Path planning method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a path planning method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring driving environment information of a vehicle, and mapping the driving environment information into a two-dimensional grid, so that the driving environment of the vehicle is converted into a two-dimensional environment from a three-dimensional environment; the method comprises the following steps: taking vehicles in a two-dimensional environment as particles to form a particle swarm, obtaining a vehicle path generated by the particle swarm through each iteration based on a particle swarm algorithm, and calculating a length reward value, a safety reward value and a smoothness reward value of the path; integrating the length reward value, the security reward value and the smoothness reward value of the path generated by each iteration to obtain an integrated reward value of the path generated by each iteration; and continuing the iteration process until a preset condition is met, stopping iteration, and determining a final vehicle path according to the vehicle path corresponding to the maximum integrated reward value. By adopting the method, the paths meeting the requirements can be quickly and efficiently generated.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a path planning method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the rapid development of modern intelligent vehicles, the effective integration of information, sensors and planning and control technology has become a key research issue to promote its intelligent process. Path planning is an important part of intelligent vehicles to complete their autonomous driving functions.

[0003] The current path planning methods include graph method, interpolation method, sampling method and numerical optimization method. However, the above path planning technologies all face the problems of large amount of calculation, poor real-time performance and insufficient adaptability. Summary of the invention

[0004] Based on this, it is necessary to provide an efficient path planning method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.

[0005] In a first aspect, the present application provides a path planning method, comprising:

[0006] Acquire driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules;

[0007] The vehicles in the two-dimensional environment are used as particles to form a particle swarm, and based on the particle swarm algorithm, a vehicle path generated by the particle swarm after each iteration is obtained, and a length reward value, a safety reward value, and a smoothness reward value of the vehicle path are calculated;

[0008] Integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration;

[0009] The above iteration process is continued until the preset conditions are met and the iteration is stopped. The final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value.

[0010] In one embodiment, the acquiring the driving environment information of the vehicle and mapping the driving environment information into a two-dimensional grid includes:

[0011] Converting the road layout into a two-dimensional grid layout, and marking the grid where the corresponding obstacle is located as an inaccessible area according to the obstacle position;

[0012] The traffic rules are converted into attributes in the two-dimensional grid, wherein the attributes include constraint conditions.

[0013] In one embodiment, the calculation process of the length reward value, the safety reward value and the smoothness reward value of the vehicle path includes:

[0014] Normalizing the length of the vehicle path and multiplying it by a preset positive coefficient to obtain a vehicle path length reward value;

[0015] Quantifying the distance between the vehicle path and the obstacle and the judgment result of whether the vehicle complies with traffic regulations to obtain a safety reward value;

[0016] The steering operation data of the vehicle path is quantified to obtain a smoothness reward value.

[0017] In one embodiment, the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated in each iteration are integrated to obtain the integrated reward value of the vehicle path generated in each iteration, including:

[0018] The length reward value, the safety reward value and the smoothness reward value of the vehicle path generated in each iteration are weightedly summed to obtain an integrated reward value of the vehicle path generated in each iteration.

[0019] In one embodiment, the preset conditions include an integrated reward value greater than a preset value, a total number of iterations reaching a preset number of iterations, a change value between the integrated reward values ​​generated by two adjacent iterations being less than a preset change value, or a vehicle path satisfying at least one of the preset path conditions; the preset path conditions include a vehicle path length being less than a path length threshold, a safety reward value being higher than a preset safety threshold, or a smoothness reward value being higher than a preset smoothness threshold.

[0020] In one embodiment, the method further comprises:

[0021] Quantifying the path length, driving time, energy consumption and safety of the final path of the vehicle, and performing weighted summation to obtain a comprehensive evaluation result;

[0022] When the comprehensive evaluation is less than the preset evaluation threshold, the step of returning to the particle swarm algorithm to obtain the vehicle path generated by the particle swarm after each iteration is continued.

[0023] In a second aspect, the present application also provides a path planning device, comprising:

[0024] A mapping module, used to obtain driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid, so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules;

[0025] A calculation module, used to use the vehicles in the two-dimensional environment as particles to form a particle swarm, obtain a vehicle path generated by the particle swarm after each iteration based on a particle swarm algorithm, and calculate a length reward value, a safety reward value, and a smoothness reward value of the vehicle path;

[0026] An integration module, used to integrate the length reward value, the safety reward value and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration;

[0027] The determination module is used to continue the above iterative process until the iteration is stopped when the preset conditions are met, and determine the final path of the vehicle according to the vehicle path corresponding to the maximum integrated reward value.

[0028] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0029] Acquire driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules;

[0030] The vehicles in the two-dimensional environment are used as particles to form a particle swarm, and based on the particle swarm algorithm, a vehicle path generated by the particle swarm after each iteration is obtained, and a length reward value, a safety reward value, and a smoothness reward value of the vehicle path are calculated;

[0031] Integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration;

[0032] The above iteration process is continued until the preset conditions are met and the iteration is stopped. The final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0034] Acquire driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules;

[0035] The vehicles in the two-dimensional environment are used as particles to form a particle swarm, and based on the particle swarm algorithm, a vehicle path generated by the particle swarm after each iteration is obtained, and a length reward value, a safety reward value, and a smoothness reward value of the vehicle path are calculated;

[0036] Integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration;

[0037] The above iteration process is continued until the preset conditions are met and the iteration is stopped. The final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value.

[0038] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0039] Acquire driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules;

[0040] The vehicles in the two-dimensional environment are used as particles to form a particle swarm, and based on the particle swarm algorithm, a vehicle path generated by the particle swarm after each iteration is obtained, and a length reward value, a safety reward value, and a smoothness reward value of the vehicle path are calculated;

[0041] Integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration;

[0042] The above iteration process is continued until the preset conditions are met and the iteration is stopped. The final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value.

[0043] The above-mentioned path planning method, device, computer equipment, computer-readable storage medium and computer program product, first, obtain the driving environment information of the vehicle, map the driving environment information into a two-dimensional grid, so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; use the vehicle in the two-dimensional environment as particles to form a particle swarm, based on the particle swarm algorithm, obtain the vehicle path generated by the particle swarm after each iteration, calculate the length reward value, safety reward value and smoothness reward value of the vehicle path; integrate the length reward value, safety reward value and smoothness reward value of the vehicle path generated by each iteration, and obtain the integrated reward value of the vehicle path generated by each iteration; continue the above-mentioned iterative process until the preset conditions are met, stop the iteration, and determine the final path of the vehicle according to the vehicle path corresponding to the maximum integrated reward value. In this way, the present application realizes path planning through the particle swarm algorithm and various user-defined parameters, realizes efficient and stable path planning, and generates a more reasonable planning path. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A diagram of an application environment of a path planning method in an embodiment;

[0046] Figure 2 A schematic diagram of a process flow of a path planning method in one embodiment;

[0047] Figure 3 is a structural block diagram of a path planning device in one embodiment;

[0048] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The path planning method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0051] In an exemplary embodiment, Figure 2 As shown, a path planning method is provided, which is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, including the following steps 202 to 208. Among them:

[0052] Step 202 , obtaining driving environment information of the vehicle, and mapping the driving environment information into a two-dimensional grid, so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment.

[0053] Among them, driving environment information includes road layout, obstacle location and traffic rules.

[0054] In some embodiments, environmental information such as the layout of the road on which the vehicle is about to drive, the location of obstacles on the road, and traffic rules on the road are obtained, and the environmental information is mapped into a two-dimensional grid, so that the vehicle's driving environment is converted from a three-dimensional environment to a two-dimensional environment.

[0055] Step 204 , using vehicles in the two-dimensional environment as particles to form a particle swarm, obtaining the vehicle path generated by the particle swarm after each iteration based on the particle swarm algorithm, and calculating the length reward value, safety reward value and smoothness reward value of the vehicle path.

[0056] Exemplarily, vehicles in a two-dimensional environment are used as particles to form a particle swarm, and the parameters of the particle swarm algorithm such as population size, individual optimality and global optimality are initialized. Each particle continuously adjusts its position and speed according to the global optimal position of the entire particle swarm and its own optimal position, thereby obtaining the vehicle path generated by the particle swarm after each iteration.

[0057] In another embodiment, when the particle swarm algorithm falls into a local optimal solution, the parameters of the particle swarm are dynamically adjusted to ensure that the particle swarm algorithm has a stronger search capability in the early stage and gradually converges to the local optimal solution in the later stage.

[0058] Furthermore, according to the vehicle path generated in each iteration, a length reward value, a safety reward value and a smoothness reward value of the vehicle path are calculated.

[0059] Step 206 , integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated in each iteration to obtain an integrated reward value of the vehicle path generated in each iteration.

[0060] In some embodiments, the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated for each iteration are integrated to obtain an integrated reward value of the vehicle path generated for each iteration.

[0061] Step 208, the above iteration process is continued until the preset condition is met and the iteration is stopped, and the final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value.

[0062] In some embodiments, the particle swarm continuously iterates in the two-dimensional environment formed by the driving environment of the vehicle until a preset condition is met, stops iterating, and determines the final path of the vehicle based on the vehicle path corresponding to the maximum integrated reward value.

[0063] In the above path planning method, the driving environment information of the vehicle is obtained, and the driving environment information is mapped into a two-dimensional grid, so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the vehicle in the two-dimensional environment is used as a particle to form a particle swarm, and based on the particle swarm algorithm, the vehicle path generated by the particle swarm after each iteration is obtained, and the length reward value, safety reward value and smoothness reward value of the vehicle path are calculated; the length reward value, safety reward value and smoothness reward value of the vehicle path generated by each iteration are integrated to obtain the integrated reward value of the vehicle path generated by each iteration; the above iterative process is continued until the preset conditions are met and the iteration is stopped, and the final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value. In this way, the present application realizes path planning through the particle swarm algorithm and various user-defined parameters, realizes efficient and stable path planning, and generates a more reasonable planning path.

[0064] In some exemplary embodiments, the driving environment information of the vehicle is obtained and mapped into a two-dimensional grid, including: converting the road layout into a two-dimensional grid layout, and marking the grid where the corresponding obstacle is located as an inaccessible area according to the position of the obstacle; converting the traffic rules into attributes in the two-dimensional grid, and the attributes include constraints.

[0065] In actual implementation, after obtaining the driving environment information, two-dimensional rasterization processing is performed to map the driving environment information to a two-dimensional grid. Each grid represents a certain spatial area. The road layout is converted into a two-dimensional grid layout, and the location of the obstacle is marked as an inaccessible area, and the rest are passable areas. The vehicle is simplified into a particle, and the position of the vehicle is represented in the two-dimensional grid. The other nodes are used as candidate nodes for path planning.

[0066] Furthermore, traffic rules are converted into attributes in a two-dimensional grid, and the attributes include constraints. Specifically, traffic rules (such as traffic rules, road signs, driving direction restrictions, etc.) can be converted into specific marks through information encoding. For example, the position of a red light can be marked as an impassable obstacle, and road signs (such as speed limits and turn instructions) can be converted into additional information of two-dimensional grid cells through information encoding, so that these rules can be considered during path planning.

[0067] In the above embodiment, by mapping the driving environment information from three dimensions to a two-dimensional grid, the efficiency of path planning is improved and the final path display is more intuitive.

[0068] In some exemplary embodiments, the calculation process of the length reward value, safety reward value and smoothness reward value of the vehicle path includes: normalizing the length of the vehicle path and multiplying it by a preset positive coefficient to obtain the vehicle path length reward value; quantifying the distance between the vehicle path and the obstacle and the judgment result of whether the vehicle complies with traffic regulations to obtain the safety reward value; quantifying the steering operation data of the vehicle path to obtain the smoothness reward value.

[0069] In actual implementation, the shorter the length of the vehicle path, the faster the vehicle can reach the destination. The path length is normalized with a uniform unit and ratio, and multiplied by a preset positive coefficient to obtain the length reward value of the vehicle path; the distance between the vehicle path and the obstacle and the judgment result of whether the vehicle complies with traffic regulations are quantified according to user needs to obtain the safety reward value of the vehicle path; the steering operation data of the vehicle on the vehicle path is quantified to obtain the smoothness reward value.

[0070] Among them, smoothness affects the stability of vehicle driving and the comfort of passengers.

[0071] In the above embodiment, by quantifying the safety and smoothness of the vehicle during driving and converting them into specific data, the data can be accurately represented, thus avoiding the subjectivity and ambiguity of traditional qualitative analysis.

[0072] In some exemplary embodiments, the length reward value, safety reward value and smoothness reward value of the vehicle path generated in each iteration are integrated to obtain the integrated reward value of the vehicle path generated in each iteration, including: weighted summing the length reward value, safety reward value and smoothness reward value of the vehicle path generated in each iteration to obtain the integrated reward value of the vehicle path generated in each iteration.

[0073] In actual implementation, the length reward value, safety reward value and smoothness reward value of the vehicle path generated in each iteration are assigned weights preset by the user, and weighted summation is performed to obtain the integrated reward value of the vehicle path generated in each iteration.

[0074] In the above embodiment, the user performs an importance analysis on the length, safety and smoothness of the vehicle path and assigns preset weights, so that the final vehicle path better meets the customer's expectations.

[0075] In some exemplary embodiments, the preset conditions include an integrated reward value greater than a preset value, a total number of iterations reaching a preset number of iterations, a change value between the integrated reward values ​​generated by two adjacent iterations being less than a preset change value, or a vehicle path satisfying at least one of the preset path conditions; the preset path conditions include a vehicle path length being less than a path length threshold, a safety reward value being higher than a preset safety threshold, or a smoothness reward value being higher than a preset smoothness threshold.

[0076] In actual implementation, in the process of continuous iteration, if the integrated reward value is greater than the preset value, the particle swarm stops iterating when the total number of iterations reaches the preset number of iterations, the change value between the integrated reward values ​​generated by two adjacent iterations is less than the preset change value, or the vehicle path meets any of the preset path conditions.

[0077] The preset path conditions include that the length of the vehicle path is less than a path length threshold, the safety reward value is higher than a preset safety threshold, or the smoothness reward value is higher than a preset smoothness threshold.

[0078] In the above embodiment, by presetting the stopping iteration condition of the particle swarm in advance, it is ensured that when the iteration is finally stopped, the path of the output vehicle is a path that meets the user's requirements.

[0079] In some exemplary embodiments, the path planning method further includes: quantifying the path length, driving time, energy consumption and safety of the vehicle's final path, and performing weighted summation to obtain a comprehensive evaluation result; when the comprehensive evaluation is less than a preset evaluation threshold, returning to the step of obtaining the vehicle path generated by the particle swarm algorithm after each iteration and continuing to execute.

[0080] In actual implementation, the path length, driving time, energy consumption and safety of the vehicle's final path are quantified according to their importance, and preset evaluation weights are assigned according to their importance. The weighted sum is then taken to obtain a comprehensive evaluation result of the vehicle's final path.

[0081] When the comprehensive evaluation result is greater than the preset evaluation threshold, the final vehicle path is output; when the comprehensive evaluation result is less than the preset evaluation threshold, the particle swarm algorithm is returned to obtain the steps of the vehicle path generated by the particle swarm after each iteration and continue to execute to generate a new vehicle path.

[0082] In another embodiment, if the comprehensive evaluation result is less than the preset evaluation threshold, it may be caused by inaccurate data, improper weight distribution or errors in the calculation process. In this case, the step of obtaining the vehicle path generated by the particle swarm algorithm after each iteration should be returned to for correction.

[0083] In the above embodiment, by comprehensively evaluating parameters of various aspects of the final path of the vehicle, the comprehensive evaluation result is used to intuitively display the pros and cons of the final path of the vehicle, so that the user can directly understand whether the final path of the vehicle meets the requirements.

[0084] To explain the path planning method in the present application in detail, an embodiment is used for explanation below. By way of example, the present application is described with a path planning method in a specific vehicle driving scenario.

[0085] First, the driving environment information of the vehicle is obtained, and the driving environment information of the vehicle is processed into a two-dimensional grid. The driving environment information is mapped to a two-dimensional grid. Each grid represents a certain spatial area. The road layout is converted into a two-dimensional grid layout. The location of the obstacle is marked as an inaccessible area, and the rest is a passable area. The vehicle is simplified into a particle, and the position of the vehicle is represented in the two-dimensional grid. The other nodes are used as candidate nodes for path planning.

[0086] Furthermore, traffic rules are converted into attributes in a two-dimensional grid, and the attributes include constraints. Specifically, traffic rules (such as traffic rules, road signs, driving direction restrictions, etc.) can be converted into specific marks through information encoding. For example, the position of a red light can be marked as an impassable obstacle, and road signs (such as speed limits and turn instructions) can be converted into additional information of two-dimensional grid cells through information encoding, so that these rules can be considered during path planning.

[0087] The vehicles in the two-dimensional environment are regarded as particles to form a particle swarm. The parameters such as the population size, individual optimality and global optimality of the particle swarm algorithm are initialized. Each particle continuously adjusts its position and speed according to the global optimal position of the entire particle swarm and its own optimal position, thereby obtaining the vehicle path generated by the particle swarm after each iteration.

[0088] The path length is normalized with a uniform unit and ratio, and multiplied by a preset positive coefficient to obtain the length reward value of the vehicle path; the distance between the vehicle path and the obstacle and the judgment result of whether the vehicle complies with traffic regulations are quantified according to user needs to obtain the safety reward value of the vehicle path; the steering operation data of the vehicle on the vehicle path is quantified to obtain the smoothness reward value.

[0089] The length reward value, safety reward value and smoothness reward value of the vehicle path generated in each iteration are assigned the weights preset by the user, and the weighted sum is performed to obtain the integrated reward value of the vehicle path generated in each iteration.

[0090] In the process of continuous iteration, if the integrated reward value is greater than the preset value, the particle swarm stops iterating when the total number of iterations reaches the preset number of iterations, the change value between the integrated reward values ​​generated by two adjacent iterations is less than the preset change value, or the vehicle path meets any of the preset path conditions.

[0091] The final path of the vehicle is determined based on the vehicle path corresponding to the maximum integrated reward value.

[0092] This application maps the driving environment to a two-dimensional grid for path planning, maps the intelligent driving vehicle as a point, scales the obstacles according to their shapes, covers part of the grid, and uses the remaining grids as candidate nodes for path planning to facilitate subsequent planning.

[0093] This application pre-sets different weights and preset conditions according to the importance of different factors, which can more directly screen out the final vehicle path that meets the user's expectations.

[0094] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0095] Based on the same inventive concept, the embodiment of the present application also provides a path planning device for implementing the path planning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more path planning device embodiments provided below can refer to the limitations of the path planning method above, and will not be repeated here.

[0096] In an exemplary embodiment, Figure 3 As shown, a path planning device is provided, including: a mapping module 301, a calculation module 302, an integration module 303 and a determination module 304, wherein:

[0097] The mapping module is used to obtain the driving environment information of the vehicle and map the driving environment information into a two-dimensional grid so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle location and traffic rules.

[0098] The calculation module is used to use the vehicles in the two-dimensional environment as particles to form a particle swarm, obtain the vehicle path generated by the particle swarm after each iteration based on the particle swarm algorithm, and calculate the length reward value, safety reward value and smoothness reward value of the vehicle path.

[0099] The integration module is used to integrate the length reward value, the safety reward value and the smoothness reward value of the vehicle path generated in each iteration to obtain the integrated reward value of the vehicle path generated in each iteration.

[0100] The determination module is used to continue the above iterative process until the iteration is stopped when the preset conditions are met, and determine the final path of the vehicle according to the vehicle path corresponding to the maximum integrated reward value.

[0101] In some embodiments, the above-mentioned mapping module is also used to convert the road layout into a two-dimensional grid layout, and mark the grid where the corresponding obstacle is located as an inaccessible area according to the position of the obstacle; and convert the traffic rules into attributes in the two-dimensional grid, and the attributes include constraints.

[0102] In some embodiments, the above-mentioned calculation module is also used to normalize the length of the vehicle path, multiply it by a preset positive coefficient, and obtain a vehicle path length reward value; quantify the distance between the vehicle path and the obstacle and the judgment result of whether the vehicle complies with traffic regulations to obtain a safety reward value; quantify the steering operation data of the vehicle path to obtain a smoothness reward value.

[0103] In some embodiments, the above-mentioned integration module is also used to perform weighted summation on the length reward value, safety reward value and smoothness reward value of the vehicle path generated in each iteration to obtain the integrated reward value of the vehicle path generated in each iteration.

[0104] In some embodiments, the preset conditions include an integrated reward value greater than a preset value, a total number of iterations reaching a preset number of iterations, a change value between the integrated reward values ​​generated by two adjacent iterations being less than a preset change value, or a vehicle path satisfying at least one of the preset path conditions; the preset path conditions include the length of the vehicle path being less than a path length threshold, a safety reward value being higher than a preset safety threshold, or a smoothness reward value being higher than a preset smoothness threshold.

[0105] In some embodiments, the device also includes an evaluation module for quantifying the path length, driving time, energy consumption and safety of the vehicle's final path, and performing weighted summation to obtain a comprehensive evaluation result; when the comprehensive evaluation is less than a preset evaluation threshold, it returns to the step of obtaining the vehicle path generated by the particle swarm algorithm after each iteration and continues to execute.

[0106] Each module in the above-mentioned path planning device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0107] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store path data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a path planning method is implemented.

[0108] The display unit of the computer device is used to form a visually visible picture, and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball, or touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0109] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure 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. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0110] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0111] Acquire driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules;

[0112] The vehicles in the two-dimensional environment are used as particles to form a particle swarm, and based on the particle swarm algorithm, a vehicle path generated by the particle swarm after each iteration is obtained, and a length reward value, a safety reward value, and a smoothness reward value of the vehicle path are calculated;

[0113] Integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration;

[0114] The above iteration process is continued until the preset conditions are met and the iteration is stopped. The final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value.

[0115] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0116] Acquire driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules;

[0117] The vehicles in the two-dimensional environment are used as particles to form a particle swarm, and based on the particle swarm algorithm, a vehicle path generated by the particle swarm after each iteration is obtained, and a length reward value, a safety reward value, and a smoothness reward value of the vehicle path are calculated;

[0118] Integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration;

[0119] The above iteration process is continued until the preset conditions are met and the iteration is stopped. The final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value.

[0120] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0121] Acquire driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules;

[0122] The vehicles in the two-dimensional environment are used as particles to form a particle swarm, and based on the particle swarm algorithm, a vehicle path generated by the particle swarm after each iteration is obtained, and a length reward value, a safety reward value, and a smoothness reward value of the vehicle path are calculated;

[0123] Integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration;

[0124] The above iteration process is continued until the preset conditions are met and the iteration is stopped. The final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value.

[0125] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0126] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0127] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this application.

[0128] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A path planning method, characterized in that: The method comprises: Acquire driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules; The vehicles in the two-dimensional environment are used as particles to form a particle swarm, and based on the particle swarm algorithm, a vehicle path generated by the particle swarm after each iteration is obtained, and a length reward value, a safety reward value, and a smoothness reward value of the vehicle path are calculated; Integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration; The above iteration process is continued until the preset conditions are met and the iteration is stopped. The final path of the vehicle is determined according to the vehicle path corresponding to the maximum integrated reward value.

2. The method according to claim 1, characterized in that The obtaining of the driving environment information of the vehicle and mapping the driving environment information into a two-dimensional grid includes: Converting the road layout into a two-dimensional grid layout, and marking the grid where the corresponding obstacle is located as an inaccessible area according to the obstacle position; The traffic rules are converted into attributes in the two-dimensional grid, wherein the attributes include constraint conditions.

3. The method according to claim 1, characterized in that The calculation process of the length reward value, the safety reward value and the smoothness reward value of the vehicle path includes: Normalizing the length of the vehicle path and multiplying it by a preset positive coefficient to obtain a vehicle path length reward value; Quantifying the distance between the vehicle path and the obstacle and the judgment result of whether the vehicle complies with traffic regulations to obtain a safety reward value; The steering operation data of the vehicle path is quantified to obtain a smoothness reward value.

4. The method according to claim 1, characterized in that: The step of integrating the length reward value, the safety reward value, and the smoothness reward value of the vehicle path generated in each iteration to obtain the integrated reward value of the vehicle path generated in each iteration includes: The length reward value, the safety reward value and the smoothness reward value of the vehicle path generated in each iteration are weightedly summed to obtain an integrated reward value of the vehicle path generated in each iteration.

5. The method according to claim 1, characterized in that The preset conditions include an integrated reward value greater than a preset value, a total number of iterations reaching a preset number of iterations, a change value between the integrated reward values ​​generated by two adjacent iterations being less than a preset change value, or a vehicle path satisfying at least one of the preset path conditions; the preset path conditions include a vehicle path length being less than a path length threshold, a safety reward value being higher than a preset safety threshold, or a smoothness reward value being higher than a preset smoothness threshold.

6. The method according to claim 1, characterized in that The method further comprises: Quantifying the path length, driving time, energy consumption and safety of the final path of the vehicle, and performing weighted summation to obtain a comprehensive evaluation result; When the comprehensive evaluation is less than the preset evaluation threshold, the step of returning to the particle swarm algorithm to obtain the vehicle path generated by the particle swarm after each iteration is continued.

7. A path planning device, characterized in that: The device comprises: A mapping module, used to obtain driving environment information of the vehicle, and map the driving environment information into a two-dimensional grid, so that the driving environment of the vehicle is converted from a three-dimensional environment to a two-dimensional environment; the driving environment information includes road layout, obstacle locations and traffic rules; A calculation module, used to use the vehicles in the two-dimensional environment as particles to form a particle swarm, obtain the vehicle path generated by the particle swarm after each iteration based on the particle swarm algorithm, and calculate the length reward value, safety reward value and smoothness reward value of the vehicle path; An integration module, used to integrate the length reward value, the safety reward value and the smoothness reward value of the vehicle path generated by each iteration to obtain an integrated reward value of the vehicle path generated by each iteration; The determination module is used to continue the above iterative process until the iteration is stopped when the preset conditions are met, and determine the final path of the vehicle according to the vehicle path corresponding to the maximum integrated reward value.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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 steps of the method according to any one of claims 1 to 6 are implemented.

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

Images