Parking path planning method and device, vehicle, and storage medium

Abstract

The application discloses a parking path planning method and device, a vehicle and a storage medium. The method comprises the following steps: after determining that the vehicle enters a target parking lot, acquiring environmental data of the vehicle, wherein the environmental data of the vehicle comprises spatial position information of a sensing target and spatial position information of an obstacle; acquiring an electronic map of a ramp region in the target parking lot based on the spatial position information of the sensing target, and acquiring an electronic map of a flat region in the target parking lot based on the spatial position information of the sensing target; and performing path planning based on the electronic map of the ramp region, the electronic map of the flat region and the spatial position information of the obstacle, so as to obtain a planned parking path of the vehicle. The technical scheme provided in the application embodiment can realize autonomous navigation and automatic parking in the target parking lot with the ramp region, and the intelligence of automatic driving is improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a parking route planning method, device, vehicle, and storage medium. Background Technology

[0002] Currently, vehicles need accurate electronic maps to achieve autonomous navigation and automatic parking in indoor parking lots.

[0003] The parking route planning method provided by related technologies is usually as follows: obtain the location information of the perceived target in the indoor parking lot, then generate an electronic map based on the above location information, and finally rely on the generated electronic map to complete the parking route planning.

[0004] However, the above parking route planning scheme is not applicable to multi-story parking garages, meaning that it cannot generate electronic maps of multi-story parking garages, which makes it impossible to complete the subsequent parking route planning smoothly. Summary of the Invention

[0005] This application proposes a parking route planning method, device, vehicle, and storage medium.

[0006] In a first aspect, embodiments of this application provide a parking route planning method, the method comprising: after determining that a vehicle has entered a target parking lot, acquiring environmental data of the vehicle, the environmental data of the vehicle including spatial location information of a perceived target and spatial location information of obstacles; acquiring an electronic map of a ramp area in the target parking lot based on the spatial location information of the perceived target, and acquiring an electronic map of a flat area in the target parking lot based on the spatial location information of the perceived target; and performing route planning based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of obstacles to obtain a planned parking route for the vehicle.

[0007] Secondly, embodiments of this application provide a parking route planning device, which includes: a data acquisition module, used to acquire environmental data of the vehicle after determining that the vehicle has entered the target parking lot, the environmental data of the vehicle including spatial location information of the perceived target and spatial location information of obstacles; a first map acquisition module, used to acquire an electronic map of the ramp area in the target parking lot based on the spatial location information of the perceived target; a second map acquisition module, used to acquire an electronic map of the flat area in the target parking lot based on the spatial location information of the perceived target; and a route planning module, used to perform route planning based on the electronic map of the ramp area, the electronic map of the flat area and the spatial location information of obstacles to obtain the planned parking route of the vehicle.

[0008] Thirdly, embodiments of this application provide a vehicle, including: one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to perform the parking route planning method as described in the first aspect.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions that can be invoked by a processor to execute the parking path planning method as described in the first aspect.

[0010] Fifthly, embodiments of this application provide a computer program product that, when executed, enables the implementation of the parking route planning method as described in the first aspect.

[0011] Compared to existing technologies, the parking route planning method provided in this application involves the vehicle sensing environmental data through a fusion perception module after entering the target parking lot. This environmental data includes spatial location information of the perceived targets and spatial location information of obstacles. The vehicle generates electronic maps of the ramp area and the flat area in the target parking lot based on the spatial location information of the perceived targets. Finally, the vehicle can plan a parking route based on the electronic maps of the ramp area, the flat area, and the spatial location data of the obstacles, thereby achieving autonomous navigation and automatic parking in target parking lots with ramp areas, improving the intelligence of autonomous driving. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the implementation environment provided in the embodiments of this application.

[0014] Figure 2 This is a flowchart of a parking route planning method provided in one embodiment of this application.

[0015] Figure 3 This is a flowchart of another parking route planning method provided in one embodiment of this application.

[0016] Figure 4 This is a schematic diagram of path point division provided in one embodiment of this application.

[0017] Figure 5This is a flowchart of another parking route planning method provided in one embodiment of this application.

[0018] Figure 6 This is a structural block diagram of a parking route planning device provided in one embodiment of this application.

[0019] Figure 7 This is a structural block diagram of a vehicle provided in one embodiment of this application.

[0020] Figure 8 This is a structural block diagram of a computer storage medium provided in one embodiment of this application. Detailed Implementation

[0021] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0022] To enable those skilled in the art to better understand the solutions of this application, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0023] Please see Figure 1 This diagram illustrates an implementation environment provided in one embodiment of the present application. The implementation environment includes a vehicle 100, which refers to a means of transportation driven or towed by a power unit for the purpose of carrying people or transporting goods, including but not limited to cars, suburban utility vehicles (SUVs), multi-purpose vehicles (MPVs), etc.

[0024] In this embodiment, the vehicle 100 includes a fusion perception module, which is used to perceive environmental data of the vehicle 100, including but not limited to: road information on which the vehicle 100 travels (such as road boundaries, traffic lights, traffic signs, traffic cones, speed bumps), and information on obstacles around the vehicle 100 (such as vehicles, pedestrians, trees, animals, etc.). In some embodiments, the vehicle 100 includes a visual perception submodule and a radar perception submodule.

[0025] The visual perception submodule is used to capture environmental images of the vehicle 100. This submodule can be a dashcam mounted on the vehicle 100 or a surround-view camera. The radar perception submodule is used to detect parameters such as the distance between obstacles around the vehicle 100 and the vehicle 100, the shape of the obstacles, the angle of the obstacles relative to the vehicle 100, and the speed of the obstacles. The radar perception submodule can include one or more of the following: lidar, millimeter-wave radar, ultrasonic radar, etc. These radar perception submodules enable the vehicle 100 to have three-dimensional perception capabilities, allowing it to accurately determine the position of obstacles even on undulating terrain (such as slopes).

[0026] In this embodiment, the vehicle 100 further includes a mapping module, which generates an electronic map based on environmental data acquired by the fusion perception module. Optionally, the mapping module establishes the electronic map using Simultaneous Localization and Mapping (SLAM) technology. In this embodiment, the vehicle 100 also includes a storage module, which stores the generated electronic map and can also store previously used electronic maps.

[0027] In this embodiment, the vehicle 100 further includes a path planning module, which is used to plan the vehicle's driving path based on environmental data acquired by the fusion perception module. In some embodiments, the vehicle 100 includes multiple path planning sub-modules, which are used to plan paths based on different driving scenarios of the vehicle 100. The driving scenarios may include: long straight road scenarios, turning scenarios, intersection scenarios, narrow road meeting scenarios, etc. The path planning algorithms used by different path planning sub-modules may be the same or different. The path planning algorithms include at least one of the following: Linear Quadratic Regulator (LQR) algorithm, Model Predictive Control (MPC) algorithm, Iterative LQR algorithm, etc., Constrained Iterative Linear Quadratic Regulator (CILQR) algorithm, etc.

[0028] In this embodiment of the application, after the vehicle 100 enters the target parking lot, it will generate an electronic map of the ramp area and an electronic map of the flat area in the target parking lot based on the environmental data sensed by the fusion perception module, thereby obtaining an electronic map of the entire target parking lot. Then, the vehicle 100 can perform parking route planning based on the electronic map and the environmental data sensed by the fusion perception module, thereby realizing autonomous navigation and automatic parking in the target parking lot.

[0029] In some embodiments, the vehicle 100 further includes a positioning module, which locates the current position of the vehicle 100, i.e., its latitude and longitude information. The positioning module may be a Global Positioning System (GPS) module. In some embodiments, the vehicle 100 also includes a sensor sensing module, which senses the driving parameters of the vehicle 100. The sensor sensing module includes, but is not limited to, speed sensors, acceleration sensors, wheel speed sensors, temperature sensors, etc.

[0030] Figure 2 This is a flowchart of a parking route planning method provided in an embodiment of this application. The method includes the following steps S201-S204.

[0031] Step S201: After confirming that the vehicle has entered the target parking lot, acquire the vehicle's environmental data.

[0032] The target parking lot can be a multi-level parking garage, comprising multiple ramp areas and multiple flat areas. The ramp areas connect adjacent flat areas; for example, there might be a ramp between the first and second levels, and another between the second and third levels. The target parking lot can also be a single-level parking garage where the flat area (parking area) is at a different height than the area before the vehicle enters. Therefore, a ramp is needed to connect the parking area to the vehicle's external position. For example, if the target parking lot is underground, there would be a ramp at its entrance. Vehicles can detect whether they have entered the target parking lot using the following methods.

[0033] In some embodiments, the vehicle acquires its current location signal, and determines that it has entered the target parking lot if the signal strength of the current location signal is less than a preset strength. The preset strength is set based on experiments or experience, and this application embodiment does not limit it. The target parking lot is usually a semi-enclosed environment, where the location signal is limited by the obstruction of walls and is usually weak. Therefore, the strength of the location signal can be used to determine whether the vehicle has entered the target parking lot.

[0034] In other embodiments, the vehicle acquires environmental images using a visual sensor, performs image recognition on the environmental images, and determines that the vehicle has entered the parking lot if the environmental image includes a preset parking lot sign. The preset parking lot sign can be a conventional symbol, text, image, etc., such as "P" or "xx parking lot". This application does not limit the algorithm used for image recognition. In this embodiment, the vehicle can further detect the existence of an entry ramp. If an entry ramp is determined to exist, the vehicle enters the target parking lot. Specifically, the vehicle detects the entry ramp as follows: it acquires the height information of multiple path points along the driving path, calculates the slope of each path point based on the height information, and determines the existence of an entry ramp if the slope of any path point falls within a preset slope range. The entry ramp is the path point whose slope falls within the preset slope range. The driving path can be determined by default by the vehicle.

[0035] In some embodiments, the vehicle detects the presence of a turnstile in its direction of travel. If a turnstile is detected, the vehicle determines that it is entering the parking lot. The vehicle can detect the presence of a turnstile in the following ways: First, the vehicle captures an image of the environment and then identifies whether the image includes a turnstile. Second, the vehicle uses lidar to detect the presence of a turnstile. In this embodiment, the vehicle can further detect the presence of an entry ramp. If an entry ramp is determined to exist, the vehicle determines that it is entering the target parking lot.

[0036] The vehicle's environmental data includes spatial location information of perceived targets and spatial location information of obstacles. Perceived targets include, but are not limited to: walls, pillars, parking lines, traffic cones, speed bumps, and waypoints on the default path. The spatial location information of the perceived targets includes the location and height information of the first perceived target. This location information can be represented by latitude and longitude information or based on a specified coordinate system, such as a spatial rectangular coordinate system established with the vehicle's current position as the origin. In this embodiment, the vehicle includes a fusion perception module. The vehicle obtains the angle of the first perceived target relative to the vehicle and the distance between the target and the vehicle through the fusion perception module, and then calculates the spatial location information of the perceived target based on the vehicle's current position, the angle of the perceived target relative to the vehicle, and the distance between the target and the vehicle. Obstacles include pedestrians, other vehicles, and animals. The spatial location information of obstacles includes the location and height information of the obstacles. Similarly, the vehicle obtains the angle of the obstacle relative to the vehicle and the distance between the obstacle and the vehicle through the fusion perception module, and then calculates the spatial location information of the obstacle based on the vehicle's current position, the angle of the obstacle relative to the vehicle, and the distance between the obstacle and the vehicle.

[0037] In some embodiments, during vehicle operation, environmental data is acquired by the vehicle's fusion perception module at predetermined intervals. These predetermined intervals are negatively correlated with the level of autonomous driving; for example, higher levels of autonomous driving (e.g., L4, L5) require shorter predetermined intervals. Conversely, lower levels of autonomous driving (e.g., L1, L2) require longer predetermined intervals.

[0038] Step S202: Obtain an electronic map of the ramp area in the target parking lot based on the spatial location information of the perceived target.

[0039] After a vehicle enters the target parking lot, an electronic map of the ramp area is generated based on the spatial location information of the perceived target. The method for generating the electronic map of the ramp area will be described in the following embodiments. It should be noted that, due to the limitations of the sensing range of the fusion sensing module, the electronic map of the ramp area may not be generated all at once, but rather gradually generated as the vehicle moves.

[0040] In some embodiments, the electronic map of the ramp area in the target parking lot can be in raster format, marking the passable area for vehicles and image icons of other navigation elements. Navigation elements refer to elements that affect the vehicle's travel path, including but not limited to: walls, pillars, speed bumps, turnstiles, parking lines, traffic cones, and other fixed facilities. The image icons of the aforementioned navigation elements can be predetermined. The size of the image icons of the navigation elements on the raster electronic map can be determined based on the actual size of the navigation elements and the scale of the raster electronic map.

[0041] In other embodiments, the electronic map of the ramp area in the target parking lot can be a vector map. The vector map includes vector graphics corresponding to the navigation elements mentioned above, and the size of the vector graphics is determined by the actual size of the navigation elements and the scale of the raster-style electronic map. Vector maps have the advantage of being lightweight, thus supporting the generation of electronic maps with a wider coverage area.

[0042] In some embodiments, before executing step S202, the vehicle may send a map acquisition request to the server. The map acquisition request requests an electronic map of the target parking lot, carrying point-of-interest (POI) tags for the target parking lot. The server can query whether an electronic map of the target parking lot exists based on this request. If an electronic map of the target parking lot exists, the server sends the map to the vehicle. If no electronic map of the target parking lot exists, the server sends a mapping reminder to the vehicle, and the vehicle executes step S202 based on this reminder. The vehicle can determine the POI tags of the target parking lot based on a first mapping relationship, which is a mapping relationship between different location information and POI tags of different parking lots. The location information refers to the vehicle's current location, which can be approximated as the location information of the target parking lot. The server can detect whether an electronic map of the target parking lot exists based on a second mapping relationship, which includes the mapping relationship between different POI tags and different electronic maps.

[0043] Optionally, the vehicle stores an electronic map of a designated parking lot. The designated parking lot can be a parking lot with a parking frequency greater than a preset frequency, such as a parking lot in a residential area or a parking lot corresponding to an office building. The vehicle first checks whether the target parking lot is a designated parking lot. If the target parking lot is not a designated parking lot, it sends a map retrieval request to the server. If the target parking lot is a designated parking lot, it directly reads the electronic map of the target parking lot from the local machine.

[0044] Step S203: Obtain an electronic map of the flat area in the target parking lot based on the spatial location information of the perceived target.

[0045] After the vehicle enters the target parking lot, an electronic map of the flat area will be generated based on the spatial location information of the second perceived target in the flat area. The method for generating the electronic map of the flat area will be described in the following embodiments. Similarly, due to the limitation of the sensing range of the fusion sensing module, the electronic map of the flat area may not be generated all at once, but rather gradually generated as the vehicle moves.

[0046] In this embodiment, the type of electronic map for flat areas is the same as the type of electronic map for slope areas. If the electronic map for the slope area is a raster map, the electronic map for the flat areas is also a raster map. If the electronic map for the slope area is a vector map, the electronic map for the flat areas is also a vector map.

[0047] It should be noted that the execution order of steps S202 and S203 is determined based on the actual driving conditions of the vehicle. For example, if the vehicle travels through a slope area first and then through a flat area, then step S202 is executed first, followed by step S203. Specifically, if the vehicle travels through a flat area first and then through a slope area, then step S203 is executed first, followed by step S202.

[0048] Step S204: Based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles, path planning is performed to obtain the planned parking path for the vehicle.

[0049] The vehicle's planned path refers to the route from the vehicle's current location to the designated parking location (near the target parking space). It includes spatial location information for multiple parking path points, as well as the vehicle's expected driving parameters at each path point. These parameters include the vehicle's expected speed, expected acceleration, expected steering wheel angle, etc. By following the expected driving parameters for each parking path point, the vehicle can smoothly reach the designated parking location. Afterward, the vehicle enters automatic parking mode and parks itself in the target parking space.

[0050] In summary, the technical solution provided in this application embodiment allows a vehicle to perceive environmental data through a fusion perception module after entering a target parking lot. This environmental data includes spatial location information of perceived targets and spatial location information of obstacles. The vehicle then generates electronic maps of the ramp area and the flat area in the target parking lot based on the spatial location information of the perceived targets. Finally, the vehicle can plan a parking route based on the electronic maps of the ramp area, the flat area, and the spatial location data of obstacles, thereby achieving autonomous navigation and automatic parking in target parking lots with ramp areas, improving the intelligence of autonomous driving.

[0051] The following sections describe the processes for generating electronic maps of slope areas and flatland areas. Based on... Figure 2 In the optional embodiments provided by the examples, Figure 2 Step S202 can be replaced by steps S302-S305. Figure 2 Step S203 can be replaced by step S306.

[0052] Please refer to Figure 3 The diagram illustrates a flowchart of a parking route planning method provided in one embodiment of this application. The method includes the following steps S301-S307.

[0053] Step S301: After confirming that the vehicle has entered the target parking lot, acquire the vehicle's environmental data.

[0054] The vehicle's environmental data includes spatial location information of the perceived target and spatial location information of obstacles. In this embodiment, the perceived target includes multiple waypoints, which can be waypoints in a default path. The default path can be a single path, such as a driving path perpendicular to the vehicle's front axle, or the centerline of the road the vehicle is currently traveling on (which can be directly marked on the road or calculated). There can also be multiple default paths, such as multiple paths divided (e.g., evenly) based on the width of the road the vehicle is currently traveling on, each path parallel to the road boundary. The spatial location information of the waypoints includes their position and height information.

[0055] Step S302: Based on the height information of multiple path points, divide the multiple path points into flat points and ramp points.

[0056] Flat points refer to waypoints in flat terrain. Slope points refer to waypoints in sloping terrain. Vehicles perform clustering processing on the height information of multiple waypoints, classifying them into flat points and slope points based on the clustering results. Clustering is the process of dividing a dataset into different classes or clusters according to a specific criterion.

[0057] In some embodiments, the vehicle identifies path points whose height information falls within a specified height range as ramp points, and points outside the specified height range as flat points. The boundary values ​​of the specified height range can be set based on practical experience, and this embodiment does not limit this.

[0058] In other embodiments, the vehicle sorts the height information of multiple waypoints in ascending order, then divides the waypoints into n groups, where n is less than the number of waypoints. Each group includes at least two waypoints with adjacent height information. The variance of each group is then calculated. Waypoints in groups with variances less than a predetermined value are designated as level points, and waypoints in groups with variances greater than a predetermined value are designated as ramp points. The predetermined value is set based on experiments or experience, and this embodiment does not limit it.

[0059] Reference Figure 4 This illustrates a schematic diagram of a defined ramp area provided in one embodiment of this application. Figure 4 In part (a), the vehicle divides ramp points and path points based on the height information of each path point. The path points between the two dashed lines are ramp points, and the path points outside the two dashed lines are ramp points.

[0060] Step S303: Determine the entry point from the ramp points based on the height information of multiple path points.

[0061] The entry point refers to a path point in the first transition area between the first flat area and the slope area. In some embodiments, step S303 can be implemented as the following sub-step.

[0062] Step S303a: Based on the height information of multiple path points, determine the candidate entry point from the ramp points.

[0063] In some embodiments, candidate entry points can be determined based on the vehicle's current height and the height information of the aforementioned ramp points. For example, if the vehicle's current height is greater than the height information of each ramp point (i.e., the area in front of the vehicle is downhill), the ramp point with the highest height information is determined as the candidate entry point. Conversely, if the vehicle's current height is less than the height information of each ramp point (i.e., the area in front of the vehicle is uphill), the ramp point with the lowest height information is determined as the candidate entry point.

[0064] Please refer to it again. Figure 4 ,exist Figure 4 In part (b), the area in front of the vehicle is a downhill area, and the vehicle determines the slope point A with the highest height information as the candidate entry point.

[0065] Step S303b: Obtain the slope of the candidate entry point.

[0066] In some embodiments, the vehicle fits the height information of multiple waypoints to obtain a fitting function, then determines the derivative function of the fitting function, and then substitutes the height information of the candidate entry points into the above derivative function in turn to obtain the slope of the candidate entry points.

[0067] Step S303c: If the slope of the candidate entry point belongs to the first slope interval, the candidate entry point is determined as the entry point.

[0068] In this embodiment, the lower boundary value of the first slope interval can be obtained by statistically analyzing the slopes of path points in a flat area. For example, the lower boundary value refers to the maximum or average slope of the path points in the flat area. The upper boundary value of the first slope interval can be obtained by statistically analyzing the slopes of path points in a slope area. For example, the upper boundary value refers to the minimum or average slope of the path points in the slope area.

[0069] If the slope of the candidate entry point falls within the first slope range mentioned above, it indicates that the candidate entry point is likely to be a point in the first transition zone between the first flat area and the slope area, and can be approximated as an entry point.

[0070] Step S303d: If the slope of the candidate entry point does not belong to the first slope interval, search for entry points starting from the candidate entry point based on the slopes of the candidate entry point and multiple path points.

[0071] If the slope of a candidate entry point is less than the lower boundary value of the first slope interval mentioned above, it indicates that the candidate entry point is likely a pathpoint in a flat area, and the search for entry points needs to continue. Specifically, when the area in front of the vehicle is uphill, pathpoints that are adjacent to the candidate entry point in terms of height and whose height information is greater than that of the candidate entry point can be re-identified as candidate entry points. Then, the search continues based on the first slope interval to determine whether the updated candidate entry point is indeed an entry point, until the entry / exit point is determined. When the area in front of the vehicle is downhill, pathpoints that are adjacent to the candidate entry point in terms of height and whose height information is less than that of the candidate entry point can be re-identified as candidate entry points. Then, the search continues based on the first slope interval to determine whether the updated candidate entry point is indeed an entry point, until the entry / exit point is determined.

[0072] If the slope of a candidate entry point is greater than the upper boundary value of the first slope interval, it indicates that the candidate entry point is likely a path point in the slope area, and the search for entry points needs to continue. Specifically, when the area in front of the vehicle is uphill, path points that are adjacent in height to the candidate entry point but have lower height information can be re-identified as candidate entry points. Then, the search continues based on the first slope interval to determine whether the updated candidate entry point is indeed an entry point, until the entry / exit point is determined. When the area in front of the vehicle is downhill, path points that are adjacent in height to the candidate entry point but have higher height information can be re-identified as candidate entry points. Then, the search continues based on the first slope interval to determine whether the updated candidate entry point is indeed an entry point, until the entry / exit point is determined.

[0073] Please refer to it again. Figure 4 ,exist Figure 4 In part (c), the vehicle searches based on candidate entry point A and finally determines entry / exit point C.

[0074] Step S304: Determine the slope point among the slope points based on the height information of multiple path points.

[0075] The exit point refers to a path point in the second transition area between the second flat area and the slope area. The first flat area and the second flat area are not the same. In some embodiments, step S304 can be implemented as the following sub-step.

[0076] Step S304a: Based on the height information of multiple path points, determine the candidate exit points among the slope points.

[0077] In some embodiments, candidate exit points can be determined based on the vehicle's current height and the height information of the aforementioned ramp points. For example, if the vehicle's current height is greater than the height information of each ramp point (i.e., the area in front of the vehicle is downhill), the ramp point with the lowest height information is determined as the candidate exit point. Conversely, if the vehicle's current height is less than the height information of each ramp point (i.e., the area in front of the vehicle is uphill), the ramp point with the highest height information is determined as the candidate exit point.

[0078] Please refer to it again. Figure 4 ,exist Figure 4 In part (b), the vehicle identifies the ramp point B with the lowest height information as the candidate exit point.

[0079] Step S304b: Obtain the slope of the candidate exit point.

[0080] In step S304c, if the slope of the candidate exit point belongs to the second slope interval, the candidate exit point is determined as the exit point.

[0081] In this embodiment, the lower boundary value of the second slope interval can be obtained statistically based on the slope of path points in a flat area. For example, the lower boundary value refers to the maximum or average slope of path points in a flat area. The upper boundary value of the second slope interval can be obtained statistically based on the slope of path points in a slope area. For example, the upper boundary value refers to the minimum or average slope of path points in a slope area. The first slope interval and the second slope interval can be the same or different.

[0082] If the slope of the candidate exit point falls within the first slope range mentioned above, it indicates that the candidate exit point is likely to be a point in the second transition area between the second flat area and the slope area, and can be approximated as an exit point.

[0083] Step S304d: If the slope of the candidate exit point does not belong to the second slope interval, search for an exit point starting from the candidate exit point based on the slope of the candidate exit point and the path point.

[0084] If the slope of a candidate exit point is less than the lower boundary value of the second slope interval mentioned above, it indicates that the candidate exit point is likely a pathpoint in a flat area, and the search for exit points needs to continue. Specifically, when the area in front of the vehicle is uphill, pathpoints that are adjacent to the candidate exit point in height but have lower height information can be re-identified as candidate exit points. Then, the search continues based on the second slope interval to determine whether the updated candidate exit point is indeed an exit point, until an exit point is identified. When the area in front of the vehicle is downhill, pathpoints that are adjacent to the candidate exit point in height but have higher height information can be re-identified as candidate exit points. Then, the search continues based on the second slope interval to determine whether the updated candidate exit point is indeed an exit point, until an exit point is identified.

[0085] If the slope of a candidate exit point is greater than the upper boundary value of the second slope interval mentioned above, it indicates that the candidate exit point is likely a pathpoint in the slope area, and the search for exit points needs to continue. Specifically, when the area in front of the vehicle is uphill, pathpoints that are adjacent to the candidate exit point in height and whose height information is greater than that of the candidate exit point can be re-identified as candidate exit points. Then, the search continues based on the second slope interval to determine whether the updated candidate exit point is indeed an exit point, until an exit point is identified. When the area in front of the vehicle is downhill, pathpoints that are adjacent to the candidate exit point in height and whose height information is less than that of the candidate exit point can be re-identified as candidate exit points. Then, the search continues based on the second slope interval to determine whether the updated candidate exit point is indeed an exit point, until an exit point is identified.

[0086] Please refer to it again. Figure 4 ,exist Figure 4 In part (b), the vehicle searches based on candidate exit point B and ultimately determines exit point D. The area between entry point C and exit point D is also known as the ramp area.

[0087] Step S305: Based on the spatial location information of the entry point, exit point, and the first designated sensing target, generate an electronic map of the slope area.

[0088] The first designated sensing target refers to the sensing target within the slope area determined based on the entry and exit points. It should be noted that, when there is only one default path, the vehicle acquires a first straight line and a second straight line, and defines the area between the first and second straight lines as the slope area. The first straight line is a straight line passing through the entry point and perpendicular to the road boundary of the road the vehicle is traveling on, and the second straight line is a straight line passing through the exit point and perpendicular to the road boundary of the road the vehicle is traveling on. When there are multiple default paths, the vehicle calculates the exit and entry points of each default path through steps S302-S304, then acquires a first curve and a second curve, and defines the area between the first and second curves as the slope area. The first curve refers to the curve passing through the exit points corresponding to each of the multiple default paths, and the second curve refers to the curve passing through the entry points corresponding to each of the multiple default paths.

[0089] In this embodiment of the application, the vehicle generates an electronic map of the slope area based on the spatial location information of the entry point, exit point and the first designated sensing target through synchronous positioning and mapping technology.

[0090] Step S306: Based on the spatial location information of the entry point, exit point, and the second designated sensing target, generate an electronic map of the flat area.

[0091] The second designated sensing target refers to a sensing target within a flat area determined based on the entry and exit points of the slope. The aforementioned flat area refers to the area outside the slope area. In this embodiment, the vehicle generates an electronic map of the flat area using synchronous positioning and mapping technology, based on the spatial location information of the entry and exit points and the second designated sensing target.

[0092] Step S307: Based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles, path planning is performed to obtain the planned parking path for the vehicle.

[0093] In summary, the technical solution provided in this application can accurately determine the ramp area and flat area in the target parking lot by using the height information of the waypoints, thereby making the generated electronic map more accurate.

[0094] The following sections describe the processes for generating electronic maps of slope areas and flatland areas. Based on... Figure 2 or Figure 3 In the optional embodiments provided by the examples, Figure 2 Step S204 or Figure 3 Step S307 in the embodiment can be replaced by steps S504-S505.

[0095] Please refer to Figure 5The diagram illustrates a flowchart of a parking route planning method provided in one embodiment of this application. The method includes the following steps S501-S505.

[0096] Step S501: After determining that the vehicle has entered the target parking lot, acquire the environmental data of the vehicle.

[0097] The vehicle's environmental data includes spatial location information of perceived targets and spatial location information of obstacles.

[0098] Step S502: Obtain an electronic map of the ramp area in the target parking lot based on the spatial location information of the perceived target.

[0099] Step S503: Obtain an electronic map of the flat area in the target parking lot based on the spatial location information of the perceived target.

[0100] Step S504: Determine the target parking space.

[0101] A target parking space is a parking space where no vehicle is parked. A vehicle can identify a target parking space using one or more of the following methods.

[0102] In some embodiments, the target parking space is a parking space pre-stored by the vehicle. For example, the vehicle can record the parking space rented or purchased by the driver and store the parking space identifier and location information of the parking space accordingly. In this case, the vehicle can directly read the target parking space and the location information of the target parking space from the local storage.

[0103] In other embodiments, the target parking space is determined by the vehicle based on historical parking records. For example, the vehicle obtains historical parking records and identifies the parking space with the most parking frequency in the historical records as the target parking space.

[0104] In other embodiments, an electronic display screen at the entrance of the target parking lot shows one or more parking spaces with no vehicles parked there. The vehicle takes a first environmental image at the entrance of the target parking lot, and then identifies the target parking space based on the first environmental image.

[0105] In other embodiments, the vehicle captures a second environmental image at the target parking lot, and then identifies parking spaces where no vehicles are parked based on the second environmental image. The vehicle then further detects whether the parking spaces where no vehicles are parked meet the collision-free parking conditions based on the environmental data perceived by the fusion perception module. If the collision-free parking conditions are met, the parking spaces where no vehicles are parked are identified as target parking spaces.

[0106] Step S505: Based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles, path planning is performed to obtain the planned parking path for the vehicle.

[0107] Planning a parking route refers to the path from the vehicle's current location to the target parking space. In some embodiments, planning a parking route refers to the path from the vehicle's current location to a specified location of the target parking space, where the specified location may be directly in front of the target parking space.

[0108] In some embodiments, step S505 can be replaced by the following sub-steps:

[0109] Step S505a: Determine the vehicle's driving scenario based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles.

[0110] The vehicle's driving scenarios include at least one of the following: straight-ahead scenario, oncoming traffic scenario, obstacle avoidance scenario, turning scenario, and intersection scenario. Specifically, a straight-ahead scenario refers to a planned parking path containing a long straight section parallel to the vehicle's direction of travel. An oncoming traffic scenario refers to a scenario where other vehicles are traveling in the opposite direction. An obstacle avoidance scenario refers to a scenario where an obstacle exists in the vehicle's direction of travel. A turning scenario refers to a planned parking path containing a turn. An intersection scenario refers to a planned parking path containing an intersection.

[0111] Step S505b: Obtain the target path planning submodule corresponding to the vehicle's driving scenario.

[0112] In this embodiment, different path planning submodules are used to plan paths for different driving scenarios, making path planning more flexible and adaptable to changes in the scenario. The path planning algorithms used by the target path planning submodules for different driving scenarios can be the same or different.

[0113] Step S505c: Based on the target path planning submodule, perform path planning to obtain the planned parking path for the vehicle.

[0114] In some embodiments, when the vehicle is traveling straight, the path planning submodule corresponding to the straight-traffic scenario can obtain the speed limit value, and then determine the target speed based on the speed limit value. The target speed is less than the speed limit value, and then the vehicle can travel at a constant speed on the long straight road at the target speed.

[0115] In some embodiments, when vehicles are in a meeting scenario, the path planning submodule for that scenario performs path planning as follows: Based on the vehicle's own driving parameters, the driving parameters of other vehicles, and road information, the meeting position is determined. Then, the vehicle plans its path based on its current position, the meeting position, its current driving parameters, and the first desired driving parameters at the meeting position. When the vehicle is at this meeting position, the distance between the side of the vehicle furthest from the first road boundary and the second road boundary is greater than a preset lateral distance, allowing other vehicles to pass smoothly without collision. The meeting position can be in front of or behind the vehicle's direction of travel.

[0116] In some embodiments, when a vehicle is at an intersection, it can determine whether it needs to go straight or turn. If it needs to go straight, it can perform path planning based on the detected obstacle information (such as vehicles on roads perpendicular to the vehicle's direction of travel). If it needs to turn, it can first determine a first target position (the starting position of turning to another road), then determine a first driving curve (such as a Bezier curve) based on the current position and the first target position, and finally perform path planning based on the first driving curve.

[0117] In some embodiments, in an obstacle avoidance scenario, the vehicle can first fit a detour area based on the location and shape information of the obstacle, then determine a second target position based on the detour area, then determine a second driving curve (such as a Bezier curve) based on the current position and the second target position, and finally perform path planning based on the second driving curve.

[0118] In summary, the technical solutions provided in this application adopt different path planning schemes for different driving scenarios, making path planning more flexible and better adaptable to scenario changes.

[0119] Please refer to Figure 6 The diagram illustrates a block diagram of a parking route planning device according to an embodiment of this application. The parking route planning device includes: a data acquisition module 610, a first map acquisition module 620, a second map acquisition module 630, and a route planning module 640.

[0120] The data acquisition module 610 is used to acquire the vehicle's environmental data after determining that the vehicle has entered the target parking lot. The vehicle's environmental data includes the spatial location information of the perceived target and the spatial location information of obstacles.

[0121] The first map acquisition module 620 is used to acquire an electronic map of the ramp area in the target parking lot based on the spatial location information of the perceived target.

[0122] The second map acquisition module 630 is used to acquire an electronic map of the flat area in the target parking lot based on the spatial location information of the perceived target.

[0123] The path planning module 640 is used to perform path planning based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of obstacles, so as to obtain the planned parking path of the vehicle.

[0124] In some embodiments, the sensing target includes multiple waypoints, and the spatial location information of the waypoints includes the height information of the multiple waypoints; the first map acquisition module 620 is used to divide the multiple waypoints into flat points and slope points based on the height information of the multiple waypoints; determine the entry point of the slope among the slope points based on the height information of the multiple waypoints; and determine the exit point of the slope among the slope points based on the height information of the multiple waypoints; and generate an electronic map of the slope area based on the entry point, exit point and the spatial location information of the first designated sensing target, wherein the first designated sensing target refers to the sensing target in the slope area determined based on the entry point and exit point.

[0125] In some embodiments, the first map acquisition module 620 is used to determine candidate entry points among ramp points based on the height information of multiple path points; acquire the slope of the candidate entry point; if the slope of the candidate entry point belongs to a first slope interval, determine the candidate entry point as an entry point; if the slope of the candidate entry point does not belong to the first slope interval, search for entry points starting from the candidate entry point based on the slope of the candidate entry point and the slope of multiple path points.

[0126] In some embodiments, the first map acquisition module 620 is used to determine candidate exit points among slope points based on the height information of multiple path points; acquire the slope of the candidate exit points; if the slope of the candidate exit points belongs to a second slope interval, determine the candidate exit points as exit points; if the slope of the candidate exit points does not belong to the second slope interval, search for exit points starting from the candidate exit points based on the slopes of the candidate exit points and the path points.

[0127] In some embodiments, the second map acquisition module 630 is used to generate an electronic map of the flat area based on the spatial location information of the entry point, exit point and the second designated sensing target, wherein the second designated sensing target refers to the sensing target within the flat area determined based on the entry point and exit point.

[0128] In some embodiments, the path planning module 640 is used to determine the target parking space, which is a parking space where no vehicle is parked; and to perform path planning based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles to obtain the planned parking path of the vehicle, which is the path between the current position of the vehicle and the target parking space.

[0129] In some embodiments, the path planning module 640 is used to determine the vehicle's driving scenario based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles. The vehicle's driving scenario includes at least one of the following: straight driving scenario, oncoming traffic scenario, obstacle avoidance scenario, turning scenario, and intersection scenario; obtain the target path planning submodule corresponding to the vehicle's driving scenario; and perform path planning based on the target path planning submodule to obtain the planned parking path of the vehicle.

[0130] In summary, the technical solution provided in this application embodiment allows a vehicle to perceive environmental data through a fusion perception module after entering a target parking lot. This environmental data includes spatial location information of perceived targets and spatial location information of obstacles. The vehicle then generates electronic maps of the ramp area and the flat area in the target parking lot based on the spatial location information of the perceived targets. Finally, the vehicle can plan a parking route based on the electronic maps of the ramp area, the flat area, and the spatial location data of obstacles, thereby achieving autonomous navigation and automatic parking in target parking lots with ramp areas, improving the intelligence of autonomous driving.

[0131] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0132] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0133] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0134] Please see Figure 7 The illustration shows that an embodiment of this application also provides a vehicle 700, which includes one or more processors 710, a memory 720, and one or more application programs. The one or more application programs are stored in the memory and configured to be executed by the one or more processors, and are configured to perform the methods described in the above embodiments.

[0135] The processor 710 may include one or more processing cores. The processor 710 connects to various parts of the entire battery management system using various interfaces and lines, and performs various functions and processes data of the battery management system by running or executing instructions, programs, code sets, or instruction sets stored in the memory 720, and by calling data stored in the memory 720. Optionally, the processor 710 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 710 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 710 and may be implemented separately through a communication chip.

[0136] The memory 720 may include random access memory (RAM) or read-only memory (ROM). The memory 720 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 720 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described above. The data storage area may also store data created during vehicle operation (e.g., phonebook, audio / video data, chat log data, etc.).

[0137] Please see Figure 8 The present application also provides a computer-readable storage medium 800, which stores computer program instructions 810 that can be invoked by a processor to perform the methods described in the above embodiments.

[0138] The computer-readable storage medium 800 may be, for example, flash memory, electrically erasable programmable read-only memory (EEPROM), electrically programmable read-only memory (EPROM), hard disk, or read-only memory (ROM). Optionally, the computer-readable storage medium includes non-transitory computer-readable storage medium. The computer-readable storage medium 800 has storage space for computer program instructions 810 that perform any of the method steps described above. These computer program instructions 810 may be read from or written to one or more computer program products.

[0139] The above are merely preferred embodiments of this application and are not intended to limit this application in any way. Although this application has disclosed preferred embodiments as above, it is not intended to limit this application. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the technical solution of this application. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of this application without departing from the scope of the technical solution of this application shall still fall within the scope of the technical solution of this application.

Claims

1. A parking route planning method, characterized in that, The method includes: After determining that the vehicle has entered the target parking lot, the environmental data of the vehicle is acquired. The environmental data of the vehicle includes the spatial location information of the perceived target and the spatial location information of the obstacles. Based on the spatial location information of the perceived target, an electronic map of the ramp area in the target parking lot is obtained, and an electronic map of the flat area in the target parking lot is obtained based on the spatial location information of the perceived target. Based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles, a path planning is performed to obtain the planned parking path for the vehicle. The sensing target includes multiple waypoints, and the spatial location information of the waypoints includes the height information of the multiple waypoints; the step of obtaining an electronic map of the ramp area in the target parking lot based on the spatial location information of the sensing target includes: Based on the height information of multiple path points, the multiple path points are divided into flat points and ramp points; An entry point is determined from the ramp points based on the height information of multiple path points; and an exit point is determined from the ramp points based on the height information of multiple path points; wherein, the entry point is a candidate entry point whose slope belongs to a first slope interval, or the entry point is obtained by searching for candidate entry points whose slope does not belong to the first slope interval and the slopes of multiple path points; the candidate entry point is determined from the ramp points based on the height information of multiple path points. Based on the spatial location information of the entry point, the exit point, and the first designated sensing target, an electronic map of the slope area is generated. The first designated sensing target refers to the sensing target within the slope area determined based on the entry point and the exit point.

2. The method according to claim 1, characterized in that, The determination of the entry point from the ramp points based on the height information of multiple path points includes: Candidate entry points are determined from the ramp points based on the height information of multiple path points. Obtain the slope of the candidate entry point; If the slope of the candidate entry point belongs to the first slope interval, the candidate entry point is determined as the entry point. If the slope of the candidate entry point does not belong to the first slope interval, the entry point is searched based on the slope of the candidate entry point and the slopes of the multiple path points, starting from the candidate entry point.

3. The method according to claim 1, characterized in that, The step of determining the exit point from the ramp points based on the height information of multiple path points includes: Based on the height information of multiple path points, candidate exit points are determined among the ramp points; Obtain the slope of the candidate exit point; If the slope of the candidate exit point belongs to the second slope interval, the candidate exit point is determined as the exit point. If the slope of the candidate exit point does not belong to the second slope interval, the exit point is searched based on the slope of the candidate exit point and the path point, starting from the candidate exit point.

4. The method according to claim 1, characterized in that, The step of obtaining an electronic map of the flat area in the target parking lot based on the spatial location information of the perceived target includes: Based on the spatial location information of the flat area, the entry point, the exit point, and the second designated sensing target, an electronic map of the flat area is generated. The second designated sensing target refers to the sensing target within the flat area determined based on the entry point and the exit point.

5. The method according to any one of claims 1 to 4, characterized in that, The method of performing path planning based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles to obtain the planned parking path for the vehicle includes: Identify the target parking space, which is a parking space where no vehicle is parked; Based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles, path planning is performed to obtain the planned parking path of the vehicle. The planned parking path refers to the path between the current position of the vehicle and the target parking space.

6. The method according to claim 5, characterized in that, The method of performing path planning based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles to obtain the planned parking path for the vehicle includes: The driving scenario of the vehicle is determined based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacle. The driving scenario of the vehicle includes at least one of the following: straight driving scenario, meeting oncoming traffic scenario, obstacle avoidance scenario, turning scenario, and intersection scenario. Obtain the target path planning submodule corresponding to the driving scenario of the vehicle; Based on the target path planning submodule, path planning is performed to obtain the planned parking path for the vehicle.

7. A parking route planning device, characterized in that, The device includes: The data acquisition module is used to acquire the environmental data of the vehicle after determining that the vehicle has entered the target parking lot. The environmental data of the vehicle includes the spatial location information of the perceived target and the spatial location information of the obstacles. The first map acquisition module is used to acquire an electronic map of the ramp area in the target parking lot based on the spatial location information of the perceived target. The second map acquisition module is used to acquire an electronic map of the flat area in the target parking lot based on the spatial location information of the perceived target. The path planning module is used to perform path planning based on the electronic map of the ramp area, the electronic map of the flat area, and the spatial location information of the obstacles, so as to obtain the planned parking path of the vehicle. The sensing target includes multiple waypoints, and the spatial location information of the waypoints includes the height information of the multiple waypoints; the first map acquisition module is specifically used for: Based on the height information of multiple path points, the multiple path points are divided into flat points and ramp points; An entry point is determined from the ramp points based on the height information of multiple path points; and an exit point is determined from the ramp points based on the height information of multiple path points; wherein, the entry point is a candidate entry point whose slope belongs to a first slope interval, or the entry point is obtained by searching for candidate entry points whose slope does not belong to the first slope interval and the slopes of multiple path points; the candidate entry point is determined from the ramp points based on the height information of multiple path points. Based on the spatial location information of the entry point, the exit point, and the first designated sensing target, an electronic map of the slope area is generated. The first designated sensing target refers to the sensing target within the slope area determined based on the entry point and the exit point.

8. A vehicle, characterized in that, The vehicles include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that can be invoked by a processor to perform the method as described in any one of claims 1-6.

Images