Vehicle driving path planning method, device and equipment and computer storage medium

Abstract

The application discloses a vehicle driving path planning method and device, equipment and a computer storage medium. The vehicle driving path planning method comprises the following steps: obtaining a target driving area of a vehicle, a first path point and a preset first reference path, the first path point and the first reference path are located in the target driving area, the distance between the first reference path and a preset parking point is less than a first distance threshold, and the first path point is not located in the first reference path; determining a second path point from the first reference path; planning a first planning path of the vehicle from the first path point to the second path point; and splicing the first reference path and the first planning path to obtain a first target driving path of the vehicle in the target driving area. The vehicle can be reliably guided to the vicinity of the parking point while avoiding too drastic changes in the driving path of the vehicle.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of path planning, and particularly relates to a vehicle driving path planning method, device, equipment and computer storage medium. BACKGROUND

[0002] At present, intelligent driving technology has been gradually applied to various scenes. For example, in a mine scene, intelligent driving vehicles such as mine trucks can be applied.

[0003] In the mine scene, the mine truck generally drives to the vicinity of the excavator to load articles. However, the position of the excavator usually changes, and the mine truck needs to update the global driving path accordingly, resulting in too drastic changes in the driving path. SUMMARY

[0004] The embodiments of the present application provide a vehicle driving path planning method, device, equipment and computer storage medium to solve the problem that the mine truck needs to frequently update the global driving path in the related art, resulting in too drastic changes in the driving path.

[0005] In a first aspect, the embodiments of the present application provide a vehicle driving path planning method, and the method comprises:

[0006] obtaining a target driving area of a vehicle, a first path point and a preset first reference path, the first path point and the first reference path are both located in the target driving area, the distance between the first reference path and a preset parking point is less than a first distance threshold, and the first path point is not located in the first reference path;

[0007] determining a second path point from the first reference path;

[0008] planning a first planning path of the vehicle from the first path point to the second path point;

[0009] splicing the first reference path and the first planning path to obtain a first target driving path of the vehicle in the target driving area.

[0010] In a second aspect, the embodiments of the present application provide a vehicle driving path planning device, and the device comprises:

[0011] a first obtaining module configured to obtain a target driving area of a vehicle, a first path point and a preset first reference path, the first path point and the first reference path are both located in the target driving area, the distance between the first reference path and a preset parking point is less than a first distance threshold, and the first path point is not located in the first reference path;

[0012] a first determining module configured to determine a second path point from the first reference path;

[0013] The first planning module is configured to plan a first planning path of the vehicle from the first path point to a second path point;

[0014] The splicing module is configured to splice the first reference path and the first planning path to obtain a first target driving path of the vehicle in the target driving area.

[0015] In a third aspect, an electronic device is provided, and the device includes a processor and a memory storing computer program instructions;

[0016] The processor, when executing the computer program instructions, implements the vehicle driving path planning method as shown in the first aspect.

[0017] In a fourth aspect, a computer storage medium is provided, and the computer readable storage medium stores computer program instructions, and the computer program instructions, when executed by a processor, implement the vehicle driving path planning method as shown in the first aspect.

[0018] In a fifth aspect, a computer program product is provided, and instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the vehicle driving path planning method as shown in the first aspect.

[0019] The vehicle driving path planning method provided in the embodiments of the present application acquires a target driving area of a vehicle, a first path point, and a preset first reference path, the first path point and the first reference path are both located in the target driving area; a second path point is determined from the first reference path; a first planning path of the vehicle from the first path point to the second path point is planned; and the first reference path and the first planning path are spliced to obtain a first target driving path of the vehicle in the target driving area. In this embodiment, the preset first reference path has a relatively fixed path, and the distance from the parking point is less than a first distance threshold. The first planning path from the first path point to the second path point located on the first reference path can also be relatively fixed. Accordingly, based on the first target driving path obtained by splicing, the vehicle can be reliably guided to the vicinity of the parking point while avoiding too drastic changes in the driving path of the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. For those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0021] Figure 1 is a schematic view of an open space of a mining area;

[0022] Figure 2FIG. 1 is a flowchart of a vehicle driving path planning method according to an embodiment of the present application;

[0023] Figure 3 FIG. 2 is a flowchart of a process of planning a driving path of a vehicle from a first path point to a parking point;

[0024] Figure 4 FIG. 3 is a flowchart of a process of planning a driving path of a vehicle from the parking point or its vicinity to a fifth path point;

[0025] Figure 5 FIG. 4 is a logic diagram of a process of selecting a path planning mode of a vehicle;

[0026] Figure 6 FIG. 5 is a flowchart of a process of planning a fourth planning path;

[0027] Figure 7 FIG. 6 is a flowchart of a process of smoothing a spliced path based on a smoother;

[0028] Figure 8 FIG. 7 is a flowchart of a process of local smoothing of a spliced path;

[0029] Figure 9 FIG. 8 is a flowchart of a process of path planning in a local coordinate system;

[0030] Figure 10 FIG. 9 is a flowchart of a vehicle driving path planning method in a specific application example according to an embodiment of the present application;

[0031] Figure 11a FIG. 10 is a diagram of changes of output paths in a process of multiple smoothing of a global path;

[0032] Figure 11b FIG. 11 is a diagram of changes of curvatures in various paths in a process of multiple smoothing of a global path;

[0033] Figure 12 FIG. 12 is a diagram of effects of resampling of a global path in a drivable region of an open space;

[0034] Figure 13 FIG. 13 is a structural diagram of a vehicle driving path planning device according to an embodiment of the present application;

[0035] Figure 14 FIG. 14 is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0037] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0038] In many application scenarios, vehicles may need to plan their paths. For example, Figure 1 As shown, Figure 1 This is a schematic diagram of an open space in a mining area. A mine cart working in the mining area may have a need for path planning in the open space.

[0039] Open space in a mining area generally refers to the drivable area on the side of the blast pile boundary where mining trucks can enter, exit, queue, and park. During the mining process, the open space may change accordingly.

[0040] The open space may have a corresponding boundary, and the blast pile boundary may generally be a component of the boundary of the open space. The blast pile boundary generally refers to a mining boundary formed by the accumulation of ore after blasting in the mining area.

[0041] Open spaces may contain a mix of structured roads and unstructured areas. Structured roads can be hardened roads or well-maintained gravel roads that connect mining areas with unloading areas, offer good driving conditions, and are infrequently updated. Unstructured areas, on the other hand, typically lack specific road boundaries.

[0042] based on Figure 1It can be seen that the equipment working in the mining area can include a shovel and the above-described mining truck. The shovel can be used to excavate resources such as ores. The mining truck can travel to a parking area near the shovel to facilitate loading of resources in the mining truck by the shovel. Meanwhile, the mining truck can also transport the loaded resources out of the mining area.

[0043] The path of the mining truck towards the parking area or the path of the mining truck away from the parking area can be obtained through path planning.

[0044] Generally, path planning can include global path navigation and local path planning.

[0045] The global path navigation can refer to planning a path suitable for vehicle travel according to global prior environmental information, including drivable areas, etc. The path generally includes global pose, curvature, and mileage, etc. static information. The real-time requirement is not very high, which can be 0 to 10 seconds depending on specific needs. The length of the planned path is relatively long, which can be 0 meters to 1000 meters or even longer.

[0046] The local path planning can refer to planning a path that meets the kinematics of the vehicle according to local environmental information such as perceived obstacles and road boundaries. The path generally includes global pose, curvature, and mileage, etc. static information. The path has good obstacle avoidance capability. The real-time requirement is relatively high, generally limited within 100 milliseconds. The length of the planned path is relatively short, generally about 8 seconds of path length.

[0047] In combination Figure 1 Taking the mining truck driving towards the parking area as an example, the mining truck can directly plan a global path from the structured road to the parking area. However, in the process of mining ores, the position of the shovel can frequently change, and the position of the parking area will also usually change with the change of the position of the shovel, that is, the planning endpoint of the global path will frequently change, resulting in the need for the mining truck to frequently re-plan the global path as a whole. At the same time, due to the complexity of the shape of the boundary of the open area and the internal road conditions, the planning of the global path is also difficult, and the global path is prone to drastic changes, affecting the driving stability of the mining truck in the mining area.

[0048] Of course, in addition to the above-mentioned application scenarios of the mining area, there can also be a demand for vehicle path planning in other application scenarios.

[0049] For example, in a warehouse with multiple racks, the trolley can also have the demand for path planning. Since the trolley can need to load and unload goods at multiple positions of a row of racks, that is, the parking point of the trolley can change frequently. During the process of the trolley driving to the parking point, directly taking the parking point as the planning endpoint of the global path can cause the trolley to need to frequently re-plan the global path as a whole, and the global path changes sharply. At the same time, due to the distance limitation between the racks, it can also cause the difficulty of planning the global path to be relatively large.

[0050] To solve the problems in the prior art, the embodiments of the present application provide a vehicle driving path planning method, device, equipment and computer storage medium. First, the vehicle driving path planning method provided by the embodiments of the present application is introduced.

[0051] Figure 2 The flowchart of the vehicle driving path planning method provided by an embodiment of the present application is shown. As shown in Figure 2 The method comprises the following steps:

[0052] Step 201, obtaining a target driving area of a vehicle, a first path point and a preset first reference path, the first path point and the first reference path are located in the target driving area, the distance between the first reference path and the preset parking point is less than the first distance threshold, and the first path point is not located in the first reference path;

[0053] Step 202, determining a second path point from the first reference path;

[0054] Step 203, planning a first planning path of the vehicle from the first path point to the second path point;

[0055] Step 204, splicing the first reference path and the first planning path to obtain a first target driving path of the vehicle in the target driving area.

[0056] The vehicle driving path planning method provided by the embodiments of the present application can be applied to the vehicle. Alternatively, the method can also be applied in the server, and the planning of the vehicle driving path can be realized through the communication between the server and the vehicle.

[0057] To simplify the description, the vehicle driving path planning method provided by the embodiments of the present application will be described mainly in combination with the application scene of the above-mentioned mine area, and correspondingly, the vehicle driving path planning method can be applied in the above-mentioned mine car.

[0058] In step 201, the vehicle can obtain its target driving area, first path point and preset first reference path.

[0059] The target driving area can be an area where the vehicle can drive to some extent. For example, the target driving area can be the open space described above.

[0060] Alternatively, considering that the boundary area of the open space has more gravel and the road condition is more complex, the target driving area can also be an area surrounded by the boundary of the open space after being inwardly contracted by a preset distance.

[0061] Alternatively, when the open area has marked obstacles (such as large gravel, lakes, etc.), the target driving area can also be an area in the open area except the area occupied by these obstacles.

[0062] The first path point is located in the target driving area. The first path point can be the starting point of the overall path to be planned, or the starting point of a certain section of the overall path, etc.

[0063] For example, the first path point can be a path point on the end of the structured road, i.e., a path point at the position where the structured road transitions to the unstructured area.

[0064] The first path point can be set as needed. For example, the first path point can be a fixed path point, or can also be a randomly selected path point from a plurality of preset reference points, etc., which is not specifically limited here.

[0065] The first reference path can be preset, and the first reference path can also be located in the target driving area.

[0066] In combination with the example of the mining area application scenario described above, there can be a mining face in the mining area, which can be located on the blast pile boundary. Generally, the mining face is relatively fixed within a period of time, and the mining face can be calibrated by some means, such as based on radar detection or image detection technology, etc., to calibrate the mining face; or based on a global satellite positioning system to calibrate the mining face, etc. As for the specific calibration process of the mining face, it can be implemented based on existing technologies, which is not described here.

[0067] In combination with Figure 1 As can be seen, the excavator is generally located near the mining face, and the mine truck needs to drive to the vicinity of the excavator for loading of the ore. The position of the mine truck for loading the ore can correspond to the above-described preset parking point, which is located in the open space and near the mining face. In other words, the distance between the parking point and the mining face is less than a preset distance, so that the excavator can conveniently load the ore for the mine truck parked at the parking point.

[0068] In some examples, the first reference path can correspond to the extension path of the mining face, or the first reference path can be located on the extension path of the mining face after the mining face translates by a preset distance towards the open space. Accordingly, the first reference path can be located near the parking point. In another aspect, the distance between the first reference path and the parking point is less than the first distance threshold. The first distance threshold can be greater than 0, and the specific value can be set as needed.

[0069] Since the mining face can be pre-calibrated, accordingly, in the process of planning the driving path of the vehicle, the first reference path can be considered as a preset path.

[0070] Of course, the above is some examples of the first reference path in the mining area, and in actual application, the first reference path can also be a reference path determined by other ways, for example, the first reference path can be a relatively flat road segment near the parking point, and the like.

[0071] As for the distance between the first reference path and the parking point, it can refer to the perpendicular distance from the parking point to the first reference path or its extension line, or the minimum value of the distance between the parking point and multiple reference points on the first reference path, and the like, which can be selected as needed.

[0072] The first path point can not be located on the first reference path, that is, the vehicle needs to plan a driving path from the first path point to the first reference path, which is the first planning path described above. In this embodiment, the vehicle can first determine a second path point in the first reference path, and further plan a first planning path from the first path point to the second path point.

[0073] As described above, the first reference path can include multiple reference points, and the second path point can be any reference point in the multiple reference points. That is, in step 202, the vehicle can randomly select a reference point from the first reference path as the second path point.

[0074] Of course, in actual application, the second path point can also be a preset reference point in the first reference path, for example, the second path point can be an endpoint or a midpoint of the first reference path, and the like.

[0075] For another example, the second path point can also be the endpoint of the first planning path obtained in the historical path planning process.

[0076] In step 203, the vehicle can plan a first planning path for the vehicle from the first path point to the second path point. In this step, the vehicle can plan the first planning path based on a heuristic search algorithm, such as A-star algorithm or hybrid A-star algorithm. Alternatively, the vehicle can also connect the first path point and the second path point by an analytic path, and take the analytic path successfully connecting the two path points as the first planning path, where the type of the analytic path can be Reeds-Shepp curve or Dubins curve, etc.

[0077] As to the specific implementation of the first planning path by the heuristic search algorithm or the analytic path, no further description is made herein. In actual applications, the vehicle can also use other types of path planning algorithms, i.e., the specific planning manner of the first planning path can not be specifically limited herein.

[0078] In step 204, the vehicle can splice the first reference path and the first planning path to obtain a first target driving path, which can be located in the target driving area.

[0079] In combination with some application scenarios, each reference point on the first reference path can have corresponding pose information, and the vehicle can take the pose information of the second path point as the input of the path planning algorithm when planning the first planning path. Accordingly, the first planning path output by the path planning algorithm can smoothly transition to the first reference path under the condition of satisfying the vehicle dynamics parameters.

[0080] Of course, in some possible application scenarios, there can be path points with discontinuous curvature or pose in the path obtained by splicing the first reference path and the first planning path. At this time, the spliced path can be smoothed to obtain the above-mentioned first target driving path.

[0081] In actual applications, the second path point can be selected at the middle part of the first reference path, and in the path splicing process, the first planning path can be spliced with the side of the first reference path close to the parking point, so as to obtain the first target driving path that can guide the vehicle to the parking point as much as possible.

[0082] In some feasible embodiments, the first target driving path can be a global path or a component of the global path, which can generally guide the vehicle to drive to the vicinity of the parking point. The vehicle can drive from the vicinity of the parking point to the parking point through the planning of a local path, and the planning manner of the local path can be implemented by the prior art, and no further description is made herein.

[0083] As shown above, the first reference path can be a relatively fixed path, such as a mining face. When planning the first planned path, the vehicle can select a relatively fixed starting point and ending point, so that the first planned path can be updated frequently due to changes in the parking point.

[0084] The first target driving path is mainly determined according to the first reference path and the first planned path, so the vehicle does not need to update the first target driving path frequently. At the same time, the distance between the first reference path and the parking point is less than the first distance threshold, and accordingly, the first target driving path can be used to reliably guide the vehicle to the vicinity of the parking point.

[0085] The vehicle driving path planning method provided by the embodiments of the present application acquires a target driving area of a vehicle, a first path point, and a preset first reference path. The first path point and the first reference path are located in the target driving area. A second path point is determined from the first reference path. A first planned path of the vehicle from the first path point to the second path point is planned. The first reference path and the first planned path are spliced to obtain a first target driving path of the vehicle in the target driving area. In this embodiment, the preset first reference path has a relatively fixed path, and the distance between the first reference path and the parking point is less than the first distance threshold. The first planned path from the first path point to the second path point on the first reference path can also be relatively fixed. Accordingly, based on the first target driving path obtained by splicing, the vehicle can be reliably guided to the vicinity of the parking point while avoiding the vehicle driving path changing too drastically, thereby improving the driving stability of the vehicle.

[0086] It is worth emphasizing again that the vehicle driving path planning method provided by the embodiments of the present application can not only be used in a mining truck in a mining area, but also be applied to a forklift in a warehouse, and the like, which are not listed here.

[0087] Optionally, the method further comprises:

[0088] Acquiring a third path point from the target driving area, the distance between the third path point and the parking point being less than a second distance threshold;

[0089] Planning a second planned path of the vehicle from the first path point to the third path point, the second planned path being an alternative path of the first target driving path.

[0090] In combination with some examples, the first target driving path can be a global path or a component of the vehicle in the target driving area. The second planned path is an alternative path of the first target driving path, and accordingly, the second planned path can also be a global path or a component of the vehicle in the target driving area.

[0091] The global path can be used to guide the vehicle to the vicinity of the parking point. Therefore, in the embodiment, the end point of the second planning path can also be set in the vicinity of the parking point. Specifically, the end point of the second planning path corresponds to the third path point, which is located in the target travel area and is within a second distance threshold from the parking point. The second distance threshold can be a value greater than 0.

[0092] In some examples, the parking point can be located on the mining face. The road condition near the mining face can be relatively complex. Therefore, the third path point can be determined as a position after the parking point is translated by a preset distance into the open space.

[0093] In other examples, the third path point can also be set as any point within a preset distance range of the parking point, as long as the third path point is located in the target travel area.

[0094] Of course, in some feasible embodiments, when the parking point is located in the target travel area, the third path point can also be the parking point.

[0095] As for the manner of planning the second planning path of the vehicle from the first path point to the third path point, it can be similar to the manner of planning the first target travel path, which will not be described herein.

[0096] In actual applications, the planning process of the second planning path can be performed after the first target travel path is obtained, i.e., after step 204, the third path point is obtained from the target travel area.

[0097] Alternatively, the determination of the first target travel path and the planning of the second planning path can be performed synchronously.

[0098] As indicated above, the position of the excavator can frequently change, and the parking point usually changes with the change of the position of the excavator. The third path point located in the vicinity of the parking point usually also changes with the change of the parking point. Therefore, the second planning path can need to be frequently updated. However, since the selection of the third path point is relatively flexible, and the second planning path can be planned as a whole, i.e., without the need for splicing of local paths, and the problem of path mutation caused by path splicing is less considered, the planning success rate of the second planning path is relatively high.

[0099] In other words, when planning the travel path of the vehicle from the first path point to the vicinity of the parking point, from the perspective of avoiding excessively frequent path updates, the first target travel path is a more optimal travel path than the second planning path. From the perspective of planning success rate, the planning success rate of the second planning path is higher than that of the first target travel path.

[0100] Therefore, in the embodiment, the first target driving path and the second planning path can be planned, and the second planning path is used as an alternative path of the first target driving path. When the first target driving path can be successfully planned, the first target driving path can be used to guide the vehicle to travel preferentially, so as to avoid that the travel path of the vehicle changes too sharply; and when the first target driving path cannot be successfully planned, the second planning path can be used as an alternative path to ensure that the vehicle can travel to the vicinity of the parking point.

[0101] As shown in Figure 3 , Figure 3 is a flowchart of a process of planning a driving path of the vehicle from the first path point to the vicinity of the parking point.

[0102] Figure 3 In the embodiment, the conventional path can correspond to the first target driving path, and the alternative path can correspond to the second planning path.

[0103] In the process of generating the conventional path, the vehicle can take the mining face as a set of subsequent passing points. The mining face can correspond to the first reference path, and the set of subsequent passing points corresponds to a set of reference points on the first reference path. It is easy to understand that the mining face here can be an actual mining face in the mining area, or can be a mining face translated by a preset distance into the inside of the open space, which is not limited here.

[0104] In the process of generating the alternative path, the vehicle can select any point of the mining face in the open space as a subsequent passing point. Similarly to the generation of the conventional path, the mining face here can be an actual mining face or a translated mining face. The subsequent passing point selected here can correspond to the third path point. In general, the subsequent passing point selected here can be relatively close to the parking space near the actual mining face in position.

[0105] Optionally, the method further comprises:

[0106] obtaining a fourth path point and a fifth path point from the target driving area, the distance between the fourth path point and the parking point is less than a third distance threshold, and the distance between the fifth path point and the first path point is less than a fourth distance threshold;

[0107] planning a third planning path of the vehicle from the fourth path point to the fifth path point.

[0108] In combination with the application scenario of the mining area, the first target driving path can be a path of the vehicle driving to the vicinity of the parking point. In actual application, after the vehicle is fully loaded at the parking point, the vehicle usually needs to drive away from the parking point. In the embodiment, the third planning path to be planned can be a path of the vehicle driving away from the parking point.

[0109] The fourth path point can be any point near the parking point, and the fourth path point is located in the target driving area. The fourth path point is near the parking point, which can be expressed as that the distance between the fourth path point and the parking point is less than a third distance threshold, which can be a value greater than 0.

[0110] In combination with some examples, the fourth path point can be a path point that is translated along the length direction of the parking point corresponding to the parking space by a preset distance. The vehicle can drive from the parking point to the fourth path point through simple local path planning.

[0111] Of course, the fourth path point can also not be limited to being obtained by translating the parking point along the length direction of the parking space, but can also be located at the oblique side or other positions of the parking space.

[0112] As shown above, the parking point can be near the mining surface with complex road conditions. When the vehicle reaches the fourth path point, it can be considered to have left the area with complex road conditions, thereby helping to reduce the difficulty of subsequent global path planning.

[0113] The fifth path point can be a path point near the first path point, that is, the distance between the fifth path point and the first path point is less than a fourth distance threshold, which can be a value greater than 0.

[0114] For example, in combination with Figure 1 , the vehicle can enter the unstructured area from one side of the width direction of the structured road, and when returning, the vehicle can enter the structured road from the other side of the width direction of the structured road. Accordingly, the first path point can be located at one side of the width direction of the structured road, and the fifth path point can be located at the other side of the width direction of the structured road.

[0115] In some possible implementations, when the structured road is relatively narrow, the first path point and the fifth path point can also be coincident.

[0116] After obtaining the fourth path point and the fifth path point, a third planning path of the vehicle from the fourth path point to the fifth path point can be planned. As for the planning manner of the third planning path, it can be similar to the planning manner of the first target driving path described above, and details are not repeated here.

[0117] In actual application, the planning of the third planning path can be performed after the first target driving path is determined, that is, after step 204, the steps of obtaining the fourth path point and the fifth path point from the target driving area are performed.

[0118] Alternatively, the planning of the third planning path and the planning of the first target driving path can also be performed synchronously.

[0119] The embodiment can plan a path for the vehicle to drive away from the parking spot, and better meet the demand of path planning for the vehicle in the target driving area. Meanwhile, the fourth path point near the parking spot is taken as the planning starting point of the third planning path, which helps to reduce the planning difficulty of the third planning path.

[0120] The selection of the fourth path point is relatively flexible, and therefore, the third planning path can be successfully planned, which generally meets the guidance demand of the vehicle driving away from the parking spot.

[0121] However, from the perspective of overall path planning, the vehicle still needs to use a local path planning algorithm to plan a driving path from the parking spot to the fourth path point on the basis of the third planning path.

[0122] To simplify the overall path planning process, optionally, after planning the third planning path of the vehicle from the fourth path point to the fifth path point, the method further includes:

[0123] planning a fourth planning path of the vehicle from the parking spot to the fifth path point;

[0124] In the case that the fourth planning path is successfully planned, the third planning path is determined as a candidate path of the fourth planning path.

[0125] In combination with some application scenarios, the position of the parking spot can be determined at a time point, that is, the parking spot can be a fixed path planning starting point. After the vehicle is fully loaded, if a global path from the parking spot to the fifth path point can be directly planned, the overall path planning demand of the vehicle can be effectively reduced.

[0126] That is, to some extent, the embodiment can be considered as seeking a more optimal global path on the basis of the third planning path from the perspective of simplifying the overall path planning.

[0127] Based on planning the fourth planning path of the vehicle from the parking spot to the fifth path point, it can be considered that the vehicle is in the process of seeking a more optimal global path. When the fourth planning path is successfully planned, it can be considered that the vehicle obtains a more optimal global path.

[0128] Therefore, in the embodiment, in the case that the fourth planning path is successfully planned, the third planning path is determined as a candidate path of the fourth planning path.

[0129] In other words, in the case that the fourth planning path is obtained, the fourth planning path can be preferentially used to guide the vehicle to drive, so as to meet the path planning requirements of the vehicle in different working conditions.

[0130] As for the planning manner of the fourth planning path, it can be similar to the planning manner of the first target driving path, which is not described herein again.

[0131] In some application scenarios, the fourth planned path may need to be further optimized to conform to the vehicle's kinematic model. When the optimization fails, for example, the curvature of at least one point in the fourth planned path is greater than the curvature threshold, the vehicle can be further guided based on the backup third planned path to ensure the completeness of the path for the vehicle to leave the parking point.

[0132] like Figure 4 As shown, Figure 4 A schematic diagram of a process for planning a vehicle's driving path from a parking spot or its vicinity to a fifth path point.

[0133] Combine Figure 4 The vehicle can select a point in the open space along the length of the garage as the starting point for open space global path planning, and generate an alternative path based on this starting point and the fifth path point. The alternative path here corresponds to the third planned path mentioned above, and the starting point selected during the alternative path planning process can correspond to the fourth path point mentioned above.

[0134] When generating an alternative path, the vehicle can further select the center of the garage as the starting point for open space global path planning and generate a regular path based on this starting point and the fifth path point. The regular path here corresponds to the fourth planned path described above, and the starting point selected during the regular path planning process can correspond to the parking point described above.

[0135] Generally speaking, the parking spot may be associated with posture information, which may be used as input to, for example, a hybrid A-star planning algorithm, or as input to a planning algorithm using an analytical path.

[0136] like Figure 5 As shown, Figure 5 This is a logic diagram of the vehicle path planning method selection process in a specific application example.

[0137] based on Figure 5 As can be seen, when there is a need for global path planning, the vehicle can determine whether to start the planning method of generating an analytical path. The planning method of generating an analytical path can correspond to the path planning method mentioned above that uses an analytical path to connect the starting point and the end point.

[0138] In some feasible implementations, when it is necessary to generate the above-mentioned first planned path, second planned path or third planned path, the vehicle may determine not to start the planning method for generating the parsed path, and may use a planning method based on a heuristic search algorithm.

[0139] When the fourth planned path mentioned above needs to be generated, the vehicle may determine to start a planning method for generating an analytical path.

[0140] In other words, when planning a path for the vehicle to travel to the vicinity of the parking spot, the first planned path and the second planned path can both be planned based on the heuristic search algorithm. When planning a path for the vehicle to travel away from the vicinity of the parking spot, the third planned path can be planned based on the heuristic search algorithm, and the fourth planned path can be planned based on the planning manner of generating an analytical path.

[0141] In combination with some examples, the heuristic search algorithm described above can be an A* algorithm or a hybrid A* algorithm. In the planning manner of generating an analytical path, a Reeds-Shepp curve or a Dubins curve can be used.

[0142] Referring to Figure 5 In Figure 5 In a corresponding application example, the A* algorithm can be used to generate a rough path, and the Dubins curve can be used to generate an analytical path.

[0143] In combination with the planning process of the first target travel path, the first planned path generated can also need to be spliced with the first reference path. The first reference path can be considered to include at least one passing point located behind the first planned path. The splicing process here can be located as the splicing of the first planned path and the subsequent passing point.

[0144] Similarly, when there is a passing point in front of the first planned path, the first planned path can also be considered to have a splicing process with the preceding passing point.

[0145] For the second planned path, the third planned path, or the fourth planned path generated, there can also be a splicing process with the preceding passing point and / or the subsequent passing point, which will not be described one by one here.

[0146] In actual applications, when the A* algorithm is used to plan a path, the curvature of some positions can be greater than the upper limit of the curvature, etc. Or, after the splicing of the path is completed, there can be a discontinuity at the splicing position, such as a sudden change in curvature at the splicing position. Accordingly, subsequent smoothing processing can be performed on the spliced path to generate a smooth path with limited curvature. The specific implementation manner of the smoothing processing will be further described below.

[0147] Based on Figure 5 As shown in the specific application example, the vehicle travel path planning method provided by the embodiments of the present application can mainly use a heuristic search algorithm when planning a global path, which helps to ensure the success rate of planning a vehicle travel path.

[0148] The planning process for the fourth planning path can be considered as a process of planning a more optimal global path in the case that the vehicle has successfully implemented the global path near the parking spot, and the planning method of generating the analytic path is helpful to efficiently obtain a driving path that conforms to the kinematic model of the vehicle.

[0149] Optionally, the fourth planning path of the vehicle from the parking spot to the fifth path point comprises:

[0150] A curvature constraint value is determined, the curvature constraint value is greater than or equal to a first curvature threshold value and less than or equal to a second curvature threshold value, and the curvature constraint value is used to constrain a maximum curvature value on the analytic path;

[0151] Under the constraint of the curvature constraint value, an initial analytic path for connecting the parking spot and the fifth path point is generated;

[0152] In the case that at least one initial analytic path is obtained, the shortest initial analytic path is determined as the fourth planning path;

[0153] In the case that no initial analytic path is obtained and the curvature constraint value is less than or equal to the difference between the second curvature threshold value and a preset step length, the curvature constraint value is increased by the preset step length, and the step of generating the initial analytic path for connecting the fourth path point to the fifth path point is returned to be executed.

[0154] For simplicity of description, the present embodiment will be mainly described by taking the analytic path as a Dubins curve.

[0155] It is easy to understand that when the curvature of the planned path is too large, it may exceed the turning ability of the vehicle, resulting in that the vehicle cannot drive according to the planned path.

[0156] Therefore, when planning the fourth planning path, a curvature constraint value can be determined, the curvature constraint value is greater than or equal to a first curvature threshold value and less than or equal to a second curvature threshold value. The second curvature threshold value can be related to the turning ability of the vehicle, for example, the second curvature threshold value can be equal to or slightly less than the inverse of the maximum turning radius of the vehicle, and the first curvature threshold value can be greater than 0.

[0157] The curvature constraint value can be used to constrain the maximum curvature value on the analytic path. That is, in the case that the parking spot and the fifth path point are determined as the starting point and the ending point of the planned path respectively, a Dubins curve can be used to connect the starting point and the ending point, and the curvature at any position on the Dubins curve needs to be less than or equal to the curvature constraint value.

[0158] As shown above, the parking point is associated with the pose information, and the fifth path point can also be given corresponding pose information as needed. In the process of connecting the two points by Dubins curve, the pose information of the two points can be used. As for the specific principle of Dubins curve for path planning, it is not described here.

[0159] Under the constraint of the curvature constraint value, if at least one Dubins curve can be used to connect the parking point and the fifth path point, the at least one Dubins curve here can correspond to the at least one initial analytical path described above. In this case, the shortest Dubins curve can be determined as the fourth planning path.

[0160] As shown above, the curvature constraint value can be a value in the curvature range from the first curvature threshold to the second curvature threshold, so when no Dubins curve can be obtained to connect the parking point and the fifth path point under the existing curvature constraint of the curvature constraint value, the embodiment can relax the constraint of the curvature constraint value.

[0161] Relaxing the constraint of the curvature constraint value can specifically be that when the curvature constraint value is less than or equal to the difference between the second curvature threshold and the preset step length, the curvature constraint value is increased by the preset step length. That is, under the condition of meeting the vehicle turning ability limit, the maximum curvature that can appear in the Dubins curve is increased.

[0162] In the case of increasing the curvature constraint value by the preset step length, the vehicle can again attempt to use the Dubins curve to connect the parking point and the fifth path point, that is, return to execute the step of generating the initial analytical path for connecting the fourth path point to the fifth path point.

[0163] In the embodiment, by determining the curvature constraint value and its increasing rule, it is helpful to make the obtained fourth planning path have smaller curvature and shorter length, and improve the quality of the fourth planning path.

[0164] As shown in FIG. 6, in one specific application example, the planning process of the fourth planning path can include steps 601 to 608. Figure 6

[0165] Step 601, give the first curvature threshold and the second curvature threshold, and establish a priority queue with the shortest path length as the cost, so as to quickly obtain the Dubins path with the shortest path length in the case of successfully generating the Dubins path.

[0166] The Dubins path can correspond to the Dubins curve described above that can connect the start point and the end point. The first curvature threshold can take a value greater than 0, the second curvature threshold is associated with the turning ability of the vehicle, and the first curvature threshold is less than the second curvature threshold. ​

[0167] Step 602, determine whether the current priority queue is empty, if yes, execute step 603, if no, output the Dubins path with the shortest length from the priority queue.

[0168] Step 603, obtain the given curvature constraint value.

[0169] In the initial state, the curvature constraint value can take the first curvature threshold value, and the curvature constraint value is used to constrain the maximum curvature value on the Dubins path.

[0170] Step 604, traverse all the subsequent route points to attempt to generate the Dubins path from the starting point to the subsequent route point.

[0171] In this step, the starting point can be the parking point described above, and the subsequent route point can correspond to the fifth path point described above. In some embodiments, the number of fifth path points can be one or more, and the vehicle can attempt to generate a Dubins path from the starting point to each fifth path point.

[0172] Step 605, determine whether the Dubins path is successfully generated, if yes, execute step 606, if no, execute step 607;

[0173] Step 606, add the Dubins path from the starting point to the subsequent route point to the priority queue, and execute step 608.

[0174] Step 607, increase the curvature constraint value of the current path by a preset step size, and execute step 608.

[0175] For example, the preset step size can be 0.01, of course, the specific value of the step size can be set as needed.

[0176] Step 608, determine whether the maximum curvature value on the current path is less than or equal to the curvature constraint value, if yes, output the shortest Dubins path, if no, return to execute step 602.

[0177] The above specific application example applies the planning method with Dubins path, which not only reduces the obstacle of excessive curvature to the actual vehicle execution, but also improves the success rate of path generation.

[0178] Optionally, after the step 204 of splicing the first reference path and the first planning path to obtain the first target driving path of the vehicle in the target driving area, the method further comprises:

[0179] Updating the target driving area, wherein the updated target driving area does not include the road area corresponding to the first target driving path;

[0180] Planning a third planning path of the vehicle from the fourth path point to the fifth path point, comprising:

[0181] In the updated target driving area, a third planned path of the vehicle from the fourth path point to a fifth path point is planned.

[0182] The definition of each path point in the embodiment is described above and will not be repeated here.

[0183] In combination Figure 1 The application scenario shown, the first target driving path can be the path of the vehicle driving from the structured road to the parking point, which can be simply referred to as the entry path.

[0184] After the vehicle is fully loaded, it often needs to drive from the parking point or its vicinity to the structured road, and the corresponding driving path can be considered as a third planned path to be planned, which is referred to as the exit path below.

[0185] Figure 1 In the open space shown, there can be entry and exit vehicles at the same time. In order to avoid collision between entry and exit vehicles, in the embodiment, the target driving area can be updated after the entry path is obtained.

[0186] In some embodiments, in the case where the entry path is planned, the vehicle can determine the road area corresponding to the entry path. For example, the vehicle can expand a preset distance to both sides with the entry path as the center line, thereby obtaining the road area corresponding to the entry path.

[0187] The updated target driving area can exclude the road area corresponding to the entry path. In this way, the exit path planned in the updated target driving area subsequently can avoid the road area corresponding to the entry path. In this way, the collision between the entry vehicle and the exit vehicle can be effectively prevented, and the safety of vehicle driving can be improved.

[0188] Optionally, the first target driving path of the vehicle in the target driving area is obtained by splicing the first reference path and the first planned path, comprising:

[0189] Splicing the first reference path and the first planned path to obtain a spliced path;

[0190] The spliced path is smoothed to obtain the first target driving path.

[0191] The first planned path can be planned based on one path point in the first reference path as the terminal point. Therefore, the first planned path can actually realize splicing with the first reference path to obtain the spliced path.

[0192] The spliced path can be considered to give a rough path of the vehicle from the first path point to the vicinity of the parking point, that is, the spliced path can be a rough path. In actual application, the curvature of some road segments in the spliced path can exceed the steering capability limit of the vehicle, or the vehicle can make many sharp turns when driving according to the spliced path.

[0193] In combination with some application scenarios, the vehicle can use the A-star algorithm when planning the first planning path. The A-star algorithm usually does not consider the heading angle parameter, resulting in excessive curvature of some path points in the planned path, which exceeds the steering capability of the vehicle.

[0194] For another example, at the connection position of the first planning path and the first reference path, a curvature mutation can occur, which causes the vehicle to be unable to pass normally.

[0195] Therefore, in this embodiment, the spliced path can be smoothed to obtain the first target driving path.

[0196] As for the smoothing manner of the spliced path, the spliced path can be smoothed as a whole, or the spliced path can be smoothed locally (for example, at the connection position of the first planning path and the first reference path), or both the whole smoothing and the local smoothing can be performed, which is not limited here.

[0197] In general, through the smoothing processing, the first target driving path obtained can meet the steering capability requirement of the vehicle, and the situation of sharp turning of the vehicle can be reduced, and the quality of the path is improved.

[0198] It is easy to understand that, in combination with Figure 1 the application scenario of the mining area shown in FIG. 1, the processing manner of splicing the multi-segment path can also occur in the planning process of the driving-out path. For example, when the vehicle plans to obtain the second planning path, the second planning path can need to be spliced with the reference path on the structured road, and the like.

[0199] Correspondingly, the vehicle can also perform smoothing processing on these spliced paths, so as to obtain a high-quality planning path meeting the kinematic model of the vehicle.

[0200] Optionally, the smoothing processing on the spliced path to obtain the first target driving path comprises:

[0201] determining P first sampling points in the spliced path, P being an integer greater than 1;

[0202] respectively determining a corresponding bounding box for each first sampling point in the i th smoothing processing period, wherein i is a positive integer less than or equal to M, and M is a preset maximum smoothing number;

[0203] input the P first sampling points and the corresponding bounding boxes to a preset smoother to perform smoothing processing, to obtain a first smoothed path, the first smoothed path including P second sampling points corresponding to the P first sampling points, wherein each second sampling point is located in the bounding box corresponding to the corresponding first sampling point;

[0204] in a case where the first smoothed path meets a preset condition, output the first smoothed path as a first target driving path, the preset condition including that the curvature of each second sampling point on the first smoothed path is less than or equal to a preset curvature threshold, and the road region corresponding to the first smoothed path is located in the target driving region as a whole;

[0205] in a case where the first smoothed path does not meet the preset condition and i is less than M, determine the P second sampling points as the P first sampling points, and enter an (i+1)th smoothing processing period.

[0206] In some feasible embodiments, the vehicle can sample on the spliced path according to a preset sampling rule to obtain a plurality of first sampling points, i.e., the P first sampling points.

[0207] For the preset sampling rule, it can be equidistant sampling, or it can be interval sampling in the order of the existing path points of the path segments (such as the first reference path and the first planning path), and the like, which is not limited here.

[0208] In this embodiment, the vehicle can perform one or more smoothing processes on the spliced path, and each smoothing process can correspond to a smoothing processing period. The maximum number of smoothing processes can be preset, i.e., the M above can be preset, which can be equal to 1 or an integer greater than 1.

[0209] In the first smoothing processing period, the pose of each first sampling point can be the pose on the spliced path.

[0210] During the smoothing process, the pose of each first sampling point can change. In each smoothing processing period, the embodiment can determine a corresponding bounding box for each first sampling point, which can be used to limit the position change range of the corresponding first sampling point in the smoothing processing period.

[0211] In other words, in a smoothing processing period, the position of the first sampling point can change, and the first sampling point after the position change can be referred to as a second sampling point, and the second sampling point can be located in the bounding box corresponding to the first sampling point.

[0212] In this embodiment, the P first sampling points and their corresponding bounding boxes can be input to a preset smoother for smoothing processing. Each first sampling point can carry corresponding pose information, and the smoother can be implemented by existing technology, and its specific type is not limited here.

[0213] After one smoothing processing, the smoother can output a first smoothed path, which can include P second sampling points, which can be considered as the P first sampling points after pose updating.

[0214] In this embodiment, the vehicle can output the first smoothed path as the first target driving path when the first smoothed path meets a preset condition.

[0215] The preset condition can include that the curvature of each second sampling point on the first smoothed path is less than or equal to a preset curvature threshold, and the road region corresponding to the first smoothed path is located entirely within the target driving region.

[0216] The preset curvature threshold can be less than or equal to the inverse of the maximum turning radius of the vehicle, to ensure that the first target driving path can meet the turning ability limit of the vehicle.

[0217] When the first smoothed path does not meet the preset condition and the number of smoothing processing has not reached the maximum smoothing number, the vehicle can enter the next smoothing processing cycle.

[0218] Generally, in the i+1th smoothing processing cycle, the P first sampling points input to the smoother can be the P second sampling points obtained in the ith smoothing processing cycle. Therefore, in this embodiment, after the P second sampling points are determined as the P first sampling points, the i+1th smoothing processing cycle can be entered.

[0219] The smoothing processing in each smoothing processing cycle can be similar and will not be repeated here.

[0220] This embodiment can be considered as overall smoothing processing of the spliced path, and the output driving path can meet the kinematic constraints of the vehicle and ensure that the vehicle drives within the target driving region, thereby improving the quality of the planned vehicle driving path.

[0221] In some possible embodiments, the above-mentioned preset curvature threshold can be less than the inverse of the maximum turning radius of the vehicle, to limit the maximum turning radius of the vehicle in actual driving, reduce the phenomenon of sharp turning of the vehicle in driving, and improve the driving safety of the vehicle.

[0222] In some other possible implementations, when the first smoothed path does not satisfy the preset condition and the number of times of smoothing is equal to the maximum number of times of smoothing, it can be considered that the smoothing of the existing spliced path fails, and at this time, a selected alternative planning path (for example, the second planning path described above) can be further smoothed to obtain an actually available vehicle navigation path.

[0223] It is easy to understand that the smoothing described above can also be applied to other spliced paths, such as the spliced paths obtained in the exit path planning described above.

[0224] As shown in Figure 7 , Fig. 7 is a flowchart of a process of smoothing a spliced path based on a smoother in a specific application example, including steps 701 to 709. Figure 7

[0225] Step 701, interpolating the input spliced path to obtain a plurality of path points, and filling the path point information, such as curvature.

[0226] In this step, the path points obtained by interpolation correspond to the first sampling points described above.

[0227] Step 702, generating an initial path boundary with the spliced path as a center line, and checking whether the initial path boundary will collide, and in the case of no collision, entering step 703.

[0228] Step 703, creating a smoother and taking the initial path boundary as input.

[0229] Step 704, judging whether the number of times of smoothing is less than the maximum number of times of smoothing, if yes, executing step 705, and if no, ending;

[0230] Step 705, judging whether it is necessary to re-smooth, if yes, executing step 706, and if no, ending and outputting the smoothed path.

[0231] The basis for judging whether it is necessary to re-smooth can be the preset condition described above, that is, the curvature of each second sampling point on the first smoothed path is less than or equal to the preset curvature threshold, and the road region corresponding to the first smoothed path is located in the target driving region as a whole.

[0232] Step 706, adjusting the path boundary and taking the updated path boundary as input of the smoother;

[0233] Step 707, judging whether the smoothing is successful, if yes, executing step 708, and if no, executing step 709.

[0234] Step 708, storing the smoothed path, which can be used as an alternative path for global path planning next time. ​

[0235] Step 709, generating a path boundary with the alternative path, and returning to perform step 705.

[0236] In this application example, the output smooth path can ensure that the maximum absolute value of the curvature is limited within a certain threshold, thereby helping to generate a drivable path for the vehicle.

[0237] Optionally, a corresponding boundary box is determined for each first sampling point, comprising:

[0238] The curvature corresponding to the first sampling point is obtained, and the size of the boundary box corresponding to the first sampling point is determined according to the curvature corresponding to the first sampling point and a preset corresponding relationship between the curvature and the size of the boundary box.

[0239] In some examples, when the curvature corresponding to the first sampling point is less than or equal to a preset value, a boundary box of a reference size can be determined for the first sampling point. When the curvature corresponding to the first sampling point is greater than a preset value, the size of the corresponding boundary box can be appropriately enlarged.

[0240] For example, when the curvature corresponding to the first sampling point is greater than 0.05m -1 , the length and width of the boundary box can be expanded by a certain percentage (such as 1.5 times) respectively.

[0241] As can be seen in the above examples, the curvature of the first sampling point and the size of the boundary box have a positive correlation, which corresponds to the above-mentioned preset corresponding relationship between the curvature and the size of the boundary box.

[0242] Of course, in other examples, the corresponding relationship between the curvature and the size of the boundary box can be represented by a mapping table or a function, which will not be exemplified one by one here.

[0243] The curvature corresponding to the first sampling point can be the curvature on the spliced path without smoothing, or the curvature on the first smooth path after smoothing, etc.

[0244] This embodiment can be considered as determining the size of the boundary box corresponding to the first sampling point according to the curvature corresponding to the first sampling point, which helps to speed up the smoothing rate of the smoother on the spliced path and improve the generation efficiency of the first target driving path.

[0245] Optionally, after determining the corresponding boundary box for each first sampling point, the method further comprises:

[0246] In the case that the boundary box corresponding to the first sampling point is at least partially located outside the target driving area, the size of the boundary box corresponding to the first sampling point is reduced so that the boundary box after size reduction is located entirely within the target driving area.

[0247] It is easy to understand that when the first sampling point corresponds to a bounding box at least partially outside the target driving area, the second sampling point corresponding to the first sampling point after smoothing may be outside the target driving area, i.e., in a position difficult for the vehicle to reach, and the first smoothed path obtained accordingly does not meet the actual demand.

[0248] Therefore, the embodiment can reduce the bounding box falling outside the target driving area, so that the reduced bounding box is entirely within the target driving area.

[0249] For example, in the process of reducing the bounding box, the vehicle can reduce the length and width of the bounding box to 0.9 times of the original, and when the reduced bounding box is still partially outside the target driving area, the length and width of the bounding box can be further reduced until the reduced bounding box is entirely within the target driving area.

[0250] It can be seen that the embodiment can constrain the first smoothed path within the target driving area in the path smoothing stage, and further ensure that the output first target driving path is also located in the target driving area, meeting the actual driving demand of the vehicle.

[0251] Optionally, the P first sampling points in the spliced path are determined, comprising:

[0252] The path points in the spliced path within a preset range of a target position are locally smoothed to obtain a second smoothed path, the target position being an intersection position between the first reference path and the first planning path;

[0253] The P first sampling points are determined from the second smoothed path.

[0254] If the process of smoothing the spliced path using a smoother is referred to as overall smoothing, in the embodiment, it can be considered as local smoothing of the spliced path at the splicing position.

[0255] As indicated above, the first planning path can be a relatively rough path, and after splicing with the first reference path, a mutation in curvature or other parameters can occur.

[0256] Therefore, in the embodiment, the path points in the spliced path within a preset range of a target position can be locally smoothed to obtain a second smoothed path, and then the P first sampling points are determined from the second smoothed path, so as to further perform overall smoothing on the path.

[0257] In the embodiment, the local smoothing can be considered as a first smoothing of the spliced path, and the overall smoothing can be considered as a second smoothing of the spliced path, which helps to effectively improve the quality of the vehicle driving path obtained by planning.

[0258] In some possible embodiments, the local smoothing can employ a convolution smoothing, and the main purpose is to perform a rough smoothing on the junctions of the rough path, so that the position coordinates, the orientation angle, and the curvature are continuous with respect to the accumulated distance. Optionally, the local smoothing can not require the curvature maximum and minimum to be limited.

[0259] In practical applications, the convolution smoothing can be over-smoothed, and therefore the vehicle can also perform a collision detection on the smoothed path and the target driving area, so as to ensure that the smoothed path is still within the target driving area.

[0260] In some other possible embodiments, the first reference path and the first planning path described above can be locally smoothed respectively. On the basis of smoothing the first reference path and the first planning path respectively, the smoothing of the intersection position is performed again.

[0261] Referring to Figure 1 , the first planning path described above can be a planning path from the end of the structured road (corresponding to the first path point) to the vicinity of the parking point (corresponding to the second path point). Behind the first planning path, there can be the first reference path determined according to the mining face. In front of the first planning path, there can also be a reference path determined according to the structured road.

[0262] For the convenience of planning a global path for the vehicle in the target driving area in Figure 1 or the like, in an embodiment, the above-mentioned obtaining of the first path point comprises:

[0263] obtaining a preset second reference path;

[0264] determining the first path point from the second reference path;

[0265] splicing the first reference path and the first planning path to obtain a first target driving path of the vehicle in the target driving area, and specifically comprising:

[0266] splicing the first reference path, the first planning path, and the second reference path to obtain a target driving path of the vehicle in the target driving area.

[0267] Similarly, in combination with the application scenario shown in Figure 1 , the second reference path can be a reference path determined according to the structured road. For example, the structured road can be based on a relatively obvious edge, or the structured road can have lane lines, and the second reference path can be determined based on the road edge or the lane lines.

[0268] There can be multiple reference points in the second reference path, and the first path point can be any one of the reference points. Since the second reference path can be considered to be located in front of the first planning path, the reference points in the second reference path can all be called predecessor waypoints, and multiple predecessor waypoints can constitute a predecessor waypoint set.

[0269] Correspondingly, the first target driving path can be obtained by splicing the first reference path, the first planning path, and the second reference path. In this way, a relatively complete global driving path can be obtained in the target driving area.

[0270] The path obtained by splicing the first reference path, the first planning path, and the second reference path can also be called a spliced path. In addition, when planning the exit path, the second planning path or the third planning path described above can also need to be spliced with other paths to obtain a spliced path. The spliced path can also be subjected to smoothing processing.

[0271] The following will be described in combination with a specific application example. As shown in FIG. 8, the local smoothing process can include steps 801 to 804. Figure 8

[0272] In step 801, the predecessor waypoint set and the successor waypoint set are obtained, and a coarse path / Dubins path based on heuristic search is obtained.

[0273] In this step, the coarse path can be the first planning path, the second planning path, or the third planning path described above. The Dubins path can correspond to the fourth planning path described above.

[0274] In combination with the above description of the predecessor waypoints and the successor waypoints of the first planning path, the predecessor waypoints can be path points located in front of the planning path, and the successor waypoints can be path points located in front of the planning path. When the predecessor waypoints or the successor waypoints are points on the reference path, the number of the predecessor waypoints or the successor waypoints can be multiple, thereby constituting a corresponding point set.

[0275] In step 802, the predecessor waypoint set and the successor waypoint set are locally smoothed and added to the spliced path.

[0276] This step can be considered as individual smoothing of the reference paths described above.

[0277] In step 803, the coarse path / Dubins path is added to the spliced path.

[0278] In step 804, the target position of the spliced path is locally smoothed.

[0279] ​The target position can be an intersection position between the rough path and the preceding set of waypoints, an intersection position between the rough path and the following set of waypoints, an intersection position between the Dubins path and the preceding set of waypoints, an intersection position between the Dubins path and the following set of waypoints, or the like.

[0280] Optionally, a target driving area of the vehicle is obtained, including:

[0281] A first boundary of a preset open space and a second boundary of an obstacle in the open space are obtained.

[0282] The first boundary is shrunk by a first preset distance, and the second boundary is inflated by a second preset distance.

[0283] An area located within the shrunk first boundary and located outside the second boundary after the collision is determined as the target driving area of the vehicle.

[0284] In combination Figure 1 As shown in the application scenario, in a mining area, the first boundary of the open space can include a blast pile boundary. In a theoretical case, the vehicle can drive to the blast pile boundary edge.

[0285] However, in actual application, the driving path of the vehicle can be obtained by simplifying the vehicle as a point, and the simplified point can be a center of mass of the vehicle or a position of an inertial unit, etc. If there is a path point in the planned driving path located at the first boundary, when the vehicle drives to the path point, the vehicle body can be scraped or collided with a mining surface due to a certain width of the vehicle body.

[0286] Alternatively, there can be a large amount of gravel near the first boundary of the open space, resulting in poor road conditions.

[0287] Considering the above factors, in some feasible embodiments, the first boundary can be shrunk, and the distance of the shrinkage, i.e., the first preset distance, can be half the width of the vehicle. When the vehicle reaches the shrunk first boundary, scraping or collision with the actual first boundary can be avoided.

[0288] Alternatively, the distance of the shrinkage can also be other first preset distances, such as 5 m, so that the complex road near the actual first boundary can be avoided when planning a global path.

[0289] In the open space, there can be some known obstacles, such as large pieces of gravel or lakes, etc. The second boundary of these obstacles can be obtained by pre-marking. Based on the similar consideration of shrinking the first boundary, in this embodiment, the second boundary can be inflated by a second preset distance.

[0290] The second preset distance may be equal to or different from the first preset distance, and can be selected according to needs.

[0291] In this embodiment, the area within the first boundary after retraction and outside the second boundary after collision is determined as the target driving area of ​​the vehicle. Subsequent path planning can be carried out in the target driving area, which helps to improve the reliability and practicality of the planned driving path.

[0292] In practical applications, the vehicle driving path planning can be performed in, for example, a map coordinate system or a geodetic coordinate system.

[0293] Generally speaking, the coordinates of each point in a map coordinate system or a geodetic coordinate system may have many decimal places. When performing path planning, excessive decimal places may lead to a large consumption of computing resources. Therefore, in some feasible embodiments, before obtaining the first boundary of the preset open space and the second boundary of the obstacle in the open space, the method further includes:

[0294] Establish a local coordinate system for the open space;

[0295] Obtaining a first boundary of a preset open space and a second boundary of an obstacle in the open space includes:

[0296] Get the first boundary and the second boundary in the local coordinate system.

[0297] In this embodiment, a local coordinate system is established for open space. Because the area of ​​open space is much smaller than the area covered by coordinate systems such as the geodetic coordinate system, the coordinate values ​​of each point in the local coordinate system can be set to a small number of decimal places. Subsequent determination of the target driving area and route planning can be performed in the local coordinate system, thereby helping to reduce computing resource consumption during the entire route planning process.

[0298] like Figure 9 As shown, in a specific application example, the process of performing path planning in the local coordinate system may include steps 901 to 904 .

[0299] Step 901: Construct a local coordinate system of the open space.

[0300] In step 902 , the coordinates of the boundary of the drivable area in the open space are transformed and unified into the local coordinate system.

[0301] In the step, the drivable area may correspond to the target drivable area, and the boundary of the drivable area may include a first boundary after shrinking and a second boundary after expanding.

[0302] Step 903: Generate a predecessor path point and a successor path point.

[0303] In this step, the coordinates of each path point in the reference path can be converted into the local coordinate system.

[0304] Step 904, the entry path or exit path of the drivable area in the open space is generated.

[0305] The above embodiments describe the generation method of the entry path or exit path, which will not be repeated here.

[0306] In this application example, the entry path and exit path generation can be performed in the local coordinate system. The construction of the local coordinate system of the open space can avoid the numerical error of the global coordinate system, and is beneficial to data analysis and processing.

[0307] As shown in Figure 10 , in the application scenario of the mining area shown in Figure 1 , the vehicle driving path planning method provided by the embodiments of the application can generally include steps 1001 to 1004.

[0308] Step 1001, structured road reference line processing.

[0309] In this step, the reference line of the structured road extending in the open space drivable area can be obtained as the splicing path of the entry and exit path.

[0310] Step 1002, inner shrinkage of open space boundary and expansion of obstacle.

[0311] In this step, the target driving area meeting the actual driving requirements of the vehicle can be obtained.

[0312] Step 1003, global path generation in the open space drivable area.

[0313] Step 1004, resampling and outputting the final path.

[0314] In this step, the global path can be smoothed to reduce the maximum curvature value in the global path as much as possible, and to avoid the global path reaching outside the drivable area.

[0315] As shown in Figure 11a and Figure 11b , the path change diagram output in the multiple smoothing process of the global path is shown in Figure 11a . The horizontal axis in the figure can be the X axis in the local coordinate system, with the unit of m; the vertical axis is the Y axis in the local coordinate system, with the unit of m.

[0316] Figure 11aThe initial global path and the final path output are shown in the figure. It can be seen that the maximum curvature in the final path is smaller, and the path is shorter, and the quality is significantly improved compared with the initial global path.

[0317] Figure 11b The figure shows the change of curvature in each path output during the smoothing process with respect to the cumulative distance. The horizontal axis in the figure can be the cumulative distance, denoted as s, with the unit of m; the vertical axis is the curvature, denoted as kappa, with the unit of m -1 .

[0318] Based on Figure 11b It can be seen that as the smoothing process proceeds, the maximum curvature (corresponding to the peak value) in the global path gradually decreases, and the maximum curvature of the final path output can be less than 0.15 m -1 .

[0319] Referring to Figure 12 , Figure 12 The figure shows the effect comparison of the global path before and after resampling in the drivable area of the open space. The horizontal axis in the figure is the X axis, and the vertical axis is the Y axis. The outermost dotted boundary point can be the boundary of the drivable area of the open space. The relatively rough trajectory in the open space is the initial spliced trajectory, and the relatively smooth trajectory is the final converged smoothing path.

[0320] As can be seen from the above description, the embodiments of the present application can adopt different conventional path and alternative path generation strategies to meet the requirements of different working conditions for the global navigation path, thereby reducing the problem of frequent updating of the navigation path caused by the dynamic updating of the open space in the mine. The open space exit path generation adopts multiple strategies, and the Dubins path method is applied, which not only reduces the excessive curvature that hinders the actual vehicle execution, but also improves the success rate of the exit path generation. A multi-level smoothing algorithm is adopted to improve the quality of the global navigation path. The local smoothing effectively reduces the curvature discontinuity at the splicing point, and the final smoother performs global smoothing to limit the curvature value within a reasonable range and meet the kinematic constraints of the vehicle. The pre-processing of the actual situation in the mine is also provided in the embodiments of the present application, especially the inward shrinking algorithm for the boundary of the open space, which solves the problem of insecurity and low efficiency of the generated entry path or exit path close to the boundary of the open space operation in the mine.

[0321] As Figure 13 shown, the embodiments of the present application also provide a vehicle driving path planning device. The device comprises:

[0322] The first acquisition module 1301 is configured to acquire a target driving area of a vehicle, a first path point, and a first reference path. The first path point and the first reference path are both located in the target driving area. The distance between the first reference path and a preset parking point is less than a first distance threshold, and the first path point is not located in the first reference path.

[0323] The first determining module 1302 is configured to determine a second path point from the first reference path;

[0324] The first planning module 1303 is configured to plan a first planning path of the vehicle from the first path point to the second path point;

[0325] The splicing module 1304 is configured to splice the first reference path and the first planning path to obtain a first target driving path of the vehicle in the target driving area.

[0326] Optionally, the vehicle driving path planning apparatus can further include:

[0327] The second obtaining module is configured to obtain a third path point from the target driving area, the distance between the third path point and the parking point being less than a second distance threshold;

[0328] The second planning module is configured to plan a second planning path of the vehicle from the first path point to the third path point, the second planning path being an alternative path of the first target driving path.

[0329] Optionally, the first planning path and the second planning path are both planned based on a heuristic search algorithm.

[0330] Optionally, the vehicle driving path planning apparatus can further include:

[0331] The third obtaining module is configured to obtain a fourth path point and a fifth path point from the target driving area, the distance between the fourth path point and the parking point being less than a third distance threshold, and the distance between the fifth path point and the first path point being less than a fourth distance threshold;

[0332] The third planning module is configured to plan a third planning path of the vehicle from the fourth path point to the fifth path point.

[0333] Optionally, the third planning path is planned based on a heuristic search algorithm.

[0334] Optionally, the vehicle driving path planning apparatus can further include:

[0335] The fourth planning module is configured to plan a fourth planning path of the vehicle from the parking point to the fifth path point;

[0336] The second determining module is configured to determine the third planning path as an alternative path of the fourth planning path in the case that the fourth planning path is successfully planned.

[0337] Optionally, the fourth planning module includes:

[0338] The first determining unit is configured to determine a curvature constraint value, the curvature constraint value being greater than or equal to a first curvature threshold and less than or equal to a second curvature threshold, the curvature constraint value being used to constrain a maximum curvature value on the analytic path.

[0339] The generating unit is configured to generate an initial analytic path for connecting the parking point and the fifth path point under the constraint of the curvature constraint value.

[0340] The second determining unit is configured to, in a case where the at least one initial analytic path is obtained, determine the shortest initial analytic path as the fourth planning path.

[0341] The executing unit is configured to, in a case where the initial analytic path is not obtained and the curvature constraint value is less than or equal to the difference between the second curvature threshold and the preset step length, increase the curvature constraint value by the preset step length, and return to execute the step of generating the initial analytic path for connecting the fourth path point to the fifth path point.

[0342] Optionally, the vehicle travel path planning apparatus can further include:

[0343] The updating module is configured to update the target travel area, wherein the updated target travel area does not include the road area corresponding to the first target travel path.

[0344] Correspondingly, the third planning module can be specifically configured to:

[0345] plan, in the updated target travel area, a third planning path of the vehicle from the fourth path point to the fifth path point.

[0346] Optionally, the splicing module 1304 includes:

[0347] The splicing unit is configured to splice the first reference path and the first planning path to obtain a spliced path.

[0348] The first smoothing unit is configured to perform smoothing processing on the spliced path to obtain the first target travel path.

[0349] Optionally, the first smoothing unit includes:

[0350] The first determining subunit is configured to determine P first sampling points in the spliced path, P being an integer greater than 1.

[0351] The second determining subunit is configured to determine, in the ith smoothing processing period, a corresponding bounding box for each first sampling point, wherein i is a positive integer less than or equal to M, and M is a preset maximum smoothing number.

[0352] The smoothing subunit is configured to input the P first sampling points and the corresponding bounding boxes to a preset smoother to perform smoothing processing, to obtain a first smoothed path, the first smoothed path including P second sampling points corresponding to the P first sampling points, wherein each second sampling point is located in the corresponding bounding box of the corresponding first sampling point.

[0353] The output subunit is configured to output the first smoothed path as a first target driving path when the first smoothed path meets preset conditions, the preset conditions including that curvatures of each second sampling point on the first smoothed path are all less than or equal to a preset curvature threshold, and a road region corresponding to the first smoothed path is located in the target driving region as a whole;

[0354] The control subunit is configured to, when the first smoothed path does not meet the preset conditions and i is less than M, determine the P second sampling points as the P first sampling points, and enter an i+1th smoothing processing period.

[0355] Optionally, the second determination subunit can be specifically configured to:

[0356] The first sampling point corresponding curvature is obtained, and the size of the first sampling point corresponding bounding box is determined according to the first sampling point corresponding curvature and a preset corresponding relationship between the curvature and the size of the bounding box.

[0357] Optionally, the first smoothing unit can further include:

[0358] The size of the first sampling point corresponding bounding box is reduced to make the size-reduced bounding box located in the target driving region as a whole when the first sampling point corresponding bounding box is at least partially located outside the target driving region.

[0359] Optionally, the first determination subunit can be specifically configured to:

[0360] The path points in the spliced path located within a preset range of the target position are subjected to local smoothing processing to obtain a second smoothed path, the target position being an intersection position between the first reference path and the first planning path.

[0361] The P first sampling points are determined from the second smoothed path.

[0362] Optionally, the first acquisition module 1301 can include:

[0363] The first acquisition unit is configured to acquire a preset second reference path.

[0364] The third determination unit is configured to determine the first path point from the second reference path.

[0365] Correspondingly, the splicing module 1304 can be specifically configured to:

[0366] The first reference path, the first planning path and the second reference path are spliced to obtain a first target driving path of the vehicle in the target driving region.

[0367] Optionally, the first acquisition module 1301 can include:

[0368] The second acquisition unit is configured to acquire a first boundary of a preset open space and a second boundary of an obstacle in the open space.

[0369] The inner contraction and expansion unit is configured to contract the first boundary by a first preset distance and expand the second boundary by a second preset distance.

[0370] The fourth determination unit is configured to determine a region located within the contracted first boundary and outside the collided second boundary as a target driving region of the vehicle.

[0371] Optionally, the vehicle driving path planning apparatus can further include:

[0372] The establishing module is configured to establish a local coordinate system for the open space.

[0373] Correspondingly, the second acquisition unit can be specifically configured to:

[0374] acquire the first boundary and the second boundary in the local coordinate system.

[0375] It should be noted that the vehicle driving path planning apparatus corresponds to the vehicle driving path planning method described above, and all implementation manners in the method embodiments are applicable to the embodiments of the apparatus and can achieve the same technical effects.

[0376] Figure 14 A hardware structure schematic diagram of an electronic device provided by an embodiment of the present application is shown.

[0377] The electronic device can include a processor 1401 and a memory 1402 having stored computer program instructions.

[0378] Specifically, the processor 1401 can include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or can be configured to implement one or more integrated circuits of the embodiments of the present application.

[0379] The memory 1402 can include a mass storage for data or instructions. By way of example and not limitation, the memory 1402 can include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 1402 can include removable or non-removable (or fixed) media. Where appropriate, the memory 1402 can be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, the memory 1402 is a non-volatile solid-state memory.

[0380] In particular embodiments, memory 1402 can include read-only memory (ROM), random-access memory (RAM), magnetic disk storage mediums, optical storage mediums, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, in general, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software that, when executed, is operable to perform operations as described with reference to the methods according to an aspect of the present disclosure.

[0381] Processor 1401 implements any of the vehicle travel path planning methods in the above embodiments by reading and executing computer program instructions stored in memory 1402.

[0382] In one example, the electronic device can further include a communication interface 1403 and a bus 1410. As shown, processor 1401, memory 1402, and communication interface 1403 are connected through bus 1410 and complete communication among each other. Figure 14

[0383] Communication interface 1403 is mainly used to realize the communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0384] Bus 1410 includes hardware, software, or both, that couples components of the online data traffic billing device to each other in a known manner. By way of example, and not limitation, a bus can include an accelerated graphics port (AGP) or other graphics bus, an enhanced industry standard architecture (EISA) bus, a front-side bus (FSB), a HyperTransport (HT) interconnect, an industry standard architecture (ISA) bus, an infiniband (IB) interconnect, a low pin count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standards board (VLB) bus, or another suitable bus or a combination of two or more of these. Where appropriate, bus 1410 can include one or more buses. Although the present application is described and illustrated with a particular bus, the present application contemplates any suitable bus or interconnect.

[0385] In addition, in combination with the vehicle travel path planning method in the above embodiments, the embodiments of the present application can provide a computer storage medium to realize. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to realize any of the vehicle travel path planning methods in the above embodiments.

[0386] ​It is to be understood that the application is not limited to particular configurations and processes described herein and shown in the drawings. The detailed description is not to be taken as limiting the application. In the above embodiments, several specific steps are described and illustrated in order to provide a thorough understanding of the application. However, the application can be practiced with fewer or additional steps, and in a different order. The application is to be limited only by the claims.

[0387] The functional blocks shown in the structural block diagrams above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, and the like. When implemented in software, the elements of the application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine-readable medium" includes any medium that can store or transfer information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. The code segments can be downloaded via computer networks such as the Internet, intranets, and the like.

[0388] It is also to be understood that the example embodiments described herein are based on a series of steps or apparatuses to describe some methods or systems. However, the application is not limited to the order of the steps described above, that is, the steps can be performed in the order mentioned in the embodiments, or in an order different from the embodiments, or several steps can be performed simultaneously.

[0389] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. Alternatively, computer program implemented steps can be implemented by special purpose logic circuitry, e.g., an FPGA or an ASIC, or by a combination of special purpose logic circuitry and computer hardware. Those skilled in the art will recognize that the present application is not limited to the specific implementations described herein, and thus features of the present application are not limited to any particular implementation, but extend to any and all implementations that would otherwise fall within the scope of the present application.

[0390] The above is merely specific implementation of the present application, and those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein again. It should be understood that the protection scope of the present application is not limited to this, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed in the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A vehicle travel path planning method characterized by comprising: The method comprises: obtaining a target driving area of a vehicle, a first path point and a preset first reference path, the first path point and the first reference path are located in the target driving area, a distance between the first reference path and a preset parking point is less than a first distance threshold, and the first path point is not located in the first reference path; determining a second path point from the first reference path; planning a first planning path of the vehicle from the first path point to the second path point; splicing the first reference path and the first planning path to obtain a first target driving path of the vehicle in the target driving area.

2. The method of claim 1, wherein, The method further comprises: obtaining a third path point from the target driving area, the distance between the third path point and the parking point is less than a second distance threshold; planning a second planning path of the vehicle from the first path point to the third path point, the second planning path is an alternative path of the first target driving path.

3. The method of claim 1, wherein, The method further comprises: obtaining a fourth path point and a fifth path point from the target driving area, the distance between the fourth path point and the parking point is less than a third distance threshold, and the distance between the fifth path point and the first path point is less than a fourth distance threshold; planning a third planning path of the vehicle from the fourth path point to the fifth path point.

4. The method of claim 3, wherein, After the planning of the third planning path of the vehicle from the fourth path point to the fifth path point, the method further comprises: planning a fourth planning path of the vehicle from the parking point to the fifth path point; in the case of successfully planning the fourth planning path, determining the third planning path as an alternative path of the fourth planning path.

5. The method of claim 4, wherein, The planning of the fourth planning path of the vehicle from the parking point to the fifth path point comprises: determining a curvature constraint value, the curvature constraint value is greater than or equal to a first curvature threshold and less than or equal to a second curvature threshold, and the curvature constraint value is used to constrain the maximum curvature value on the analytic path; generating an initial analytic path for connecting the parking point and the fifth path point under the constraint of the curvature constraint value; in the case of obtaining at least one initial analytic path, determining the shortest initial analytic path as the fourth planning path; in the case of not obtaining the initial analytic path and the curvature constraint value being less than or equal to the difference between the second curvature threshold and a preset step length, increasing the curvature constraint value by the preset step length and returning to execute the step of generating the initial analytic path for connecting the fourth path point to the fifth path point.

6. The method of claim 3, wherein, After the splicing of the first reference path and the first planning path to obtain the first target driving path of the vehicle in the target driving area, the method further comprises: updating the target driving area, wherein the updated target driving area does not include the road area corresponding to the first target driving path; the planning of the third planning path of the vehicle from the fourth path point to the fifth path point comprises: In the updated target driving area, a third planned path of the vehicle from the fourth path point to the fifth path point is planned.

7. The method of claim 1, wherein, The splicing the first reference path and the first planned path to obtain the first target driving path of the vehicle in the target driving area comprises: splicing the first reference path and the first planned path to obtain a splicing path; smooth the splicing path to obtain the first target driving path.

8. The method of claim 7, wherein, The smooth processing of the splicing path to obtain the first target driving path comprises: determining P first sampling points in the splicing path, P being an integer greater than 1; In the i th smoothing processing period, a corresponding bounding box is determined for each first sampling point, wherein i is a positive integer less than or equal to M, and M is a preset maximum smoothing number; input the P first sampling points and their corresponding bounding boxes into a preset smoother for smoothing processing to obtain a first smoothed path, the first smoothed path comprising P second sampling points corresponding to the P first sampling points, wherein each second sampling point is located in the bounding box corresponding to the corresponding first sampling point; if the first smoothed path meets a preset condition, output the first smoothed path as the first target driving path, the preset condition comprising that the curvature of each second sampling point on the first smoothed path is less than or equal to a preset curvature threshold, and the road area corresponding to the first smoothed path is located entirely within the target driving area; if the first smoothed path does not meet the preset condition and i is less than M, determine the P second sampling points as the P first sampling points, and enter the i+1 th smoothing processing period.

9. The method of claim 8, wherein, The determination of the corresponding bounding box for each first sampling point comprises: obtain the curvature corresponding to the first sampling point, and determine the size of the bounding box corresponding to the first sampling point according to the curvature corresponding to the first sampling point and a preset correspondence between curvature and bounding box size.

10. The method of claim 8, wherein, After determining the corresponding bounding box for each first sampling point, the method further comprises: if the bounding box corresponding to the first sampling point is at least partially located outside the target driving area, reduce the size of the bounding box corresponding to the first sampling point so that the size-reduced bounding box is located entirely within the target driving area.

11. The method of claim 8, wherein, The determination of the P first sampling points in the splicing path comprises: locally smooth the path points in the splicing path within a preset range of a target position to obtain a second smoothed path, the target position being an intersection position between the first reference path and the first planned path; determine the P first sampling points from the second smoothed path.

12. The method of claim 1, wherein, The obtaining of the first path point comprises: obtain a preset second reference path; determine the first path point from the second reference path; The splicing the first reference path and the first planned path to obtain the first target driving path of the vehicle in the target driving area comprises: Splice the first reference path, the first planning path and the second reference path to obtain the first target driving path of the vehicle in the target driving area.

13. The method of claim 1, wherein, The target driving area of the vehicle is obtained by: Obtaining a first boundary of a preset open space and a second boundary of an obstacle in the open space; The first boundary is shrunk by a first preset distance, and the second boundary is inflated by a second preset distance; The area located within the shrunk first boundary and outside the second boundary after the collision is determined as the target driving area of the vehicle.

14. The method of claim 13, wherein, Before the first boundary of the preset open space and the second boundary of the obstacle in the open space are obtained, the method further comprises: Establishing a local coordinate system for the open space; The first boundary and the second boundary are obtained in the local coordinate system. The device comprises:

15. A vehicle travel path planning device characterized by comprising: The first acquisition module is configured to obtain a target driving area of a vehicle, a first path point and a preset first reference path, the first path point and the first reference path are located in the target driving area, the distance between the first reference path and a preset parking point is less than a first distance threshold, and the first path point is not located in the first reference path; The first determination module is configured to determine a second path point from the first reference path; The first planning module is configured to plan a first planning path of the vehicle from the first path point to the second path point; The splicing module is configured to splice the first reference path and the first planning path to obtain a first target driving path of the vehicle in the target driving area. The device comprises a processor and a memory storing computer program instructions; 16. An electronic device, comprising: The processor executes the computer program instructions to implement the vehicle driving path planning method of any one of claims 1-14. The computer readable storage medium stores computer program instructions, and the computer program instructions are executed by the processor to implement the vehicle driving path planning method of any one of claims 1-14.

17. A computer-readable storage medium, characterized in that, The instructions in the computer program product are executed by the processor of the electronic device to make the electronic device execute the vehicle driving path planning method of any one of claims 1-14.

18. A computer program product, characterised in that, ​

Images