Parking space matching method, parking control method, computer program product and electronic equipment

Abstract

The invention provides a parking space matching method, a parking control method, a computer program product and electronic equipment, according to the parking space matching method provided by the invention, after a parking auxiliary function of a vehicle is activated, first parking space related information of a target parking space detected for a surrounding area of the vehicle can be acquired; wherein the first parking space related information at least comprises first position information of an entrance corner point of the target parking space; if the entrance corner point of the target parking space and the entrance corner point of a historical parking space are identified to meet a position consistency judgment condition based on the first position information of the entrance corner point of the target parking space and the second position information of the entrance corner point of the historical parking space, the target parking space is determined to be the target parking space. And if yes, determining that the target parking space and the historical parking space belong to the same parking space.

Description

Technical Field

[0001] This application relates to the field of assisted parking technology, and in particular to a parking space matching method, a parking control method, a computer program product, and an electronic device. Background Technology

[0002] With the continuous development of intelligent driving technology, parking assistance functions have become an important part of automotive intelligence. Some parking assistance functions can combine data from sensors on the vehicle's surrounding environment to identify the location of existing parking spaces and estimate their area. If the area of ​​the current parking space matches the area of ​​historical parking spaces in the same area stored in the system, it can be determined that they belong to the same parking space. Then, by combining this information with the relevant information of the existing parking spaces around the vehicle, automatic parking control can be performed. While this approach improves the convenience and efficiency of parking operations to some extent, its parking space matching process is relatively cumbersome and its accuracy is not ideal, making it difficult to meet users' needs for an efficient and precise parking experience. Summary of the Invention

[0003] Based on this, this application provides a parking space matching method, a parking control method, a computer program product, and an electronic device. By adopting this parking space matching method, the convenience and accuracy of parking space matching can be improved.

[0004] On the one hand, this application provides a parking space matching method, the method comprising: After the parking assist function of this vehicle is activated, the first parking space related information detected for the target parking space in the area around this vehicle is obtained; wherein, the first parking space related information includes at least: the first position information of the entrance corner point of the target parking space; Based on the first location information of the entrance corner of the target parking space and the second location information of the entrance corner of the historical parking space, when it is identified that the entrance corner of the target parking space and the entrance corner of the historical parking space meet the location consistency determination condition, it is determined that the target parking space and the historical parking space belong to the same parking space.

[0005] On the other hand, this application also provides a parking control method, including: After the parking assist function of this vehicle is activated, the parking space matching result is obtained; wherein, the parking space matching result includes: based on the first position information of the entrance corner point of the target parking space detected in the area around this vehicle, and the second position information of the entrance corner point of the historical parking space, the information indicating whether the target parking space and the historical parking space belong to the same parking space is determined by identifying whether the entrance corner point of the target parking space and the entrance corner point of the historical parking space meet the position consistency judgment condition; Based on the parking space matching results, parking control is performed on this vehicle.

[0006] On the other hand, this application also provides a computer program product comprising a computer program that, when executed, implements the steps of the above-described parking space matching method and / or parking control method.

[0007] On the other hand, this application also provides an electronic device, including: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and execute the steps of the above-described parking space matching method and / or parking control method.

[0008] According to the parking space matching method and parking control method provided in this application, after the parking assistance function of the vehicle is activated, the first parking space-related information of the target parking space detected in the area surrounding the vehicle can be obtained. The first parking space-related information can include at least: the first position information of the entrance corner point of the target parking space. Based on the first position information of the entrance corner point of the target parking space and the second position information of the entrance corner points of historical parking spaces, when it is determined that the entrance corner point of the target parking space and the entrance corner point of the historical parking space meet the position consistency determination condition, it is determined that the target parking space and the historical parking space belong to the same parking space. This improves the convenience and accuracy of parking space matching, and further improves the reliability and vehicle safety of the parking assistance function when automatically parking based on the parking space matching result.

[0009] It should be understood that the description in the Summary Section is not intended to limit the key or essential features of the embodiments of this application, nor is it intended to restrict the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0010] Figure 1 A flowchart illustrating a parking space matching method provided in an embodiment of this application; Figure 2 A schematic diagram of a parking scenario provided in an embodiment of this application; Figure 3 A schematic flowchart illustrating a parking control method provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. The order of some steps in the methods provided in one or more embodiments of this application can be interchanged according to actual needs, or some steps can be omitted or deleted, without specific limitations.

[0012] In the description of one or more embodiments of this application, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based 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 and are not used to limit their quantity. Other explicit and implicit definitions may also be included below.

[0013] The term "at least one" should be understood to include one or more situations. For example, "at least one of A and B" can include "A alone," "B alone," and "A and B." Similarly, "at least one of A, B, and C" can include "A alone," "B alone," "C alone," "A and B," "A and C," "C and B," and "A, B, and C." Other explicit and implicit definitions may also be included below, but are not specifically limited thereto.

[0014] In the description of one or more embodiments of this application, the term "and / or" should be understood to include one or more situations. For example, "A and / or B" may include "A alone", "B alone", and "A and B". As another example, "A and / or B and / or C" may include "A alone", "B alone", "C alone", "A and B", "A and C", "C and B", and "A, B and C".

[0015] Currently, the parking assistance function on vehicles can rely on real-time data collected by sensor devices to identify the location information of the current parking space in the area around the vehicle and estimate its area. This allows the system to determine that the historical parking spaces and the current parking space in the same area have similar areas, thus identifying them as belonging to the same parking space. Furthermore, it can combine the relevant information of the current parking space to automatically control the vehicle's parking.

[0016] However, the two entrance corners of a parking space, being exposed on the outside, are usually less affected by obstruction, allowing for more accurate location information. In contrast, the two inner corners are easily obstructed by surrounding obstacles, making accurate location information difficult to obtain. Existing solutions typically combine the shape and size parameters of a baseline parking space to estimate and complete the positions of the inner corners, then combine this with the vehicle's inner and outer corner positions to calculate the corresponding parking space area. This approach not only increases the computational complexity of parking space matching but also easily leads to inaccurate parking space area calculations due to deviations in the estimated inner corner positions, affecting the accuracy of parking space matching results and thus limiting the practical application and user experience of parking assistance functions.

[0017] Based on this, this application proposes a parking space matching method and a parking control method. This method, after the parking assist function of the vehicle is activated, acquires first parking space-related information for a target parking space detected in the area surrounding the vehicle. The first parking space-related information may include at least: first position information of the entrance corner point of the target parking space. Based on the first position information of the entrance corner point of the target parking space and the second position information of the entrance corner points of historical parking spaces, when the entrance corner points of the target parking space and the historical parking spaces meet the position consistency determination condition, it is determined that the target parking space and the historical parking space belong to the same parking space. This improves the convenience and accuracy of parking space matching, and further enhances the reliability and vehicle safety of the parking assist function when automatically parking based on the parking space matching results.

[0018] Please see Figure 1 This is a schematic flowchart illustrating a parking space matching method provided in an embodiment of this application. The executing entity of this process can be a program mounted on a radar device, image acquisition device, domain controller, or vehicle. Alternatively, the executing entity of this process can also be a radar device, image acquisition device, vehicle controller, or vehicle, or other devices capable of communicating with the radar device, image acquisition device, vehicle controller, or vehicle; no specific limitation is made thereto.

[0019] The following is about Figure 1 The process shown is described in detail, and the parking space matching method may specifically include the following steps: Step S102: After the parking assist function of the vehicle is activated, the first parking space related information of the target parking space detected in the area around the vehicle is obtained; wherein, the first parking space related information includes at least: the first position information of the entrance corner point of the target parking space.

[0020] In this embodiment, the parking assist function can be a function that automatically identifies the required parking space using intelligent technology and controls the vehicle to park in the corresponding space to complete the parking operation. In practical applications, the parking assist function can be of various types, such as memory parking function (Home Zone Parking Assist), automated valet parking function, or other types of intelligent parking functions, and is not specifically limited thereto.

[0021] In the embodiments of this application, after the parking assistance function of the vehicle is activated, target detection technology can usually be used to obtain the first parking space information of the target parking space currently existing around the vehicle. In order to combine the first parking space information of the target parking space and determine that the target parking space belongs to the same parking space as a certain historical parking space in the same area, automatic parking control can be performed by combining the more accurate and reliable first parking space information of the target parking space.

[0022] The types of information related to the first parking space of the target parking space can be varied. For example, it may include the first location information of the entrance corner point of the target parking space. In addition, it may include the existence probability and size information of the target parking space, etc., without specific limitations. In practical applications, the entrance corner point of the target parking space may include the two vertices constituting the boundary of the parking space entrance (i.e., the side of the parking space that the vehicle first enters when parking in the target parking space). For ease of understanding, this is combined with... Figure 2 Here's an example illustrating the entrance corner point of a parking space. For example... Figure 2 As shown, assuming that vehicle 201 needs to park in parking space 204 while moving forward or reversing along the road in the direction indicated by the arrow, the entrance corner point of parking space 204 may include entrance corner point 205 and entrance corner point 206, which will not be elaborated further.

[0023] Step S104: Based on the first position information of the entrance corner of the target parking space and the second position information of the entrance corner of the historical parking space, when it is identified that the entrance corner of the target parking space and the entrance corner of the historical parking space meet the position consistency determination condition, it is determined that the target parking space and the historical parking space belong to the same parking space.

[0024] In this embodiment of the application, during the operation of the parking assistance function equipped in the vehicle, the parking assistance function can obtain the position information of the entrance corner point of the target parking space currently existing in the same area and the historical parking space existing at a historical time. When the entrance corner point of the target parking space and a certain historical parking space meet the position consistency determination condition, it can be determined that the two belong to the same parking space. In this case, it can be considered that the accuracy and reliability of the currently detected target parking space are good. In addition, it can also meet the needs of the parking assistance function in some cases to control the vehicle to park in the historical parking space.

[0025] In some feasible implementations, the historical parking spaces may include at least one of the following: the parking space where the vehicle was parked during the historical memory parking process, other parking spaces detected by the vehicle during the historical memory parking process, parking spaces detected by the vehicle during the historical automatic valet parking process, and parking spaces included in the electronic map data of the area where the vehicle is located. No specific limitation is made in this regard.

[0026] In this embodiment of the application, when the user needs to use the memory parking function of the vehicle, the user usually needs to trigger the memory parking learning mode and drive the vehicle from the starting point to a specific parking space, and then drive the vehicle into the specific parking space. During this process, the vehicle can collect real-time data on the surrounding environment, vehicle positioning data, vehicle pose data, and parking space-related information of the specific parking space in order to build and store the corresponding global map and / or local map data.

[0027] In this case, the specific parking space mentioned above (i.e., the parking space where the vehicle was parked during the historical parking process) can be used as a historical parking space. This allows us to identify whether the target parking space belongs to the parking space that the user wants the vehicle to park in by detecting whether the target parking space currently existing around the vehicle belongs to the same historical parking space set by the user.

[0028] Understandably, when the vehicle is in memory parking learning mode, it can also identify and store information about other parking spaces around the vehicle besides the specific parking space mentioned above (i.e., other parking spaces detected by the vehicle during historical memory parking), and use these parking spaces as historical parking spaces. By detecting whether the target parking spaces currently existing around the vehicle belong to the same category of historical parking spaces, the vehicle's current location can be accurately and reliably identified. Furthermore, based on actual needs, the vehicle can select the parking space it needs from the currently existing target parking spaces corresponding to these historical parking spaces, which helps improve the flexibility and success rate of automatic parking.

[0029] In this embodiment, the automatic valet parking function of this vehicle can also collect real-time data on the vehicle's surrounding environment, vehicle positioning data, vehicle pose data, and parking space information around the vehicle during historical operation, in order to construct and store corresponding global and / or local map data. In this case, the aforementioned parking spaces (i.e., parking spaces detected by the vehicle during historical automatic valet parking) can be used as historical parking spaces, so as to identify whether the target parking space is accurate and reliable by detecting whether the currently existing target parking space around the vehicle belongs to the same historical parking space.

[0030] In this embodiment of the application, the vehicle may also obtain electronic map data of the area where the vehicle is located, which is pre-built by the service provider (e.g., parking lot manager, electronic map provider), and use the parking spaces contained in the electronic map data as historical parking spaces, so as to identify whether the target parking space is accurate and reliable by detecting whether the target parking space currently existing around the vehicle and the historical parking space belong to the same parking space.

[0031] Figure 1 The method described above can obtain first parking space-related information for a target parking space detected in the area surrounding the vehicle after the vehicle's parking assistance function is activated. This first parking space-related information can include at least: first location information of the entrance corner of the target parking space; based on the first location information of the entrance corner of the target parking space and the second location information of the entrance corner of historical parking spaces, when the entrance corner of the target parking space and the entrance corner of the historical parking space meet the location consistency determination condition, it is determined that the target parking space and the historical parking space belong to the same parking space, which helps improve the convenience and accuracy of parking space matching.

[0032] In some feasible implementations, the target parking space may include at least one of the following: a radar object belonging to the parking space type obtained by processing the vehicle's surrounding environment perception data collected by radar equipment, a visual object belonging to the parking space type obtained by processing the vehicle's surrounding environment image data collected by image acquisition equipment, and a fusion object belonging to the parking space type obtained by processing the vehicle's surrounding environment perception data and the vehicle's surrounding environment image data.

[0033] In this embodiment, image target detection technology, radar target detection technology, and / or target fusion technology can be used to process image data of the vehicle's surrounding environment acquired by image acquisition equipment and / or perceived data of the vehicle's surrounding environment acquired by radar equipment. This allows for the identification of target objects belonging to parking space types, represented by ground parking space markings, parking space barriers, parked vehicles, etc., which can then be used as the currently existing target parking spaces around the vehicle. Alternatively, image target detection technology, radar target detection technology, and / or target fusion technology can be used to identify areas that meet parking needs (e.g., parking spaces without parking lines) in areas that have not been occupied by other target objects and do not have parking space markings, which can then be used as the currently existing target parking spaces around the vehicle, offering good flexibility. No specific limitations are imposed on this approach.

[0034] In some feasible implementations, the location consistency determination condition may include: the distance between the entrance corner of the target parking space belonging to the same parking space corner type and the entrance corner of the historical parking space is less than a distance threshold.

[0035] Among them, the parking space corner point types can include: the left corner point of the parking space entrance and the right corner point of the parking space entrance.

[0036] In this embodiment of the application, a parking space may have two entrance corner points located at different positions. In order to facilitate the distinction between the entrance corner points, it can be assumed that when looking from inside the parking space towards the entrance, the entrance corner point located to the left of the longitudinal center line of the parking space belongs to the left corner point of the parking space entrance, and the entrance corner point located to the right of the longitudinal center line of the parking space belongs to the right corner point of the parking space entrance.

[0037] Understandably, other strategies can also be used to classify the types of parking space entrance corners. For example, when a vehicle approaches a parking space along a specific path, the type of each parking space entrance corner can be determined based on the distance between the entrance corner and the vehicle, such as near-end parking space entrance corner or far-end parking space entrance corner, without making specific restrictions.

[0038] In this embodiment, when the parking space corner point type includes: the left corner point of the parking space entrance and the right corner point of the parking space entrance, the entrance corner points of the currently existing target parking spaces around the vehicle may include: the left corner point of the first parking space entrance and the right corner point of the first parking space entrance, while the entrance corner points of the historical parking spaces may include: the left corner point of the second parking space entrance and the right corner point of the second parking space entrance. In this case, the position consistency determination condition may include: the distance between the aforementioned left corner point of the first parking space entrance and the left corner point of the second parking space entrance is less than a first distance threshold, and the distance between the aforementioned right corner point of the first parking space entrance and the right corner point of the second parking space entrance is less than a second distance threshold. The first distance threshold and the second distance threshold are both distance thresholds, and they can be the same or different; no specific limitation is made. In practical applications, the value of the aforementioned distance thresholds can be set according to actual needs, for example, from a few centimeters to several hundred centimeters; no specific limitation is made.

[0039] For ease of understanding, this is combined with Figure 2 Examples are provided to illustrate the conditions for determining positional consistency. For instance... Figure 2 As shown, assuming that while vehicle 201 is traveling along the road in the direction indicated by the arrow, it obtains the position information of the left corner point 202 and the right corner point 203 of the first parking space entrance of the target parking space, and the position information of the left corner point 205 and the right corner point 206 of the second parking space entrance of the historical parking space 204, then when the distance between the left corner point 202 and the left corner point 205 of the first parking space entrance, and the distance between the right corner point 203 and the right corner point 206 of the first parking space entrance, are both less than the corresponding distance thresholds, the position consistency determination condition is met, and thus it is determined that the target parking space and the historical parking space 204 belong to the same parking space. This method is simple, easy to implement, and has good accuracy.

[0040] In some feasible implementations, the distance threshold may be determined based on at least one of parking space detection accuracy information, user driving preference information, the size information of the historical parking spaces, and the surrounding obstacle information of the historical parking spaces.

[0041] In this embodiment, the parking space detection accuracy information can reflect the accuracy of the information about the vehicle's surrounding environment collected by the sensor device, and / or the accuracy of the first position information of the entrance corner point of the target parking space determined based on the information about the vehicle's surrounding environment. In this case, the better the accuracy of the information about the vehicle's surrounding environment and / or the first position information of the entrance corner point of the target parking space as represented by the parking space detection accuracy information, the smaller the distance threshold can be. This is beneficial for improving the accuracy of parking space matching results.

[0042] User driving preference information can characterize a user's tolerance for parking accuracy. In this case, if the user's driving preference information reflects a preference for lenient parking space matching conditions, the aforementioned distance threshold can be appropriately increased; conversely, if the user seeks high-precision parking, the distance threshold can be appropriately decreased to strictly limit the deviation of the parking space entrance corner position between historical parking spaces belonging to the same parking space and the currently existing target parking space, which is beneficial to improving the user experience.

[0043] Historical parking space size information may include, but is not limited to, parking space width data, parking space length data, and parking space area data. Since matching large parking spaces (such as large vehicle parking spaces) has a higher tolerance for positional deviations at the parking space entrance corner, the distance threshold can be appropriately increased; conversely, when matching small parking spaces (such as compact parking spaces), the tolerance for positional deviations at the parking space entrance corner is lower, so the distance threshold can be appropriately decreased. This improves the flexibility, accuracy, and universality of parking space matching.

[0044] Information on obstacles surrounding historical parking spaces can reflect obstacles that may affect the accuracy of parking space detection and the parking process, such as pillars and guardrails. To reduce the interference of these obstacles on the parking space matching process, the aforementioned distance threshold can be appropriately increased when such obstacles are present around historical parking spaces. No specific limitations are imposed on this.

[0045] In some feasible implementations, the first location information of the entrance corner of the target parking space may include: the first coordinate data of the entrance corner of the target parking space in a preset coordinate system; the second location information of the entrance corner of the historical parking space includes: the second coordinate data of the entrance corner of the historical parking space in the preset coordinate system.

[0046] The method of determining that the target parking space and the historical parking space belong to the same parking space when the target parking space and the historical parking space's entrance corner point satisfy the position consistency determination condition, based on the first position information of the entrance corner point of the target parking space and the second position information of the entrance corner point of the historical parking space, may include: Based on the first coordinate data of the entrance corner of the target parking space belonging to the same parking space corner point type, and the second coordinate data of the entrance corner of the historical parking space, when it is determined that the Euclidean distance between the entrance corner of the target parking space and the entrance corner of the historical parking space at a specific horizontal plane is less than a distance threshold, the target parking space and the historical parking space are determined to belong to the same parking space.

[0047] In this embodiment of the application, in order to reduce the interference of the height information of the parking space entrance corner point (i.e., its vertical distance from a specific horizontal plane) on the parking space matching result, the coordinate data of the entrance corner points of the target parking space and the historical parking space belonging to the same type in the same preset coordinate system can be combined to calculate the Euclidean distance between the entrance corner points of the target parking space and the historical parking space belonging to the same type at a specific horizontal plane. By comparing the magnitude of this Euclidean distance with the distance threshold, it can be determined whether the target parking space and the historical parking space belong to the same parking space, which helps to improve the accuracy and reliability of parking space matching.

[0048] The aforementioned specific horizontal plane can be the surface of a level road where the vehicle is located, or, if the road where the vehicle is located is a sloping road, the aforementioned specific horizontal plane can be a horizontal plane passing through the bottom of the vehicle's tires, or it can be any other horizontal plane parallel to the horizontal plane passing through the bottom of the vehicle's tires. No specific limitations are imposed.

[0049] In some feasible implementations, the preset coordinate system may include: a geocentric coordinate system, a local map coordinate system constructed based on simultaneous localization and mapping technology, or other coordinate systems obtained by performing coordinate system transformation on the geocentric coordinate system or the local map coordinate system.

[0050] In this embodiment, during operation, the parking assistance function can combine acquired vehicle surrounding environment data and vehicle positioning data to construct a global map in a geocentric coordinate system, and / or a local map constructed based on simultaneous localization and mapping (SLT / Map) technology. This allows the acquisition of first coordinate data of the entrance corner points of currently existing target parking spaces around the vehicle in the geocentric coordinate system, the local map coordinate system, and / or other coordinate systems obtained through coordinate system transformation. Based on the principle of type, second coordinate data of the entrance corner points of historical parking spaces in the same area can also be acquired in the geocentric coordinate system, the local map coordinate system, and / or other coordinate systems obtained through coordinate system transformation. This facilitates the determination of whether the entrance corner points of the target parking space and historical parking spaces belong to the same parking space by combining their coordinate data in the same coordinate system. In this case, the aforementioned preset coordinate system can include at least one of the following: a geocentric coordinate system, a local map coordinate system constructed based on SLT / Map technology, or other coordinate systems obtained by performing coordinate system transformation on the geocentric coordinate system or the local map coordinate system. This is flexible and convenient, and no specific limitation is made.

[0051] Please see Figure 3This is a schematic flowchart illustrating a parking control method provided in an embodiment of this application. The executing entity of this process can be a program mounted on a radar device, an image acquisition device, a domain controller, or a vehicle. Alternatively, the executing entity of this process can also be a radar device, an image acquisition device, a vehicle controller, or a vehicle, or other devices capable of communicating with the radar device, image acquisition device, vehicle controller, or vehicle; no specific limitation is made thereto.

[0052] The following is about Figure 3 The process shown is described in detail. The parking control method may specifically include the following steps: Step S302: After the parking assist function of this vehicle is activated, obtain the parking space matching result; wherein, the parking space matching result may include: based on the first position information of the entrance corner point of the target parking space detected in the area around this vehicle, and the second position information of the entrance corner point of the historical parking space, by identifying whether the entrance corner point of the target parking space and the entrance corner point of the historical parking space meet the position consistency determination condition, information indicating whether the target parking space and the historical parking space belong to the same parking space is determined.

[0053] In this embodiment, the parking assist function can be a function that automatically identifies the required parking space using intelligent technology and controls the vehicle to park in the corresponding space to complete the parking operation. In practical applications, the parking assist function can be of various types, such as memory parking function (Home Zone Parking Assist), automated valet parking function, or other types of intelligent parking functions, and is not specifically limited thereto.

[0054] In this embodiment of the application, after the parking assistance function of this vehicle is activated, it can obtain information based on... Figure 1 The parking space matching results generated by the parking space matching scheme provided in the embodiments are used to decide whether to control the vehicle to park in the currently detected target parking space based on the parking space matching results. Specifically, the first position information of the entrance corner point of the target parking space currently existing around the vehicle can be obtained based on target detection technology, and the second position information of the entrance corner point of the historical parking space can also be obtained. By combining the above information and the position consistency judgment condition, an accurate and reliable parking space matching result can be conveniently and accurately generated to characterize whether the target parking space and the historical parking space belong to the same parking space. This will not be elaborated further.

[0055] Step S304: Based on the parking space matching result, perform parking control on the vehicle.

[0056] Figure 3 The method described above, after the vehicle's parking assist function is activated, can obtain the first position information of the entrance corner point of the currently existing target parking space around the vehicle, the second position information of the entrance corner point of the historical parking space, and the position consistency judgment condition to generate an accurate and reliable parking space matching result that reflects whether the target parking space and the historical parking space belong to the same parking space. By combining the parking assist function with the parking space matching result with a high degree of accuracy, parking control can be performed, which helps to improve the reliability of the parking assist function and the vehicle safety during operation.

[0057] In some feasible implementations, the step of controlling the parking of the vehicle based on the parking space matching result may include: When the parking assistance function is activated, and the parking space matching result indicates that the target parking space and the historical parking space belong to the same parking space, and the target parking space meets the parking conditions, the vehicle is controlled to park in the target parking space.

[0058] In this embodiment, an active parking assist function can be run to detect whether the target parking space currently existing around the vehicle belongs to the same parking space as a historical parking space in the same area and meets the parking conditions. If so, the parking assist function can be used to control the vehicle to automatically park in the target parking space. If not, the parking assist function can choose not to control the vehicle to automatically park in the target parking space, which helps to improve the convenience and reliability of vehicle parking.

[0059] The parking conditions can be set according to actual needs. For example, when the parking assistance function is an automatic valet parking function, the parking conditions may include, but are not limited to: the target parking space is an empty and available parking space, the target parking space is closest to the vehicle, and the target parking space belongs to at least one of a specific type of parking space (e.g., mechanical parking space, flat parking space, parallel parking space, perpendicular parking space, and angled parking space). When the parking assistance function is a memory parking function, the parking conditions may include, but are not limited to: the target parking space is a user-specified parking space (e.g., a parking space that the vehicle has previously parked in during the memory parking learning mode), and the target parking space is an empty and available parking space. There are no specific limitations on these conditions.

[0060] This application also provides a computer program product, which may include a computer program. When the computer program is executed, it can implement the steps of the parking space matching method and / or parking control method provided in at least some of the above embodiments. For the specific execution process, please refer to the specific description in the above embodiments, which will not be repeated here.

[0061] This application also provides Figure 4 The diagram shows the structure of the electronic device. Figure 4As shown, at the hardware level, the electronic device may include a processor 41 and a memory 45, and may also include an internal bus 42, a network interface 43, a memory 44, and other hardware required for the business. The processor 41 can read the corresponding computer program from the memory 45 into the memory and then run it to implement the above-mentioned parking space matching method and / or parking control method. For the specific execution process, please refer to the detailed description in the above embodiments, which will not be repeated here.

[0062] In some feasible implementations, the electronic device may include at least one of radar equipment, image acquisition equipment, parking controller and domain controller, without specific limitation.

[0063] In some feasible implementations, the above-mentioned electronic device may also include other mechanical structures, electronic devices or electronic systems, and there are no specific limitations on this.

[0064] Finally, the various embodiments in this application are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for embodiments such as computer program products and electronic devices, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments.

[0065] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A parking space matching method, comprising: After the parking assist function of this vehicle is activated, the first parking space related information detected for the target parking space in the area around this vehicle is obtained; wherein, the first parking space related information includes at least: the first position information of the entrance corner point of the target parking space; Based on the first location information of the entrance corner of the target parking space and the second location information of the entrance corner of the historical parking space, when it is identified that the entrance corner of the target parking space and the entrance corner of the historical parking space meet the location consistency determination condition, it is determined that the target parking space and the historical parking space belong to the same parking space.

2. The method according to claim 1, wherein the target parking space comprises: The vehicle is classified as a parking space by processing the vehicle's surrounding environment perception data collected by radar equipment, a parking space by processing the vehicle's surrounding environment image data collected by image acquisition equipment, and a parking space by processing the vehicle's surrounding environment perception data and the vehicle's surrounding environment image data.

3. The method according to claim 1, wherein the historical parking spaces include: The parking space that this vehicle entered during the historical parking memory process, other parking spaces detected by this vehicle during the historical parking memory process, parking spaces detected by this vehicle during the historical automatic valet parking process, and parking spaces included in the electronic map data of the area where this vehicle is located, are at least one of the following:

4. The method according to claim 1, wherein the position consistency determination condition includes: The distance between the entrance corner of the target parking space belonging to the same parking space corner point type and the entrance corner of the historical parking space is less than a distance threshold; The parking space corner point types include: the left corner point of the parking space entrance and the right corner point of the parking space entrance.

5. The method according to claim 4, wherein the first location information of the entrance corner point of the target parking space includes: The first coordinate data of the entrance corner point of the target parking space in the preset coordinate system; The second location information of the entrance corner point of the historical parking space includes: the second coordinate data of the entrance corner point of the historical parking space in the preset coordinate system; Based on the first location information of the entrance corner point of the target parking space and the second location information of the entrance corner point of the historical parking space, when it is determined that the entrance corner point of the target parking space and the entrance corner point of the historical parking space meet the location consistency determination condition, the method of determining that the target parking space and the historical parking space belong to the same parking space includes: Based on the first coordinate data of the entrance corner of the target parking space belonging to the same parking space corner point type, and the second coordinate data of the entrance corner of the historical parking space, when it is determined that the Euclidean distance between the entrance corner of the target parking space and the entrance corner of the historical parking space at a specific horizontal plane is less than a distance threshold, the target parking space and the historical parking space are determined to belong to the same parking space.

6. The method according to claim 5, wherein the distance threshold is determined based on at least one of parking space detection accuracy information, user driving preference information, size information of the historical parking space, and surrounding obstacle information of the historical parking space.

7. The method according to claim 5, wherein the preset coordinate system comprises: The geocentric coordinate system is a local map coordinate system constructed based on simultaneous localization and mapping technology, or other coordinate systems obtained by performing coordinate system transformation on the geocentric coordinate system or the local map coordinate system.

8. The method according to any one of claims 1-7, wherein the parking assistance function includes: At least one of memory parking function and automatic valet parking function.

9. A parking control method, comprising: After the parking assist function of this vehicle is activated, the parking space matching result is obtained; wherein, the parking space matching result includes: based on the first position information of the entrance corner point of the target parking space detected in the area around this vehicle, and the second position information of the entrance corner point of the historical parking space, the information indicating whether the target parking space and the historical parking space belong to the same parking space is determined by identifying whether the entrance corner point of the target parking space and the entrance corner point of the historical parking space meet the position consistency judgment condition; Based on the parking space matching results, parking control is performed on this vehicle.

10. The method according to claim 9, wherein the step of controlling the parking of the vehicle based on the parking space matching result includes: When the parking assistance function is activated, and the parking space matching result indicates that the target parking space and the historical parking space belong to the same parking space, and the target parking space meets the parking conditions, the vehicle is controlled to park in the target parking space.

11. The method according to claim 9 or 10, wherein the parking assistance function includes: At least one of memory parking function and automatic valet parking function.

12. A computer program product comprising a computer program that, when executed, performs the steps of the method according to any one of claims 1 to 11.

13. An electronic device, comprising: A processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the steps of the method as claimed in any one of claims 1 to 11.

14. The electronic device of claim 13, wherein the electronic device comprises: At least one of radar equipment, image acquisition equipment, parking controller, and domain controller.

Images