Global path planning control method, device, equipment, medium and program product

Abstract

The present application provides a global path planning control method, device, equipment, medium and program product, which obtains a high-precision map and an initial path; determines whether the initial path passes through at least one geometric prohibited area based on the high-precision map; if so, uses a preset cost model to determine one or more pre-anchor points required to bypass each geometric prohibited area based on the initial path and each geometric prohibited area; uses a preset path model to optimize and modify the initial path to a target path based on each pre-anchor point. It solves the technical problem of optimizing and improving the planning and control of the global path in order to achieve a higher level of autonomous driving functions. It achieves the technical effect of reducing the number of nodes that need to be searched during global path planning, reducing the global path planning time, and providing overall system operation efficiency.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and in particular to a global path planning control method, device, equipment, medium and program product. Background Art

[0002] With the development of artificial intelligence technology, people's demand for autonomous driving and intelligent control is also increasing. For example, automobile electrification and intelligent technology have brought about new changes. According to the classification of autonomous driving levels by SAE (Society of Automotive Engineers), major OEMs (Original Equipment Manufacturers) in the automotive industry have achieved autonomous driving functions below L2+ level.

[0003] However, L3 and above autonomous driving functions have higher requirements for vehicle intelligence and functions, among which global path planning and control is an important part of realizing autonomous driving. Existing technologies are not sufficient to support the needs of autonomous driving functions in this regard.

[0004] Therefore, in order to achieve higher levels of autonomous driving and intelligent control functions, optimizing and improving the planning and control of the global path has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a global path planning control method, device, equipment, medium and program product to solve the technical problem of optimizing and improving the planning control of the global path in order to achieve a higher level of autonomous driving functions.

[0006] In a first aspect, the present application provides a global path planning control method, comprising:

[0007] Obtain high-precision maps and initial paths;

[0008] Determine whether the initial path passes through at least one geometric prohibited area based on the high-precision map;

[0009] If yes, then using a preset cost model, according to the initial path and each geometrically prohibited area, determine one or more pre-anchor points required to bypass each geometrically prohibited area;

[0010] Using the preset path model, the initial path is optimized and modified into the target path according to each pre-anchor point.

[0011] In a possible design, the high-precision map contains the contour information of each obstacle, and judging whether the initial path passes through at least one geometric prohibited area according to the high-precision map includes:

[0012] Determine one or more geometric prohibited areas according to each contour information in the high-precision map, and the geometric prohibited area includes one or more obstacles;

[0013] Determine whether the initial path passes through at least one geometric prohibited area.

[0014] In a possible design, a preset cost model is used to determine one or more pre-anchor points required to bypass each geometric prohibited area according to the initial path and each geometric prohibited area, including:

[0015] For each geometrically prohibited area, a preset cost model is used to calculate the cost values ​​of running from the cost reference point to each vertex position of the geometrically prohibited area;

[0016] According to the preset cost requirement, at least one pre-anchor point corresponding to each geometric prohibited area is selected from each cost value;

[0017] The cost reference point includes: a starting point position, an end point position of the initial path, and at least one of the pre-anchor points that have been determined.

[0018] In a possible design, when determining the first pre-anchor point, the cost reference point includes the starting point position and / or the ending point position, and when determining other pre-anchor points, the cost reference point includes the last determined pre-anchor point.

[0019] In a possible design, the preset cost requirements include:

[0020] The vertex position corresponding to the minimum value among the cost values ​​is used as the pre-anchor point.

[0021] In a possible design, the vertex position corresponding to the minimum value among the cost values ​​is used as a pre-anchor point, including:

[0022] When the minimum value corresponds to multiple vertex positions, any vertex position is taken as the pre-anchor point.

[0023] In a possible design, the vertex position corresponding to the minimum value among the cost values ​​is used as a pre-anchor point, including:

[0024] When the minimum value corresponds to multiple vertex positions, the pre-anchor point is determined according to the coordinate values ​​of the multiple vertex positions corresponding to the minimum value in the high-precision map and the preset coordinate requirements.

[0025] Optionally, the vertex position corresponding to the minimum value among the cost values ​​is used as a pre-anchor point, including:

[0026] When the minimum value corresponds to multiple vertex positions, the pre-anchor point is determined according to the distances from the multiple vertex positions corresponding to the minimum value to the cost reference point and the preset requirements.

[0027] In a possible design, each pre-anchor point divides the target path into multiple segments, and the initial path is optimized and modified into the target path according to each pre-anchor point using a preset path model, including:

[0028] When determining the first section, a preset path model is used to determine a geometric line corresponding to the first section according to the starting position of the initial path and a first pre-anchor point, wherein the first pre-anchor point includes: at least one pre-anchor point corresponding to a first geometric prohibited area passed through by the initial path;

[0029] When determining the remaining segments, the preset path model is used to determine the geometric lines corresponding to the remaining segments based on the segment end point of the previous segment and the second pre-anchor point, and the second pre-anchor point includes: at least one pre-anchor point corresponding to the next geometric prohibited area passed by the initial path.

[0030] In a possible design, obtaining an initial path includes:

[0031] Get the starting point and the end point;

[0032] The first path model is used to determine an initial path that meets a preset distance requirement according to a starting point position and an end point position.

[0033] In a second aspect, the present application provides a global path planning control device, comprising:

[0034] Acquisition module, used to obtain high-precision maps and initial paths;

[0035] Processing modules for:

[0036] Determine whether the initial path passes through at least one geometric prohibited area based on the high-precision map;

[0037] If yes, then using a preset cost model, according to the initial path and each geometrically prohibited area, determine one or more pre-anchor points required to bypass each geometrically prohibited area;

[0038] Using the preset path model, the initial path is optimized and modified into the target path according to each pre-anchor point.

[0039] In one possible design, the processing module is used to:

[0040] Determine one or more geometric prohibited areas according to each contour information in the high-precision map, and the geometric prohibited area includes one or more obstacles;

[0041] Determine whether the initial path passes through at least one geometric prohibited area.

[0042] In one possible design, the processing module is used to:

[0043] For each geometrically prohibited area, a preset cost model is used to calculate the cost values ​​of running from the cost reference point to each vertex position of the geometrically prohibited area;

[0044] According to the preset cost requirement, at least one pre-anchor point corresponding to each geometric prohibited area is selected from each cost value;

[0045] The cost reference point includes: a starting point position, an end point position of the initial path, and at least one of the pre-anchor points that have been determined.

[0046] In one possible design, the processing module is used to:

[0047] When determining the first pre-anchor point, the cost reference point includes the starting point position and / or the end point position, and when determining other pre-anchor points, the cost reference point includes the last determined pre-anchor point.

[0048] In one possible design, the processing module is used to:

[0049] The vertex position corresponding to the minimum value among the cost values ​​is used as the pre-anchor point.

[0050] In one possible design, the processing module is used to:

[0051] When the minimum value corresponds to multiple vertex positions, any vertex position is taken as the pre-anchor point.

[0052] In one possible design, the processing module is used to:

[0053] When the minimum value corresponds to multiple vertex positions, the pre-anchor point is determined according to the coordinate values ​​of the multiple vertex positions corresponding to the minimum value in the high-precision map and the preset coordinate requirements.

[0054] Optionally, a processing module is used to:

[0055] When the minimum value corresponds to multiple vertex positions, the pre-anchor point is determined according to the distances from the multiple vertex positions corresponding to the minimum value to the cost reference point and the preset requirements.

[0056] In a possible design, each pre-anchor point divides the target path into multiple segments, and the corresponding processing module is used to:

[0057] When determining the first section, a preset path model is used to determine a geometric line corresponding to the first section according to the starting position of the initial path and a first pre-anchor point, wherein the first pre-anchor point includes: at least one pre-anchor point corresponding to a first geometric prohibited area passed through by the initial path;

[0058] When determining the remaining segments, the preset path model is used to determine the geometric lines corresponding to the remaining segments based on the segment end point of the previous segment and the second pre-anchor point, and the second pre-anchor point includes: at least one pre-anchor point corresponding to the next geometric prohibited area passed by the initial path.

[0059] In a possible design, the acquisition module is used to acquire the starting position and the end position;

[0060] The processing module is used to determine an initial path that meets a preset distance requirement according to a starting point position and an end point position by using the first path model.

[0061] In a third aspect, the present application provides an electronic device, including:

[0062] A memory for storing program instructions;

[0063] The processor is used to call and execute the program instructions in the memory to execute any possible global path planning control method provided by the first aspect.

[0064] In a fourth aspect, the present application provides a storage medium, in which a computer program is stored. The computer program is used to execute any possible global path planning control method provided in the first aspect.

[0065] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements any possible global path optimization system method provided in the first aspect.

[0066] The present application provides a global path planning control method, device, equipment, medium and program product, which obtains a high-precision map and an initial path; determines whether the initial path passes through at least one geometric prohibited area based on the high-precision map; if so, uses a preset cost model to determine one or more pre-anchor points required to bypass each geometric prohibited area based on the initial path and each geometric prohibited area; uses a preset path model to optimize and modify the initial path to a target path based on each pre-anchor point. It solves the technical problem of optimizing and improving the planning and control of the global path in order to achieve a higher level of autonomous driving functions. It achieves the technical effect of reducing the number of nodes that need to be searched during global path planning, reducing the global path planning time, and providing overall system operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0068] Figure 1A schematic diagram of the structure of a wearable device provided in this application;

[0069] Figure 2 A flowchart of a global path planning control method provided in an embodiment of the present application;

[0070] Figure 3 A flowchart of another global path planning control method provided in an embodiment of the present application;

[0071] Figure 4 A schematic diagram of placing an initial path on a high-precision map provided in an embodiment of the present application;

[0072] Figure 5 A method provided in the embodiment of the present application Figure 4 Schematic diagram of the vertex positions corresponding to the geometric forbidden areas;

[0073] Figure 6 A schematic diagram of a target path in a high-precision map provided in an embodiment of the present application;

[0074] Figure 7 A schematic diagram of the structure of a global path planning control device provided in an embodiment of the present application;

[0075] Figure 8 A schematic diagram of the structure of an electronic device provided in this application.

[0076] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work, including but not limited to the combination of multiple embodiments, belong to the scope of protection of this application.

[0078] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0079] The planning and control of the global path is an important part of realizing autonomous driving. Although various car manufacturers in the automotive industry have realized the autonomous driving functions below the L2+ level in the SAE classification of autonomous driving, the current global path planning and control technology still cannot meet the higher requirements for autonomous driving functions at the L3 level and above. After in-depth analysis, the inventor of the present application found that in the existing global planning and control methods, only the two reference points of the starting point and the end point are generally used for path finding calculations, which will involve the verification of a large number of possible paths between the two points, making the computing resources required for path planning larger and the processing time longer, which cannot meet the requirements of autonomous driving at the L3 level or above for real-time or global path planning processing efficiency.

[0080] In order to solve the above technical problems, the invention concept of this application is:

[0081] The computational complexity of the pathfinding algorithm is reduced through three aspects. The first aspect is to introduce high-precision maps, so that a geometric no-travel area is set between the starting point and the end point, which allows the pathfinding algorithm to exclude path points within the geometric no-travel area; the second aspect is to set one or more intermediate process points (hereinafter referred to as pre-anchor points) that bypass the geometric no-travel area through the vertex positions of the geometric area, which also greatly reduces the calculation nodes that need to be checked by the pathfinding algorithm; the third aspect is to first use a less accurate but more efficient pathfinding algorithm to roughly obtain an initial path, and then optimize and adjust it through the above two aspects, which can further reduce the nodes of pathfinding calculation, shorten the pathfinding time of the global path, and improve processing efficiency.

[0082] The following is a detailed introduction on how the present application realizes the transmission of information through touch.

[0083] Figure 1 A schematic diagram of an application scenario of a global path planning control method provided in this application. Figure 1As shown, the automatic moving object 100, including: vehicles, robots, drones, etc. that can be driven automatically, may have many different operating modes when it needs to move from point A to point B, and the global path planning is to select a suitable route for its movement between two points, that is, the global path. For different automatic moving objects 100, the global path may be a plane geometric line, or it may be a three-dimensional geometric line, that is, a space curve, a space fold line, a space straight line, etc. Since the existing global path planning takes a long time, there are many path nodes involved, and many nodes are actually invalid, or the operating cost is too high, such as the phenomenon of detours causing uneconomical phenomena. The global path planning control method provided in the present application introduces a high-precision map, and corrects the initial path obtained by a relatively fast path-finding algorithm to quickly obtain the final target path, thereby improving the processing efficiency of the global path and meeting the application requirements with high real-time requirements such as automatic driving and automatic control.

[0084] Figure 2 A flow chart of a global path planning control method provided in an embodiment of the present application. Figure 2 As shown in FIG. 1 , the global path planning control method can be applied to scenarios such as vehicle automatic driving, drone automatic driving, and automatic path finding of logistics warehousing robots. The specific steps include:

[0085] S201. Obtain a high-precision map and an initial path.

[0086] In this step, the initial path is obtained, including:

[0087] Get the starting point and the end point;

[0088] The first path model is used to determine an initial path that meets a preset distance requirement according to a starting point position and an end point position.

[0089] It should be noted that the first path model only requires low-precision map data or common navigation data, and is a rough path obtained by quickly calculating the path according to the starting point and the end point, ie, the initial path.

[0090] High-precision maps require the use of special data collection equipment, such as high-precision map collection vehicles, to establish complete 3D map data, such as map data of a certain city area, or map data of a certain warehousing and logistics center, or map data of a low-altitude drone flight area.

[0091] S202: Determine whether the initial path passes through at least one geometric prohibited area based on the high-precision map.

[0092] In this step, if yes, step S203 is executed, if no, the initial path is the target path and no optimization is required, that is, the process ends directly.

[0093] In a possible design, the high-precision map contains the contour information of each obstacle. First, one or more geometric prohibited areas are determined based on the contour information in the high-precision map, and the geometric prohibited areas include one or more obstacles; then it is determined whether the initial path passes through at least one geometric prohibited area.

[0094] It should be noted that a geometric no-entry area is a geometric figure with multiple vertices, which is covered with obstacles that hinder movement. For outdoor high-precision maps, obstacles include: buildings, fences, trees, etc. For indoor high-precision maps, obstacles include: storage racks, storage boxes, furniture, etc.

[0095] Specifically, the map range corresponding to the initial path can be gridded, the high-precision map can be segmented by polygonal grids, and then the polygonal grid units to which the outlines of each obstacle belong can be pieced together to form a polygonal geometric no-entry area. The shapes of the polygonal grid units obtained by the gridding process include: triangles, quadrilaterals, pentagons, hexagons, octagons, etc.

[0096] S203: using a preset cost model, according to the initial path and each geometrically prohibited area, determine one or more pre-anchor points required to bypass each geometrically prohibited area.

[0097] In this step, the initial path passes through multiple geometric prohibited areas in sequence, so the initial path needs to be corrected so that the corrected target path bypasses these geometric prohibited areas.

[0098] Specifically, the vertex position of each geometric forbidden area can be used as a reference point for detour. Since each geometric forbidden area has multiple vertex positions, one or more vertex positions need to be screened out from these vertex positions as the intermediate points for detour the geometric forbidden area, i.e., the so-called pre-anchor points. One implementation of the screening method includes: calculating the cost value of each vertex position of the same geometric forbidden area to a cost reference point or the sum of the cost values ​​to multiple cost reference points through a preset cost model.

[0099] Select the vertex position whose cost value meets the preset cost requirement as the pre-anchor point, for example, arrange the cost values ​​from small to large, and select the vertex positions in the top n positions as the pre-anchor points. For example, the value of n can be 1, 2, 3, etc.

[0100] For example, when calculating the pre-anchor point corresponding to the first geometric forbidden area passed by the initial path, assuming that only one vertex position is taken as the pre-anchor point, then it is necessary to calculate the cost value from each vertex position of the first geometric forbidden area to the starting position of the initial path. At this time, the preset cost model can be expressed by formula (1):

[0101] f(x)=g(x) (1)

[0102] Among them, f(x) represents the cost corresponding to a vertex position, and g(x) represents the actual cost or the measure of the actual consumed resources or energy from the starting position to a vertex position.

[0103] After the cost values ​​corresponding to the positions of each vertex are calculated, the vertex position corresponding to the minimum value among the cost values ​​is selected as the pre-anchor point.

[0104] In a possible design, the preset cost model can also calculate the cost value from each vertex position to multiple cost reference points, and then take the sum of the cost values ​​as the final cost value of the vertex position. In this case, the preset cost model can be expressed by formula (2):

[0105] f(x)=g(x)+h(x)+…+m i (x) (2)

[0106] Where f(x) represents the cost of a vertex position, g(x) represents the actual cost or the measure of the actual consumed resources or energy from the starting position to a vertex position, h(x) represents the actual cost or the measure of the actual consumed resources or energy from the end position to a vertex position, and m i (x) represents the actual cost or the measure of the actual resources or energy consumed from a certain pre-anchor point to a certain vertex position.

[0107] For example, in the above example, when calculating the pre-anchor point corresponding to the first geometric restricted area passed by the initial path, assuming that only one vertex position is taken as the pre-anchor point, it is necessary to calculate the sum of the cost values ​​of the vertex positions of the first geometric restricted area to the starting position of the initial path and the cost value to the end position as the cost value of each vertex position of the first geometric restricted area, and then select the vertex position corresponding to the minimum cost value as the pre-anchor point of the first geometric restricted area.

[0108] For calculating the cost value of a vertex position of the second geometric area, the starting point position may be replaced by the pre-anchor point of the first geometric forbidden area; or, instead of replacing, the vertex position of the second geometric forbidden area may be directly increased to the cost value of the pre-anchor point of the first geometric forbidden area.

[0109] In general, the cost reference points for calculating the cost value of each vertex position in the geometric no-entry area can be one or more, that is, the cost reference points include: the starting position of the initial path, the end position and at least one of the determined pre-anchor points.

[0110] In one possible design, the pre-anchor point is a grid cell adjacent to the vertex position and the grid cell is outside the geometric no-go area.

[0111] S204: Using the preset path model, according to each pre-anchor point, the initial path is optimized and modified into the target path.

[0112] In this step, the preset path model includes the AStar algorithm model. When the target path bypasses each geometric prohibited area, it needs to pass through one or more pre-anchor points. Optionally, the target path passes through all pre-anchor points, that is, each pre-anchor point divides the target path into multiple sections.

[0113] It should be noted that the more pre-anchor points are passed, the fewer paths the AStar algorithm model needs to search, which can improve the processing efficiency of the target path.

[0114] Specifically, for the first segment, the AStar algorithm model and high-precision map are used to search for the optimal path between the starting point of the initial path and the first pre-anchor point, which is the first segment. Next is the second segment, which is also searched for the optimal path between the first pre-anchor point and the second pre-anchor point through the AStar algorithm model and high-precision map, which is the second segment. This cycle is repeated until a new global path from the starting point of the initial path to the terminal position is established, which is the target path.

[0115] This embodiment improves the node search method of the AStar algorithm model. The original AStar algorithm will also calculate when encountering a path trajectory that does not need to be searched. After the improvement of this embodiment, the AStar algorithm uses the geometric vertices after obstacle optimization as preview points and performs calculations in segments when some obstacles are loaded in advance, thereby greatly reducing the search nodes, avoiding some path points that do not need to be calculated, improving the node search method, reducing the node search, reducing the running time, and running the algorithm quickly, thereby improving the efficiency of the entire decision control.

[0116] This embodiment provides a global path optimization system method, which obtains a high-precision map and an initial path; determines whether the initial path passes through at least one geometric prohibited area based on the high-precision map; if so, uses a preset cost model to determine one or more pre-anchor points required to bypass each geometric prohibited area based on the initial path and each geometric prohibited area; uses a preset path model to optimize and modify the initial path to a target path based on each pre-anchor point. It solves the technical problem of optimizing and improving the planning and control of the global path in order to achieve a higher level of autonomous driving functions. It achieves the technical effect of reducing the number of nodes that need to be searched during global path planning, reducing the global path planning time, and providing overall system operation efficiency.

[0117] Figure 3 A flowchart of another global path planning control method provided in an embodiment of the present application. Figure 3 As shown, the specific steps of the global path planning control method include:

[0118] S301. Obtain a high-precision map, a starting point location, and an end point location.

[0119] S302: using the first path model, according to the starting point position and the end point position, determine an initial path that meets the preset distance requirement.

[0120] In this step, the preset distance requirement includes: the total length of the initial path is less than or equal to the preset distance threshold, the preset distance threshold can be k times the straight-line distance between the starting position and the end position, k is greater than or equal to 1, optionally, the value range of k is [1,3], preferably, k = 1.5.

[0121] S303. Determine one or more geometric prohibited areas according to the contour information of each obstacle in the high-precision map.

[0122] In this step, the high-precision map is first gridded, that is, the part of the map area corresponding to the initial path is gridded, and one or more geometric prohibited areas are determined according to the contour information of each obstacle, and each geometric prohibited area includes one or more obstacles.

[0123] Specifically, the grid cells in the area to which the contour information of each obstacle belongs are merged to obtain the geometric prohibited area.

[0124] Figure 4 A schematic diagram of an initial path on a high-precision map is provided in an embodiment of the present application. Figure 4As shown in the figure, for ease of understanding, the initial path is simplified to a straight line, that is, the first path model establishes a straight path 403 from the starting position 401 to the end position 402 as the initial path. After the high-precision map is gridded, the starting position 401 to the end position 402 also correspond to a grid unit respectively. Figure 4 As shown, the various geometric no-entry areas include: area A, area B, area C, area D, area E, area F and area G.

[0125] S304: Determine whether the initial path passes through at least one geometric prohibited area.

[0126] In this step, if yes, then steps S305 to S306 are executed repeatedly to select the pre-anchor points corresponding to each geometric no-travel area. If no, then the initial path is the target path and no optimization is required, that is, the process ends directly.

[0127] In this embodiment, if Figure 4 As shown, the initial path, that is, the straight path 403, passes through three geometric prohibited areas, namely area C, area F and area G.

[0128] S305 , using a preset cost model, calculating the cost values ​​of running from the cost reference point to each vertex position of the geometric prohibited area.

[0129] In this step, the cost reference point includes: the starting point position, the end point position of the initial path and at least one of the pre-anchor points that have been determined.

[0130] In this embodiment, when determining the first pre-anchor point, the cost reference point includes the starting point position and / or the ending point position, and when determining other pre-anchor points, the cost reference point includes the last determined pre-anchor point.

[0131] Specifically, Figure 4 As shown, the initial path, i.e., the straight path 403, passes through region C, region F, and region G in sequence, and then the pre-anchor points corresponding to region C, region F, and region G are determined respectively in this order.

[0132] For ease of understanding, in this embodiment, only one vertex position is selected as a pre-anchor point for each geometric no-entry area. Technical personnel in this field can select the number of pre-anchor points corresponding to each geometric no-entry area according to the needs of the actual application scenario, and this application does not limit it.

[0133] Figure 5 A method provided in the embodiment of the present application Figure 4 Schematic diagram of the vertex positions corresponding to the geometric forbidden areas. Figure 5As shown, the vertex positions corresponding to region C include: C1, C2, C3, C4, the vertex positions corresponding to region F include: F1, F2, F3, F4, and the vertex positions corresponding to region G include: G1, G2, G3, G4.

[0134] First, the cost values ​​of the four vertex positions C1, C2, C3, and C4 and the starting position 401 and / or the end position 402 are calculated. The cost value calculation method can refer to formula (1) or formula (2). Then, the screening step S306 is performed, assuming that the pre-anchor point corresponding to the screened area C is C1.

[0135] Then calculate the cost value of the four vertex positions F1, F2, F3, and F4 with C1, or with the starting position 401 and / or the end position 402, or with C1 and / or the starting position 401 and / or the end position 402, and then perform the screening step S306, assuming that the pre-anchor point corresponding to the screened area F is F1

[0136] Finally, calculate the cost values ​​of the four vertex positions G1, G2, G3, and G4 with the starting position 401 and / or the end position 402, or the cost value with F1, or the cost value with F1 and / or the starting position 401 and / or the end position 402, or the cost value with C1 and / or F1 and / or the starting position 401 and / or the end position 402, and then execute the screening step S306, assuming that the pre-anchor point corresponding to the screened area F is G1.

[0137] S306: Filter out at least one pre-anchor point corresponding to each geometric prohibited area from each cost value according to a preset cost requirement.

[0138] In this embodiment, the preset cost requirement includes:

[0139] The vertex position corresponding to the minimum value among the cost values ​​is used as the pre-anchor point.

[0140] There are two cases here. One is that the minimum cost value corresponds to only one vertex position, in which case the vertex position is the pre-anchor point. The other is that the minimum cost value corresponds to multiple vertex positions. In this case, there are several ways to select the pre-anchor point:

[0141] (1) Take any vertex position as the pre-anchor point.

[0142] (2) Determine the pre-anchor point based on the coordinate values ​​of multiple vertex positions corresponding to the minimum value in the high-precision map and the preset coordinate requirements. It should be noted that the preset coordinate requirements include: when there is only one highest or lowest point, select the vertex position with the largest or smallest vertical coordinate as the pre-anchor point; when there are multiple highest or lowest points, select the highest or lowest point on the far left as the pre-anchor point.

[0143] (3) Determine a pre-anchor point according to the distances from the multiple vertex positions corresponding to the minimum value to the cost reference point and the preset requirements. It should be noted that the preset requirements include: taking the vertex position with the minimum distance as the pre-anchor point, or taking the vertex position with a distance less than a preset threshold as the pre-anchor point.

[0144] Repeat S305 to S306 until all pre-anchor points corresponding to the geometric prohibited areas are selected. It is worth noting that the number of pre-anchor points corresponding to each geometric prohibited area is one or more, and the specific number can be selected by those skilled in the art according to the requirements of different application scenarios.

[0145] S307: Using the preset path model, according to each pre-anchor point, the initial path is optimized and modified into the target path.

[0146] In this step, each pre-anchor point divides the target path into multiple sections. When determining the first section, the preset path model is used to determine the geometric lines corresponding to the first section according to the starting position of the initial path and the first pre-anchor point. The first pre-anchor point includes: at least one pre-anchor point corresponding to the first geometric prohibited area passed by the initial path;

[0147] When determining the remaining segments, the preset path model is used to determine the geometric lines corresponding to the remaining segments based on the segment end point of the previous segment and the second pre-anchor point, and the second pre-anchor point includes: at least one pre-anchor point corresponding to the next geometric prohibited area passed by the initial path.

[0148] In this embodiment, the preset path model includes an AStar algorithm model.

[0149] Figure 6 A schematic diagram of a target path in a high-precision map provided in an embodiment of the present application. Figure 6 As shown, the AStar algorithm model is used to calculate the optimal route from the starting point 401 to the C1 point, i.e., the first section, then the optimal route from the C1 point to the F1 point, i.e., the second section, then the optimal route from the F1 point to the G1 point, i.e., the third section, and finally the optimal route from the G1 point to the end point 402, i.e., the fourth section. The above four sections are connected end to end to form the target path 600.

[0150] This embodiment provides a global path optimization system method, which obtains a high-precision map and an initial path; determines whether the initial path passes through at least one geometric prohibited area based on the high-precision map; if so, uses a preset cost model to determine one or more pre-anchor points required to bypass each geometric prohibited area based on the initial path and each geometric prohibited area; uses a preset path model to optimize and modify the initial path to a target path based on each pre-anchor point. It solves the technical problem of optimizing and improving the planning and control of the global path in order to achieve a higher level of autonomous driving functions. It achieves the technical effect of reducing the number of nodes that need to be searched during global path planning, reducing the global path planning time, and providing overall system operation efficiency.

[0151] Figure 7 A schematic diagram of the structure of a global path planning control device provided in an embodiment of the present application. The global path planning control device 700 can be implemented by software, hardware or a combination of both.

[0152] like Figure 7 As shown, the global path planning control device 700 includes:

[0153] The acquisition module 701 is used to acquire a high-precision map and an initial path;

[0154] The processing module 702 is used to:

[0155] Determine whether the initial path passes through at least one geometric prohibited area based on the high-precision map;

[0156] If yes, then using a preset cost model, according to the initial path and each geometrically prohibited area, determine one or more pre-anchor points required to bypass each geometrically prohibited area;

[0157] Using the preset path model, the initial path is optimized and modified into the target path according to each pre-anchor point.

[0158] In one possible design, the processing module 702 is configured to:

[0159] Determine one or more geometric prohibited areas according to each contour information in the high-precision map, and the geometric prohibited area includes one or more obstacles;

[0160] Determine whether the initial path passes through at least one geometric prohibited area.

[0161] In one possible design, the processing module 702 is configured to:

[0162] For each geometrically prohibited area, a preset cost model is used to calculate the cost values ​​of running from the cost reference point to each vertex position of the geometrically prohibited area;

[0163] According to the preset cost requirement, at least one pre-anchor point corresponding to each geometric prohibited area is selected from each cost value;

[0164] The cost reference point includes: a starting point position, an end point position of the initial path, and at least one of the pre-anchor points that have been determined.

[0165] In one possible design, the processing module 702 is configured to:

[0166] When determining the first pre-anchor point, the cost reference point includes the starting point position and / or the end point position, and when determining other pre-anchor points, the cost reference point includes the last determined pre-anchor point.

[0167] In one possible design, the processing module 702 is configured to:

[0168] The vertex position corresponding to the minimum value among the cost values ​​is used as the pre-anchor point.

[0169] In one possible design, the processing module 702 is configured to:

[0170] When the minimum value corresponds to multiple vertex positions, any vertex position is taken as the pre-anchor point.

[0171] In one possible design, the processing module 702 is configured to:

[0172] When the minimum value corresponds to multiple vertex positions, the pre-anchor point is determined according to the coordinate values ​​of the multiple vertex positions corresponding to the minimum value in the high-precision map and the preset coordinate requirements.

[0173] Optionally, the processing module 702 is used to:

[0174] When the minimum value corresponds to multiple vertex positions, the pre-anchor point is determined according to the distances from the multiple vertex positions corresponding to the minimum value to the cost reference point and the preset requirements.

[0175] In a possible design, each pre-anchor point divides the target path into multiple sections. Accordingly, the processing module 702 is used to:

[0176] When determining the first section, a preset path model is used to determine a geometric line corresponding to the first section according to the starting position of the initial path and a first pre-anchor point, wherein the first pre-anchor point includes: at least one pre-anchor point corresponding to a first geometric prohibited area passed through by the initial path;

[0177] When determining the remaining segments, the preset path model is used to determine the geometric lines corresponding to the remaining segments based on the segment end point of the previous segment and the second pre-anchor point, and the second pre-anchor point includes: at least one pre-anchor point corresponding to the next geometric prohibited area passed by the initial path.

[0178] In a possible design, the acquisition module 701 is used to acquire the starting position and the end position;

[0179] The processing module 702 is used to determine an initial path that meets a preset distance requirement according to a starting point position and an end point position by using the first path model.

[0180] It is worth mentioning that Figure 7 The device provided in the illustrated embodiment can execute the method provided in any of the above method embodiments. Its specific implementation principles, technical features, professional terminology explanations and technical effects are similar and will not be repeated here.

[0181] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 As shown, the electronic device 800 may include: at least one processor 801 and a memory 802 . Figure 8 An electronic device is shown using a processor as an example.

[0182] The memory 802 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer operation instructions.

[0183] The memory 802 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0184] The processor 801 is used to execute the computer-executable instructions stored in the memory 802 to implement the methods described in the above method embodiments.

[0185] The processor 801 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0186] Optionally, the memory 802 may be independent or integrated with the processor 801. When the memory 802 is a device independent of the processor 801, the electronic device 800 may further include:

[0187] The bus 803 is used to connect the processor 801 and the memory 802. The bus may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0188] Optionally, in a specific implementation, if the memory 802 and the processor 801 are integrated on a chip, the memory 802 and the processor 801 can communicate through an internal interface.

[0189] An embodiment of the present application also provides a computer-readable storage medium, which may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes. Specifically, the computer-readable storage medium stores program instructions, and the program instructions are used for the methods in the above-mentioned method embodiments.

[0190] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in the above-mentioned method embodiments when executed by a processor.

[0191] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

[0192] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A global path planning control method, characterized in that: Applied to a mobile terminal, the method comprises: Obtain high-precision maps and initial paths; Determining whether the initial path passes through at least one geometric prohibited area according to the high-precision map; If so, for each of the geometric forbidden areas, use the preset cost model to calculate the cost values ​​of running from the cost reference point to each vertex position of the geometric forbidden area; select at least one pre-anchor point corresponding to each of the geometric forbidden areas from each of the cost values ​​according to the preset cost requirements; the cost value represents the actual cost from the cost reference point to the vertex position or the measure of the actual consumed resources or energy; the preset cost requirements include: determining the pre-anchor point according to the coordinate values ​​of the multiple vertex positions corresponding to the minimum value of each of the cost values ​​in the high-precision map, and the preset coordinate requirements, the preset coordinate requirements include: when there is only one highest or lowest point, select the vertex position with the largest or smallest vertical coordinate as the pre-anchor point; when there are multiple highest or lowest points, select the highest or lowest point on the far left as the pre-anchor point; The preset path model is used to optimize and modify the initial path into a target path according to each of the pre-anchor points.

2. The global path planning control method according to claim 1, characterized in that: The high-precision map includes contour information of each obstacle, and judging whether the initial path passes through at least one geometrically prohibited area according to the high-precision map includes: Determine one or more geometric prohibited areas according to each of the contour information in the high-precision map, wherein the geometric prohibited areas include one or more obstacles; Determine whether the initial path passes through at least one geometric prohibited area.

3. The global path planning control method according to claim 1, characterized in that: in, The cost reference point includes: a starting point position of the initial path and at least one of the determined pre-anchor points.

4. The global path planning control method according to claim 3, characterized in that: When determining the first pre-anchor point, the cost reference point is the starting point position, and when determining other pre-anchor points, the cost reference point is the last determined pre-anchor point.

5. The global path planning control method according to claim 1, characterized in that: Each of the pre-anchor points divides the target path into a plurality of sections, and the use of a preset path model to optimize and modify the initial path into a target path according to each of the pre-anchor points includes: When determining the first section, the preset path model is used to determine the geometric line corresponding to the first section according to the starting position of the initial path and the first pre-anchor point, wherein the first pre-anchor point includes: at least one pre-anchor point corresponding to the first geometric prohibited area passed by the initial path; When determining the remaining segments, the preset path model is used to determine the geometric lines corresponding to the remaining segments based on the segment end point of the previous segment and the second pre-anchor point, and the second pre-anchor point includes: at least one pre-anchor point corresponding to the next geometric prohibited area passed by the initial path.

6. The global path planning control method according to any one of claims 1 to 5, characterized in that: The obtaining of the initial path comprises: Get the starting point and the end point; The first path model is used to determine the initial path that meets the preset distance requirement according to the starting point position and the end point position.

7. A global path planning control device, characterized in that: include: Acquisition module, used to obtain high-precision maps and initial paths; Processing modules for: Determining whether the initial path passes through at least one geometric prohibited area according to the high-precision map; If yes, for each of the geometrically prohibited areas, using a preset cost model, calculates the cost values ​​of running from the cost reference point to each vertex position of the geometrically prohibited area; Filtering out at least one pre-anchor point corresponding to each of the geometric prohibited areas from the cost values ​​according to a preset cost requirement; The cost value represents the actual cost or the measure of the resources or energy actually consumed from the cost reference point to the vertex position; The preset cost requirement includes: determining the pre-anchor point according to the coordinate values ​​of the plurality of vertex positions corresponding to the minimum value of each cost value in the high-precision map and the preset coordinate requirement, wherein the preset coordinate requirement includes: when there is only one highest or lowest point, selecting the vertex position with the largest or smallest ordinate as the pre-anchor point; when there are multiple highest or lowest points, selecting the highest or lowest point on the left as the pre-anchor point; The preset path model is used to optimize and modify the initial path into a target path according to each of the pre-anchor points.

8. An electronic device, characterized in that: include: processor; as well as, a memory for storing a computer program for the processor; Wherein, the processor is configured to execute the global path planning control method according to any one of claims 1 to 6 by executing the computer program.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the global path planning control method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the global path planning control method according to any one of claims 1 to 6 is implemented.

Images