Basement parking method, device and equipment for autonomous vehicle and medium

Abstract

The embodiment of the invention discloses a basement parking method, device and equipment for an automatic driving vehicle and a medium. The method comprises the steps that starting point position information when a current vehicle enters a basement is recorded; when the current vehicle runs in the basement, real-time position information of the current vehicle relative to the starting point position information is determined; according to the real-time position information, whether the current vehicle enters a geofence corresponding to a map starting point of a preset memory parking map or not is judged, and the preset memory parking map is a parking map which is trained and corresponds to the current garage; the map fence is a geographic area with the map starting point of the preset memory parking map as the circle center and the preset length as the radius; if it is judged that the current vehicle enters the geo-fence, a preset memory parking map corresponding to the map starting point serves as a current target parking map, and parking is conducted according to the current target parking map. By the adoption of the technical scheme, the problem that the memory parking success rate is low is solved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of autonomous driving technology, and more specifically, to a method, device, equipment and medium for underground parking of an autonomous driving vehicle. Background Art

[0002] Autonomous driving memory parking is an advanced car parking technology that allows the vehicle to automatically complete the entire parking process without human intervention.

[0003] Memory parking technology usually includes a learning phase and an application phase. During the learning phase, when the memory parking function is used for the first time, the driver needs to manually drive the vehicle to perform parking operations. During this process, the vehicle will collect information about the surrounding environment, including the size of the parking space, obstacles around the vehicle, etc. During the application phase, the driver can enable the memory parking function, and the vehicle will automatically sense the surrounding environment and use the previously learned information to perform parking operations. However, when the scenes where the garage exists in two locations are very similar, for example, for a multi-story basement, when the surrounding environment information of a certain position A on the first underground floor and a certain position B on the second underground floor is the same, the autonomous driving vehicle may have a positioning error problem, such as positioning position B on the second underground floor as position A on the first underground floor, or positioning position A on the first underground floor as position B on the second underground floor. Position positioning errors may lead to a low success rate for subsequent memory parking. Summary of the invention

[0004] Embodiments of the present invention provide a method, device, equipment and medium for underground parking of an autonomous driving vehicle to solve the problem of low success rate of memory parking due to positioning errors of the autonomous driving vehicle.

[0005] The specific technical solutions are as follows:

[0006] In a first aspect, an embodiment of the present invention provides a method for parking an autonomous driving vehicle in an underground parking garage, comprising:

[0007] Record the starting position information of the current vehicle when it enters the basement;

[0008] When the current vehicle is traveling in the basement, determining the real-time position information of the current vehicle relative to the starting position information;

[0009] According to the real-time location information, determine whether the current vehicle enters the geographic fence corresponding to the map starting point of the preset memory parking map, wherein the preset memory parking map is a trained parking map corresponding to the current garage, and the map starting points of different preset memory parking maps have different positions, and the map fence is a geographic area with the map starting point of the preset memory parking map as the center and a preset length as the radius;

[0010] If it is determined that the current vehicle enters the geographic fence, the preset memory parking map corresponding to the map starting point is used as the current target parking map, and the vehicle is driven according to the current target parking map to park.

[0011] It can be seen from the above scheme that by determining the real-time position information of the vehicle relative to the starting point of entering the underground garage, and based on the positional relationship between the real-time position information and the map starting point of the preset memory parking map, if it is determined that the current autonomous driving vehicle enters the geographic fence of the map starting point of a preset memory parking map, the preset memory parking map corresponding to the map starting point is used as the target parking map, and parking is performed according to the target parking map. This setting solves the problem of incorrect positioning of two positions due to the same surrounding environment information of two positions in the underground garage scenario, and also solves the problem that the autonomous driving vehicle cannot determine the current target parking map when there are multiple preset memory parking maps in the underground garage, effectively improving the success rate of autonomous driving vehicles parking in the underground garage.

[0012] Optionally, record the starting position information of the current vehicle when it enters the basement, including:

[0013] Identify whether the current vehicle enters the basement based on the vehicle pitch angle and / or visual image texture features collected by the sensor configured for the current vehicle;

[0014] Under the condition of identifying that the current vehicle enters the basement, the starting position information of the current vehicle when entering the basement is recorded.

[0015] Optionally, determining the real-time position information of the current vehicle relative to the starting position information includes:

[0016] The real-time position information of the current vehicle relative to the starting position information is determined by any one of the following sensor data, or the real-time position information of the current vehicle relative to the starting position information is determined by fusing the sensor data, wherein each sensor includes an inertial measurement unit IMU, an image sensor, a radar and an odometer.

[0017] Optionally, the method provided by the embodiment of the present invention further includes:

[0018] When the current vehicle is driving in the basement, the real-time position information of the current vehicle relative to the starting position is saved;

[0019] When the current vehicle is turned off and powered off, the location information of the current vehicle at the time of power off is obtained as the historical location information;

[0020] When the current vehicle is powered on again, the current position information is calculated based on the historical position information as the real-time position information after power-on.

[0021] Through the above technical solution, it can be seen that under the premise that the current autonomous driving vehicle does not leave the basement, it is still possible to determine whether it has entered the geographic fence of the starting point of a preset memory parking map based on the vehicle's real-time location information, without having to leave the basement again to obtain a GPS signal, and the memory parking function can continue to be used, which effectively improves the efficiency of automatic parking in the basement scenario.

[0022] Optionally, the method provided by the embodiment of the present invention further includes:

[0023] In the case where it is detected that there is no preset memory parking map in the current basement, if a memory parking map building instruction triggered by a user is received, a memory parking map is created according to the driving trajectory of the current vehicle in the manual driving mode.

[0024] In a second aspect, an embodiment of the present invention further provides an underground parking device for an autonomous driving vehicle, comprising:

[0025] The starting position recording module is configured to record the starting position information of the current vehicle when it enters the basement;

[0026] A real-time position determination module is configured to determine the real-time position information of the current vehicle relative to the starting position information when the current vehicle is traveling in the basement;

[0027] a map starting point determination module, configured to determine whether the current vehicle enters a geographic fence corresponding to a map starting point of a preset memory parking map according to the real-time location information, wherein the preset memory parking map is a trained parking map corresponding to the current garage, and the locations of the map starting points of different preset memory parking maps are different, and the map fence is a geographic area with the map starting point of the preset memory parking map as the center and a preset length as the radius;

[0028] The target parking map determination module is configured to use the preset memory parking map corresponding to the map starting point as the current target parking map if it is determined that the current vehicle enters the geographic fence, and drive according to the current target parking map to park.

[0029] Optionally, the starting point location recording module is configured as follows:

[0030] Identify whether the current vehicle enters the basement based on the vehicle pitch angle and / or visual image texture features collected by the sensor configured for the current vehicle;

[0031] Under the condition of identifying that the current vehicle enters the basement, the starting position information of the current vehicle when entering the basement is recorded.

[0032] Optionally, the real-time location determination module is specifically configured as follows:

[0033] The real-time position information of the current vehicle relative to the starting position information is determined by any one of the following sensor data, or the real-time position information of the current vehicle relative to the starting position information is determined by fusing the sensor data, wherein each sensor includes an inertial measurement unit IMU, an image sensor, a radar and an odometer.

[0034] Optionally, the device provided by the embodiment of the present invention further includes:

[0035] The real-time position information holding module is configured to store the real-time position information of the current vehicle relative to the starting position during the driving of the current vehicle in the basement;

[0036] The historical position information acquisition module is configured to acquire the position information of the current vehicle when the current vehicle is turned off as the historical position information;

[0037] The power-on position information determination module is configured to calculate the current position information according to the historical position information when the current vehicle is powered on again, as the real-time position information after power-on.

[0038] Optionally, the device provided by the embodiment of the present invention further includes:

[0039] The mapping module is configured to create a memory parking map according to the driving trajectory of the current vehicle in the manual driving mode if it detects that there is no preset memory parking map in the current basement and receives a memory parking map mapping instruction triggered by a user.

[0040] In a third aspect, an embodiment of the present invention provides a computer device, the computer device comprising:

[0041] At least one processor is coupled to a memory, and the memory stores a program or instruction that runs on the processor. When the program or instruction is executed by the processor, the underground parking method for an autonomous driving vehicle provided in any embodiment of the present invention is implemented.

[0042] In a fourth aspect, an embodiment of the present invention provides a readable storage medium having a program or instruction stored thereon, which, when executed by a processor, implements a method for underground parking of an autonomous driving vehicle as provided in any embodiment of the present invention.

[0043] In a fifth aspect, an embodiment of the present invention provides a vehicle, which includes the underground parking device for an autonomous driving vehicle provided by any embodiment of the present invention, or includes the computer device provided by any embodiment of the present invention.

[0044] In a sixth aspect, an embodiment of the present invention provides a computer program, which includes program instructions, and when the program instructions are executed by a computer, implements the underground parking method of an autonomous driving vehicle provided in any embodiment of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1a A flowchart of an underground parking method for an autonomous driving vehicle provided in Embodiment 1 of the present invention;

[0047] Figure 1b A schematic diagram of a basement scene provided in Embodiment 1 of the present invention;

[0048] Figure 2 A structural block diagram of an underground parking device for an autonomous driving vehicle provided in Embodiment 2 of the present invention;

[0049] Figure 3 A structural block diagram of a computer device provided in Embodiment 3 of the present invention;

[0050] Figure 4 A schematic diagram of a vehicle provided in accordance with a fourth embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0053] The embodiments of the present invention disclose a method, device, equipment and medium for underground parking of an autonomous driving vehicle, which are described in detail below.

[0054] Embodiment 1

[0055] Figure 1a This is a flowchart of a method for underground parking of an autonomous driving vehicle provided in the first embodiment of the present invention. The method can be applied to vehicle terminals such as vehicle computers and vehicle industrial personal computers (IPC), and can also be applied to servers, and the present embodiment does not limit this. The method provided in this embodiment can be applied to the application scenario of underground parking. The method provided in this embodiment can be executed by an underground parking device for an autonomous driving vehicle, which can be implemented by software and / or hardware. Figure 1a As shown, the method provided in this embodiment specifically includes:

[0056] S110, recording the starting position information of the current vehicle when it enters the basement.

[0057] In this embodiment, in order to record the starting position information of the current vehicle when it enters the basement, it is necessary to first detect whether the current vehicle enters the basement.

[0058] As an optional implementation, image texture features may be obtained based on image information collected by an onboard sensor of the current vehicle, and then it may be determined whether the current vehicle has entered the basement based on the image texture features.

[0059] As another optional implementation, since there is usually a slope section when driving from the ground surface into the underground garage, and when the vehicle is driving on the slope section, there will be a certain angle between the vehicle posture and the horizontal plane, that is, the pitch angle of the vehicle relative to the horizontal plane. The size of the pitch angle of the current vehicle relative to the horizontal plane can be used to determine whether the vehicle has entered the underground garage. For example, if the pitch angle is greater than 4°, it means that the vehicle is driving on the slope section entering the underground garage, which means that the current vehicle has entered the underground garage. The pitch angle of the vehicle can be determined by an IMU (Inertial Measurement Unit), or it can be obtained by fusing data from multiple on-board sensors (such as IMU, GPS, and image sensors, etc.).

[0060] As another optional implementation, the pitch angle of the vehicle and the visual image texture features collected by the sensor currently configured for the vehicle may be combined to identify whether the vehicle enters the basement.

[0061] Under the condition that it is determined that the current vehicle enters the basement, the starting position information of the current vehicle when entering the basement can be recorded. For example, the starting position can be set as the coordinate starting point 0.

[0062] S120: When the current vehicle is traveling in the basement, determine the real-time position information of the current vehicle relative to the starting point position information.

[0063] In this embodiment, the real-time position information of the current vehicle relative to the starting position information can be determined by any of the following sensor data, or the real-time position information of the current vehicle relative to the starting position information can be determined by fusing multiple sensor data, wherein each sensor data includes: IMU data, image data, radar point cloud data, and odometer data, etc. This embodiment does not specifically limit the type and number of sensors.

[0064] S130. Determine whether the current vehicle enters the geographic fence corresponding to the starting point of the preset memory parking map according to the real-time location information. If so, execute step S140; otherwise, return to execute step S130.

[0065] Among them, the preset memory parking map is a trained parking map corresponding to the current garage. In the process of training the memory parking map, the driver needs to manually start the memory parking function of the autonomous driving vehicle. The autonomous driving vehicle will record the parking route according to the driver's driving route and create a parking map. When the driver turns off the parking function, the parking map is created. The locations of the map starting points of different preset memory parking maps are different. For each map starting point, there is a corresponding geographic fence, which is a geographical area with the map starting point of the preset memory parking map as the center and a preset length (for example, two meters) as the radius.

[0066] Specifically, Figure 1b A schematic diagram of a basement scene provided in the first embodiment of the present invention, such as Figure 1b As shown in the figure, point A is the starting point for the driver to start the memory parking function, and memory parking route 1 corresponds to the preset memory parking map 1. Point B is another starting point for the driver to start the memory parking function, and memory parking route 2 corresponds to the preset memory parking map Figure 2 .like Figure 1b As shown, the end point where the driver ends the memory parking function may be the target parking space p, or may be a position near the target parking space q, both of which are possible.

[0067] In this embodiment, when the autonomous driving vehicle is driving in the basement, the preset memory parking map corresponding to the current position can be selected based on the position relationship between the real-time position information and the map starting point of the preset memory parking map, so that automatic parking can be performed according to the preset memory parking map. Figure 1b If the car is within the geographic fence of point A shown in the figure, select the preset memory parking map 1, and the current real-time location is Figure 1b If the vehicle is within the geographic fence of point B, select the preset memory parking location. Figure 2 This avoids the problem of incorrect positioning of points A and B due to the same surrounding environment information of points A and B in the basement scene.

[0068] In addition, in the related art, the autonomous driving vehicle can currently only select one preset memory parking map as the target parking map for guiding the current autonomous driving vehicle to automatically park. If a basement has multiple memory parking maps, such as Figure 1b In the present embodiment, different preset parking maps correspond to different map starting points. By determining the real-time position information of the current vehicle relative to the starting point of the basement, and according to the position relationship between the real-time position information and the starting point of the preset map, the target parking map corresponding to the position can be selected according to the current real-time position information, thereby solving the problem in the related art that when there are multiple preset memory parking maps in a basement, the automatic driving vehicle cannot determine the target parking map to be selected at present.

[0069] S140: Using the preset memory parking map corresponding to the map starting point as the current target parking map, and driving according to the target parking map to park.

[0070] Those skilled in the art can understand that, if it is determined that the current vehicle has entered the geographic fence of the map starting point of the preset memory parking map, then compared with the method of matching the preset memory parking map from the starting point of the basement, the technical solution provided in this embodiment can reduce the matching point judgment threshold between the current real-time position and the preset memory parking map, thereby increasing the positioning success rate.

[0071] Those skilled in the art may also understand that, when the autonomous driving vehicle is driving according to the target parking map, it needs to drive in combination with the perceived environmental scene. If a braking factor occurs, such as an obstacle ahead, it needs to brake and stop. Alternatively, if there is a vehicle parked in the target parking space corresponding to the target parking map, then even if the end point of the memory parking route of the target parking map is to reach the target parking space, the current autonomous driving vehicle needs to brake and stop before entering the target parking space. After the current autonomous driving vehicle brakes and stops, the autonomous driving vehicle can reselect a suitable target parking space based on the perceived current environmental information, or the driver can enable the manual driving mode to park. If the end point of the parking route of the target parking map is a certain position in front of the target parking space, for example Figure 1bThe end point of the preset parking map 1 shown is a certain position before entering the parking space q. The current autonomous driving vehicle performs the first stage of parking according to the target parking map, that is, the autonomous driving vehicle drives to the front of the target parking space and completes the first stage of parking at the end point of the target parking map. In the second stage of the parking action, the autonomous driving vehicle can determine the target parking space based on the current environmental information perceived, or it can also use the manual driving mode to determine the target parking space in the second stage.

[0072] In addition, in the related art, if the autonomous driving vehicle is already in the basement when memory parking is needed, since the autonomous driving vehicle cannot obtain the GPS signal of the vehicle in the basement scenario, after the autonomous driving vehicle is turned off and powered on again, the vehicle must first be driven out of the basement to obtain the GPS coordinates of the vehicle, and then the vehicle can be driven into the basement, otherwise the memory parking function cannot be used directly in the basement. In this embodiment, the real-time position information of the current vehicle relative to the starting position can be saved during the driving of the current autonomous driving vehicle in the basement. When the current vehicle is turned off and powered off, the position information of the current vehicle at the time of power off can be obtained as the historical position information. After the vehicle is turned off and powered off, it will continue to move forward for a distance due to inertia. When the current vehicle is powered on again, the current position information can be calculated based on the historical position information as the real-time position information after power on. The advantage of this setting is that if the vehicle is turned off and the power is lost, when the vehicle is powered on again, and provided that the current autonomous driving vehicle does not leave the basement, it can still be determined based on the vehicle's real-time location information whether it has entered the geographic fence of the starting point of a preset memory parking map, without the need to leave the basement again to obtain a GPS signal, effectively improving the efficiency of automatic parking in the basement scenario.

[0073] Specifically, the method for calculating the current position information based on the historical position information can be based on sensor data such as IMU data, image data, radar point cloud data or odometer data, or it can also be calculated by combining the above-mentioned multiple sensors. This embodiment does not make specific limitations on this.

[0074] The technical solution provided in this embodiment determines the real-time position information of the vehicle relative to the starting point of entering the underground garage, and based on the positional relationship between the real-time position information and the map starting point of the preset memory parking map, if it is determined that the current autonomous driving vehicle enters the geographic fence of the map starting point of a preset memory parking map, the preset memory parking map corresponding to the map starting point is used as the target parking map, and parking is performed according to the target parking map. This setting solves the problem of incorrect positioning of two positions due to the same surrounding environment information of two positions in the underground garage scenario, and also solves the problem that the autonomous driving vehicle cannot determine the current target parking map when there are multiple preset memory parking maps in the underground garage, thereby effectively improving the success rate of autonomous driving vehicles parking in the underground garage.

[0075] Furthermore, when it is detected that there is no preset memory parking map in the current basement, if a memory parking map building instruction triggered by a user is received, a memory parking map is created according to the driving trajectory of the current vehicle in the manual driving mode.

[0076] Embodiment 2

[0077] Figure 2 This is a structural block diagram of an underground parking device for an autonomous driving vehicle provided in Embodiment 2 of the present invention, such as Figure 2 As shown, the device includes: a starting position recording module 210, a real-time position determination module 220, a map starting point determination module 230 and a target parking map determination module 240, wherein:

[0078] The starting position recording module 210 is configured to record the starting position information of the current vehicle when it enters the basement;

[0079] The real-time position determination module 220 is configured to determine the real-time position information of the current vehicle relative to the starting position information when the current vehicle is traveling in the basement;

[0080] The map starting point determination module 230 is configured to determine whether the current vehicle enters a geographic fence corresponding to a map starting point of a preset memory parking map according to the real-time location information, wherein the preset memory parking map is a trained parking map corresponding to the current garage, and the locations of the map starting points of different preset memory parking maps are different. The map fence is a geographic area with the map starting point of the preset memory parking map as the center and a preset length as the radius;

[0081] The target parking map determination module 240 is configured to use the preset memory parking map corresponding to the map starting point as the current target parking map if it is determined that the current vehicle enters the geographic fence, and drive according to the current target parking map to park.

[0082] Optionally, the starting point location recording module 210 is configured to:

[0083] Identify whether the current vehicle enters the basement based on the vehicle pitch angle and / or visual image texture features collected by the sensor configured for the current vehicle;

[0084] Under the condition of identifying that the current vehicle enters the basement, the starting position information of the current vehicle when entering the basement is recorded.

[0085] Optionally, the real-time location determination module 220 is specifically configured as follows:

[0086] The real-time position information of the current vehicle relative to the starting position information is determined by any one of the following sensor data, or the real-time position information of the current vehicle relative to the starting position information is determined by fusing the sensor data, wherein each sensor includes an inertial measurement unit IMU, an image sensor, a radar and an odometer.

[0087] Optionally, the device provided by the embodiment of the present invention further includes:

[0088] The real-time position information holding module is configured to store the real-time position information of the current vehicle relative to the starting position during the driving of the current vehicle in the basement;

[0089] The historical position information acquisition module is configured to acquire the position information of the current vehicle when the current vehicle is turned off as the historical position information;

[0090] The power-on position information determination module is configured to calculate the current position information according to the historical position information when the current vehicle is powered on again, as the real-time position information after power-on.

[0091] Optionally, the device provided by the embodiment of the present invention further includes:

[0092] The mapping module is configured to create a memory parking map according to the driving trajectory of the current vehicle in the manual driving mode if it detects that there is no preset memory parking map in the current basement and receives a memory parking map mapping instruction triggered by a user.

[0093] The underground parking device for an autonomous driving vehicle provided in the embodiment of the present invention can execute the underground parking method for an autonomous driving vehicle provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in the above embodiments, please refer to the underground parking method for an autonomous driving vehicle provided in any embodiment of the present invention.

[0094] Embodiment 3

[0095] Figure 3 A structural block diagram of a computer device provided in Embodiment 3 of the present invention is shown in FIG. Figure 3 As shown, the computer device includes:

[0096] At least one processor ( Figure 3 A processor 520 is shown,

[0097] The processor 520 is coupled to the memory 510, and the memory 510 stores a program or instruction that runs on the processor 520. When the program or instruction is executed by the processor 520, the underground parking method for the autonomous driving vehicle provided in any embodiment of the present invention is implemented.

[0098] Based on the above embodiments, another embodiment of the present invention provides a vehicle, wherein the vehicle includes the apparatus as described in any of the above embodiments, or includes the computer device as described above.

[0099] Embodiment 4

[0100] Figure 4 This is a schematic diagram of a vehicle provided in Embodiment 4 of the present invention. Figure 4 As shown, the vehicle includes a speed sensor 61, an ECU (Electronic Control Unit) 62, a GPS (Global Positioning System) positioning device 63, and a T-Box (Telematics Box) 64. The speed sensor 61 is used to measure the vehicle speed and use the vehicle speed as an empirical speed for model training; the GPS positioning device 63 is used to obtain the current geographic location of the vehicle; the T-Box 64 can communicate with the server as a gateway; and the ECU 62 can execute the above-mentioned underground parking method of the autonomous driving vehicle.

[0101] In addition, the vehicle may also include: a V2X (Vehicle-to-Everything) module 65, a radar 66 and a camera 67. The V2X module 65 is used to communicate with other vehicles, roadside equipment, etc.; the radar 66 or the camera 67 is used to sense the road environment information in the front and / or other directions to obtain original point cloud data; the radar 66 and / or the camera 67 can be configured at the front and / or rear of the vehicle body.

[0102] Based on the above method embodiments, another embodiment of the present invention provides a readable storage medium having a program or instruction stored thereon, which, when executed by a processor, enables the processor to implement the underground parking method for an autonomous driving vehicle as described in any of the above embodiments.

[0103] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0104] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed accordingly and located in one or more devices different from the embodiment. The modules in the above embodiment can be combined into one module, or can be further divided into multiple sub-modules.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for underground parking of an autonomous driving vehicle, characterized in that: include: Record the starting position information of the current vehicle when it enters the basement; When the current vehicle is traveling in the basement, determining the real-time position information of the current vehicle relative to the starting position information; According to the real-time location information, determining whether the current vehicle enters a geographic fence corresponding to a map starting point of a preset memory parking map, wherein the preset memory parking map is a trained parking map corresponding to the current garage, and different preset memory parking maps have different map starting points, and the map fence is a geographic area with the map starting point of the preset memory parking map as the center and a preset length as the radius; If it is determined that the current vehicle enters the geographic fence, the preset memory parking map corresponding to the map starting point is used as the current target parking map, and the vehicle is driven according to the current target parking map to park.

2. The method according to claim 1, characterized in that The starting position information of the current vehicle entering the basement is recorded, including: Identify whether the current vehicle enters the basement based on the vehicle pitch angle and / or visual image texture features collected by the sensor configured for the current vehicle; Under the condition of identifying that the current vehicle enters the basement, the starting position information of the current vehicle when entering the basement is recorded.

3. The method according to claim 1, characterized in that The determining of the real-time position information of the current vehicle relative to the starting position information includes: The real-time position information of the current vehicle relative to the starting position information is determined by any one of the following sensor data, or the real-time position information of the current vehicle relative to the starting position information is determined by fusing the sensor data, wherein each sensor includes an inertial measurement unit IMU, an image sensor, a radar and an odometer.

4. The method according to claim 1, characterized in that The method further comprises: During the driving of the current vehicle in the basement, saving the real-time position information of the current vehicle relative to the starting position; When the current vehicle is turned off and powered off, the location information of the current vehicle when powered off is used as the historical location information; When the current vehicle is powered on again, the current position information is calculated based on the historical position information as the real-time position information after power-on.

5. The method according to claim 1, characterized in that The method further comprises: In the case where it is detected that there is no preset memory parking map in the current basement, if a memory parking map building instruction triggered by a user is received, a memory parking map is created according to the driving trajectory of the current vehicle in the manual driving mode.

6. An underground parking device for an autonomous driving vehicle, characterized in that: include: The starting position recording module is configured to record the starting position information of the current vehicle when it enters the basement; A real-time position determination module, configured to determine the real-time position information of the current vehicle relative to the starting position information when the current vehicle is traveling in the basement; a map starting point determination module, configured to determine, based on the real-time location information, whether the current vehicle enters a geographic fence corresponding to a map starting point of a preset memory parking map, wherein the preset memory parking map is a trained parking map corresponding to the current garage, and different preset memory parking maps have different map starting points, and the map fence is a geographic area with the map starting point of the preset memory parking map as the center and a preset length as the radius; The target parking map determination module is configured to use the preset memory parking map corresponding to the map starting point as the current target parking map if it is determined that the current vehicle enters the geographic fence, and drive according to the current target parking map to park.

7. The device according to claim 6, characterized in that The starting point location recording module is configured as follows: Identify whether the current vehicle enters the basement based on the vehicle pitch angle and / or visual image texture features collected by the sensor configured for the current vehicle; Under the condition of identifying that the current vehicle enters the basement, the starting position information of the current vehicle when entering the basement is recorded.

8. The device according to claim 6, characterized in that The real-time location determination module is specifically configured as follows: The real-time position information of the current vehicle relative to the starting position information is determined by any one of the following sensor data, or the real-time position information of the current vehicle relative to the starting position information is determined by fusing the sensor data, wherein each sensor includes an inertial measurement unit IMU, an image sensor, a radar and an odometer.

9. The device according to claim 6, characterized in that The device also includes: A real-time position information maintaining module, configured to save the real-time position information of the current vehicle relative to the starting position during the driving of the current vehicle in the basement; A historical position information acquisition module is configured to use the position information of the current vehicle when the current vehicle is powered off as the historical position information when the current vehicle is powered off; The power-on position information determination module is configured to calculate the current position information according to the historical position information when the current vehicle is powered on again, as the real-time position information after power-on.

10. A computer device, characterized in that: The method comprises at least one processor, wherein the processor is coupled to a memory, wherein the memory stores a program or instruction running on the processor, and wherein the program or instruction, when executed by the processor, implements the steps of the underground parking method for an autonomous driving vehicle as described in any one of claims 1 to 5.

11. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by the processor, the steps of the underground parking method for an autonomous driving vehicle as described in any one of claims 1 to 5 are implemented.

Images