Continuous learning motion planning method, device, equipment, medium and product

Abstract

The invention discloses a continuous learning motion planning method and device, equipment, a medium and a product, and relates to the field of intelligent driving, and the method comprises the steps: projecting the point cloud data of a current cross-country environment to a grid map, and generating a terrain height map and a pavement roughness map; according to the speed information, constructing a guide map, and inputting the terrain height map, the pavement roughness map and the guide map into the (k-1) th updated motion planning model to generate a planning track map of the current cross-country environment; acquiring a real track of the unmanned vehicle after driving according to the planned track map, and adding the real track into the sample data set; and according to the sample data set of the current cross-country environment and a preset historical sample data set, adopting a mean square error as a loss function and performing k-th update on the motion planning model through a back propagation algorithm. According to the invention, through continuous learning and iterative optimization, the motion planning capability and driving safety of the unmanned vehicle in a complex cross-country scene are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving, and in particular to a motion planning method, device, equipment, medium and product for continuous learning. Background Art

[0002] Intelligent driving is the product of the deep integration of the automotive industry and information technology. It uses advanced technologies such as sensors, computer vision, and artificial intelligence to enable vehicles to have the ability to drive automatically. Intelligent driving can not only improve the safety and efficiency of road driving, but also effectively reduce traffic congestion and environmental pollution. It is an important direction for the future development of automobiles.

[0003] In the field of intelligent driving, motion planning is one of the core modules, responsible for calculating the optimal or approximately optimal driving trajectory based on the current environmental information and vehicle status, ensuring that the vehicle can reach the destination safely and efficiently. Especially in off-road environments, due to complex terrain, variable obstacles and constantly changing environmental factors, the requirements for motion planning algorithms are more stringent.

[0004] The motion planning methods of related technologies have many shortcomings when dealing with off-road scenarios. Traditional rule-based or parameter-based methods often have difficulty adapting to complex and changing terrain features and environmental conditions, resulting in suboptimal planned paths and even safety issues. Although learning-based methods perform well in some scenarios, their generalization and robustness are often limited when data is scarce or environmental features are complex, affecting the overall performance and reliability of the system. Summary of the invention

[0005] The purpose of this application is to provide a continuous learning motion planning method, device, equipment, medium and product that can handle complex off-road terrain features and generate adaptive planning paths.

[0006] To achieve the above objectives, this application provides the following solutions.

[0007] In a first aspect, the present application provides a continuous learning motion planning method, including: projecting the point cloud data of the current off-road environment onto the grid map of the current off-road environment to obtain a terrain height map of the current off-road environment; calculating the road surface roughness of the current off-road environment according to the pixel values ​​of the terrain height map of the current off-road environment to obtain a road surface roughness map of the current off-road environment; constructing a guidance map from the starting point to the target point according to the speed information of the unmanned vehicle in the current off-road environment; wherein the target point is the end point of the global trajectory; inputting the terrain height map, road surface roughness map and guidance map of the current off-road environment into the motion planning model after the k-1th update to obtain the planned trajectory of the current off-road environment. map; wherein k is a natural number greater than or equal to 2, and the first k-1 updates correspond to k-1 off-road environments; obtaining the actual trajectory of the unmanned vehicle after driving according to the planned trajectory map of the current off-road environment, and adding the actual trajectory to the sample data set; the sample data set includes a terrain height map, a road roughness map, a guide map and the corresponding actual trajectory of the current off-road environment; according to the sample data set of the current off-road environment and the preset historical sample data set, the mean square error is used as the loss function and the motion planning model is updated for the kth time through the back propagation algorithm; wherein the preset historical sample data set includes a sample data set of a previous off-road environment different from the current off-road environment.

[0008] Optionally, the terrain height calculation formula of the terrain height map is: .

[0009] in, M h represents the topographic height of the grid cell, x , y Respectively represent the horizontal and vertical coordinates of the grid cell, G xy Represents a grid cell on a grid map. Represents the average height value of all point cloud data in the grid cell. n xy Represents the total number of point cloud data in a grid cell. z i Indicates i The height value of the point cloud data, i =1,2,3,..., n xy .

[0010] Optionally, the road roughness calculation formula of the road roughness map is: .

[0011] in, M r represents the roughness of the grid cell, x and yRespectively represent the horizontal and vertical coordinates of the grid cell, It represents the mean square error of the height values ​​of all point cloud data in the grid cell. G xy Represents a grid cell on a grid map. Represents the average height value of all point cloud data in the grid cell. n xy Represents the total number of point cloud data in a grid cell. z i Indicates i The height value of the point cloud data, i =1,2,3,..., n xy .

[0012] Optionally, the expression of the guide map is specifically: .in, M s Represents the pixel value of the coordinate point in the guide map, E Indicates the starting point, x ego and y ego Represent the horizontal and vertical coordinates of the starting point, respectively. G represents the target point, x target and y target Represent the horizontal and vertical coordinates of the target point respectively. x j and y j Respectively represent the horizontal and vertical coordinates of each coordinate point in the guide map, j =1,2,3,... J , J Indicates the total number of coordinate points in the guide map. v Indicates the current speed of the driverless car.

[0013] Optionally, the constraint condition for using mean square error as the loss function is: .

[0014] in, M Represents the preset historical sample data set, Indicates that the sample dataset based on the current off-road environment has been updated t -1 motion planning model, Indicates that the motion planning model has been updated for the tth time based on the sample data set of the current off-road environment. l ( ) represents the loss function of the motion planning model.

[0015] Optionally, the gradient update formula in the back-propagation algorithm is: .

[0016] in, is the final updated gradient value of the motion planning model in the current off-road environment, is the gradient value updated by the motion planning model for the current off-road environment, is the average gradient of the updated motion planning model for all off-road environments, for The transpose of for The transpose of .

[0017] In a second aspect, the present application provides a motion planning device for continuous learning, including: a terrain height map acquisition module, a road roughness map acquisition module, a guidance map acquisition module, a planning trajectory map acquisition module, a real trajectory acquisition module and a model update module.

[0018] The terrain height map acquisition module is used to project the point cloud data of the current off-road environment onto the grid map of the current off-road environment to obtain the terrain height map of the current off-road environment.

[0019] The road surface roughness map acquisition module is used to calculate the road surface roughness of the current off-road environment according to the pixel values ​​of the terrain height map of the current off-road environment, and obtain the road surface roughness map of the current off-road environment.

[0020] The guidance map acquisition module is used to construct a guidance map from the starting point to the target point according to the speed information of the unmanned vehicle in the current off-road environment; wherein the target point is the end point of the global trajectory.

[0021] The planning trajectory map acquisition module is used to input the terrain height map, road roughness map and guidance map of the current off-road environment into the motion planning model after the k-1th update to obtain the planning trajectory map of the current off-road environment; wherein k is a natural number greater than or equal to 2, and the first k-1 updates correspond to k-1 off-road environments.

[0022] The real trajectory acquisition module is used to obtain the real trajectory of the unmanned vehicle after driving according to the planned trajectory map of the current off-road environment, and add the real trajectory to the sample data set; the sample data set includes the terrain height map, road roughness map, guidance map and corresponding real trajectory of the current off-road environment.

[0023] A model updating module is used to update the motion planning model for the kth time based on the sample data set of the current off-road environment and the preset historical sample data set, using the mean square error as the loss function and through the back propagation algorithm; wherein the preset historical sample data set includes a sample data set of a previous off-road environment that is different from the current off-road environment.

[0024] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the continuous learning motion planning method described in any one of the above.

[0025] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned continuous learning motion planning methods.

[0026] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned continuous learning motion planning methods.

[0027] According to the specific embodiments provided by the present application, the present application has the following technical effects: the present application provides a motion planning method, device, equipment, medium and product for continuous learning, which obtains a terrain height map by projecting the point cloud data of the current off-road environment onto a raster map, thereby solving the problem that the off-road environment has complex terrain and is difficult to intuitively understand and quantify, and realizes the accurate digital expression of terrain information, providing a solid and reliable data foundation for subsequent motion planning; by combining the pixel values ​​of the terrain height map, the road roughness of the current off-road environment is calculated, and a road roughness map is drawn; at the same time, according to the real-time speed information of the unmanned vehicle, a guidance map from the starting point to the target point is constructed, thereby solving the problem of off-road environment. The system overcomes the challenges of changeable road conditions and difficult to accurately judge the driving direction in off-road environments, realizes a comprehensive assessment of road conditions and intelligent optimization of driving paths, and significantly improves the driving safety and efficiency of unmanned vehicles. By inputting key information such as terrain height map, road roughness map and guidance map into the motion planning model that has been iteratively updated many times, the planned trajectory map in the current off-road environment is obtained, and based on the actual trajectory of the unmanned vehicle after actual driving, the model is continuously corrected and optimized, realizing the continuous learning and self-improvement of the motion planning model, solving the problem that traditional motion planning methods are difficult to adapt to changes in complex off-road environments, and improving the adaptability and planning accuracy of unmanned vehicles in different off-road scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments 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 drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 This is a diagram of an application environment for a continuous learning motion planning method in one embodiment of the present application.

[0030] Figure 2 A flowchart of a motion planning method for continuous learning provided in one embodiment of the present application.

[0031] Figure 3 A flowchart of a motion planning method for continuous learning provided in another embodiment of the present application.

[0032] Figure 4 A schematic diagram of the functional modules of a motion planning device for continuous learning provided in one embodiment of the present application.

[0033] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0035] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0036] In an exemplary embodiment, Figure 2 As shown, a motion planning method for continuous learning is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server in is taken as an example to illustrate, including the following steps 101 to 106.

[0037] Step 101 , projecting the point cloud data of the current off-road environment onto a grid map of the current off-road environment to obtain a terrain height map of the current off-road environment.

[0038] Step 102 , calculating the road surface roughness of the current off-road environment according to the pixel values ​​of the terrain height map of the current off-road environment, and obtaining a road surface roughness map of the current off-road environment.

[0039] Step 103, constructing a guidance map from the starting point to the target point according to the speed information of the unmanned vehicle in the current off-road environment; wherein the target point is the end point of the global trajectory.

[0040] Step 104, input the terrain height map, road roughness map and guidance map of the current off-road environment into the motion planning model after the k-1th update, and obtain the planned trajectory map of the current off-road environment; wherein k is a natural number greater than or equal to 2, and the first k-1 updates correspond to k-1 off-road environments, and any two off-road environments can be the same or different.

[0041] Step 105, obtaining the actual trajectory of the unmanned vehicle after driving according to the planned trajectory map of the current off-road environment, and adding the actual trajectory to the sample data set; the sample data set includes the terrain height map, road roughness map, guidance map and corresponding actual trajectory of the current off-road environment.

[0042] Step 106, based on the sample data set of the current off-road environment and the preset historical sample data set, the motion planning model is updated for the kth time using the mean square error as the loss function and the back propagation algorithm; wherein the preset historical sample data set includes a sample data set of a previous off-road environment that is different from the current off-road environment.

[0043] By implementing the above steps 101 to 106, each time the model is updated, the constraints can be controlled to ensure that the average loss of the old scene is not increased while learning the new scene data, so that the model can effectively retain and transfer the acquired knowledge while adapting to the new scene.

[0044] In another exemplary embodiment of the present application, Figure 3 As shown in Figure 1, another motion planning method with continuous learning is provided. Taking an off-road scenario as an example, the specific implementation steps are as follows.

[0045] Step S1, environmental map and data processing. The collected current off-road environmental data is processed into a single-channel environmental map and a guide map. The environmental map and the guide map are used as model inputs, and the trajectory truth is used as a label. Various features in the environment are represented in the form of a single-channel map, and the features are distinguished by the pixel value of the map. The features represented, such as terrain height, roughness, slope, etc., can be determined according to the main characteristics of the environment and planning requirements.

[0046] Step S11: Terrain height map At the moment , point cloud data collected by unmanned vehicles is projected onto a grid map , the x and y coordinates of each point cloud correspond to the grid unit , and take the average z value of the point cloud projected into the grid cell to generate a terrain height map.

[0047] The formula for calculating terrain height is: .

[0048] in,M h represents the topographic height of the grid cell, x , y Respectively represent the horizontal and vertical coordinates of the grid cell, G xy Represents a grid cell on a grid map. Represents the average height value of all point cloud data in the grid cell. n xy Represents the total number of point cloud data in a grid cell. z i Indicates i The height value of the point cloud data, i =1,2,3,..., n xy .

[0049] Finally, the raster map is converted into a single-channel image to obtain a single-channel terrain height map, and the pixel values ​​of the single-channel terrain height map represent the height information of each location.

[0050] Step S12: Road surface roughness map The road surface roughness at each location is calculated based on the mean square error of the z value of the point cloud projected to the grid cell.

[0051] The calculation formula of road roughness is: .

[0052] in, M r represents the roughness of the grid cell, x and y Respectively represent the horizontal and vertical coordinates of the grid cell, It represents the mean square error of the height values ​​of all point cloud data in the grid cell. G xy Represents a grid cell on a grid map. Represents the average height value of all point cloud data in the grid cell. n xy Represents the total number of point cloud data in a grid cell. z i Indicates i The height value of the point cloud data, i =1,2,3,..., n xy .

[0053] Similarly, the raster map is converted into a single-channel image to obtain a single-channel road surface roughness map, and the pixel value of the single-channel road surface roughness map represents the road surface roughness information at each position.

[0054] Step S13: Guidance map The guide map obtains the speed information of the unmanned vehicle through IMU (Inertial Measurement Unit) data and uses it as the background pixel value of the single-channel guide map. E : The location of the vehicle on the map, represented by a pixel value of 255, specifically . Target point G : The boundary intersection of the global trajectory and the grid map is represented by a pixel value of 0. The other pixels represent the current speed of the driverless car.

[0055] The expression for the guide map is: .

[0056] in, M s Represents the pixel value of the coordinate point in the guide map, E Indicates the starting point, x ego and y ego Represent the horizontal and vertical coordinates of the starting point, respectively. G represents the target point, x target and y target Represent the horizontal and vertical coordinates of the target point respectively. x j and y j Respectively represent the horizontal and vertical coordinates of each coordinate point in the guide map, j =1,2,3,... J , J Indicates the total number of coordinate points in the guide map. v Indicates the current speed of the driverless car.

[0057] Step S14: Trajectory truth value The actual trajectory of the unmanned vehicle after driving according to the planned trajectory map of the current off-road environment is obtained as the trajectory truth value of the model. The trajectory truth value is generated by GPS and IMU heading angle data. First, the GPS coordinates Convert to UTM (Universal Transverse Mercator Grid System) coordinates , and then take the starting point of the true value of the trajectory as the coordinate origin, the heading angle For the y-axis direction, generate the real trajectory: .

[0058] Ultimately, driverless cars will be The trajectory coordinates are taken as the true value of the trajectory .

[0059] .

[0060] in, is the length of the true trajectory sequence.

[0061] Step S2: Establishment and training of motion planning model.

[0062] Step S21, input data formatting. Convert the single-channel terrain height map, single-channel road roughness map and single-channel guidance map into three-channel RGB images (in this embodiment, it is not necessary to use a conversion module because it is exactly the same size as the ViT input tensor), and input them into the Vision Transformer (ViT) network.

[0063] First, the three-channel RGB image Convert to A flattened 2D image patch: .in, is the size of the image block, is the number of image blocks.

[0064] Step S22, ViT network structure. The Transformer encoder is composed of a multi-head self-attention mechanism and a multilayer perceptron (MLP) alternating. Each block uses layer normalization (LN) and adds residual connections to improve the training efficiency and stability of the motion planning model. The features output by the encoder are input into the fully connected layer to generate the planning trajectory. .

[0065] The output format of the planned trajectory is: .

[0066] Step S23: Compare the predicted trajectory output by the motion planning model with the actual trajectory, and use the back propagation algorithm to update the parameters to optimize the model convergence. The loss function can use the mean squared error (MSE) or other applicable loss functions to ensure that the model gradually improves the prediction accuracy during the training process.

[0067] Through the above steps, the constructed motion planning model can effectively learn motion planning tasks in complex off-road environments and achieve good generalization capabilities after training.

[0068] Step S3: Multi-environment adaptation based on continuous learning. In order to solve the problem of "catastrophic forgetting", a continuous learning algorithm is introduced to ensure that the knowledge already acquired will not be affected when learning new scene data. Specifically, each time the model is updated, a constraint is set to ensure that the average loss of the old scene does not increase. The constraint can be expressed by the following formula.

[0069] .

[0070] in, M Represents the preset historical sample data set, Indicates that the sample dataset based on the current off-road environment has been updated t -1 motion planning model, Indicates that the sample dataset based on the current off-road environment has been updated t The motion planning model l ( ) represents the loss function of the motion planning model.

[0071] At the gradient update level, the final updated gradient It is expressed as: .

[0072] in, is the final updated gradient value of the motion planning model in the current off-road environment, is the gradient value updated by the motion planning model for the current off-road environment, is the average gradient of the updated motion planning model for all off-road environments, for The transpose of for This mechanism ensures the balance between new and old knowledge and improves the adaptability and robustness of the model.

[0073] Repeating the above steps, this embodiment realizes multi-scenario adaptive motion planning in complex off-road environments through the combination of environmental data processing, deep learning model training and continuous learning algorithms. This embodiment introduces a continuous learning algorithm so that the model can adapt to the complex changes of different scenarios without losing the knowledge it has mastered. This method classifies and processes multiple key elements in the off-road environment, effectively enhancing the comprehensive understanding of the environment and planning accuracy. In the process of coping with multiple scenarios, the model has achieved improvements in robustness and adaptability, and can maintain high stability in data scarce or new environments.

[0074] The beneficial effects of the present application are as follows: (1) The end-to-end motion planning model constructed in the present application can handle complex off-road terrain features and generate adaptive planning paths. The motion planning model can accurately analyze environmental data, respond to dynamic changes and complex environmental conditions in off-road scenes in real time, and ensure that the unmanned vehicle can safely and efficiently plan motion paths in various terrains. (2) The motion planning model constructed in the present application exhibits good generalization ability. The motion planning model can transfer knowledge learned from an off-road scene to a new off-road scene. Even when encountering off-road scenes with scarce data or unseen data, the motion planning model can still maintain good planning results. This makes the motion planning method for continuous learning in multiple off-road scenes have a wide range of application adaptability and can work effectively in a changing off-road environment. (3) The continuous learning algorithm proposed in the present application enables the motion planning model to effectively retain existing knowledge when updating, avoiding "catastrophic forgetting" when learning new off-road scenes. This mechanism enables the motion planning model to continuously adapt to new off-road scenes without losing the grasp of old off-road scenes, thereby improving the robustness and long-term adaptability of the motion planning model in multiple off-road scenes.

[0075] The present application also provides an application scenario, which applies the above-mentioned continuous learning motion planning method. Specifically: the continuous learning motion planning method provided in this embodiment can be applied in the unmanned vehicle autonomous exploration scenario. The unmanned vehicle autonomous exploration scenario includes an environmental perception link, a path planning link, and an execution navigation link; the unmanned vehicle enters the path planning link from the environmental perception link, generates a safe driving path by processing and analyzing the perceived off-road environmental data, and enters the execution navigation link to perform actual driving operations. The continuous learning motion planning method provided in this embodiment belongs to the path planning link in the unmanned vehicle autonomous exploration. Specifically, in the process of unmanned vehicle autonomous exploration, the motion planning model can be continuously updated and optimized based on the real-time collected environmental data to adapt to the changing off-road environment and ensure that the unmanned vehicle can reach the destination safely and efficiently.

[0076] Based on the same inventive concept, the embodiment of the present application also provides a motion planning device for continuous learning in multiple off-road scenarios for implementing the above-mentioned motion planning method for continuous learning. The implementation solution provided by the device for solving the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more motion planning devices for continuous learning provided below can refer to the limitations of the motion planning method for continuous learning above, and will not be repeated here.

[0077] In an exemplary embodiment, Figure 4As shown, a continuous learning motion planning device is provided, including: a terrain height map acquisition module 201, a road roughness map acquisition module 202, a guidance map acquisition module 203, a planning trajectory map acquisition module 204, a real trajectory acquisition module 205 and a model updating module 206.

[0078] The terrain height map acquisition module 201 is used to project the point cloud data of the current off-road environment onto the grid map of the current off-road environment to obtain the terrain height map of the current off-road environment.

[0079] The road surface roughness map acquisition module 202 is used to calculate the road surface roughness of the current off-road environment according to the pixel values ​​of the terrain height map of the current off-road environment, and obtain the road surface roughness map of the current off-road environment.

[0080] The guidance map acquisition module 203 is used to construct a guidance map from the starting point to the target point according to the speed information of the unmanned vehicle in the current off-road environment; wherein the target point is the end point of the global trajectory.

[0081] The planning trajectory map acquisition module 204 is used to input the terrain height map, road roughness map and guidance map of the current off-road environment into the motion planning model after the k-1th update to obtain the planning trajectory map of the current off-road environment; wherein k is a natural number greater than or equal to 2, and the first k-1 updates correspond to k-1 off-road environments.

[0082] The real trajectory acquisition module 205 is used to obtain the real trajectory of the unmanned vehicle after driving according to the planned trajectory map of the current off-road environment, and add the real trajectory to the sample data set; the sample data set includes the terrain height map, road roughness map, guidance map and corresponding real trajectory of the current off-road environment.

[0083] The model updating module 206 is used to update the motion planning model for the kth time according to the sample data set of the current off-road environment and the preset historical sample data set, using the mean square error as the loss function and through the back propagation algorithm; wherein the preset historical sample data set includes a sample data set of a previous off-road environment that is different from the current off-road environment.

[0084] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is 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 sample data set data of a motion planning model for continuous learning in multiple off-road scenarios. 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 motion planning method for continuous learning is implemented.

[0085] Those skilled in the art will understand that Figure 5 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. 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 the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0086] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0087] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0088] 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.

[0089] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods 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 this application can include at least one of non-volatile 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), magnetoresistive 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. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0090] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. 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, etc., but is not limited thereto.

[0091] 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 specification.

[0092] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A motion planning method for continuous learning, characterized in that: The motion planning method of continuous learning includes: Projecting the point cloud data of the current off-road environment onto the grid map of the current off-road environment to obtain a terrain height map of the current off-road environment; Calculate the road surface roughness of the current off-road environment according to the pixel values ​​of the terrain height map of the current off-road environment to obtain a road surface roughness map of the current off-road environment; According to the speed information of the unmanned vehicle in the current off-road environment, a guidance map from the starting point to the target point is constructed; wherein the target point is the end point of the global trajectory; Input the terrain height map, road roughness map and guidance map of the current off-road environment into the motion planning model after the k-1th update to obtain the planned trajectory map of the current off-road environment; where k is a natural number greater than or equal to 2, and the first k-1 updates correspond to k-1 off-road environments; Obtain the actual trajectory of the unmanned vehicle after driving according to the planned trajectory map of the current off-road environment, and add the actual trajectory to the sample data set; the sample data set includes a terrain height map, a road roughness map, a guidance map and the corresponding actual trajectory of the current off-road environment; According to the sample data set of the current off-road environment and the preset historical sample data set, the motion planning model is updated for the kth time using the mean square error as the loss function and the back propagation algorithm; wherein the preset historical sample data set includes a sample data set of a previous off-road environment that is different from the current off-road environment.

2. The motion planning method of continuous learning according to claim 1, characterized in that: The terrain height calculation formula of the terrain height map is: ； in, M h represents the topographic height of the grid cell, x and y Represent the horizontal and vertical coordinates of the grid cell, G xy Represents a grid cell on a grid map. Represents the average height value of all point cloud data in the grid cell. n xy Represents the total number of point cloud data in a grid cell. z i Indicates i The height value of the point cloud data, i =1,2,3,..., n xy .

3. The motion planning method of continuous learning according to claim 1, characterized in that: The road roughness calculation formula of the road roughness map is: ； in, M r represents the roughness of the grid cell, x and y Represent the horizontal and vertical coordinates of the grid cell, It represents the mean square error of the height values ​​of all point cloud data in the grid cell. G xy Represents a grid cell on a grid map. Represents the average height value of all point cloud data in the grid cell. n xy Represents the total number of point cloud data in a grid cell. z i Indicates i The height value of the point cloud data, i =1,2,3,..., n xy .

4. The motion planning method of continuous learning according to claim 1, characterized in that: The expression of the guide map is specifically: ； in, M s Represents the pixel value of the coordinate point in the guide map, E Indicates the starting point, x ego and y ego Represent the horizontal and vertical coordinates of the starting point, respectively. G represents the target point, x target and y target Respectively represent the horizontal and vertical coordinates of the target point, x j and y j Respectively represent the horizontal and vertical coordinates of each coordinate point in the guide map, j =1,2,3,... J , J Indicates the total number of coordinate points in the guide map. v Indicates the current speed of the driverless car.

5. The motion planning method of continuous learning according to claim 1, characterized in that: The constraints for using mean square error as the loss function are: ； in, M Represents the preset historical sample data set, Indicates that the sample dataset based on the current off-road environment has been updated t -1 motion planning model, Indicates that the sample dataset based on the current off-road environment has been updated t The motion planning model l ( ) represents the loss function of the motion planning model.

6. The motion planning method of continuous learning according to claim 1, characterized in that: The gradient update formula in the back propagation algorithm is: ； in, is the final updated gradient value of the motion planning model in the current off-road environment, is the gradient value updated by the motion planning model for the current off-road environment, is the average gradient of the updated motion planning model for all off-road environments, for The transpose of for The transpose of .

7. A motion planning device for continuous learning, characterized in that: The motion planning device for continuous learning comprises: A terrain height map acquisition module is used to project the point cloud data of the current off-road environment onto a grid map of the current off-road environment to obtain a terrain height map of the current off-road environment; A road surface roughness map acquisition module is used to calculate the road surface roughness of the current off-road environment according to the pixel values ​​of the terrain height map of the current off-road environment, and obtain the road surface roughness map of the current off-road environment; The guidance map acquisition module is used to construct a guidance map from the starting point to the target point according to the speed information of the unmanned vehicle in the current off-road environment; wherein the target point is the end point of the global trajectory; A planning trajectory map acquisition module is used to input the terrain height map, road roughness map and guidance map of the current off-road environment into the motion planning model after the k-1th update to obtain the planning trajectory map of the current off-road environment; wherein k is a natural number greater than or equal to 2, and the first k-1 updates correspond to k-1 off-road environments; The real trajectory acquisition module is used to obtain the real trajectory of the unmanned vehicle after driving according to the planned trajectory map of the current off-road environment, and add the real trajectory to the sample data set; the sample data set includes the terrain height map, road roughness map, guidance map and corresponding real trajectory of the current off-road environment; A model updating module is used to update the motion planning model for the kth time based on the sample data set of the current off-road environment and the preset historical sample data set, using the mean square error as the loss function and through the back propagation algorithm; wherein the preset historical sample data set includes sample data of the previous off-road environment that is different from the current off-road environment.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the motion planning method for continuous learning according to any one of claims 1 to 6.

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 motion planning method of continuous learning described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the motion planning method of continuous learning described in any one of claims 1 to 6 is implemented.

Images