Global Path Planning Method, Device, Equipment and Storage Medium

Abstract

The present invention discloses a method, device, equipment and storage medium for global path planning, relating to the technical field of path planning, and solving the problem of low path planning efficiency. The method for global path planning includes: obtaining a road network topological map, where the road network topological map includes a plurality of nodes, and the nodes are used to indicate channel information; respectively calculating the cost values between the nodes to obtain a cost set of the nodes of the road network topological map, and the cost value is used to indicate the passing cost of the node; obtaining the starting point information and the ending point information, and obtaining a passing route according to the starting point information, the ending point information and the cost set; and smoothing the passing route to obtain a planned path.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular, to a method, device, equipment and storage medium for global path planning. Background Art

[0002] With the development of artificial intelligence technology, multi-sensor fusion technology and control decision-making technology, autonomous driving technology has gradually entered people's daily lives and imperceptibly changed people's travel modes. Among them, path planning technology plays an important role in autonomous driving technology.

[0003] The existing global path planning methods mainly perform path search in a road network topological map by using a graph search algorithm. However, when the amount of road network map data is large, the computational amount of using the graph search algorithm is large, resulting in a slow path search speed and low path planning efficiency. Summary of the Invention

[0004] The present invention provides a method, device, equipment and storage medium for global path planning, which solves the problem of low path planning efficiency.

[0005] In the first aspect of the embodiments of the present application, a method for global path planning is provided. The method includes: obtaining a road network topological map, where the road network topological map includes multiple nodes, and the nodes are used to indicate channel information; respectively calculating the cost values between the nodes to obtain a cost set of the nodes in the road network topological map, and the cost value is used to indicate the passing cost of the node; obtaining start point information and end point information, and obtaining a passing route according to the start point information, end point information and cost set; and performing smoothing processing on the passing route to obtain a planned path.

[0006] In one embodiment, the nodes include a starting node, a current node and a previous node, and there are corresponding edges between the nodes. Calculating the cost values between the nodes includes:

[0007] Obtaining the cost value between the previous node and the starting node to obtain a first-generation cost value;

[0008] Obtaining the cost value of the edge between the previous node and the current node to obtain an edge cost value;

[0009] Obtaining the cost value of the current node to obtain a second-generation cost value;

[0010] Obtaining the cost value between the current node and the starting node according to the first-generation cost value, edge cost value and second-generation cost value.

[0011] In one embodiment, the edge is used to indicate a channel connection area, and the connection area includes a lane change area or a traffic light. Obtaining the cost value of the edge between the previous node and the current node to obtain an edge cost value includes:

[0012] Obtain the regional length of the corresponding channel connection area according to the edge.

[0013] Obtain the edge cost value according to the regional length, the first preset value, and the second preset value, where the first preset value is used to indicate the penalty coefficient of the lane change area, and the second preset value is used to indicate the penalty coefficient of the indicator light.

[0014] In one embodiment, the channel information includes the length of the channel, the passing speed of the channel, and the turning type of the channel. Obtaining the cost value of the current node includes:

[0015] Obtain the cost value of the current node according to the length of the channel corresponding to the current node, the passing speed of the channel, and the turning type of the channel.

[0016] In one embodiment, obtaining the passing route according to the starting point information, the ending point information, and the cost set includes:

[0017] Input the starting point information, the ending point information, and the cost set into a preset heuristic search model to obtain multiple target node identifiers and the order of each target node identifier;

[0018] Obtain the passing route according to each target node identifier and the order of each target node identifier.

[0019] In one embodiment, obtaining the passing route according to each target node identifier and the order of each target node identifier includes:

[0020] Obtain the center line of the corresponding channel according to each target node identifier;

[0021] Connect the center lines according to the order of each target node identifier to obtain the passing route.

[0022] In one embodiment, smoothing the passing route to obtain the planned path includes:

[0023] Perform segmented sampling on the passing route to obtain multiple sampling points, and perform fitting processing on the sampling points to obtain a fitting equation;

[0024] Solve the fitting equation according to the preset constraint conditions to obtain the solution of the fitting equation;

[0025] Input the passing route and the solution of the fitting equation into a preset quadratic programming algorithm to obtain the planned path.

[0026] In one embodiment, the method further includes:

[0027] Generate the target node identifier and the order of the target node identifier by using the first thread;

[0028] Output the target node identifier and the order of the target node identifiers using a second thread;

[0029] Use a third thread to smooth the traffic route to obtain a planned path.

[0030] In a second aspect of the embodiments of the present application, there is provided a device for planning a global path, the device includes:

[0031] A first acquisition module, configured to acquire a road network topology map, the road network topology map includes a plurality of nodes, and the nodes are used to indicate channel information;

[0032] A calculation module, configured to calculate the cost values between the nodes respectively to obtain a cost set of the nodes of the road network topology map, and the cost value is used to indicate the traffic cost of the node;

[0033] A second acquisition module, configured to acquire start point information and end point information, and obtain a traffic route according to the start point information, the end point information and the cost set;

[0034] A processing module, configured to smooth the traffic route to obtain a planned path.

[0035] In a third aspect of the embodiments of the present application, there is provided a computer device, the device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, it implements the global path planning method in the first aspect of the embodiments of the present application.

[0036] In a fourth aspect of the embodiments of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by the processor, it implements the global path planning method in the first aspect of the embodiments of the present application.

[0037] The global path planning method provided by the embodiments of the present application obtains a road network topology map, calculates the cost values between the nodes in the road network topology map to obtain a cost set of the nodes in the road network topology map, and obtains a traffic route according to the start point information, the end point information and the cost set, and finally smooths the traffic route to obtain a planned path. The global path planning method provided by the embodiments of the present application searches for a traffic route according to the cost values between the nodes, where the cost value refers to the traffic cost of the node, which can improve the efficiency of path search and planning. Description of the Drawings

[0038] Figure 1 It is an internal structure schematic diagram of a computer device provided by the embodiments of the present application;

[0039] Figure 2 It is a flowchart of a global path planning method provided by the embodiments of the present application;

[0040] Figure 3 A flowchart of a technical process for calculating the cost value between computing nodes provided by an embodiment of the present application;

[0041] Figure 4 A structural diagram of a global path planning device provided by an embodiment of the present application. Detailed implementation manners

[0042] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] Hereinafter, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "a plurality" is two or more.

[0044] In addition, the use of "based on" or "according to" means open and inclusive, because a process, step, calculation, or other action "based on" or "according to" one or more conditions or values may, in practice, be based on additional conditions or values beyond those stated.

[0045] To solve the problem of low path planning efficiency, an embodiment of the present application provides a method, device, equipment, and storage medium for global path planning. By obtaining a road network topology map, calculating the cost value between nodes in the road network topology map, obtaining a cost set of nodes in the road network topology map, obtaining a passing route based on the starting point information, ending point information, and the cost set, and finally smoothing the passing route to obtain a planned path. The global path planning method provided by the embodiment of the present application searches for a passing route according to the cost value between each node. Among them, the cost value refers to the passing cost of the node, which can improve the search and planning efficiency of the path.

[0046] The execution subject of the global path planning method provided by the embodiment of the present application can be a computer device, a terminal device, or a server. Among them, the terminal device can be an in-vehicle terminal, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices, etc. The present application does not make specific limitations in this regard.

[0047] Figure 1 An internal structural diagram of a computer device provided by an embodiment of the present application. As Figure 1As shown in the figure, the computer device includes a processor and a memory connected by a system bus. Among them, the processor is used to provide computing and control capabilities. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program can be executed by the processor to implement the steps of a global path planning method provided in each of the above embodiments. The internal memory provides a cache operating environment for the operating system and the computer program in the non-volatile storage medium.

[0048] Those skilled in the art can understand that Figure 1 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. Specifically, the computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0049] Based on the above execution subject, an embodiment of the present application provides a global path planning method. As Figure 2 shown in the figure, the method includes the following steps:

[0050] Step 201, obtain a road network topology map.

[0051] Optionally, a road network topology map can be generated according to a high-precision map. The road network topology map includes multiple nodes and edges connecting the nodes. Among them, the nodes are used to represent roads or channels, and the edges are used to represent the channel connection areas for entering the next channel from the current channel.

[0052] Step 202, calculate the cost values between the nodes respectively to obtain a cost set of the nodes of the road network topology map.

[0053] Among them, the cost value is used to indicate the passing cost of the node. According to the cost values between the nodes, the optimal node among the multiple nodes connected to the current node can be determined.

[0054] Step 203, obtain the start point information and the end point information, and obtain a passing route according to the start point information, the end point information and the cost set.

[0055] Among them, obtaining the start point information and the end point information may be to obtain the start point information and the end point information input by the user, and then perform node search according to the start point information, the end point information and the cost set to obtain a passing route.

[0056] Step 204, perform smoothing processing on the passing route to obtain a planned path.

[0057] The global path planning method provided by the embodiments of the present application obtains a road network topology map, calculates the cost values between nodes in the road network topology map to obtain a cost set of nodes in the road network topology map, obtains a passing route based on the starting point information, the ending point information, and the cost set, and finally smooths the passing route to obtain a planned path. The global path planning method provided by the embodiments of the present application searches for a passing route according to the cost values between nodes. Among them, the cost value refers to the passing cost of a node, which can improve the search and planning efficiency of the path.

[0058] As Figure 3 shown, where the nodes include a starting node, a current node, and a previous node, and corresponding edges are included between the nodes. The embodiments of the present application provide a technical process for calculating the cost values between nodes, and this process includes the following steps:

[0059] Step 301: Obtain the cost value between the previous node and the starting node to obtain the first generation cost value.

[0060] Step 302: Obtain the cost value of the edge between the previous node and the current node to obtain the edge cost value.

[0061] Step 303: Obtain the cost value of the current node to obtain the second generation cost value.

[0062] Step 304: Obtain the cost value between the current node and the starting node according to the first generation cost value, the edge cost value, and the second generation cost value.

[0063] Optionally, the edge is used to indicate a channel connection area, and the connection area includes a lane change area or a traffic light. Obtaining the cost value of the edge between the previous node and the current node to obtain the edge cost value includes:

[0064] Obtain the area length of the corresponding channel connection area according to the edge, and obtain the edge cost value according to the area length, the first preset value, and the second preset value, where the first preset value is used to indicate the penalty coefficient of the lane change area, and the second preset value is used to indicate the penalty coefficient of the traffic light.

[0065] Optionally, the channel information includes the length of the channel, the passing speed of the channel, and the turning type of the channel. Obtaining the cost value of the current node includes:

[0066] Obtain the cost value of the current node according to the length of the channel corresponding to the current node, the passing speed of the channel, and the turning type of the channel.

[0067] In practical applications, the cost value between two nodes can be calculated by formula (1):

[0068] G i =G i-1 +ω1cost(edge)i + ω2 * cos(t(node)) i Equation (1)

[0069] Wherein, G in Equation (1) i represents the cost value from the current node to the starting node, G i-1 represents the cost value from the previous node to the starting node, cost(edge) i represents the cost value of the edge from the previous node to the current node, cost(node) i represents the cost value of the current node, ω1 and ω2 are proportionality coefficients; when the current node coincides with the starting node, G i is equal to 0.

[0070] Specifically, the cost value of the edge from the previous node to the current node can be calculated by Equation (2).

[0071] cost(edge) = change_penalty × f(x) + light_penalty Equation (2)

[0072]

[0073] Wherein, change_penalty is the penalty coefficient for the lane-changing area, light_penalty is the penalty coefficient for the indicator light, x is the length of the lane-changing area, and base_change_length is the basic length of the lane-changing area.

[0074] Calculate the cost value of the current node through Equation (4).

[0075] cost(node) = lane_length × f(limit_speed) + turn_type_cost Equation (4)

[0076]

[0077] Wherein, lane_length is the length of the lane, limit_speed is the maximum passing speed of the lane, base_speed is the basic passing speed of the lane, turn_type_cost is the cost value of the turning type of the lane, and the turning types of the lane include left turn, right turn, and U-turn.

[0078] By obtaining the cost values between each node in the road network topology map, a cost set is obtained.

[0079] In one embodiment, a passing route is obtained according to start point information, end point information, and a cost set, including: inputting the start point information, end point information, and cost set into a preset heuristic search model to obtain multiple target node identifiers and the order of each target node identifier; obtaining a passing route according to each target node identifier and the order of each target node identifier.

[0080] Optionally, obtaining a passing route according to each target node identifier and the order of each target node identifier includes: obtaining the center line of the corresponding passage according to each target node identifier; connecting the center lines according to the order of each target node identifier to obtain a passing route.

[0081] In practical applications, the corresponding passage or lane can be determined according to each target node identifier in a high-precision map, the center line of the lane can be extracted from the lane, and then the center lines are connected to obtain a passing route.

[0082] In one embodiment, smoothing the passing route to obtain a planned path includes: performing segmented sampling on the communication route to obtain multiple sampling points, and performing fitting processing on the sampling points to obtain a fitting equation; solving the fitting equation according to preset constraint conditions to obtain the solution of the fitting equation; inputting the passing route and the solution of the fitting equation into a preset quadratic programming algorithm to obtain a planned path.

[0083] In practical applications, when smoothing the passing route, the passing route can be first roughly processed and then finely processed to obtain a planned path, which can improve the processing efficiency of route smoothing.

[0084] Among them, the rough smoothing process of the passing route includes: segmenting and roughly sampling the passing route,

[0085] and using a third-order polynomial interpolation algorithm to fit the equation for the roughly sampled points. By establishing continuous and smooth constraint conditions at each sampling point, a set of solutions for the coefficients of the low-order equation can be obtained. Since this low-order polynomial interpolation algorithm does not require iterative solution, it has high algorithm efficiency.

[0086] In the rough smoothing algorithm, parametric equations are selected to represent the curve segment, as shown in Formulas (7) and (8):

[0087] x i =a i0 +a i1 *(s - s i ) + a i2 *(s - s i ) 2 +…+a in *(s - s i ) n Equation (7)

[0088] y i = b i0 + b i1 *(s - s i ) + b i2 *(s - s i ) 2 + … + b in *(s - s i ) n Equation (8)

[0089] Assume that the reference line is divided into k segments, then there are k low - order polynomial equations (k >= 3), and n takes the value of 3 in the above formula.

[0090] By establishing interpolation and differential continuity constraints (up to second - order differential continuity) and introducing first - order differential constraints on both endpoints, a system of equations can be obtained:

[0091]

[0092]

[0093] Where: h i represents the sampling point step size, h i = s i+1 - s i ; m i represents the second - order derivative of the parametric equations x(s), y(s) at x i (y i ). That is, m i = x i ′′(m i = y i ′′).

[0094] After solving the system of equations, the general solution of the coefficients can be obtained as:

[0095]

[0096] After obtaining the solution of the rough smoothing algorithm, use the solution of the rough smoothing algorithm as the initial condition of the quadratic programming algorithm, and then input the solution of the rough smoothing algorithm and the traffic route into the preset quadratic programming algorithm to perform fine smoothing on the traffic route to obtain the planned route. Since the initial condition is introduced in the fine smoothing algorithm, the number of iterations of the algorithm can be reduced, thereby greatly shortening the entire algorithm cycle.

[0097] In one embodiment, the method further includes: using the first thread to generate the target node identifier and the order of the target node identifier; using the second thread to output the target node identifier and the order of the target node identifier; using the third thread to perform smoothing processing on the traffic route to obtain the planned path.

[0098] In practical applications, when planning the global path, a thread can perform node search based on the starting point information and the ending point information to obtain the target node identifier and the order of the target node identifiers. Then, the second thread outputs the searched target node identifiers and the order of the target node identifiers. Finally, the third thread smoothes the passing route to obtain the planned path. By using three threads to process data in the global path planning, the data processing efficiency can be improved, and at the same time, the real-time requirement of data processing for autonomous driving can be met.

[0099] It should be noted that when it is detected that the starting point information or the ending point information in the first thread is updated, the historical data in the first thread can be cleared, and node search can be performed again using the updated starting point information or ending point information. Then, the target node identifiers and the order of the target node identifiers obtained from the re-search are output through the second thread. Next, the historical data in the third thread is cleared, and the passing route obtained from the re-search is smoothed.

[0100] For the convenience of understanding by those skilled in the art, the embodiment of the present application also provides a method for planning a global path. Specifically, the method includes:

[0101] (1) Obtain a road network topology map, where the road network topology map includes multiple nodes, and the nodes are used to indicate channel information;

[0102] (2) Obtain the cost value between the previous node and the starting node to obtain the first generation cost value;

[0103] (3) Obtain the regional length of the corresponding channel connection area according to the edge;

[0104] (4) Obtain the edge cost value according to the regional length, the first preset value, and the second preset value, where the first preset value is used to indicate the penalty coefficient of the lane change area, and the second preset value is used to indicate the penalty coefficient of the traffic light.

[0105] (5) Obtain the cost value of the current node according to the length of the channel corresponding to the current node, the passing speed of the channel, and the turning type of the channel.

[0106] (6) Obtain the cost value between the current node and the starting node according to the first generation cost value, the edge cost value, and the second generation cost value.

[0107] (7) Obtain the cost set of the nodes of the road network topology map according to the cost values between each current node and the starting node, where the cost value is used to indicate the passing cost of the node;

[0108] (8) Obtain the starting point information and the ending point information;

[0109] (9) Inputting the starting point information, the end point information, and the cost set into a preset heuristic search model to obtain multiple target node identifiers and the order of each target node identifier;

[0110] (10) Obtain the center line of the corresponding channel according to each target node identifier;

[0111] (11) Connect the center lines according to the order of the target node identifiers to obtain a passable route.

[0112] (12) Segmentally sampling the communication route to obtain a plurality of sampling points, and performing fitting processing on the sampling points to obtain a fitting equation;

[0113] (13) solving the fitting equation according to the preset constraint conditions to obtain the solution of the fitting equation;

[0114] (14) The solution of the travel route and the fitting equation is input into the preset quadratic programming algorithm to obtain the planned path.

[0115] (15) using the first thread to generate a target node identifier and an order of the target node identifiers;

[0116] (16) using a second thread to output a target node identifier and a sequence of target node identifiers;

[0117] (17) The third thread is used to smooth the route to obtain the planned path.

[0118] The global path planning method provided in the embodiment of the present application obtains the road network topology map, calculates the cost value between the nodes in the road network topology map, obtains the cost set of the nodes in the road network topology map, and obtains the pass route according to the starting point information, the end point information and the cost set, and finally smoothes the pass route to obtain the planned path. The global path planning method provided in the embodiment of the present application is to search for the pass route according to the cost value between each node, wherein the cost value refers to the pass cost of the node, which can improve the efficiency of path search and planning. At the same time, when smoothing the pass route, the pass route can be roughly smoothed first, and then the pass path can be finely smoothed to obtain the planned path, which can improve the processing efficiency of route smoothing. Furthermore, using three threads to process data in global path planning can improve the processing efficiency of data, and at the same time can meet the requirements of automatic driving for real-time data processing.

[0119] The execution processes of the above (1) to (17) can be specifically referred to the descriptions of the above embodiments. Their implementation principles and technical effects are similar, and will not be elaborated here. It should be understood that the steps in the step flowcharts of the above embodiments of the global path planning methods are displayed in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowcharts may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0120] The above mainly introduces the solutions provided in the embodiments of the present application from the perspective of methods. To implement the above functions, it includes the corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the manner of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0121] As Figure 4 shown, the embodiments of the present application provide a global path planning device, and the device includes:

[0122] A first acquisition module 11, a calculation module 12, a second acquisition module 13, and a processing module 14.

[0123] The first acquisition module 11 is used to acquire a road network topology map, and the road network topology map includes multiple nodes, and the nodes are used to indicate channel information;

[0124] The calculation module 12 is used to calculate the cost values between the nodes respectively, and obtain a cost set of the nodes of the road network topology map, and the cost value is used to indicate the passing cost of the node;

[0125] The second acquisition module 13 is used to acquire start point information and end point information, and obtain a passing route according to the start point information, the end point information, and the cost set;

[0126] The processing module 14 is used to perform smoothing processing on the passing route to obtain a planned path.

[0127] In one embodiment, a node includes a starting node, a current node, and a previous node, and corresponding edges are included between the nodes. The calculation module 12 is specifically configured to: obtain the cost value between the previous node and the starting node to obtain the first cost value; obtain the cost value of the edge between the previous node and the current node to obtain the edge cost value; obtain the cost value of the current node to obtain the second cost value; and obtain the cost value between the current node and the starting node according to the first cost value, the edge cost value, and the second cost value.

[0128] In one embodiment, an edge is used to indicate a channel connection area, and the connection area includes a lane change area or an indicator light. The calculation module 12 is specifically configured to: obtain the area length of the corresponding channel connection area according to the edge; and obtain the edge cost value according to the area length, a first preset value, and a second preset value, where the first preset value is used to indicate the penalty coefficient of the lane change area, and the second preset value is used to indicate the penalty coefficient of the indicator light.

[0129] In one embodiment, the channel information includes the length of the channel, the passing speed of the channel, and the turning type of the channel. The calculation module 12 is specifically configured to: obtain the cost value of the current node according to the length of the channel, the passing speed of the channel, and the turning type of the channel corresponding to the current node.

[0130] In one embodiment, the second acquisition module 13 is specifically configured to: input the starting point information, the ending point information, and the cost set into a preset heuristic search model to obtain a plurality of target node identifiers and the order of each target node identifier;

[0131] Obtain the passing route according to each target node identifier and the order of each target node identifier.

[0132] In one embodiment, the second acquisition module 13 is specifically configured to: obtain the center line of the corresponding channel according to each target node identifier; and connect the center lines according to the order of each target node identifier to obtain the passing route.

[0133] In one embodiment, the processing module 14 is specifically configured to: perform segmented sampling on the communication route to obtain a plurality of sampling points, and perform fitting processing on the sampling points to obtain a fitting equation; solve the fitting equation according to a preset constraint condition to obtain the solution of the fitting equation; and input the passing route and the solution of the fitting equation into a preset quadratic programming algorithm to obtain the planned route.

[0134] In one embodiment, the processing module 14 is further configured to: generate the target node identifier and the order of the target node identifier by using a first thread; output the target node identifier and the order of the target node identifier by using a second thread; and perform smoothing processing on the passing route by using a third thread to obtain the planned route.

[0135] The global path planning device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0136] For the specific limitations of the global path planning device, reference can be made to the limitations of the global path planning method in the above text, which will not be elaborated here. Each module in the above global path planning device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the server in hardware form or independent of it, or stored in the memory in the server in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0137] In another embodiment of the present application, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the steps of the global path planning method as in the embodiment of the present application are implemented.

[0138] In another embodiment of the present application, a computer-readable storage medium is further provided, on which a computer program is stored, and when the computer program is executed by the processor, the steps of the global path planning method as in the embodiment of the present application are implemented.

[0139] In another embodiment of the present application, a computer program product is further provided. The computer program product includes computer instructions. When the computer instructions run on the global path planning device, the global path planning device is enabled to execute each step in the method flow of the global path planning method shown in the above method embodiment.

[0140] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer execution instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more integrated media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0141] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0142] The above embodiments only represent several implementation manners of the present invention, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the invention patent should be subject to the appended claims.

Claims

1. A method for global path planning, characterized in that, The method includes: Obtain a road network topology map, which includes multiple nodes for indicating channel information; Calculate the cost values between the nodes respectively to obtain a cost set of the nodes of the road network topology map, where the cost value is used to indicate the passing cost of the node; Obtain the starting point information and the ending point information, and obtain a passing route according to the starting point information, the ending point information and the cost set; Perform segmented sampling on the passing route to obtain multiple sampling points, and use a third-order polynomial interpolation algorithm to fit the sampling points to obtain a fitting equation; Solve the fitting equation according to preset constraint conditions to obtain the solution of the fitting equation; Input the passing route and the solution of the fitting equation into a preset quadratic programming algorithm to obtain a planned route; The node includes a starting node, a current node and a previous node, and there are corresponding edges between the nodes. The calculation of the cost value between the nodes includes: Obtain the cost value between the previous node and the starting node to obtain a first cost value; Obtain the cost value of the edge between the previous node and the current node to obtain an edge cost value; Obtain the cost value of the current node to obtain a second cost value; Obtain the cost value between the current node and the starting node according to the first cost value, the edge cost value and the second cost value; The edge is used to indicate a channel connection area, and the connection area includes a lane change area or a traffic light. Obtaining the cost value of the edge between the previous node and the current node to obtain an edge cost value includes: Obtain the area length of the corresponding channel connection area according to the edge; Obtain the edge cost value according to the area length, a first preset value and a second preset value, where the first preset value is the penalty coefficient of the lane change area, and the second preset value is the penalty coefficient of the traffic light.

2. The method according to claim 1, wherein The channel information includes the length of the channel, the passing speed of the channel and the turning type of the channel. Obtaining the cost value of the current node includes: Obtain the cost value of the current node according to the length of the channel corresponding to the current node, the passing speed of the channel and the turning type of the channel.

3. The method according to claim 1, wherein The obtaining of the passing route according to the starting point information, the ending point information and the cost set includes: Input the starting point information, the ending point information and the cost set into a preset heuristic search model to obtain multiple target node identifiers and the order of each target node identifier; Obtain a passing route according to each target node identifier and the order of each target node identifier.

4. The method according to claim 3, characterized in that, The obtaining of the passing route according to each target node identifier and the order of each target node identifier includes: Obtain the center line of the corresponding channel according to each target node identifier; Connect the center lines according to the order of each target node identifier to obtain the passing route.

5. The method according to claim 4, wherein The method further includes: Generate the target node identifier and the order of the target node identifier by using a first thread; Output the target node identifier and the order of the target node identifier by using a second thread; Use a third thread to smooth the traffic route to obtain a planned path.

6. A global path planning device, characterized in that, The device includes: A first acquisition module for acquiring a road network topology map, the road network topology map including a plurality of nodes, the nodes being used to indicate channel information; A calculation module for respectively calculating the cost values between the nodes to obtain a cost set of the nodes of the road network topology map, the cost value being used to indicate the traffic cost of the nodes; A second acquisition module for acquiring starting point information and ending point information, and obtaining a traffic route according to the starting point information, the ending point information, and the cost set; A processing module for segmentally sampling the traffic route to obtain a plurality of sampling points, and using a third-order polynomial interpolation algorithm to perform fitting processing on the sampling points to obtain a fitting equation; solving the fitting equation according to a preset constraint condition to obtain a solution of the fitting equation; inputting the traffic route and the solution of the fitting equation into a preset quadratic programming algorithm to obtain a planned path; The node includes a starting node, a current node, and a previous node, and corresponding edges are included between the nodes. The calculation module is specifically used for: Obtaining the cost value between the previous node and the starting node to obtain a first cost value; The edge is used to indicate a channel connection area, the connection area including a lane change area or a traffic light, and obtaining the area length of the corresponding channel connection area according to the edge; obtaining the edge cost value according to the area length, a first preset value, and a second preset value, where the first preset value is a penalty coefficient of the lane change area, and the second preset value is a penalty coefficient of the traffic light; Obtaining the cost value of the current node to obtain a second cost value; Obtaining the cost value between the current node and the starting node according to the first cost value, the edge cost value, and the second cost value.

7. A computer device, characterized in that, Including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, it implements the global path planning method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Stored thereon is a computer program, and when the computer program is executed by a processor, it implements the global path planning method according to any one of claims 1 to 5.

Images