Map generation method, parking assistance method and related device

Abstract

The invention relates to the technical field of vehicles, in particular to a map generation method, a parking assisting method and a related device. The map generation method comprises the steps of activating a parking lot map drawing function; obtaining parking lot data of a current parking lot collected by the vehicle to draw a current map; acquiring a historical map; wherein the historical map represents a parking lot map of the current parking lot drawn at historical moments; and fusing the current map and the historical map to form a new parking lot map. The method can reduce the number of maps of the same parking lot, thereby facilitating the improvement of the integrity of the parking lot map, and achieving the multi-path expansion of the parking lot map.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a map generation method, a parking assistance method, a map management system, a parking assistance system, a vehicle, a computer device, and a computer-readable storage medium. Background Art

[0002] With the rapid development of intelligent driving, parking assistance functions such as self-learning parking and real-time parking space recommendation have emerged. In the implementation of some parking assistance functions, it may involve the use of parking lot maps for assisted parking. However, due to the unreasonable design of the map construction process, it is easy to consume a lot of storage space and have a poor functional experience. Summary of the invention

[0003] Based on this, it is necessary to provide a map generation method, a parking assistance method, a map management system, a parking assistance system, a vehicle, a computer device and a computer-readable storage medium to address the above-mentioned technical problems, which can reduce the number of maps of the same parking lot, thereby facilitating improving the integrity of the parking lot map and realizing multi-path expansion of the parking lot map.

[0004] On the one hand, a map generation method is provided, which includes: activating a parking lot map drawing function; obtaining parking lot data of a current parking lot collected by a vehicle to draw a current map; obtaining a historical map; wherein the historical map represents a parking lot map of the current parking lot drawn at a historical moment; and fusing the current map and the historical map to form a new parking lot map.

[0005] In one embodiment of the present application, the fusion of the current map and the historical map includes: comparing the current map and the historical map Figure 2 The environmental features of the current map are compared to obtain a baseline feature, a first environmental feature and a second environmental feature; wherein the baseline feature represents an environmental feature existing in the current map and in the historical map, the first environmental feature represents an environmental feature in the historical map that is not the baseline feature, and the second environmental feature represents an environmental feature in the current map that is not the baseline feature; a first relative position of the first environmental feature in the historical map compared to the baseline feature is obtained, and the first environmental feature is added to the first relative position in the current map compared to the baseline feature; or, a second relative position of the second environmental feature in the current map compared to the baseline feature is obtained, and the second environmental feature is added to the second relative position in the historical map compared to the baseline feature.

[0006] In one embodiment of the present application, the current map and the historical map are compared. Figure 2The environmental features of the vehicle also include: obtaining semantic information and inertial navigation information formed based on parking lot data as the first modeling data; wherein, the semantic information includes road information of the current parking lot, and the inertial navigation information includes environmental information of the vehicle driving path; obtaining semantic information and inertial navigation information of the historical map as the second modeling data; fusing the depth information of obstacles in the current parking lot to perform modeling data matching on the first modeling data and the second modeling data.

[0007] In an embodiment of the present application, comparing the current map and the historical map Figure 2 The environmental features of the vehicle include: obtaining the parking lot entrance where the current map starts to be drawn as the first entrance; obtaining the parking lot entrance where the historical map starts to be drawn as the second entrance; in response to the first entrance and the second entrance being the same parking lot entrance, starting from the two, along the driving trajectory of the vehicle on the current map and the driving trajectory of the vehicle on the historical map, performing environmental feature comparison.

[0008] In an embodiment of the present application, fusing the current map and the historical map includes: obtaining the relative position relationship between the first entrance and the second entrance; wherein, the first entrance represents the parking lot entrance where the current map starts to be drawn, and the second entrance represents the parking lot entrance where the historical map starts to be drawn; based on the relative position relationship, supplementing one of the current map and the historical map to the other. Figure 2 One of the maps is supplemented to the other.

[0009] In an embodiment of the present application, the map generation method further includes: determining whether the first entrance and the second entrance are the same entrance; generating a verification request using the determination result and sending the verification request to the interaction end; obtaining the determination result in response to the verification request to determine whether the first entrance and the second entrance are the same entrance.

[0010] In an embodiment of the present application, obtaining the parking lot data of the current parking lot collected by the vehicle to draw the current map includes: obtaining the original data of the currently collected parking lot; verifying whether the original data is complete; analyzing whether there is an occlusion area in the environment represented by the original data; obtaining the working state of the sensing device; wherein, the sensing device is used to collect the original data; in response to the original data being complete, the environment it represents having no occlusion area, and the working state of the sensing device being normal, using the original data as the parking lot data.

[0011] In an embodiment of the present application, activating the parking lot map drawing function includes: in response to determining that the vehicle is in the current parking lot, obtaining the vehicle speed; in response to the vehicle speed being lower than the first vehicle speed threshold, determining to activate the parking lot map drawing function; and / or, before fusing the current map and the historical map, it further includes: obtaining the driving state of the vehicle; in response to the vehicle being in a parked state or the vehicle speed being lower than the second vehicle speed threshold, determining to allow fusing the current map and the historical map.

[0012] Another method provides a parking assistance method, which includes: obtaining a parking lot map; wherein, the parking lot map is generated by using the map generation method described in any of the above embodiments; obtaining the current position of the vehicle and the target parking space; and using the parking lot map to plan a driving path for the vehicle to drive from the current position to the target parking space.

[0013] In yet another aspect, a map management system is provided, which includes: an input module and a control module; the input module is used to obtain parking lot data of the current parking lot; the control module, connected to the input module, is used to implement the map generation method described in any of the above embodiments; or, is used to implement the parking assistance method described in any of the above embodiments.

[0014] In yet another aspect, a vehicle is provided, which includes: a vehicle body and a map management system; the vehicle body includes a sensing device, and the sensing device is used to collect parking lot data of the current parking lot; the map management system is as described in the above embodiments, and the map management system is connected to the sensing device.

[0015] In still another aspect, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the map generation method described in any of the above embodiments; or, implements the parking assistance method described in the above embodiments.

[0016] In still another aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the map generation method described in any of the above embodiments; or, implements the parking assistance method described in the above embodiments.

[0017] The above map generation method, parking assistance method, map management system, parking assistance system, vehicle, computer device, and computer-readable storage medium can, when drawing a parking lot map, use the parking lot data currently collected by the vehicle to draw the current map to implement the drawing of the parking lot map for the current driving path. The parking lot map formed at a historical moment is fused with the current parking lot map, and the parking lot information included in the parking lot map is updated so that information that exists in the current map but does not exist in the historical parking lot map can be added to the parking lot map, which is beneficial to improving the integrity of the parking lot map and further beneficial to realizing the multi-path expansion of the parking lot map. And, by fusing the current map with the parking lot map to form a new parking lot map, the parking lot map data associated with the same parking lot can be reduced, which is beneficial to reducing the occupation of storage resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic flowchart of an embodiment of the map generation method of the present application;

[0019] Figure 2 It is a schematic flowchart of another embodiment of the map generation method of the present application;

[0020] Figure 3 It is a schematic flowchart of yet another embodiment of the map generation method of the present application;

[0021] Figure 4 It is a bird's-eye view schematic diagram of an embodiment of the parking lot of the present application;

[0022] Figure 5 It is a schematic flowchart of an embodiment of the environmental feature comparison of the present application;

[0023] Figure 6 It is a schematic flowchart of an embodiment of the parking assistance method of the present application;

[0024] Figure 7 It is a schematic structural diagram of an embodiment of the map management system of the present application;

[0025] Figure 8 It is a schematic structural diagram of an embodiment of the parking assistance system of the present application;

[0026] Figure 9 It is a schematic structural diagram of an embodiment of the vehicle of the present application;

[0027] Figure 10 It is a schematic structural diagram of an embodiment of the computer device of the present application. Detailed implementation manners

[0028] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0029] To solve the technical problems in the related art that map construction consumes a large amount of storage space and the experience of the parking assistance function is relatively poor, the present application provides a map generation method, a parking assistance method, a map management system, a parking assistance system, a vehicle, a computer device, and a computer-readable storage medium. The map generation method includes:

[0030] The following is an example to illustrate the specific working principle of the present application.

[0031] Please refer to Figure 1 , Figure 1 It is a schematic flowchart of an embodiment of the map generation method of the present application.

[0032] S101: Activate the parking lot map drawing function.

[0033] In this embodiment, the parking lot map drawing function means the function of memorizing the driving trajectory of the vehicle in the parking lot and the environmental information around the driving trajectory to construct a parking lot map.

[0034] Among them, the parking lot map drawing function can be, for example, SLAM (Simultaneous Localization and Mapping), delayed mapping, etc., which are not limited herein.

[0035] S102: Obtain the parking lot data of the current parking lot collected by the vehicle to draw the current map.

[0036] In this embodiment, the vehicle may include sensing devices such as camera devices and radar devices. The sensing devices can sense the environment around the vehicle so that when the vehicle is in the parking lot, it can sense the environment around its body to collect the parking lot data of the current parking lot. Thus, in this embodiment, the parking lot data of the current parking lot collected by the vehicle can be obtained, and then the parking lot map can be drawn by combining the driving trajectory of the vehicle and the parking lot data, that is, the current map is drawn.

[0037] Among them, the parking lot data can characterize the driving trajectory of the vehicle in the current parking lot and the parking lot environment along the way. For example, the parking lot data may include the driving trajectory of the vehicle in the current parking lot, the parking lot environment data around the vehicle collected along the driving trajectory, etc., which are not limited herein.

[0038] S103: Obtain the historical map; where the historical map represents the parking lot map of the current parking lot drawn at a historical moment.

[0039] In this embodiment, the parking lot map of the current parking lot formed at a historical moment can be obtained as the historical map. Among them, the historical map can be the current map drawn at a historical moment; or, the historical map can be obtained by fusing and updating the current map at a historical moment and the historical map, which are not limited herein.

[0040] S104: Fuse the current map and the historical map to form a new parking lot map.

[0041] In this embodiment, in response to obtaining the historical map and the current map of the current parking lot, the current map and the historical map can be fused to form a new parking lot map so that the new parking lot map can include the current map and the historical map. Figure 2The parking lot features of the vehicle are thus conducive to improving the integrity of the stored parking lot map, enabling the integration of parking lot data involved in different driving trajectories within the parking lot map, realizing the multi-path expansion of the parking lot map, and further enhancing the functionality of the rich parking lot map. Moreover, by fusing the current map and the historical map, the duplicate storage of the same parking lot data in both can be reduced, thus facilitating the conservation of storage resources.

[0042] It can be seen that in this embodiment, the parking lot data currently collected by the vehicle can be used to draw the current map to realize the drawing of the parking lot map for the current driving path. By fusing the parking lot map formed at the historical moment with the currently drawn parking lot map, the parking lot information included in the parking lot map is updated to add information that exists in the current map but not in the historical parking lot map, which is thus conducive to improving the integrity of the parking lot map. Moreover, by the method of fusing the current map and the parking lot map to form a new parking lot map, the parking lot map data associated with the same parking lot can be reduced, and even only one parking lot map needs to be stored for the same parking lot, thus facilitating the reduction of the occupation of storage resources.

[0043] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of another embodiment of the map generation method of the present application.

[0044] S201: Obtain the raw data collected by the vehicle sensing device.

[0045] In this embodiment, the raw data represents the data collected by the vehicle sensing device for sensing the current parking lot.

[0046] For example, the sensing device of the vehicle may include a camera device and a radar device. The vehicle may also include an integrated inertial navigation system. Thus, through the cooperation of the camera device, the radar device, and the integrated inertial navigation system, the integration calibration and time synchronization of the raw data collected by the sensing device can be performed.

[0047] Specifically, the vehicle may include, for example, a front-view binocular camera with 8 million pixels, a side-front-view camera with 8 million pixels, a side-rear-view camera with 8 million pixels, a rear-view camera with 8 million pixels, a lidar with 128 lines, an ultrasonic radar, etc. as the sensing device. Further, the vehicle may also include, for example, a global inertial navigation satellite system for vehicle positioning, so as to be able to obtain whether the vehicle is in a parking lot and / or at a parking lot entrance position, etc. The vehicle may also include an inertial navigation system such as an IMU (Inertial Measurement Unit) to measure the three-axis attitude angle and acceleration of the vehicle. The vehicle may also include a wheel speed sensor, an intelligent driving chip, etc., which are not limited herein.

[0048] S202: Perform data quality inspection on the original data to obtain parking lot data.

[0049] In this embodiment, the original data of the current parking lot collected by the vehicle can be obtained, and data quality inspection is performed on the original data to obtain parking lot data, so as to improve the validity and reliability of the data used to draw the current map, and further improve the reliability of the current map.

[0050] That is to say, in the process of performing data quality inspection on the original data, the data that meets the data quality inspection conditions is retained as the parking lot data; the data that does not meet the data quality inspection conditions is deleted to streamline the parking lot data.

[0051] For example, the data quality inspection conditions may include at least one of a data integrity sub-condition, a data unobstructed sub-condition, and a sensing device normal sub-condition. Specifically, the data integrity sub-condition can verify whether the original data is complete. For example, whether the radar data and images are completely input, and whether they are damaged during the acquisition process or transmission process. The data unobstructed sub-condition includes analyzing whether there are occluded areas in the environment represented by the original data. The occluded areas can be for the sensing devices during the acquisition process. For example, whether the camera device for collecting images is occluded, whether the radar is partially occluded, etc. The sensing device normal sub-condition can obtain the working state of the sensing device to determine whether the sensing device is in an abnormal state or a faulty state. When the sensing device is not in an abnormal state and a faulty state (that is, the working state of the sensing device is normal), the collected original data is considered valid data.

[0052] In other words, when the data quality inspection conditions include the data integrity sub-condition, the data unobstructed sub-condition, and the sensing device normal sub-condition, in response to the original data being complete, the environment it represents having no occluded areas, and the sensing device being in a normal working state, the original data is used as the parking lot data.

[0053] S203: Use the parking lot data to draw the current map.

[0054] In this embodiment, the current map can be drawn using the original data after data quality inspection, that is, using the parking lot data to draw the current map, so as to reduce the amount of data to be analyzed when drawing the current map. Drawing the current map with more effective parking lot data can also improve the reliability of the current map.

[0055] S204: Request to determine whether the first entrance is the same as the second entrance.

[0056] In this embodiment, the parking lot entrance where the current map starts to be drawn can be obtained as the first entrance. The parking lot entrance where the historical map starts to be drawn can also be obtained as the second entrance. The user is requested to judge whether the first entrance and the second entrance are the entrances of the same parking lot.

[0057] Optionally, the parking lot entrance of the historical map, i.e., the second entrance, can be the parking lot entrance where the current parking lot map starts to be drawn for the first time; or it can be the starting parking lot entrance of the adjacent previous (i.e., the last time) drawing of the current map; or it can be the starting parking lot entrance of the current map of the current parking lot drawn historically, and the parking lot entrance selected as the second entrance is not limited here.

[0058] Furthermore, it can also be to pre-judge in this embodiment whether the first entrance and the second entrance are the entrances of the same parking lot, send the judgment result in this embodiment to the interaction end for the user to further judge, and judge whether the first entrance and the second entrance are the same entrance based on the user's judgment result. In other words, it can be judged whether the first entrance and the second entrance are the same entrance. A verification request is generated using the judgment result and sent to the interaction end. To obtain the judgment result in response to the verification request to determine whether the first entrance and the second entrance are the same entrance.

[0059] For example, in an urban road, etc., the global inertial navigation satellite system, RTK (Real-time kinematic), high-precision map, etc. can be combined to judge whether the vehicle is located in a parking lot, identify the parking lot where the vehicle is located, obtain the positions of the first entrance and the second entrance, and judge whether they are the entrances of the same parking lot, etc. In an environment such as a community, etc., the global inertial navigation satellite system and RTK, etc. can be combined to judge whether the vehicle is located in a parking lot, identify the parking lot where the vehicle is located, obtain the positions of the first entrance and the second entrance, and judge whether they are the entrances of the same parking lot, etc.

[0060] Optionally, the interaction end can include, for example, a vehicle-mounted display, a mobile terminal, etc., which is not limited here. For example, the driver and passengers can judge whether it is the same parking lot, whether it is the same entrance, etc. through the in-vehicle screen.

[0061] In an alternative embodiment, it can also be the map management system that independently completes the judgment on whether the first entrance and the second entrance are the entrances of the same parking lot, which is not limited here.

[0062] S205: Integrate the current map and the historical map to form a new parking lot map.

[0063] In this embodiment, different strategies for updating the parking lot map can be designed in combination with whether the first entrance and the second entrance are the same parking lot entrance, that is, the current map and the historical map can be fused in different ways to form a new parking lot map. The specific working principle of updating the parking lot map will be exemplified in the following embodiments. The updated parking lot map is stored to utilize it for parking assistance, thereby facilitating the improvement of the performance of parking assistance.

[0064] Please refer to Figure 3 , Figure 3 which is a schematic flowchart of another embodiment of the map generation method of the present application.

[0065] S301: Determine whether the vehicle is in a parking lot.

[0066] In this embodiment, when it is determined that the vehicle is in a parking lot, it is considered that the parking lot map of the parking lot where it is located can be updated, and step S302 is executed; when it is determined that the vehicle is not in a parking lot, step S301 can be repeatedly executed or the process ends, which is not limited herein.

[0067] For example, it can be determined whether the vehicle is in a parking lot by the position information of vehicle positioning and / or whether the vehicle passes through the parking lot enclosure.

[0068] S302: Take the parking lot where the vehicle is located as the current parking lot and obtain the vehicle speed.

[0069] In this embodiment, when it is determined that the vehicle is in a parking lot, the parking lot where it is located is used as the current parking lot for updating the parking lot map, and the vehicle speed is obtained. In other words, in response to determining that the vehicle is in the current parking lot, the vehicle speed can be obtained.

[0070] S303: Determine whether the vehicle speed is lower than the first vehicle speed threshold.

[0071] In this embodiment, when it is determined that the vehicle speed is lower than the first vehicle speed threshold, it can be considered that the parking lot data collected by the vehicle is relatively complete and can be used for parking lot map drawing, so step S304 is executed; when it is determined that the vehicle speed is higher than the first vehicle speed threshold, step S301 can be repeatedly executed or step S303 can be executed or the process ends, which is not limited herein.

[0072] Among them, Figure 3For example, when it is determined that the vehicle speed is higher than the first vehicle speed threshold, it is possible to determine whether the current location of the vehicle is still a parking lot, so that when the vehicle leaves the parking lot, the judgment on whether to draw a parking lot map can be ended, which is conducive to reducing the situation where the judgment is still carried out after the vehicle has left the parking lot, and further reducing the related computing burden and reducing the occupation of computing resources, and further improving the rationality of the map generation method in this embodiment.

[0073] For example, the first vehicle speed threshold can be 15 km / h (kilometers per hour), 20 km / h, 25 km / h, 30 km / h, 40 km / h, etc., which is not limited here.

[0074] S304: Activate the parking lot map drawing function.

[0075] In this embodiment, in response to the vehicle speed being lower than the first vehicle speed threshold, it can be considered that the currently collected raw data / parking lot data is usually relatively complete. For example, the collected images are relatively clear, and the sensed radar data is relatively complete, which can be used to reduce the screening volume of data quality inspection and improve the effectiveness of the data. Therefore, it can be determined to activate the parking lot map drawing function.

[0076] S305: Obtain the parking lot data of the current parking lot collected by the vehicle to draw the current map.

[0077] In this embodiment, the parking lot data can refer to the raw data directly collected by the sensing device, or as exemplified above, the parking lot data can be the data retained after data quality inspection of the raw data.

[0078] Specifically, a front-view binocular camera, a front-side-view camera, a rear-side-view camera, a rear-view camera, a lidar, etc. can be used as sensing devices to form the data input end for drawing the current map.

[0079] The distance between an object and the vehicle, the length, width, and height dimensions of the object, etc. can be determined by comparing the image differences of different cameras, that is, the depth information of the object is obtained, and the environmental feature comparison is carried out in combination with the depth information. By performing perception, segmentation, etc. on the input image, parking lot data is formed for semantic mapping, positioning matching, and inertial navigation information matching, etc. During the process of input image perception and segmentation processing, the attributes of the objects existing in the input image can be marked, for example, attributes such as buildings, walls, elevators, and door passages can be marked.

[0080] The surrounding environment of the vehicle can be scanned, for example, by lidar, to obtain the point cloud formed by the reflection of objects in the environment. Feature points are extracted from the scanned point cloud of the lidar to form environmental features. Among them, corner points, intersection points, and end points of walls in the surrounding environment are extracted. Attributes of the objects scanned by the lidar can be labeled, such as attributes like buildings, walls, elevators, door passages, etc.

[0081] S306: Determine whether the map fusion condition is met.

[0082] In this embodiment, when it is determined that the map fusion condition is met, step S307 can be executed; when it is determined that the map fusion condition is not met, step S205 or step S306 or step S201 can be executed, which is not limited herein.

[0083] For example, the map fusion condition can be that the vehicle is in a parked state or the vehicle speed is lower than the second vehicle speed threshold. That is to say, the driving state of the vehicle can be obtained. In response to the vehicle being in a parked state or the vehicle speed being lower than the second vehicle speed threshold, it is considered that the map fusion condition is met, and it is determined that the current map and the historical map are allowed to be fused. Among them, the second vehicle speed threshold can be lower than or equal to the first vehicle speed threshold, which is not limited herein.

[0084] S307: Obtain the historical map.

[0085] S308: Determine whether the first entrance and the second entrance are the same parking lot entrance.

[0086] In this embodiment, when it is determined that the first entrance and the second entrance are the same parking lot entrance, step S309 can be executed; when it is determined that the first entrance and the second entrance are not the same parking lot entrance, step S310 can be executed.

[0087] S309: Starting from the first entrance and the second entrance, perform environmental feature comparison along the driving trajectory of the vehicle in the current map and the driving trajectory of the vehicle in the historical map to obtain the reference features.

[0088] In this embodiment, the reference features represent environmental features that exist in the current map and also exist in the historical map.

[0089] As Figure 4 exemplified and shown in Figure 4It is a bird's-eye view schematic diagram of an embodiment of the parking lot in this application. Taking the first entrance and the second entrance as entrance X for example, the vehicle reaches parking space A001 along paths L1, L5, and L6 in the historical map, that is, the driving trajectory of the vehicle in the historical map is paths L1, L5, and L6. The vehicle reaches parking space A001 along paths L8, L2, and L6 in the current map. Entrance X can be used as the starting point, and environmental features such as paths L1, L5, L6 and paths L8, L2, and L6 can be compared in sequence. After comparing the environmental features, path L6 is used as the reference feature.

[0090] S310: Determine whether there is a reference feature.

[0091] In this embodiment, when it is determined that there is a reference feature, step S311 can be executed; when it is determined that there is no reference feature, step S312 can be executed.

[0092] That is to say, in response to the first entrance and the second entrance not being the same parking lot entrance, the environmental features included in the current map and the historical map are compared to determine whether there is a reference feature. Figure 2 The environmental features included in the current map and the historical map are compared to determine whether there is a reference feature.

[0093] For example Figure 4 As shown in the example, taking the first entrance as entrance X and the second entrance as entrance Y for example, the vehicle reaches parking space A001 along paths L1, L5, and L6 in the historical map, that is, the driving trajectory of the vehicle in the historical map is paths L1, L5, and L6.

[0094] When the vehicle reaches parking space B001 along paths L8, L2, L6, and L3 in the current map, it can be determined that the first entrance and the second entrance are not the same parking lot entrance. By comparing the environmental features of the current map and the historical map, L6 can be used as the reference feature.

[0095] When the vehicle reaches parking space B001 along paths L8 and L9 in the current map, it can be determined that the first entrance and the second entrance are not the same parking lot entrance. Through the comparison of the environmental features of the current map and the historical map, it can be determined that there is no reference feature. Figure 2 It can be determined that there is no reference feature.

[0096] S311: Based on the reference feature, perform fusion mapping on the current map and the historical map.

[0097] In this embodiment, in response to obtaining a reference feature by comparing the environmental features of the current map and the historical map, the reference feature can be used to perform fusion mapping on the current map and the historical map. Figure 2 The reference feature can be used to perform fusion mapping on the current map and the historical map.

[0098] Specifically, a historical map and the current map can be obtained. Figure 2 In one of the two, the relative positions of other environmental features with respect to the reference feature can be obtained to add the other environmental features to the relative positions with respect to the reference feature in the other. Among them, the other environmental features can represent environmental features in the current map and the historical map that are not reference features.

[0099] In detail, in this embodiment, the first environmental features in the historical map, that is, the environmental features in the historical map that are not reference features, can also be obtained; the second environmental features in the current map, that is, the environmental features in the current map that are not reference features, can also be obtained.

[0100] The first relative position of the first environmental feature in the historical map with respect to the reference feature can be obtained, the first environmental feature can be added to the first relative position in the current map with respect to the reference feature, and the updated current map can be used as a new parking lot map. This is beneficial to improving the timeliness of the current map. Or, the second relative position of the second environmental feature in the current map with respect to the reference feature can be obtained, the second environmental feature can be added to the second relative position in the historical map with respect to the reference feature, and the updated historical map can be used as a new parking lot map to reduce the computational amount of adding other environmental features.

[0101] Furthermore, when fusing and mapping the current map and the historical map based on the reference feature, it is possible that the environmental features at the same position in the parking lot are different. It can be based on the environmental features at this position in the current map, or a confirmation request can be generated to request the user to manually intervene to select and confirm the environmental features at this position, which is not limited here.

[0102] Optionally, the relative pose of the current map and the historical map can also be obtained to optimize the global pose of the parking lot map using the relative pose, so as to be able to correct the drift and is beneficial to improving the matching accuracy between the current map and the historical map.

[0103] S312: Obtain the relative position relationship between the first entrance and the second entrance.

[0104] In this embodiment, in response to the first entrance and the second entrance being different parking lot entrances and there being no intersecting environmental features between the current map and the historical map, the relative position relationship between the first entrance and the second entrance can be obtained. Figure 2 The relative position relationship between the first entrance and the second entrance can be obtained.

[0105] For example, in this embodiment, the accuracy of the first position acquisition method may be higher than that of the second position acquisition method. The first position acquisition method is used to acquire the position information of the first entrance and the second entrance, that is, to acquire the position information of the parking lot entrance where the vehicle enters the parking lot; the second position is used to acquire the vehicle position, so as to reduce the amount of data for acquiring the vehicle position while improving the accuracy of the relative position information of the parking lot entrance.

[0106] S313: Supplement one of the current map and the historical map to the other. Figure 2 Supplement one of the current map and the historical map to the other.

[0107] In this embodiment, based on the relative position relationship between the first entrance and the second entrance, one of the current map and the historical map can be supplemented to the other to fuse the current map and the historical map. Figure 2 Supplement one of the current map and the historical map to the other to fuse the current map and the historical map.

[0108] For example, the current map can be supplemented to the historical map; or, the historical map can be supplemented to the current map; or, the data amounts of the current map and the historical map can be counted, and the one with the smaller data amount can be supplemented to the other, which is not limited here.

[0109] S314: Update the parking lot map.

[0110] In this embodiment, in response to fusing the current map and the historical map to form a new parking lot map, the new parking lot map is stored, and the updated parking lot map is used to participate in functions such as parking assistance.

[0111] In an alternative embodiment, it is also possible to not discriminate whether the first entrance and the second entrance are the same parking lot entrance, and fuse the current map and the historical map by comparing environmental features. For example, when it is determined that there are benchmark features in the current map and the historical map, the current map and the historical map are fused based on the benchmark features. When it is determined that there are no benchmark features, both the historical map and the current map can be stored as multiple historical maps for environmental feature comparison after the current map is drawn next time.

[0112] Further, when the vehicle first enters the current parking lot, the current map can be drawn and stored as the parking lot map of the current parking lot. So that when the vehicle is in the current parking lot again later, the stored parking lot map can be obtained as the historical map to update the parking lot map in combination with the currently drawn current map.

[0113] In layman's terms, in this embodiment, a basic semantic map can be constructed in the same parking lot. During the mapping process, for the same parking lot entrance of the same parking lot, when a parking lot map has been drawn in the current parking lot, and the vehicle enters the parking lot after passing through a downhill slope, parking lot fence, etc., when the vehicle meets the mapping conditions (i.e., the vehicle speed is lower than the first vehicle speed threshold), the current map can be drawn. When the vehicle meets the map fusion conditions (such as the vehicle is parked in a parking space, etc.), environmental features that do not exist in the historical map, such as parking spaces, walls, etc., can be supplemented from the parking lot entrance.

[0114] For different parking entrances of the same parking lot, the current map is drawn when the vehicle meets the mapping conditions. When the vehicle meets the map fusion conditions, it can start from the current parking entrance (i.e., the first entrance) to fill in the environmental features that do not exist in the historical map. When there is an intersection (i.e., a reference feature) between the current map and the historical map, the intersection is fused and mapped through map analysis and judgment of the environment such as feature points, line segments, planes, and parking space numbers. When there is no intersection between the current map and the historical map, the relative position relationship between the first entrance and the second entrance is analyzed, and the current map is fused with the historical map.

[0115] The following is a comparison of the current map and the historical map in this application. Figure 2 It should be noted that in the process of comparing environmental features to determine whether there are baseline features, the environmental features of the current map can be exactly the same as those of the historical map and are determined as baseline features; or, the similarity between the environmental features of the current map and those of the historical map reaches a similarity threshold and is determined as a baseline feature. It is not strictly limited that the environmental features existing in the current map and the historical map should be exactly the same.

[0116] Specifically, semantic information and inertial navigation information formed based on parking lot data may be acquired as first modeling data.

[0117] The semantic information may include road information of the current parking lot. For example, the road information may include at least one of road travel direction indication information such as arrows, lane lines, speed bumps, and the like.

[0118] The inertial navigation information may include environmental information of the vehicle's driving path. For example, the environmental information may include at least one of a wall, an obstacle, a building, an elevator, etc. The semantic information of the historical map and the inertial navigation information are obtained as the second modeling data. The depth information of the obstacles in the current parking lot is integrated, and modeling data matching such as loop detection is performed on the first modeling data and the second modeling data.

[0119] Optionally, models such as the bag-of-words model can be combined during the environmental feature comparison process. The bag-of-words can include, for example, people, vehicles, stairs, columns, etc. During the modeling data matching process, the parking lot data collected by the sensing device can be converted into forms such as bird's-eye views, or depth information can be fused to judge distances between channels, columns, etc.

[0120] Please refer to Figure 5 , Figure 5 which is a schematic flowchart of an embodiment of the environmental feature comparison of the present application.

[0121] S401: Obtain the parking lot area to which the environmental feature to be compared belongs.

[0122] In this example, the environmental feature to be compared belongs to one of the current map and the historical map. Figure 2 one of them.

[0123] For example, some parking lots will divide their parking lot areas, such as parking area A, parking area B, parking area C, etc. When there is a parking lot area division in the current parking lot, obtain the parking lot area to which the environmental feature to be compared belongs. If there is no parking lot area division in the current parking lot, step S401 can be omitted.

[0124] Optionally, by recognizing the input image collected by the camera device, it can be determined whether there is a mark of the parking lot area therein, so as to determine whether the current parking lot is divided into parking lot areas, and obtain the parking lot area to which the environmental feature to be compared belongs when dividing the parking lot area.

[0125] S402: Obtain the parking space number information of the parking spaces included in the environmental feature to be compared.

[0126] In this embodiment, the parking space number information of the parking spaces included in the environmental feature can also be obtained. For example, by recognizing the input image collected by the camera device, the parking space number information included in the input image is extracted.

[0127] For example, the parking space number information can be such as Figure 4 and as exemplified above, A001, B001, etc. Different parking lots can have different numbering methods for their parking space numbers. A001 and B001 are only for illustrative purposes.

[0128] S403: Obtain the information of the feature points included in the environmental feature to be compared.

[0129] In this embodiment, the information of the features included in the environmental feature can be obtained.

[0130] For example, the feature points may include at least one of a plane, a straight line, a corner point, a column spacing, an occlusion point, a surface point, smoothness, semantic information, etc. As described in the foregoing, the semantic information includes the road information of the current parking lot. Regarding the occlusion point, it can be marked and obtained by using the depth difference and pixel spacing between different camera devices, which is not limited herein.

[0131] S404: Determine whether there is a matching feature that matches the environmental feature to be compared.

[0132] In this embodiment, when it is determined that there is a matching feature that matches the environmental feature to be compared, step S405 is executed. When it is determined that there is no matching feature that matches the environmental feature to be compared, it can be considered that the environmental feature to be compared exists in the current map or the historical map to which it belongs, and the other does not include the environmental feature to be compared. Therefore, the comparison process of the current environmental feature to be compared ends. Further, environmental feature comparison can also be performed on other environmental features that have not been compared until the environmental feature comparison between the current map and the historical map is completed.

[0133] In this embodiment, the matching feature belongs to the current map and the historical map Figure 2 the other of the two. For example, when the environmental feature to be compared is an environmental feature in the current map, it can be compared with the environmental features in the historical map to determine whether there is a matching feature in the historical map. Similarly, when the environmental feature to be compared is an environmental feature in the historical map, it can be compared with the environmental features in the current map to determine whether there is a matching feature in the current map.

[0134] S405: Determine the environmental feature to be compared and the matching feature as reference features.

[0135] In this embodiment, in response to the existence of a matching feature that matches the environmental feature to be compared, it can be considered that the environmental feature to be compared and the matching feature exist in the current map and the historical map. Therefore, the two can be used as reference features.

[0136] Please refer to Figure 6 , Figure 6 which is a schematic flowchart of an embodiment of the parking assistance method of the present application. It should be noted that in this embodiment, the parking assistance method can be applied to self-learning parking functions, parking space recommendation functions, etc., which are not limited herein.

[0137] S501: Obtain a parking lot map; wherein, the parking lot map is generated by using a map generation method.

[0138] In this embodiment, the map generation method can be exemplified as described in any of the foregoing embodiments. The obtained parking lot map can be a fusion of the current map and the historical map at a historical moment.

[0139] S502: Obtain the current position of the vehicle and the target parking space.

[0140] In this embodiment, the current position is the position where the vehicle is located at the current moment.

[0141] The target parking space can be a predicted and recommended parking space, or a parking space where the user is accustomed to parking, historically marked, etc., and is not limited herein.

[0142] S503: Use the parking lot map to plan the driving route of the vehicle from the current position to the target parking space.

[0143] In this embodiment, the parking lot map can be used to plan the driving route of the vehicle so that the vehicle can drive from the current position to the target parking space through the planned driving route.

[0144] It should be understood that although Figures 1 - 3 and Figures 5 - 6 the steps in the flowchart of Figures 1 - 3 and Figures 5 - 6 are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover,

[0145] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of an embodiment of the map management system of the present application.

[0146] In one embodiment, a map management system is provided.

[0147] The map management system includes an input module 11 and a control module 12.

[0148] The input module 11 is used to obtain the parking lot data of the current parking lot.

[0149] The control module 12 is connected to the input module 11 and is used to implement the map generation method in any of the above embodiments; or is used to implement the parking assistance method in any of the above embodiments.

[0150] That is to say, the map management system can include a map generation system, a parking assistance system, etc., and is not limited herein.

[0151] For the specific limitations of the map management system, reference can be made to the limitations of the map generation method in the foregoing text, which will not be elaborated here. Each module in the above map management system can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0152] Taking the parking assistance system capable of implementing the parking assistance function as an example of the map management system, please refer to Figure 8 , Figure 8 which is a schematic structural diagram of an embodiment of the parking assistance system of the present application.

[0153] In one embodiment, the parking assistance system includes a map generation system 21 and a parking assistance module 22.

[0154] Among them, the map generation system 21 can implement the map generation method as described in the foregoing embodiments.

[0155] The parking assistance module 22 is connected to the map generation system 21 and is used to implement the parking assistance method as described in the foregoing text.

[0156] For the specific limitations of the parking assistance system, reference can be made to the limitations of the parking assistance method in the foregoing text, which will not be elaborated here. Each module in the above parking assistance system can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0157] Please refer to Figure 9 , Figure 9 which is a schematic structural diagram of an embodiment of the vehicle of the present application.

[0158] In one embodiment, the vehicle includes a vehicle body 31 and a map management system 32.

[0159] The vehicle body 31 is a set of structures required to implement the vehicle driving function. For example, the vehicle body 31 may include the basic structures required for vehicle form, such as power structures (generators and / or engines, etc.), electrical structures, chassis, body, etc. In this embodiment, the vehicle body 31 may further include a sensing device 311, and the sensing device 311 is used to collect parking lot data of the current parking lot.

[0160] The map management system 32 is connected to the sensing device 311 to obtain the parking lot data of the current parking lot collected by the sensing device 311, so as to implement the map generation method as described in the foregoing text.

[0161] Optionally, when the sensing device 311 senses the environment of the current parking lot, it can obtain raw data, and the map management system 32 performs data quality inspection on the raw data to obtain parking lot data.

[0162] It should be noted that the map management system 32 can be provided in the vehicle body 31; or, the map management system 32 can be provided in the cloud to share the computing workload of map generation by the cloud, which is not limited herein.

[0163] Furthermore, the vehicle can also include a parking assistance system as described above. The parking assistance system can be wholly provided in the vehicle body 31; or, as exemplified above, the map management system 32 can be provided in the cloud, while the parking assistance module can be provided in the vehicle body 31, which is not limited herein.

[0164] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, it implements the steps of the map generation method described above; or, it implements the steps of the parking assistance method described above, which will not be elaborated herein.

[0165] Please refer to Figure 10 , Figure 10 which is a schematic structural diagram of an embodiment of the computer device of the present application.

[0166] In one embodiment, a computer device is provided, and the computer device can be a server or a terminal.

[0167] Taking the computer device as a server as an example, its internal structure diagram can be as Figure 10 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store at least one of historical maps, raw data, parking lot data, and parking lot maps. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a map generation method or a parking assistance method.

[0168] Those skilled in the art can understand, Figure 10The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0169] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps may be implemented:

[0170] S101: Activate parking lot mapping function.

[0171] S102: Acquire parking lot data of the current parking lot collected by the vehicle to draw the current map.

[0172] S103: Obtain a historical map; wherein the historical map represents a parking lot map of the current parking lot drawn at a historical moment.

[0173] S104: The current map and the historical map are integrated to form a new parking lot map.

[0174] In one embodiment, when the current map and the historical map are integrated, the processor may further implement the following steps when executing the computer program: comparing the current map and the historical map; Figure 2 The environmental features of the current map are compared to obtain a baseline feature, a first environmental feature and a second environmental feature; wherein the baseline feature represents an environmental feature existing in the current map and in the historical map, the first environmental feature represents an environmental feature in the historical map that is not the baseline feature, and the second environmental feature represents an environmental feature in the current map that is not the baseline feature; a first relative position of the first environmental feature in the historical map compared to the baseline feature is obtained, and the first environmental feature is added to the first relative position in the current map compared to the baseline feature; or, a second relative position of the second environmental feature in the current map compared to the baseline feature is obtained, and the second environmental feature is added to the second relative position in the historical map compared to the baseline feature.

[0175] In one embodiment, the current map and the historical map are compared. Figure 2When the processor executes a computer program to determine the environmental characteristics of the vehicle, the following steps may also be implemented: obtaining semantic information and inertial navigation information formed based on parking lot data as first modeling data; wherein, the semantic information includes road information of the current parking lot, and the inertial navigation information includes environmental information of the vehicle driving path; obtaining semantic information and inertial navigation information of a historical map as second modeling data; and fusing depth information of obstacles in the current parking lot to perform modeling data matching on the first modeling data and the second modeling data.

[0176] In one embodiment, when comparing the current map and the historical map Figure 2 When the processor executes a computer program to determine the environmental characteristics of the vehicle, the following steps may also be implemented: obtaining the parking lot entrance where the current map starts to be drawn as the first entrance; obtaining the parking lot entrance where the historical map starts to be drawn as the second entrance; and in response to the first entrance and the second entrance being the same parking lot entrance, starting from the two, comparing the environmental characteristics along the driving trajectory of the vehicle on the current map and the driving trajectory of the vehicle on the historical map.

[0177] In one embodiment, when fusing the current map and the historical map, the following steps may also be implemented by the processor when executing a computer program: obtaining the relative position relationship between the first entrance and the second entrance; wherein, the first entrance represents the parking lot entrance where the current map starts to be drawn, and the second entrance represents the parking lot entrance where the historical map starts to be drawn; and based on the relative position relationship, supplementing one of the current map and the historical map to the other. Figure 2 One of the maps is supplemented to the other.

[0178] In one embodiment, the following steps may also be implemented by the processor when executing a computer program: determining whether the first entrance and the second entrance are the same entrance; generating a verification request using the determination result and sending the verification request to the interaction end; and obtaining a determination result for responding to the verification request to determine whether the first entrance and the second entrance are the same entrance.

[0179] In one embodiment, when obtaining parking lot data of the current parking lot collected by the vehicle to draw the current map, the following steps may also be implemented by the processor when executing a computer program: obtaining the original data of the currently collected parking lot; verifying whether the original data is complete; analyzing whether there is an occlusion area in the environment represented by the original data; obtaining the working state of the sensing device; wherein, the sensing device is used to collect the original data; and in response to the original data being complete, the environment it represents having no occlusion area, and the working state of the sensing device being normal, using the original data as the parking lot data.

[0180] In one embodiment, when activating the parking lot map drawing function, the processor may further implement the following steps when executing the computer program: in response to determining that the vehicle is in the current parking lot, obtaining the vehicle speed; in response to the vehicle speed being lower than the first vehicle speed threshold, determining to activate the parking lot map drawing function; and / or, before fusing the current map and the historical map, the processor may further implement the following steps when executing the computer program: obtaining the driving state of the vehicle; in response to the vehicle being in a parked state or the vehicle speed being lower than the second vehicle speed threshold, determining to allow fusing the current map and the historical map.

[0181] In one embodiment, the processor may further implement the following steps when executing the computer program: obtaining a parking lot map; wherein, the parking lot map is generated by using the map generation method in any one of the above embodiments; obtaining the current position of the vehicle and the target parking space; using the parking lot map to plan a driving path for the vehicle to drive from the current position to the target parking space.

[0182] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps may be implemented:

[0183] S101: Activate the parking lot map drawing function.

[0184] S102: Obtain the parking lot data of the current parking lot collected by the vehicle to draw the current map.

[0185] S103: Obtain a historical map; wherein, the historical map represents the parking lot map of the current parking lot drawn at a historical moment.

[0186] S104: Fuse the current map and the historical map to form a new parking lot map.

[0187] In one embodiment, when fusing the current map and the historical map, the computer program may further implement the following steps when executed by the processor: comparing the environmental features of the current map and the historical map to obtain a reference feature, a first environmental feature, and a second environmental feature; wherein, the reference feature represents the environmental feature that exists in the current map and exists in the historical map, the first environmental feature represents the environmental feature in the historical map that is not the reference feature, and the second environmental feature represents the environmental feature in the current map that is not the reference feature; obtaining the first relative position of the first environmental feature in the historical map relative to the reference feature, and adding the first environmental feature to the first relative position in the current map relative to the reference feature; or, obtaining the second relative position of the second environmental feature in the current map relative to the reference feature, and adding the second environmental feature to the second relative position in the historical map relative to the reference feature. Figure 2 ​

[0188] In one embodiment, when comparing the current map and the environmental features of the historical one, when the computer program is executed by the processor, the following steps can also be implemented: obtaining semantic information and inertial navigation information formed based on parking lot data as the first modeling data; wherein, the semantic information includes road information of the current parking lot, and the inertial navigation information includes environmental information of the vehicle driving path; obtaining semantic information and inertial navigation information of the historical map as the second modeling data; fusing the depth information of obstacles in the current parking lot to perform modeling data matching on the first modeling data and the second modeling data. Figure 2 In one embodiment, when comparing the current map and the environmental features of the historical one, when the computer program is executed by the processor, the following steps can also be implemented: obtaining the parking lot entrance where the current map starts to be drawn as the first entrance; obtaining the parking lot entrance where the historical map starts to be drawn as the second entrance; in response to the first entrance and the second entrance being the same parking lot entrance, starting from the two, comparing the environmental features along the driving trajectory of the vehicle on the current map and the driving trajectory of the vehicle on the historical map.

[0189] In one embodiment, when comparing the current map and the environmental features of the historical one, when the computer program is executed by the processor, the following steps can also be implemented: obtaining the parking lot entrance where the current map starts to be drawn as the first entrance; obtaining the parking lot entrance where the historical map starts to be drawn as the second entrance; in response to the first entrance and the second entrance being the same parking lot entrance, starting from the two, comparing the environmental features along the driving trajectory of the vehicle on the current map and the driving trajectory of the vehicle on the historical map. Figure 2 In one embodiment, when comparing the current map and the environmental features of the historical one, when the computer program is executed by the processor, the following steps can also be implemented: obtaining the parking lot entrance where the current map starts to be drawn as the first entrance; obtaining the parking lot entrance where the historical map starts to be drawn as the second entrance; in response to the first entrance and the second entrance being the same parking lot entrance, starting from the two, comparing the environmental features along the driving trajectory of the vehicle on the current map and the driving trajectory of the vehicle on the historical map.

[0190] In one embodiment, when fusing the current map and the historical map, when the computer program is executed by the processor, the following steps can also be implemented: obtaining the relative position relationship between the first entrance and the second entrance; wherein, the first entrance represents the parking lot entrance where the current map starts to be drawn, and the second entrance represents the parking lot entrance where the historical map starts to be drawn; based on the relative position relationship, supplementing one of the current map and the historical one to the other. Figure 2 In one embodiment, when fusing the current map and the historical map, when the computer program is executed by the processor, the following steps can also be implemented: obtaining the relative position relationship between the first entrance and the second entrance; wherein, the first entrance represents the parking lot entrance where the current map starts to be drawn, and the second entrance represents the parking lot entrance where the historical map starts to be drawn; based on the relative position relationship, supplementing one of the current map and the historical one to the other.

[0191] In one embodiment, when the computer program is executed by the processor, the following steps can also be implemented: determining whether the first entrance and the second entrance are the same entrance; generating a verification request using the determination result and sending the verification request to the interaction end; obtaining the determination result in response to the verification request to determine whether the first entrance and the second entrance are the same entrance.

[0192] In one embodiment, when obtaining the parking lot data of the current parking lot collected by the vehicle to draw the current map, when the computer program is executed by the processor, the following steps can also be implemented: obtaining the original data of the currently collected parking lot; verifying whether the original data is complete; analyzing whether there is an occlusion area in the environment represented by the original data; obtaining the working state of the sensing device; wherein, the sensing device is used to collect the original data; in response to the original data being complete, the environment it represents having no occlusion area, and the working state of the sensing device being normal, using the original data as the parking lot data.

[0193] In one embodiment, when the parking lot map drawing function is activated, the computer program, when executed by a processor, may further implement the following steps: in response to determining that the vehicle is in the current parking lot, obtaining the vehicle speed; in response to the vehicle speed being lower than the first vehicle speed threshold, determining to activate the parking lot map drawing function; and / or, before fusing the current map and the historical map, the computer program, when executed by a processor, may further implement the following steps: obtaining the driving state of the vehicle; in response to the vehicle being in a parked state or the vehicle speed being lower than the second vehicle speed threshold, determining to allow fusing the current map and the historical map.

[0194] In one embodiment, the computer program, when executed by a processor, may further implement the following steps: obtaining a parking lot map; wherein, the parking lot map is generated by using the map generation method in any of the above embodiments; obtaining the current position of the vehicle and the target parking space; and planning a driving path for the vehicle to travel from the current position to the target parking space by using the parking lot map.

[0195] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application may include non-volatile and / or volatile memories. Non-volatile memories may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0196] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0197] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application.

Claims

1. A map generation method, characterized in that: The map generation method comprises: Activate parking lot mapping; Obtain parking lot data of the current parking lot collected by the vehicle to draw the current map; Acquire a historical map; wherein the historical map represents a parking lot map of the current parking lot drawn at a historical moment; The current map and the historical map are integrated to form a new parking lot map.

2. The map generation method according to claim 1, characterized in that: The fusing of the current map and the historical map comprises: Comparing the environmental features of the current map and the historical map to obtain a baseline feature, a first environmental feature, and a second environmental feature; wherein the baseline feature represents an environmental feature that exists in the current map and in the historical map, the first environmental feature represents an environmental feature in the historical map that is not the baseline feature, and the second environmental feature represents an environmental feature in the current map that is not the baseline feature; Obtaining a first relative position of the first environmental feature in the historical map compared to the reference feature, adding the first environmental feature to the first relative position of the reference feature in the current map, and using the updated historical map as a new parking lot map; or, The second relative position of the second environmental feature in the current map compared to the reference feature is obtained, the second environmental feature is added to the second relative position of the reference feature in the historical map, and the updated current map is used as a new parking lot map.

3. The map generation method according to claim 2, characterized in that: The comparing the environmental features of the current map and the historical map also includes: Acquire semantic information and inertial navigation information formed based on the parking lot data as first modeling data; wherein the semantic information includes road information of the current parking lot, and the inertial navigation information includes environmental information of the vehicle's driving path; Acquiring semantic information and inertial navigation information of the historical map as second modeling data; The depth information of the obstacles in the current parking lot is integrated to perform modeling data matching on the first modeling data and the second modeling data.

4. The map generation method according to claim 2, characterized in that: The environmental features of the current map and the historical map are compared to each other including: Obtaining a parking lot entrance for starting to draw the current map as a first entrance; Obtaining the parking lot entrance where the historical map is initially drawn as the second entrance; In response to the first entrance and the second entrance being the same parking lot entrance, starting from the first entrance and the second entrance, an environmental feature comparison is performed along the driving trajectory of the vehicle on the current map and the driving trajectory of the vehicle on the historical map.

5. The map generation method according to claim 1, characterized in that: The fusing of the current map and the historical map comprises: Obtaining a relative positional relationship between a first entrance and a second entrance; wherein the first entrance represents an entrance to a parking lot from which the current map is initially drawn, and the second entrance represents an entrance to a parking lot from which the historical map is initially drawn; Based on the relative position relationship, one of the current map and the historical map is supplemented to the other.

6. The map generation method according to claim 4 or 5, characterized in that: The map generation method further comprises: Determining whether the first entrance and the second entrance are the same entrance; Generating a verification request using the judgment result, and sending the verification request to the interaction end; A determination result in response to the verification request is obtained to determine whether the first entry and the second entry are the same entry.

7. The map generation method according to claim 1, characterized in that: The step of obtaining parking lot data of the current parking lot collected by the vehicle to draw the current map includes: Obtain the collected original data of the current parking lot; Verifying whether the original data is complete; Analyze whether there is an occlusion area in the environment represented by the original data; Acquiring the working status of a sensing device; wherein the sensing device is used to collect the raw data; In response to the original data being complete, the environment represented by the original data having no blocked area, and the sensing device being in normal working state, the original data is used as the parking lot data.

8. The map generation method according to claim 1, characterized in that: The activation of the parking lot mapping function includes: In response to determining that the vehicle is in the current parking lot, acquiring a vehicle speed of the vehicle; In response to the vehicle speed being lower than a first vehicle speed threshold, determining to activate a parking lot mapping function; and / or, Before fusing the current map and the historical map, the following step is further included: Acquiring the driving status of the vehicle; In response to the vehicle being in a stopped state or the vehicle speed being lower than a second vehicle speed threshold, it is determined that fusion of the current map and the historical map is allowed.

9. A parking assistance method, characterized in that: The parking assistance method comprises: Acquire a parking lot map; wherein the parking lot map is generated using the map generation method according to any one of claims 1 to 8; Get the current position of the vehicle and the target parking space; The parking lot map is used to plan a driving path for the vehicle from the current position to the target parking space.

10. A map management system, characterized in that: The map management system comprises: An input module, used to obtain parking lot data of the current parking lot; A control module, connected to the input module, is used to implement the map generation method as described in any one of claims 1 to 8; or, is used to implement the parking assistance method as described in claim 9.

11. A vehicle, characterized in that: The vehicle comprises: The vehicle body includes a sensing device, wherein the sensing device is used to collect parking lot data of the current parking lot; The map management system as claimed in claim 10, connected to the sensing device.

12. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the processor implements the steps of the map generation method according to any one of claims 1 to 8; or implements the steps of the parking assistance method according to claim 9.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the map generation method according to any one of claims 1 to 8 are implemented; or, the steps of the parking assistance method according to claim 9 are implemented.

Images