Logistics path planning method and device, electronic equipment and storage medium
By generating raster maps and using prediction models to optimize logistics routes, the problem of logistics objects being unable to move smoothly in logistics route planning is solved, and efficient route selection is achieved in complex environments.
Patent Information
- Application Number
- CN202511114555.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-11
- Publication Date
- 2025-09-26
AI Technical Summary
In the existing technology, logistics path planning relies on human experience, which makes it difficult to quickly determine and ensure that the specified logistics objects move smoothly to the specified location, especially in complex scene environments.
By generating a grid map and using a prediction model to optimize logistics path planning, the occupancy release rate is reflected according to the grid status value, and the target movement path is determined to ensure that the logistics object arrives at the designated location smoothly.
It improves the practicality of logistics route planning, ensures the smooth movement of logistics objects in complex environments to the greatest extent, and enhances the feasibility of route selection.
Smart Images
Figure CN120706673A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of logistics technology, and specifically to a logistics route planning method, device, electronic device and storage medium. Background Art
[0002] Scenario-based logistics scheduling relies on human experience, making it difficult to quickly and manually determine relevant logistics routes. Therefore, related technologies use path planning algorithms, along with the specified logistics object and location in the logistics instructions, to generate a movement strategy to move the specified logistics object to the specified location. However, in the process of moving the specified logistics object based on the movement strategy, the complexity of the actual scenario environment and other uncertainties may prevent the specified logistics object from moving smoothly to the specified location. Summary of the Invention
[0003] In view of the above problems, the present application provides a logistics path planning method, device, electronic device and storage medium, which are used to improve the practicality of the movement strategy to ensure that the specified logistics object moves smoothly to the specified location.
[0004] According to one aspect of the present application, a logistics path planning method is provided, the planning method comprising: in response to a logistics instruction, generating a grid map representing the current scene route according to current scene data; wherein the logistics instruction is an instruction representing the movement of a specified logistics object to a specified location; the grid map comprises grid status values representing the occupancy status of each grid, and the size of the grid status value is inversely proportional to the occupancy release rate; the grid map is input into a prediction model to obtain a target movement strategy to determine a target movement path representing the movement of the specified logistics object to the specified location; wherein the sum of the grid status values passing through the grids in the movement paths corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid status values in all movement strategies.
[0005] In an optional manner, the current scene data includes different types of scene data; the generating of a grid map representing the current scene route based on the current scene data includes: determining the corresponding maximum scene data and minimum scene data for each type of scene data, and calculating the data difference between the corresponding maximum scene data and the corresponding minimum scene data to obtain the data difference corresponding to each type of scene data; performing a quotient operation on the difference between each scene data and the corresponding minimum scene data in each type of scene data and the corresponding data difference, and using each quotient as the data value corresponding to the corresponding scene data to obtain all data values corresponding to each type of scene data; generating a grid map representing the current scene route based on the data values corresponding to all types of scene data.
[0006] In an optional manner, the current scene data includes the current position, current obstacle position and current environmental data of each logistics object; generating a grid map representing the current scene route based on the current scene data includes: generating an initial grid map based on the current position data, current obstacle position data and current environmental data of each logistics object; assigning a grid state value of each grid in the initial grid map according to a preset assignment strategy to obtain a grid map representing the current scene route.
[0007] In an optional manner, assigning the grid state value of each grid in the initial grid map according to a preset assignment strategy includes: traversing each grid in the initial grid map and taking the traversed grid as the target grid; determining the grid state value of the target grid based on the matching between the occupancy status of the target grid and the preset occupancy status, so as to obtain the grid state value of each grid.
[0008] In an optional manner, the preset occupancy status includes the occupancy status of the logistics object and the occupancy status of the obstacle; and determining the grid state value of the target grid based on the matching between the occupancy status of the target grid and the preset occupancy status includes: if the occupancy status of the target grid matches the occupancy status of the logistics object, determining the grid state value of the target grid to be a first grid state value; if the occupancy status of the target grid matches the occupancy status of the obstacle, determining the grid state value of the target grid to be a second grid state value; wherein, the first grid state value is less than the second grid state value.
[0009] In an optional manner, the planning method also includes: moving each logistics object based on the target movement strategy, and collecting the actual movement trajectory of each logistics object; determining the path error value according to the movement path of each logistics object in the target movement strategy and the corresponding actual movement trajectory to determine whether to update the prediction model.
[0010] In an optional manner, the path error value is determined based on the moving path of each logistics object in the target moving strategy and the corresponding actual moving trajectory, including: calculating the trajectory difference between the moving path of each logistics object in the target moving strategy and the corresponding actual moving trajectory to obtain multiple trajectory differences; summing the square values of each trajectory difference, and dividing the calculated sum by the total number of logistics objects to obtain the path error value.
[0011] According to another aspect of the present application, a logistics path planning device is provided, the planning device comprising: a response module for generating a grid map representing the current scene route according to current scene data in response to a logistics instruction; wherein the logistics instruction is an instruction representing the movement of a specified logistics object to a specified location; the grid map comprises grid status values representing the occupancy status of each grid, and the size of the grid status value is inversely proportional to the occupancy release rate; a determination module for inputting the grid map into a prediction model to obtain a target movement strategy to determine a target movement path representing the movement of the specified logistics object to the specified location; wherein the sum of the grid status values passing through the grids in the movement paths corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid status values in all movement strategies.
[0012] According to one aspect of the present application, an electronic device is provided, comprising: a controller; and a memory for storing one or more programs, wherein when the one or more programs are executed by the controller, the above-mentioned planning method is executed.
[0013] According to one aspect of the present application, a computer-readable storage medium is further provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the above-mentioned planning method.
[0014] According to one aspect of the present application, a computer program product or computer program is also provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the above-described planning method.
[0015] This application generates a grid map representing the real-time scene route through real-time scene data, and inputs the grid map into the prediction model to obtain a target movement strategy including a target movement path representing the movement of a specified logistics object to a specified location. This application focuses on the grid occupancy and digitizes the grid occupancy to obtain a grid state value for each grid to reflect its inversely proportional occupancy release rate; wherein, the sum of the grid state values of the grids in the movement paths corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid state values in all movement strategies, so as to maximize the feasibility of the movement of each logistics object in the target movement strategy, thereby maximizing the guarantee that the specified logistics object can move smoothly to the specified location, thereby improving the practicality of the movement strategy.
[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and it is clear that a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort.
[0018] Figure 1 It is a flowchart of a logistics route planning method shown in an exemplary embodiment of the present application.
[0019] Figure 2 It is a structural diagram of a prediction model shown in an exemplary embodiment of the present application.
[0020] Figure 3 is based on Figure 1 The exemplary embodiment shown is a schematic flow chart of another method for planning a logistics route.
[0021] Figure 4 is based on Figure 1 The exemplary embodiment shown is a schematic flow chart of another method for planning a logistics route.
[0022] Figure 5 is based on Figure 4 The exemplary embodiment shown is a schematic flow chart of another method for planning a logistics route.
[0023] Figure 6 is based on Figure 1 、 Figure 3 、 Figure 4 A schematic flow chart of another logistics path planning method shown in any of the exemplary embodiments shown.
[0024] Figure 7 This is a schematic diagram of a workshop scenario for the logistics path planning method of this application.
[0025] Figure 8 It is a structural diagram of a logistics path planning device shown in an exemplary embodiment of the present application.
[0026] Figure 9 It is a structural diagram of a computer system of an electronic device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0027] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
[0028] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0029] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.
[0030] In this application, "plurality" refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.
[0031] Related technologies use a path planning algorithm, along with the specified logistics object and location in a logistics instruction, to generate a movement strategy to move the specified logistics object to the specified location. However, due to the complexity of the actual scene and other uncertainties, the specified logistics object may not be able to move smoothly to the specified location during the movement strategy.
[0032] To this end, one aspect of this application provides a logistics path planning method. Figure 1 , Figure 1 This is a flow chart of a logistics route planning method according to an exemplary embodiment of the present application. The planning method includes at least S110 to S120, which are described in detail as follows: S110: In response to the logistics instruction, a grid map representing the current scene route is generated according to the current scene data; wherein the logistics instruction is an instruction representing the movement of a specified logistics object to a specified location; the grid map includes a grid status value representing the occupancy status of each grid, and the size of the grid status value is inversely proportional to the occupancy release rate.
[0033] The current scene data can be collected in real time by sensors and cameras in the scene. Among them, sensors include lidar, infrared sensors, etc., which are used to detect obstacles and equipment positions. Cameras are used to capture real-time images in the scene and assist sensors in environmental perception. Data collection is the basis for model training, and it is necessary to obtain a large amount of scene environmental data and its corresponding optimal path planning solution. Data sources include: sensor data (using devices such as lidar and infrared sensors to collect information such as the location of obstacles and equipment in the scene); camera data (using cameras to capture real-time images in the scene to assist sensor data in environmental perception); historical path data (collecting historical path data of logistics objects in the scene, including the movement trajectories of tractors, AGVs, and trailers); simulation data (generating virtual workshop environment data through simulation software to supplement the lack of real data).
[0034] The designated logistics object is not limited to a single object and can be a collective term for multiple logistics objects. The logistics instruction simply moves each designated logistics object to the corresponding designated location. Different logistics objects can be moved to different locations or to the same location, and this application does not limit this.
[0035] The current scene data is the relevant data that represents the scene at the current moment, including but not limited to the location data of each logistics object in the scene, and the location data of obstacles.
[0036] A grid map is a map that represents the positional relationships between various logistics objects, obstacles, etc. in a scene. The grid map includes multiple grids, each of which has a corresponding grid status value, which is used to represent the occupancy status of each grid. The larger the grid status value, the more persistent the occupancy and the lower the possibility of occupancy release, that is, the lower the occupancy release rate. The occupancy release rate represents the probability of the grid being released from the occupied state when it is occupied, that is, the probability of changing from an occupied state to an unoccupied state. The object occupying the grid can be a logistics object or an obstacle, etc. Each grid can only be occupied by one object at a time, for example, occupied by a logistics object or occupied by an obstacle, and will not be occupied by two objects at the same time.
[0037] S120: Input the grid map into the prediction model to obtain the target movement strategy to determine the target movement path representing the movement of the specified logistics object to the specified location; wherein, the sum of the grid state values passing through the grid in the movement path corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid state values in all movement strategies.
[0038] The prediction model is a model for predicting the moving path of movable objects in the grid map, which can be a CNN (convolutional neural network) model with a model structure such as Figure 2As shown in the figure, the grid map passes through the input layer, convolution layer 1, pooling layer 1, convolution layer 2, pooling layer 2, fully connected layer 1, and fully connected layer 2 in the CNN model in sequence. The details are as follows: Input layer: The model structure layer that the input raster map first passes through. The size of the raster map can be adjusted according to the scene adaptability, and this application does not limit it.
[0039] Convolutional layer 1: uses 32 3*3 convolution kernels, the activation function is ReLU, and the output feature map size is 30*30*32.
[0040] Pooling layer 1: Use 2*2 maximum pooling, and the output feature map size is 15*15*32.
[0041] Convolutional layer 2: uses 64 3*3 convolution kernels, the activation function is ReLU, and the output feature map size is 13*13*64.
[0042] Pooling layer 2: Use 2*2 maximum pooling, and the output feature map size is 6*6*64.
[0043] Fully connected layer 1: Flattens the output of pooling layer 2 into a 2304-dimensional vector, processes it using 512 neurons, and uses ReLU as the activation function.
[0044] Fully connected layer 2: As the output layer, it outputs the movement strategy including the movement path of each logistics object.
[0045] The prediction model can predict multiple movement strategies, but the target movement strategy is the output. Compared to other movement strategies, the target movement strategy minimizes the sum of the grid status values of all grids passing through the movement paths corresponding to all logistics objects. This is because the smaller the grid status value, the less likely the corresponding grid is to be occupied. Even if it is occupied, its occupancy rate is higher, thus ensuring that each logistics object can move smoothly to its designated location. Although the movement path of the designated object in this embodiment is not the shortest path, it is the most feasible path that can maximize the guarantee of the smooth movement of the designated logistics object to the designated location, thus improving the practicality of the movement strategy.
[0046] This embodiment uses real-time scene data to generate a grid map representing the real-time scene route, and inputs the grid map into a prediction model to obtain a target movement strategy that includes a target movement path representing the movement of a specified logistics object to a specified location. This embodiment focuses on grid occupancy and digitizes the grid occupancy to obtain a grid state value for each grid to reflect its inversely proportional occupancy release rate. The sum of the grid state values of the grids in the movement paths corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid state values in all movement strategies, thereby maximizing the feasibility of the movement of each logistics object in the target movement strategy, thereby maximizing the smooth movement of the specified logistics object to the specified location, and improving the practicality of the movement strategy.
[0047] In another exemplary embodiment of the present application, a detailed description is given of how to generate a grid map representing the current scene line based on the current scene data. For details, please refer to Figure 3 , Figure 3 is based on Figure 1 The exemplary embodiment shown is a flow chart of another method for planning a logistics path. Figure 1 The illustrated S110 includes S310 to S330; wherein the current scene data includes different types of scene data, which are described in detail as follows: S310: For each type of scene data, determine the corresponding maximum scene data and minimum scene data, and calculate the data difference between the corresponding maximum scene data and the corresponding minimum scene data to obtain the data difference corresponding to each type of scene data.
[0048] This embodiment processes different types of scene data one by one to unify the dimensions of different types of scene data, thereby facilitating data aggregation and data processing and analysis. For each type of scene data, a standard metric for each type of scene data is determined based on the maximum scene data and the minimum scene data.
[0049] S320: performing a quotient operation on the difference between each scene data in each type of scene data and the corresponding minimum scene data and the corresponding data difference, and taking each quotient value as the data value corresponding to the corresponding scene data to obtain all data values corresponding to each type of scene data.
[0050] The minimum scene data is used as the lower limit value to calculate the difference between each scene data and the lower limit value, and then the difference is divided by the standard metric to calculate the corresponding data value, thereby obtaining all data values corresponding to each type of scene data.
[0051] S330: Generate a grid map representing the current scene route according to data values corresponding to all types of scene data.
[0052] Because the data values corresponding to different types of scene data have the same dimension and are all normalized within the range of [0, 1], the convergence speed of the prediction model can be improved, and the data processing can be more standardized, so that the grid state value of each grid in the generated grid map is within [0, 1].
[0053] In another exemplary embodiment of the present application, a detailed description is given of how to generate a grid map representing the current scene line based on the current scene data. For details, please refer to Figure 4 , Figure 4 is based on Figure 1 The exemplary embodiment shown is a flow chart of another method for planning a logistics path. Figure 1 The illustrated S110 includes S410 to S420; wherein the current scene data includes the current position of each logistics object, the current obstacle position, and the current environment data, which are described in detail as follows: S410: Generate an initial grid map based on the current location data of each logistics object, the current obstacle location data, and the current environment data.
[0054] The initial grid map is a map that represents the spatial location of each logistics object, obstacle, and the current scene environment. The initial grid map is divided into multiple grids.
[0055] S420: Assigning a grid state value of each grid in the initial grid map according to a preset assignment strategy to obtain a grid map representing the current scene route.
[0056] The default assignment strategy represents the strategy for assigning grid status values to grids, and the assignment is based on the grid's occupancy. For example, the grid status value representing vacancy is scored from 0 to 0.25, the grid status value representing the occupation of a logistics object is scored from 0.25 to 0.5, the grid status value representing the occupation of a temporarily removable obstacle is scored from 0.5 to 0.75, and the grid status value representing the occupation of a temporarily non-removable obstacle is scored from 0.75 to 1.
[0057] In another exemplary embodiment of the present application, it is described in detail how to assign the grid state value of each grid in the initial grid map according to the preset assignment strategy. For details, please refer to Figure 5 , Figure 5 is based on Figure 4 The exemplary embodiment shown is a flow chart of another method for planning a logistics path. Figure 4 The illustrated S420 includes S510 to S520, which are described in detail as follows: S510: traverse each grid in the initial grid map, and use the traversed grid as the target grid.
[0058] By traversing each grid, it is ensured that each grid is analyzed and processed accurately without omission.
[0059] S520: Determine the grid state value of the target grid according to the matching between the occupancy status of the target grid and the preset occupancy status, so as to obtain the grid state value of each grid.
[0060] Through a simple occupancy matching method, the grid state value of the target grid is quickly determined, thereby quickly determining the grid state value of each grid.
[0061] Exemplarily, different preset occupancy conditions correspond to different grid state values. If the occupancy of the target grid matches the occupancy of the logistics object, the grid state value of the target grid is determined to be a first grid state value; if the occupancy of the target grid matches the occupancy of the obstacle, the grid state value of the target grid is determined to be a second grid state value; wherein the first grid state value is less than the second grid state value. The preset occupancy conditions include the occupancy of the logistics object and the occupancy of the obstacle. The first grid state value is a state value that represents the grid occupied by the logistics object. The second grid state value is a state value that represents the grid occupied by the obstacle. Logistics objects are essentially movable objects, meaning that their grid occupancy can change. As the logistics object moves, its current grid occupancy is subsequently released. Obstacles do not necessarily move, and their occupancy of the occupied grid is less variable. In summary, the occupancy release rate of the grid occupied by the logistics object is greater than the occupancy release rate of the grid occupied by the obstacle, resulting in the first grid state value being less than the second grid state value.
[0062] In some embodiments, there are two types of obstacle occupancy: temporary occupation, which can be subsequently released; and persistent occupation, which cannot be released. The corresponding second grid status value includes two status values: a grid status value indicating that the obstacle is temporarily occupied and can be released, and a grid status value indicating that the obstacle is continuously occupied.
[0063] In another exemplary embodiment of the present application, how to update the prediction model is described in detail. Figure 6 , Figure 6 is based on Figure 1 、 Figure 3 、 Figure 4 A flow chart of another logistics route planning method is shown in any of the exemplary embodiments shown in FIG. The planning method further includes S610 to S620, which are described in detail as follows: S610: Move each logistics object based on the target movement strategy, and collect the actual movement trajectory of each logistics object.
[0064] The target movement strategy includes the predicted movement trajectory of each logistics object.
[0065] S620: Determine a path error value based on the moving path of each logistics object in the target moving strategy and the corresponding actual moving trajectory to determine whether to update the prediction model.
[0066] This embodiment collects the actual movement trajectories of each logistics object in a real-world scenario and performs error analysis on each actual movement trajectory compared to the corresponding movement trajectory in the target movement strategy. This determines multiple error values, i.e., the error values corresponding to multiple logistics objects. Based on these error values, it is determined whether to update the prediction model. Methods for updating the prediction model include increasing the amount of data, enhancing data strength (performing operations such as rotation, translation, and scaling on input data to increase data diversity and improve the model's generalization capabilities), and adjusting model results (for example, increasing the number of convolutional or fully connected layers). The Adam optimizer can also be used to update the weights and biases of the prediction model, minimizing the loss function until the prediction model converges or reaches a predetermined number of training epochs. After every 10 training epochs, the learning rate is reduced to 90% of the original value.
[0067] For example, the difference between the movement path of each logistics object in the target movement strategy and the corresponding actual movement trajectory is calculated to obtain multiple trajectory difference values. The squares of each trajectory difference value are summed and the calculated sum is divided by the total number of logistics objects to obtain the path error value. If the path error value is greater than the preset error value, the prediction model is updated.
[0068] For example, in the target movement strategy, the movement trajectory of logistics object A is a, the movement trajectory of logistics object B is b, and the movement trajectory of logistics object C is c; the actual movement trajectory of logistics object A is a', the actual movement trajectory of logistics object B is b', and the actual movement trajectory of logistics object C is c'. The calculated differences between the three trajectories are a-a', b-b', and c-c', respectively. The path error value is [(a-a') 2 + (b-b') 2 + (c-c') 2 ] / 3.
[0069] In another exemplary embodiment of the present application, the application scenarios of the above-mentioned multiple planning methods are exemplarily described. Figure 7 , Figure 7 This is a schematic diagram of a workshop scenario for the logistics path planning method of the present application. It includes a user terminal 100, a workshop data acquisition device 200, and a server 300. The three terminals can be connected via wireless communication, and this application does not limit the connection method between them.
[0070] The user sends a logistics instruction to the server 300 through the user terminal 100, and the workshop data collection device 200 can send the real-time collected workshop scene data to the server 300. The server 300 serves as the execution subject of the planning method shown in any of the above exemplary embodiments to execute any of the above planning methods, as shown in the following exemplary embodiments: The server 300 responds to the logistics instruction and generates a grid map representing the current scene route based on the current scene data; wherein the logistics instruction is an instruction representing the movement of a specified logistics object to a specified location; the grid map includes grid status values representing the occupancy status of each grid, and the size of the grid status value is inversely proportional to the occupancy release rate; the server 300 inputs the grid map into the prediction model to obtain the target movement strategy to determine the target movement path representing the movement of the specified logistics object to the specified location; wherein, the sum of the grid status values passing through the grids in the movement paths corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid status values in all movement strategies.
[0071] Server 300 can be an independent physical server or a server cluster or distributed system composed of multiple physical servers, where multiple servers can form a blockchain, and the server is a node on the blockchain. Server 300 can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, and this is not restricted here.
[0072] Another aspect of the present application also provides a logistics path planning device, such as Figure 8 As shown, Figure 8 Schematic diagram of a logistics path planning device according to an exemplary embodiment of the present application. The planning device 800 includes: The response module 810 is used to respond to the logistics instruction and generate a grid map representing the current scene route based on the current scene data; wherein the logistics instruction is an instruction to move the specified logistics object to the specified location; the grid map includes a grid status value representing the occupancy status of each grid, and the size of the grid status value is inversely proportional to the occupancy release rate.
[0073] Determination module 830 is used to input the grid map into the prediction model to obtain the target movement strategy to determine the target movement path representing the movement of the specified logistics object to the specified location; wherein, the sum of the grid state values passing through the grid in the movement path corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid state values in all movement strategies.
[0074] In another exemplary embodiment, the current scene data includes different types of scene data; the response module 810 includes: The first calculation unit is used to determine the corresponding maximum scene data and minimum scene data for each type of scene data, and calculate the data difference between the corresponding maximum scene data and the corresponding minimum scene data to obtain the data difference corresponding to each type of scene data.
[0075] The second calculation unit is used to calculate the quotient of the difference between each scene data in each type of scene data and the corresponding minimum scene data with the corresponding data difference, and use each quotient value as the data value corresponding to the corresponding scene data to obtain all data values corresponding to each type of scene data.
[0076] The generation unit is used to generate a grid map representing the current scene route according to the data values corresponding to all types of scene data.
[0077] In another exemplary embodiment, the current scene data includes the current position of each logistics object, the current obstacle position, and the current environment data; the response module 810 includes: The initial grid map generating unit is used to generate an initial grid map according to the current position data of each logistics object, the current obstacle position data and the current environment data.
[0078] The grid map generating unit is used to assign a grid state value of each grid in the initial grid map according to a preset assignment strategy to obtain a grid map representing the current scene route.
[0079] In another exemplary embodiment, the grid map generation unit includes: The traversal section is used to traverse each grid in the initial grid map and use the traversed grid as the target grid.
[0080] The determination section is used to determine the grid state value of the target grid according to the matching between the occupancy status of the target grid and the preset occupancy status, so as to obtain the grid state value of each grid.
[0081] In another exemplary embodiment, the preset occupancy status includes the occupancy status of the logistics object and the occupancy status of the obstacle; and the determination section includes: The matching sub-module is used to determine the grid state value of the target grid to be a first grid state value if the occupancy status of the target grid matches the occupancy status of the logistics object. Alternatively, the determining sub-module is used to determine the grid state value of the target grid to be a second grid state value if the occupancy status of the target grid matches the occupancy status of the obstacle; wherein the first grid state value is less than the second grid state value.
[0082] In another exemplary embodiment, the planning device 800 further includes: The acquisition module is used to move each logistics object based on the target movement strategy and collect the actual movement trajectory of each logistics object.
[0083] The update module is used to determine the path error value based on the moving path of each logistics object in the target movement strategy and the corresponding actual movement trajectory to determine whether to update the prediction model.
[0084] In another exemplary embodiment, the update module includes: The trajectory output value calculation unit is used to calculate the trajectory difference between the moving path of each logistics object in the target movement strategy and the corresponding actual movement trajectory, and obtain multiple trajectory differences.
[0085] The path error value calculation unit is used to sum the square values of each trajectory difference and divide the calculated sum by the total number of logistics objects to obtain the path error value.
[0086] The planning device of the present application generates a grid map representing the real-time scene route through real-time scene data, and inputs the grid map into the prediction model to obtain a target movement strategy including a target movement path representing the movement of a specified logistics object to a specified location. The planning device of the present application focuses on the grid occupancy and digitizes the grid occupancy to obtain a grid state value for each grid to reflect its inversely proportional occupancy release rate; wherein, the sum of the grid state values of the grids in the movement paths corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid state values in all movement strategies, so as to maximize the feasibility of the movement of each logistics object in the target movement strategy, thereby maximizing the guarantee that the specified logistics object can be smoothly moved to the specified location, thereby improving the practicality of the movement strategy.
[0087] It should be noted that the planning device provided in the above embodiment and the planning method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here.
[0088] Another aspect of the present application provides an electronic device, comprising: a controller; and a memory for storing one or more programs, which, when executed by the controller, executes the above-mentioned planning method.
[0089] See also Figure 9 , Figure 9 1 is a structural diagram of a computer system of an electronic device shown in an exemplary embodiment of the present application, which shows a structural diagram of a computer system of an electronic device suitable for implementing an embodiment of the present application.
[0090] It should be noted that Figure 9 The computer system 900 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0091] like Figure 9 As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 902 or the program loaded from the storage part 908 into the random access memory (RAM) 903, such as executing the method in the above embodiment. Various programs and data required for system operation are also stored in the RAM 903. The CPU 901, ROM 902 and RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.
[0092] The following components are connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, and the like; an output section 907 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. Removable media 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like, are installed in the drive 910 as needed, so that computer programs read therefrom can be installed into the storage section 908 as needed.
[0093] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 909, and / or installed from a removable medium 911. When the computer program is executed by the central processing unit (CPU) 901, the various functions defined in the system of the present application are executed.
[0094] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.
[0095] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0096] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.
[0097] Another aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned planning method. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device.
[0098] Another aspect of the present application further provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the planning method provided in each of the above embodiments.
[0099] According to one aspect of an embodiment of the present application, a computer system is further provided, including a central processing unit (CPU), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage portion into a random access memory (RAM), such as executing the method in the above embodiment. Various programs and data required for system operation are also stored in the RAM. The CPU, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.
[0100] The following components are connected to the I / O interface: an input section including a keyboard, mouse, etc.; an output section including a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section including a hard disk; and a communication section including a network interface card such as a LAN (Local Area Network) card and a modem. The communication section performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. Removable media such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, etc. are installed in the drive as needed so that computer programs read from them can be installed into the storage section as needed.
[0101] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. Ordinary technicians in this field can easily make corresponding changes or modifications based on the main ideas and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.
Claims
1. A logistics path planning method, characterized in that: The planning method includes: In response to a logistics instruction, a grid map representing the current scene route is generated based on the current scene data; wherein the logistics instruction is an instruction to move a specified logistics object to a specified location; the grid map includes a grid state value representing the occupancy status of each grid, and the magnitude of the grid state value is inversely proportional to the occupancy release rate; The grid map is input into the prediction model to obtain a target movement strategy to determine the target movement path representing the movement of the specified logistics object to the specified location; wherein the sum of the grid state values passing through the grid in the movement path corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid state values in all movement strategies.
2. The planning method according to claim 1, characterized in that: The current scene data includes different types of scene data; The step of generating a grid map representing the current scene route according to the current scene data includes: For each type of scene data, determining the corresponding maximum scene data and minimum scene data, and calculating the data difference between the corresponding maximum scene data and the corresponding minimum scene data to obtain the data difference corresponding to each type of scene data; Performing a quotient operation on the difference between each scene data in each type of scene data and the corresponding minimum scene data and the corresponding data difference, and taking each quotient value as the data value corresponding to the corresponding scene data, so as to obtain all data values corresponding to each type of scene data; Based on the data values corresponding to all types of scene data, a grid map representing the current scene line is generated.
3. The planning method according to claim 1, characterized in that: The current scene data includes the current position of each logistics object, the current obstacle position and the current environment data; The step of generating a grid map representing the current scene route according to the current scene data includes: Generate an initial grid map based on the current location data of each logistics object, the current obstacle location data and the current environment data; According to a preset assignment strategy, the grid state value of each grid in the initial grid map is assigned to obtain a grid map representing the current scene route.
4. The planning method according to claim 3, characterized in that: The step of assigning a value to a grid state value of each grid in the initial grid map according to a preset assignment strategy includes: Traversing each grid in the initial grid map and using the traversed grid as the target grid; According to the matching condition between the occupancy condition of the target grid and the preset occupancy condition, the grid state value of the target grid is determined to obtain the grid state value of each grid.
5. The planning method according to claim 4, characterized in that: The preset occupancy status includes the occupancy status of the logistics object and the occupancy status of the obstacle; the grid state value of the target grid is determined based on the matching between the occupancy status of the target grid and the preset occupancy status, including: If the occupancy status of the target grid matches the occupancy status of the logistics object, determining the grid state value of the target grid to be a first grid state value; If the occupancy status of the target grid matches the occupancy status of the obstacle, determining the grid state value of the target grid to be a second grid state value; wherein the first grid state value is less than the second grid state value.
6. The planning method according to any one of claims 1 to 5, characterized in that: The planning method further comprises: Moving each logistics object based on the target movement strategy and collecting the actual movement trajectory of each logistics object; According to the moving path of each logistics object in the target movement strategy and the corresponding actual movement trajectory, a path error value is determined to determine whether to update the prediction model.
7. The planning method according to claim 6, characterized in that: The determining of the path error value according to the moving path of each logistics object in the target moving strategy and the corresponding actual moving trajectory includes: Calculating the trajectory difference between the moving path of each logistics object in the target movement strategy and the corresponding actual moving trajectory to obtain multiple trajectory differences; The square values of the trajectory differences are summed and the calculated sum is divided by the total number of logistics objects to obtain the path error value.
8. A logistics route planning device, characterized in that: The planning device comprises: a response module, configured to generate a grid map representing the current scene route in response to a logistics instruction based on current scene data; wherein the logistics instruction is an instruction to move a specified logistics object to a specified location; the grid map includes a grid state value representing the occupancy status of each grid, wherein the magnitude of the grid state value is inversely proportional to the occupancy release rate; A determination module is used to input the grid map into a prediction model to obtain a target movement strategy to determine a target movement path representing the movement of the specified logistics object to the specified location; wherein the sum of the grid state values passing through the grid in the movement path corresponding to all logistics objects in the target movement strategy is the minimum value of the sum of the grid state values in all movement strategies.
9. An electronic device, characterized in that: include: Controller; A memory for storing one or more programs, which, when executed by a controller, enables the controller to implement the planning method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that Computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the planning method according to any one of claims 1 to 7.