experience, and improve the practicality and utilization rate of the autonomous parking function. Moreover, it can reduce the pressure on computing equipment and reduce hardware costs.

[0024] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 A schematic diagram of an example environment 100 in which multiple embodiments of the present disclosure can be implemented is shown. In the example environment 100, a vehicle 1 and a parking area 3 may be included. The vehicle 1 may be any motor vehicle or non-motor vehicle, such as a car, a truck, a motorcycle, a bus, an electric car, a police car, a fire truck, or other vehicles that perform special operations. The parking area 3 may be a fixed parking lot (such as a shopping mall parking lot, a dedicated parking lot, or a community ground or underground parking lot, etc.), a temporary parking lot, or other suitable parking areas, such as locations where vehicles often park, including locations with parking space lines or temporary parking spots without parking space lines, etc.

[0026] In some embodiments, the parking area 3 may have one or more entrances or exits. Accordingly, the parking area 3 may have one or more parking routes corresponding to the vehicle 1. It should be noted that the parking route may include a parking entry route or a parking exit route. Accordingly, according to the specific configuration of the parking area 3, the parking entry route and the parking exit route may be one or more.

[0027] In one embodiment, Figure 1 As shown, the vehicle 1 may have three parking routes 101-1, 101-2 and 101-3 (also collectively referred to as parking routes 101), and the vehicle 1 may park in the parking space 121 via any one of the three parking routes. It should be noted that the three routes are merely exemplary, and the parking routes may also include any other suitable number of routes, such as only one, two, four, six or more, which is not limited in the present disclosure.

[0028] In this embodiment, continue to refer to Figure 1, vehicle 1 may also have three exit routes 111-1, 111-2 and 111-3 (also collectively referred to as exit routes 111). Vehicle 1 may leave parking space 121 via any of the three exit routes. It should be noted that the three routes are merely exemplary, and the exit routes may include any other suitable number of routes, such as only one, two, four, six or more, which is not limited in the present disclosure. It should also be noted that, Figure 1 The embodiment is merely exemplary, and the number of parking routes and parking routes does not have to be the same.

[0029] The above-mentioned parking routes 101-1, 101-2 and 101-3 and parking routes 111-1, 111-2 and 111-3 are historical tracks of vehicle parking in or out, and thus can be referred to as historical parking routes or historical parking tracks. It should be noted that routes, tracks and paths belong to the same or similar concepts in the present disclosure and can also be used interchangeably in the context of the present disclosure.

[0030] In some embodiments, continue to refer to Figure 1 In the environment 100, the frequently used area 5 can be determined based on the historical position of the vehicle 1 in the first time period. The first time period can be predetermined, for example, it can be set to any suitable number of days such as 5 days, 7 days, 10 days, etc. The historical position can correspond to the location point of the fixed parking lot, temporary parking lot or other suitable parking area in the parking area 3 mentioned above, for example Figure 1 The position point of the parking space 121 or the position point at which other vehicles appear within the parking area 3 is shown.

[0031] The following will take the first time period of 7 days and vehicle 1 parking in or out of parking area 3 as an example to continue combining Figure 1 Here we will introduce how to determine the commonly used area 5.

[0032] In this embodiment, the location information of the current location of the vehicle 1 can be recorded after the ignition of the vehicle 1. Specifically, the location information of the vehicle 1 can be determined by the vehicle-mounted GPS of the vehicle 1. In some embodiments, when the vehicle 1 is in an area such as an underground parking lot, its location information sometimes cannot be effectively read, and the location information recorded by the vehicle for the last time can be read. It should be noted that GPS acquisition of location information is only exemplary, and location information can also be acquired by other means, such as WIFI positioning, base station positioning or Beidou satellite positioning.

[0033] In such an embodiment, when the number of times that the vehicle 1 appears in the parking area 3 in the past 7 days is not less than the first threshold, the range associated with the parking area 3 can be determined as the frequently used area 5. Specifically, the parking area can be directly determined as the frequently used area 5. In other words, the frequently used area can be determined based on the frequency of the appearance of the vehicle 1 in the first time period of 7 days. The first threshold can be set by the system as needed, or by the user as needed, and the present disclosure does not limit this. For example, the first threshold can be set to 3 times, 4 times, etc.

[0034] In another embodiment, the commonly used area 5 can be determined by first determining a position point corresponding to the historical position of the vehicle in the manner described above. As described above, the position point can correspond to the parking space 121. In this embodiment, the predetermined area can be first determined based on the position point corresponding to the parking space 121 and the first predetermined distance. The first predetermined distance can be set by the system or the user as needed, for example, 200 meters, 1000 meters or any other suitable distance, and the present disclosure does not limit this. It should be noted that a circular predetermined area can be determined in this way, but the shape of the predetermined area can also be other shapes, such as a rectangle, a polygon or other irregular shapes.

[0035] In such an embodiment, after the predetermined area is determined based on the position point and the first predetermined distance, the predetermined area can be determined as the frequently used area 5 in response to the number of times the vehicle 1 appears in the predetermined area within the first time period being not less than the first threshold. In this way, the frequently used area 5 can be accurately determined.

[0036] In another embodiment, when there may be multiple location points corresponding to the historical location of the vehicle 1 in the parking area 3 (for example, there are multiple parking spaces 121 available for parking in the same parking area 3 or multiple valid location points are obtained through GPS), then there may be multiple predetermined areas determined by the above embodiment. Depending on the first predetermined distance, there may be overlapping areas in each predetermined area. In this case, after determining multiple predetermined areas based on multiple location points and the first predetermined distance, when it is determined that at least two of the multiple predetermined areas overlap, the at least two predetermined areas can be determined as the commonly used areas 5. Through such an arrangement, the scope of the commonly used area 5 can be expanded to cover all possible parking spaces 121, so as to more accurately and effectively prompt the vehicle 1 to park in or out.

[0037] It should be noted that when a new frequently used area 5 is created, the determination of the initial position point usually requires that the position point is located outside other frequently used areas 5 that have been determined. This is because if the initially determined position point is located in a frequently used area 5 that has been previously determined, the operation step of "obtaining candidate parking routes through historical parking routes" after determining the frequently used area 5 has been triggered, which will be explained in more detail below.

[0038] It should also be noted that although Figure 1 In the illustrated embodiment, the range of the commonly used area 5 is larger than the range of the parking area 3 , but this is merely exemplary, and the range of the commonly used area 5 may also be equal to or smaller than the range of the parking area 3 , which is not limited in the present disclosure.

[0039] Continue to refer Figure 1 , each of the above embodiments for determining the frequently used area 5 can be implemented by a computing device 130 or a corresponding system. In some embodiments, the computing device 130 may include a desktop computer, a tablet computer, a personal digital assistant (PDA), a server, a host, etc., or any other processor-enabled device capable of wired data communication or wireless data communication. The computing device 130 may be any computing device disposed outside the vehicle 1, and may also be preferably disposed on or in the vehicle 1, that is, the computing device 130 may be a vehicle-mounted computing device. In some embodiments, the computing device 130 may also be connected to the Internet via a wired or wireless manner to upload the above-mentioned relevant data for obtaining the frequently used area 5 to the cloud 140.

[0040] It should be noted that the cloud 140 only provides a preferred method, which is not necessary. This is because, when the network status is good, the vehicle can support cloud 140 computing and learning, and can mainly rely on cloud 140 computing and learning. When the network status is poor or disconnected, computing and learning can be performed through the computing device 130. In other words, depending on the network environment, the system under the environment 100 can effectively switch between local computing and cloud computing to meet the usage requirements in different scenarios.

[0041] It should be noted that the operations and steps to be performed in the environment 100 can be similarly processed by the computing device 130 and the cloud 140. That is, the computing and learning methods of the computing device 130 and the cloud 140 can be applied to all the steps described below. This will not be repeated below.

[0042] In some embodiments, continue to refer to Figure 1After determining the common area 5, one or more candidate parking routes of the vehicle 1 may be obtained based on one or more historical parking routes of the vehicle 1 in the common area 5. As described above, the one or more historical parking routes include one or more of parking entry routes (e.g., parking entry routes 101-1, 101-2, and 101-3) and parking exit routes (e.g., parking exit routes 111-1, 111-2, and 111-3).

[0043] In one embodiment, one or more historical parking routes may be determined by "silent learning", and one or more candidate parking routes of the vehicle may be obtained based on the one or more historical parking routes of the vehicle in the common area in a "silent" manner. In the computer field, silent mode generally refers to a mode in which a computer program processes a specific situation by itself without alerting the user, so as not to affect the normal operation of the user.

[0044] In one embodiment, when acquiring one or more candidate parking routes of the vehicle 1, one or more historical parking routes (e.g., parking entry routes 101-1, 101-2, and 101-3 or parking exit routes 111-1, 111-2, and 111-3) may be determined in response to the number of times the vehicle 1 is in the common area 5 being not less than a second threshold. In the above operation, determining one or more historical parking routes (e.g., parking entry routes 101-1, 101-2, and 101-3 or parking exit routes 111-1, 111-2, and 111-3) may include determining the specific number of one or more historical parking routes. The second threshold may be set by the system or by the user according to actual needs. For example, the second threshold may be set to 5 times, preferably 7 times, 8 times, 10 times, or any other suitable number. The purpose is to involve all possible parking entry routes or parking exit routes as much as possible through the number of times the vehicle 1 appears in the common area 5, so as to ensure that the above silent learning process can cover all possible routes.

[0045] It should be noted that, in the above embodiment, it is not necessary to set a predetermined time period to determine one or more historical parking routes (such as parking routes 101-1, 101-2 and 101-3 or parking routes 111-1, 111-2 and 111-3). That is, after determining that the common area 5 is a familiar area, the number of times the vehicle 1 is in the common area 5 can be counted within an arbitrarily long time period in the hope of learning as many routes as possible. It should be understood that those skilled in the art can also set the length of the predetermined time period according to actual needs, such as 20 days, 30 days or any other suitable number of days.

[0046] In addition, it should be noted that, for different situations of parking in and out, learning of not less than a second threshold value (e.g., 7 times) can be performed in the same frequently used area 5 in both the parking in and the parking out directions, so as to record all historical parking routes of the user in the current frequently used area 5 (e.g., parking in routes 101-1, 101-2, and 101-3 or parking out routes 111-1, 111-2, and 111-3). Figure 3 and Figure 4 The process of obtaining parking routes and parking routes is introduced in detail.

[0047] In one embodiment, continue to refer to Figure 1 , the example environment 100 may also include a camera 123 for acquiring the surrounding environment information of the commonly used area 4 or the parking area 3. In one embodiment, the camera 123 may be a vehicle-mounted camera of the vehicle 1, such as a front-view camera, a surround-view camera, etc., and the number thereof may be one or more. In such an embodiment, the environmental information of the commonly used area 5 or the parking area 3, such as SLAM information, may be acquired through the camera 123 while the vehicle 1 is parked or moving in the parking area 3. For example, the environmental information of the parking area 3 may be first acquired through the camera 123 during the process of determining the commonly used area 5, and the environmental information acquired by determining the commonly used area 5 may be used as the baseline environmental information.

[0048] In this way, after the frequently used area 5 is determined, when the vehicle 1 enters the frequently used area 5 again, the camera 123 can continue to obtain the environmental information corresponding to the successfully learned current route, such as SLAM information. Then, the environmental information of the successfully learned current route can be compared with the reference environmental information to determine one or more historical parking routes (such as one or more of the parking entry routes 101-1, 101-2 and 101-3 or the parking exit routes 111-1, 111-2 and 111-3) of the frequently used area 5 based on the comparison result.

[0049] In one embodiment, the result of the comparison is achieved based on the degree of matching. That is, when the result of the environmental information comparison is not less than the predetermined degree of matching, the current route that has been successfully learned can be determined as an available historical parking route. When the degree of matching is not enough, the current route learning fails, and the current route that has been successfully learned cannot be determined as an available historical parking route. Alternatively, the comparison based on environmental information can be a process of validating the parking route, and only when the commonly used area 5 is triggered and the environmental information of the previous location information matches. Once the match is successful, the route status is changed to "completed", and the historical parking route can be provided to the vehicle as a candidate parking route in subsequent operations for autonomous parking.

[0050] In this way, after the environmental information obtained in the above manner is compared with the reference environmental information, it can be determined whether the parking space 121 in the current parking area 3 is a temporary parking space or a fixed parking space based on the comparison result.

[0051] In other embodiments, the camera 123 may also be a camera installed in the parking area 3, and the number of the camera 123 may be one or more. In this way, the camera 123 can obtain the environmental information of the parking area 3 in real time, and does not rely on the vehicle-mounted computing device to perform real-time calculations, thereby reducing the high requirements of the computing device 130 on the software and hardware capabilities without affecting the performance.

[0052] In such an embodiment, the environmental information captured by the camera 123 can be transmitted directly to the computing device 130 or transmitted to the computing device 130 through the vehicle. In addition, the environmental information captured by the camera 123 can also be transmitted to a separate computing device different from the computing device 130, and the present disclosure is not limited to this.

[0053] It should be noted that the timing for the camera 123 to obtain environmental information can be set according to actual needs, for example, when the camera 123 is located on the vehicle 1 and the vehicle 1 is started or when the vehicle 1 is moving, or when the camera 123 is located in the parking area 3, any appropriate time, and the present disclosure does not impose any restrictions on this.

[0054] In one embodiment, continue to refer to Figure 1 , when the comparison result is lower than the predetermined matching degree, in response to the vehicle 1 being in a historical parking route in the historical parking route again, the historical parking route in the historical parking route can be acquired again. In this embodiment, due to various reasons, such as vehicle failure, equipment failure, environmental change, obstacle blocking, etc., during the learning process of a certain route in the historical parking route, the route may not be successfully learned once, so the result of the initial comparison may be lower than the predetermined matching degree, resulting in route verification failure. In order to avoid missing available routes, the vehicle 1 can perform multiple learning processes for the route when entering the common area 5 again, and re-verify the route after multiple learning, so as to obtain a more accurate parking route result. It should be noted that the matching degree can be set by the computing device 130 or the system according to actual conditions, or it can be set by the user. In addition, the number of multiple learnings is not limited in this disclosure.

[0055] In one embodiment, a second time period may be set when multiple trips of learning are performed. The second time period may be set to, for example, 8 days or 10 days. If the routes learned from multiple trips still fail to pass the comparison or verification steps described above within the second time period, the historical parking route is cleared and is no longer used as an alternative candidate parking route. Once the comparison or verification is passed within the second time period, the historical parking route is confirmed as an alternative candidate parking route, so that a route recommendation can be performed when the frequently used area 5 is triggered again in the future.

[0056] Therefore, in the embodiment of the present disclosure, after the historical parking route is successfully learned, the successfully learned route can be compared or verified. Once the comparison or verification is successful, the historical parking route can be determined as a candidate parking route. In the case of a comparison failure, multiple learning operations can be performed, and the parking routes after multiple learning can be verified, and further based on the comparison results, it is determined whether to determine the historical parking route as a candidate parking route. For the historical parking route that failed to learn or verify, its status can be changed to invalid, and no other operations are performed.

[0057] In one embodiment, in response to the number of times that the at least one provided candidate parking route is not used being higher than a fourth threshold, at least one candidate parking route may be invalidated. The fourth threshold may be user-defined or set by the computing device 130 or the system. The fourth threshold may be any suitable value such as 5 times, 6 times, 8 times, etc. Taking 5 times as an example, when the candidate parking route is recommended to the vehicle 5 times but is not adopted each time, the computing device 130 or the system may determine that the route is unavailable or erroneous, and thus change its status to invalid, and no longer recommend it to the vehicle when the frequently used area 5 is subsequently triggered.

[0058] In some embodiments, if the frequently used area 5 under the current parking direction has met the learning times requirement, but the current routes are all in an invalid state, all route data under the current frequently used area 5 can be cleared after a certain period of time (e.g., 7 days), and the state of the frequently used area 5 can be initialized, and the silent learning times can be set to 0. After initialization, it can also support re-learning, management, and recommendation of routes when frequently used areas 5 are re-created later.

[0059] In some embodiments, continue to refer to Figure 1In response to the acquired historical parking routes of the vehicle 1 including two or more parking routes (e.g., parking routes 101-1, 101-2, and 101-3), the two or more parking routes with at least a portion of characteristics consistent may be determined as a single parking route, or the portion of the two or more parking routes with consistent characteristics may be determined as a single parking route. Accordingly, in response to the acquired historical parking routes of the vehicle including two or more parking routes (e.g., parking routes 111-1, 111-2, and 111-3), the two or more parking routes with at least a portion of characteristics consistent may be determined as a single parking route, or the portion of the two or more parking routes with consistent characteristics may be determined as a single parking route. That is, the embodiments of the present disclosure may perform different fusion mechanisms for the parking routes 101-1, 101-2, and 101-3 and the parking routes 111-1, 111-2, and 111-3.

[0060] In this embodiment, parking routes 101-1, 101-2 and 101-3 are taken as examples. Figure 1 In the example, the parking routes 101-1 and 101-2 are close to each other. If the computing device 130 or the system determines that the parking routes 101-1 and 101-2 have similar characteristics, for example, if there are similar routes of 5m or more (i.e., having several common feature points), the parking routes 101-1 and 101-2 are merged. In one embodiment, the two parking routes 101-1 and 101-2 can be merged and directly merged into the same parking route. This is because, due to the different widths of the lanes, in the case of the same entrance, the trajectories of the parking routes may be different, but they still belong to the same parking route in essence. In this way, data redundancy can be reduced and the calculation pressure of the system can be reduced.

[0061] In another embodiment, the parts of the docking routes 101-1 and 101-2 with the same characteristics can be merged into one docking route, while the original paths can be retained for other inconsistencies. This can reduce the amount of data calculation and reduce system pressure.

[0062] In such an embodiment, continue to refer to Figure 1 , the parking route 101 - 3 is far from the parking routes 101 - 1 and 101 - 2 , and therefore there is no consistency in characteristics, and the route map fusion for the parking route 101 - 3 is not performed.

[0063] exist Figure 1In the illustrated embodiment, the fusion mechanism of the outgoing routes 111 - 1 , 111 - 2 , and 111 - 3 is substantially similar to the fusion mechanism of the incoming routes 101 - 1 , 101 - 2 , and 101 - 3 , and will not be described in detail in the present disclosure.

[0064] It should be noted that any other suitable fusion mechanism may be adopted according to actual needs, and the present disclosure does not limit this.

[0065] Figure 2 1 shows a flow chart of a process for autonomous parking according to an embodiment of the present disclosure. In order to more clearly understand the solution for autonomous parking provided by the embodiment of the present disclosure, reference will be made to Figure 1 To further describe the embodiments of the present disclosure. Process 200 may be performed by Figure 1 The computing device 130 and / or the cloud 140 can be implemented.

[0066] At block 210 , a frequently visited area 5 associated with one or more candidate parking routes of the vehicle 1 is determined based on the historical location of the vehicle during a first time period.

[0067] In some embodiments, as described above, the historical location may correspond to a location point of a fixed parking lot, a temporary parking lot, or other suitable parking area in the parking area 3 described above, for example Figure 1 The position point of the parking space 121 or the position point at which other vehicles appear within the parking area 3 is shown.

[0068] In some embodiments, the frequently used area 5 may be an area where the vehicle 1 frequently appears, for example, a familiar road range or area where the vehicle 1 frequently appears 3 times or more within 7 days as described above. Figure 1 The commonly used area 5 is encircled by the middle dotted circle. It should be noted that the commonly used area can also be such a familiar road range or area determined by other parameters, for example, it can also be circled by the vehicle 1 according to other preset rules or pre-set after big data analysis of the driving trajectory of the vehicle 1, and the present disclosure does not limit this.

[0069] In some embodiments, a location point corresponding to a historical location of the vehicle 1 can be determined; and based on the location point and a first predetermined distance, a predetermined area can be determined; and in response to the number of times the vehicle appears in the predetermined area within a first time period being not less than a first threshold, the predetermined area can be determined as a commonly used area 5.

[0070] In such an embodiment, the historical location corresponds to, for example, Figure 1 The first predetermined distance can be set by the user or the system as needed. According to the above, the first threshold is associated with the number of times the vehicle 1 appears in the parking area 3, for example, 3 times or more in 7 days, so that the familiar road range as described above can be determined.

[0071] In some embodiments, multiple location points corresponding to the historical location of the vehicle can also be determined; multiple predetermined areas can be determined based on the multiple location points and the first predetermined distance; and in response to determining that at least two of the multiple predetermined areas overlap, the at least two predetermined areas can be determined as commonly used areas.

[0072] In such an embodiment, Figure 1 As shown, the position point may correspond to the position point where the parking space 121 is located. In the above manner, when a plurality of predetermined areas overlap, the plurality of predetermined areas may be determined as a common area according to a preset rule.

[0073] In block 220 , one or more candidate parking routes of the vehicle 1 are obtained based on one or more historical parking routes of the vehicle 1 in the common area 5 , wherein the one or more historical parking routes include at least one of a parking entry route and a parking exit route.

[0074] In such an embodiment, the historical parking route may be, for example, Figure 1 The candidate parking routes may include all the routes of the parking routes 101-1, 101-2 and 101-3 or the parking routes 111-1, 111-2 and 111-3 that have been successfully matched or verified as described above.

[0075] In one embodiment, as described above, in the process of acquiring candidate parking routes, the historical parking routes can be acquired through the "silent learning" mode as described above. As is well known in the art, in the computer field, the silent mode generally refers to a mode in which a computer program processes itself when a specific situation occurs without alerting the user, so as not to affect the normal operation of the user. In this way, all commonly used parking routes can be automatically recorded without the need for manual operation by the user, so as to be provided to the vehicle 1 when the trigger condition is met, thereby assisting the vehicle in autonomous parking.

[0076] It should be understood that the above-mentioned method for determining the familiar road range or area can also be silent, and does not require the user to manually operate to set it, so as to improve the user experience.

[0077] In some embodiments, in response to the number of times the vehicle 1 is in the common area 5 being not less than a second threshold, one or more historical parking routes may be determined; and based on the one or more historical parking routes, one or more candidate parking routes of the vehicle 1 may be obtained.

[0078] In some embodiments, the second threshold value can be set by the system or by the user according to actual needs. For example, as described above, the second threshold value can be set to 5 times, preferably 7 times, 8 times, 10 times or any other suitable number. The purpose is to involve all possible parking routes or parking routes as much as possible to ensure that the silent learning process can cover all possible routes.

[0079] In block 230 , in response to determining that the vehicle 1 is located in the common area 5 , the obtained one or more candidate parking routes are provided to the vehicle for parking in or out of the vehicle.

[0080] In some embodiments, providing one or more candidate parking routes to the vehicle 1 may be performed in any suitable manner such as voice, text push, video, image, etc. In some embodiments, providing the candidate parking routes to the vehicle may also send the routes to the vehicle terminal or to other terminal devices, such as the vehicle user's mobile phone, etc.

[0081] In some embodiments, in response to the number of times that the at least one candidate parking route provided has not been used being higher than a fourth threshold, the at least one candidate parking route may be invalidated.

[0082] In some embodiments, the fourth threshold may be any suitable value such as 5 times, 6 times, 8 times, etc. Taking 5 times as an example, when the candidate parking route is recommended to the vehicle 5 times but is not adopted each time, the computing device 130 or the system may determine that the route is unavailable or wrong, and thus change its status to invalid, and no longer recommend it to the vehicle when the frequently used area 5 is subsequently triggered. In this way, a mode of invalidating the candidate parking route is provided.

[0083] Figure 3 FIG. 3 is a flowchart of obtaining a parking route for autonomous parking according to an embodiment of the present disclosure. Figure 1 The computing device 130 and / or cloud 140 shown in the figure are implemented. In order to more clearly understand the solution for autonomous parking provided by the embodiment of the present disclosure, reference will be made to Figure 1 To further describe the embodiments of the present disclosure. Figure 3 In the example shown, process 300 may include block 310 , optional block 320 , and block 330 .

[0084] like Figure 3 As shown, in box 310, it can be determined whether the vehicle 1 is in the common area 5. Specifically, in one embodiment, it can be determined whether the vehicle 1 is in the common area 5 when the vehicle 1 located in the parking space 123 is started. Figure 1 As shown, in this embodiment, the vehicle 1 is located in the parking space 121. Therefore, the common area 5 is triggered when the vehicle 1 is started, that is, the vehicle 1 starts the silent learning of the parking route.

[0085] Take route 111-1 as an example. When vehicle 1 is started and vehicle 1 is located in parking space 121, silent learning of the parking route is triggered. The silent learning and recording of the route can be performed directly by computing device 130, or by cloud 140, or by both. When vehicle 1 leaves common area 5, that is, away from intersection 112-1 of route 111-1 with common area 5, vehicle 1 is no longer located in common area 5, and silent learning can be terminated to obtain the parking route of vehicle 1 in box 330. Subsequently, as described above, parking route 111-1 can be determined as a historical parking route. And, if the historical parking route passes the comparison or validity check, it can be provided to vehicle 1 as a candidate parking route for autonomous parking of the vehicle.

[0086] Similarly, the parking exit routes 111-2 and 111-3 may be acquired in block 330 through the starting point of the parking space 121 and the intersection points 112-2 and 112-3 of the path with the frequently used area 5, and may be determined as candidate parking routes in a similar manner.

[0087] At optional block 320, a route for vehicle 1 to travel a second predetermined distance from the historical location may be determined in response to vehicle 1 being within frequent area 5. Figure 1 In the illustrated embodiment, as described above, the historical position corresponds to the position of the parking space 121. It should be understood that the historical position can also be used in any other way to determine the position of the frequently used area 5, and the present disclosure does not limit this.

[0088] Continuing to take the parking route 111-1 as an example, in such an embodiment, the second predetermined distance can be set by the computing device 130 or its system, or can be set by the user. The second predetermined distance can be any suitable distance, such as 450m, 500m, 1000m, etc. In this way, the parking route 111-1 can be limited to the length of the second predetermined distance to obtain a more accurate candidate parking route. Subsequently, the parking route 111-1 limited to the length of the second predetermined distance can be determined as the parking route at block 330.

[0089] It should be noted that the above method is merely exemplary, and any other method may be used to obtain the parking routes 111 - 1 , 111 - 2 , and 111 - 3 , and the present disclosure does not impose any limitation on this.

[0090] Figure 4 FIG. 4 is a flowchart of obtaining a parking route for autonomous parking according to an embodiment of the present disclosure. Figure 1The computing device 130 and / or the cloud 140 are implemented. In order to more clearly understand the solution for autonomous parking provided by the embodiment of the present disclosure, reference will be made to Figure 1 To further describe the embodiments of the present disclosure. Figure 4 In the example shown, process 400 may include block 410 , optional block 420 , and block 430 .

[0091] In box 410, it can be determined whether the driving distance of the vehicle is greater than a third threshold. In such an embodiment, the third threshold can be set by the computing device 130 or its system, or can be set by the user. The third threshold can be, for example, 2KM, 3KM or any other suitable value, which is not limited by the present disclosure. Because the parking route usually needs to start after driving a certain distance and approaching the destination, the distance of the vehicle can be calculated for the determination of the parking route. The outbound learning generally triggers the common area 5 when the vehicle is started, so it can be judged and operated only by the position information after startup.

[0092] In some embodiments, the driving distance of the vehicle 1 may be determined based on an onboard GPS device, an onboard navigation path, or by any other suitable method, which is not limited in the present disclosure.

[0093] Take the third threshold of 2KM and the parking route 101-1 as an example. When the vehicle 1 starts, the driving distance of the vehicle is first determined. When the driving distance is greater than the third threshold of 2KM, it can be determined that the vehicle is outside the common area 5. In this way, when the vehicle 1 enters the boundary point 102-1 of the common area 5, the parking silent learning in the common area 5 is triggered. The silent learning and recording of the route can be performed directly by the computing device 130, or by the cloud 140, or by both.

[0094] When the vehicle 1 enters the parking space 121 and turns off the engine, silent learning can be terminated, that is, route learning and recording are stopped, and then the parking route of the vehicle 1 is obtained at block 430 through the computing device 130 and / or the cloud 140. Subsequently, as described above, the parking route 101-1 can be determined as a historical parking route. In addition, if the historical parking route passes the comparison or validity check, it can be provided to the vehicle 1 as a candidate parking route for autonomous parking of the vehicle.

[0095] Similarly, the exit routes 111-2 and 111-3 may be acquired in block 330 by using the parking space 121 as the end point and the intersections 102-2 and 102-3 of the parking path and the frequently used area 5, and may be determined as candidate parking routes in a similar manner.

[0096] At optional block 420, a route traveled by the vehicle 1 for a third predetermined distance before parking at the historical location may be determined. Figure 1 In the illustrated embodiment, as described above, the historical position corresponds to the position of the parking space 121. It should be understood that the historical position can also be used in any other way to determine the position of the frequently used area 5, and the present disclosure does not limit this.

[0097] Continuing to take the parking route 101-1 as an example, in such an embodiment, the third predetermined distance can be set by the computing device 130 or its system, or can be set by the user. The third predetermined distance can be any suitable distance, such as 450m, 500m, 1000m, etc. That is to say, in this way, the parking route 101-1 can be intercepted as the length of the third predetermined distance (starting at the parking space 121) to obtain a more accurate candidate parking route. Different from the determination method of the parking route, the parking route 101 is determined by intercepting the path of the third predetermined distance forward after the end point is determined, so that the parking route 101-1 limited to the length of the third predetermined distance can be determined as the parking route at block 430.

[0098] It should be noted that the above method is merely exemplary, and any other method may be used to obtain the parking routes 101 - 1 , 101 - 2 , and 101 - 3 , and the present disclosure does not limit this.

[0099] Figure 5 FIG. 5 is a schematic block diagram of an apparatus 500 for determining an object state according to an embodiment of the present disclosure. The apparatus 500 may be implemented as Figure 1 The computing device 130 and / or cloud 140 are shown. Figure 5 As shown, the apparatus 500 includes: a common area determination module 510, configured to determine a common area associated with one or more candidate parking routes of the vehicle based on a historical position of the vehicle within a first time period; a candidate parking route acquisition module 520, configured to acquire one or more candidate parking routes of the vehicle based on one or more historical parking routes of the vehicle in the common area, wherein the one or more historical parking routes include at least one of a parking entry route and a parking exit route; and a candidate parking route providing module 530, configured to provide the vehicle with the acquired one or more candidate parking routes in response to determining that the vehicle is in the common area, for the vehicle to park in or out.

[0100] In some embodiments, the frequently used area determination module may include: a location point determination module, configured to determine a location point corresponding to a historical location of the vehicle; a predetermined area determination module, configured to determine a predetermined area based on the location point and a first predetermined distance; and a first determination module, configured to determine the predetermined area as a frequently used area in response to the number of times the vehicle appears in the predetermined area within a first time period being not less than a first threshold.

[0101] In some embodiments, the commonly used area determination module includes: a plurality of location point determination modules, configured to determine a plurality of location points corresponding to the historical locations of the vehicle; a plurality of predetermined area determination modules, configured to determine a plurality of predetermined areas based on the plurality of location points and a first predetermined distance; and a second determination module, configured to determine at least two predetermined areas as commonly used areas in response to determining that at least two of the plurality of predetermined areas overlap.

[0102] In some embodiments, the candidate parking route acquisition module includes: a historical parking route acquisition module configured to determine one or more historical parking routes in response to the number of times the vehicle is in a common area being not less than a second threshold; and a candidate parking route acquisition first submodule configured to acquire one or more candidate parking routes of the vehicle based on the one or more historical parking routes. In some embodiments, the candidate parking route acquisition module includes: a position determination module configured to determine whether the vehicle is in a common area; and a parking exit route acquisition module configured to acquire a parking exit route of the vehicle in response to determining that the vehicle is in a common area.

[0103] In some embodiments, the candidate parking route acquisition module includes: a driving distance determination module configured to determine whether the driving distance of the vehicle is greater than a third threshold; and a parking route acquisition module configured to acquire a parking route for the vehicle in response to determining that the driving distance to the vehicle is greater than the third threshold and when the vehicle is within a common area.

[0104] Figure 6 FIG. 6 is a block diagram of a computing device 600 capable of implementing various embodiments of the present disclosure. The device 600 may be used to implement Figure 1 The computing device 130 or the cloud 140 of the device 600. As shown in the figure, the device 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 602 or computer program instructions loaded from a storage unit 608 to a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0105] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 606, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0106] The processing unit 601 performs the various methods and processes described above, such as one or more of the processes 200 to 400. For example, in some embodiments, one or more of the processes 200 to 400 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the CPU 601, one or more steps of one or more of the processes 200 to 400 described above may be performed. Alternatively, in other embodiments, the CPU 601 may be configured to perform one or more of the processes 200 to 400 by any other appropriate means (e.g., by means of firmware).

[0107] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip systems (SOCs), load programmable logic devices (CPLDs), and the like.

[0108] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0109] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0110] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.

[0111] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for autonomous parking, comprising: Determining, based on a historical position of a vehicle within a first time period, a frequently used area associated with one or more candidate parking routes of the vehicle, comprising: determining a plurality of position points corresponding to the historical position of the vehicle; determining a plurality of predetermined areas based on the plurality of position points and a first predetermined distance; and in response to determining that at least two of the plurality of predetermined areas overlap, determining the at least two predetermined areas as the frequently used areas; acquiring the one or more candidate parking routes of the vehicle based on one or more historical parking routes of the vehicle in the common area, wherein the one or more historical parking routes are acquired through a silent learning mode, and the one or more historical parking routes include at least one of a parking entry route and a parking exit route; and In response to determining that the vehicle is in the common area, providing the vehicle with the acquired one or more candidate parking routes for the vehicle to park in or out; Wherein, obtaining the one or more candidate parking routes of the vehicle includes: In response to the vehicle being within the frequent area, determining a route for the vehicle to travel a second predetermined distance from the historical location; and The parking route of the vehicle is obtained based on the determined route of the vehicle traveling a second predetermined distance from the historical position.

2. The method according to claim 1, wherein determining the frequently used area comprises: determining a location point corresponding to the historical location of the vehicle; Determining a predetermined area based on the location point and the first predetermined distance; as well as In response to the vehicle appearing in the predetermined area during the first time period a number of times not being less than a first threshold, the predetermined area is determined as the frequently used area.

3. The method according to claim 1, wherein obtaining the one or more candidate parking routes of the vehicle comprises: In response to the number of times the vehicle is in the common area being no less than a second threshold, determining the one or more historical parking routes; as well as The one or more candidate parking routes for the vehicle are obtained based on the one or more historical parking routes.

4. The method according to claim 1, wherein obtaining the one or more candidate parking routes of the vehicle comprises: determining whether the driving distance of the vehicle is greater than a third threshold; as well as In response to determining that the driving distance to the vehicle is greater than the third threshold and when the vehicle is within the common area, the parking route of the vehicle is obtained.

5. The method according to claim 4, wherein obtaining the parking route of the vehicle comprises: In response to the vehicle being within the frequently used area, determining a route of a third predetermined distance traveled by the vehicle before parking at the historical location; as well as The parking route is obtained based on the determined route of the third predetermined distance traveled by the vehicle before parking at the historical position.

6. The method according to claim 1, further comprising: Determining environmental information of the commonly used area; In response to the vehicle being in the common area, comparing the environmental information of the common area with environmental information corresponding to the one or more historical parking routes; as well as Based on the comparison result, one or more historical parking routes in the common area are determined.

7. The method according to claim 6, further comprising: When the result of the comparison is lower than a predetermined matching degree, in response to the vehicle being in one of the historical parking routes again, the one of the historical parking routes is acquired again.

8. The method according to claim 6, wherein the environmental information includes simultaneous localization and mapping (SLAM) information.

9. The method according to claim 1, further comprising: When the acquired historical parking routes of the vehicle include two or more parking routes, the two or more parking routes having at least a portion of consistent characteristics or a portion of two or more parking routes having consistent characteristics are determined as a single parking route.

10. The method according to claim 1, further comprising: When the acquired historical parking routes of the vehicle include two or more parking exit routes, the two or more parking exit routes having at least a portion of consistent characteristics or the portions of the two or more parking exit routes having consistent characteristics are determined as a single parking exit route.

11. The method according to claim 1, further comprising: In response to the one or more provided candidate parking routes not being used a number of times greater than a fourth threshold, the one or more candidate parking routes are invalidated.

12. An apparatus for autonomous parking, comprising: The common area determination module is configured to determine the common areas associated with one or more candidate parking routes of the vehicle based on the historical positions of the vehicle within a first time period, including: determining a plurality of position points corresponding to the historical positions of the vehicle; determining a plurality of predetermined areas based on the plurality of position points and a first predetermined distance; and in response to determining that at least two of the plurality of predetermined areas overlap, determining the at least two predetermined areas as the common areas; a candidate parking route acquisition module configured to acquire the one or more candidate parking routes of the vehicle based on one or more historical parking routes of the vehicle in the common area, wherein the one or more historical parking routes are acquired through a silent learning mode, and the one or more historical parking routes include at least one of a parking entry route and a parking exit route; and a candidate parking route providing module, configured to provide the vehicle with the one or more acquired candidate parking routes for the vehicle to park in or out in response to determining that the vehicle is in the common area; The candidate parking route acquisition module includes: a parking exit route determination module, configured to determine a route for the vehicle to travel a second predetermined distance from the historical position in response to the vehicle being in the common area; and a parking exit route acquisition submodule, configured to acquire the parking exit route of the vehicle based on the determined route for the vehicle to travel the second predetermined distance from the historical position.

13. The apparatus according to claim 12, wherein the common area determination module comprises: a position point determination module, configured to determine a position point corresponding to the historical position of the vehicle; A predetermined area determination module, configured to determine a predetermined area based on the location point and a first predetermined distance; as well as The first determination module is configured to determine the predetermined area as the frequently used area in response to the number of times the vehicle appears in the predetermined area within the first time period being not less than a first threshold.

14. The device according to claim 12, wherein the candidate parking route acquisition module comprises: a historical parking route acquisition module, configured to determine the one or more historical parking routes in response to the number of times the vehicle is in the common area being not less than a second threshold; as well as The candidate parking route acquisition first submodule is configured to acquire the one or more candidate parking routes of the vehicle based on the one or more historical parking routes.

15. The device according to claim 12, wherein the candidate parking route acquisition module comprises: a driving distance determination module configured to determine whether the driving distance of the vehicle is greater than a third threshold; as well as The parking route acquisition module is configured to acquire the parking route of the vehicle in response to determining that the driving distance to the vehicle is greater than the third threshold and when the vehicle is within the common area.

16. The device according to claim 15, wherein the parking route acquisition module comprises: a parking route determination module configured to determine, in response to the vehicle being in the common area, a route of a third predetermined distance traveled by the vehicle before parking at the historical location; as well as The parking route acquisition submodule is configured to acquire the parking route based on the determined route of the third predetermined distance traveled by the vehicle before parking at the historical position.

17. The apparatus according to claim 12, further comprising: An environmental information determination module, configured to determine environmental information of the commonly used area; an environmental information comparison module, configured to compare the environmental information of the common area with environmental information corresponding to the one or more historical parking routes in response to the vehicle being in the common area; as well as The historical parking route determination module is configured to determine one or more historical parking routes in the common area based on the comparison result.

18. The apparatus according to claim 17, further comprising: The historical parking route re-acquisition module is configured to, when the result of the comparison is lower than a predetermined matching degree, in response to the vehicle being in one of the historical parking routes again, re-acquire the one of the historical parking routes.

19. The device according to claim 17, wherein the environmental information includes simultaneous localization and mapping (SLAM) information.

20. The apparatus according to claim 12, further comprising: The single parking route determining module is configured to, when the acquired historical parking routes of the vehicle include two or more parking routes, determine the two or more parking routes having at least a portion of consistent characteristics or a portion of the two or more parking routes having consistent characteristics as a single parking route.

21. The apparatus according to claim 12, further comprising: The single parking route determination module is configured to, when the acquired historical parking routes of the vehicle include two or more parking routes, determine the two or more parking routes with at least a portion of consistent characteristics or the portions of the two or more parking routes with consistent characteristics as a single parking route.

22. The apparatus according to claim 12, further comprising: The candidate parking route invalidation module is configured to invalidate the one or more candidate parking routes in response to the number of times that the one or more candidate parking routes provided are not used being higher than a fourth threshold.

23. An electronic device, comprising: one or more processors; as well as A storage device, used for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-11.

24. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

25. A computer program product, comprising a computer program, which, when executed by a processor, performs the method of any one of claims 1 to 11.

Images