Drone Path Planning Method and System Based on Intelligent Logistics Lockers

Abstract

The present application provides a method and system for UAV path planning based on an intelligent logistics cabinet, which relates to the field of logistics planning. The UAV path planning method includes: obtaining a delivery task set, and calculating the total travel time corresponding to all delivery tasks in the delivery task set to determine a scheduling time range; grouping the delivery task set to obtain multiple task groups; configuring constraint conditions for modeling; introducing binary variables and using the time-expanded network method to introduce the time dimension to construct an objective programming model; and solving the objective programming model through a preset solver. By discretizing time, the present application transforms a dynamic problem into a static network problem, making the problem more intuitive and easy to understand and analyze. The objective programming model is easy to expand and can transform problems that are difficult to model with a continuous-time model into problems that can be modeled, realizing the modeling and solution of complex problems.

Description

Technical Field

[0001] The present application relates to the technical field of logistics planning, and particularly to an unmanned aerial vehicle (UAV) path planning method and system based on an intelligent logistics cabinet. Background Art

[0002] With the development of intelligent logistics and UAV technology, driven by multiple factors such as a sharp increase in distribution demand, soaring labor costs, and complex service scenarios, UAVs have gradually become an indispensable infrastructure in modern logistics, helping the logistics industry achieve leapfrog development. Currently, a new UAV distribution method based on intelligent logistics cabinets is emerging. As a "contactless" distribution method, the collaborative distribution of logistics cabinets and UAVs can effectively respond to emergencies. For example, during the epidemic, it can effectively reduce contact between people.

[0003] In related technologies, an automated device for loading and unloading packages is provided on the top of the logistics cabinet, which serves as a take-off and landing platform for UAVs. The UAV automatically completes the loading of packages on the top of the logistics cabinet, and automatically completes the unloading of packages and the replenishment of electric energy after flying to the top of the designated logistics cabinet. The UAV distribution based on intelligent logistics cabinets is a highly automated process. The UAV performs distribution tasks by flying between different logistics cabinets while carrying packages. The efficiency of the entire distribution process depends on the path planning of the UAV.

[0004] However, currently, to plan the UAV distribution driving path, it is necessary to establish a task index to analyze the UAV task scheduling process. The entire modeling process is complex and difficult to solve. Therefore, there is an urgent need for a better path planning method to improve the efficiency of the collaborative distribution of logistics cabinets and UAVs. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present application provides a UAV path planning method and system based on an intelligent logistics cabinet, which solves the problem that it is difficult to model and solve complex problems when planning the path of the collaborative distribution of logistics cabinets and UAVs.

[0006] To achieve the above objectives, the present application is implemented through the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a UAV path planning method based on an intelligent logistics cabinet. The UAV path planning method includes: obtaining a distribution task set, and calculating the total travel time corresponding to all distribution tasks in the distribution task set to determine the scheduling time range;

[0008] Group the distribution task set to obtain multiple task groups, where the starting logistics cabinet and the ending logistics cabinet of the distribution tasks in the same task group are the same; configure the constraint conditions for modeling, and the constraint conditions include objective constraints, time constraints, path constraints, task constraints, variable constraints, and take-off and landing constraints that characterize the completion time; with the goal of minimizing the completion time, introduce binary variables and use the time-expanded network method to introduce the time dimension to construct an objective programming model, so as to transform the UAV task scheduling process into an arc selection process in the time-expanded network; solve the objective programming model through a preset solver to obtain multiple flight arcs and hold arcs, so as to determine the path planning network for the UAV to perform distribution tasks among multiple intelligent logistics cabinets.

[0009] According to the first aspect of the embodiments of the present application, the foregoing steps of introducing binary variables and using the time-expanded network method to introduce the time dimension to construct an objective programming model with the goal of minimizing the completion time may specifically include the following steps: discretize the scheduling time range into multiple time points with a sufficiently small and equal interval; create nodes based on each logistics cabinet and each time point to obtain multiple nodes connected by arcs; for each time point, create a hold arc for each logistics cabinet, and create a flight arc between one logistics cabinet and another logistics cabinet to represent the flight path of the UAV from one logistics cabinet to another logistics cabinet; both the flight arc and the hold arc correspond to a head node and a tail node; introduce binary variables to represent whether each arc is selected. When the introduced binary variable is, it means that the arc is selected, represents the index of the arc, is the set of all arcs. When is, it means that the arc is not selected.

[0010] According to the first aspect of the embodiments of the present application, the foregoing steps of solving the objective programming model through a preset solver to obtain multiple flight arcs and hold arcs to determine the path planning network for the UAV to perform distribution tasks among multiple intelligent logistics cabinets may specifically include the following steps: in the case of selecting the flight arc , based on the preset first strategy and second strategy, map the hold arcs to each flight arc, and select multiple pre-hold arcs connected to the head node of the flight arc , and multiple post-hold arcs connected to the tail node of the arc ; is the set of flight arcs, represents the index of the arc.

[0011] The first strategy includes: for the flight arc , append a set of pre-hold arcs . In the case of selecting the arc , from Determine the corresponding holding arc to characterize the take-off action of the UAV on the corresponding logistics cabinet;

[0012] The second strategy includes: Add a set of subsequent holding arcs In the case of selecting an arc Determine the corresponding holding arc from To characterize the landing action of the UAV on the corresponding logistics cabinet.

[0013] According to the first aspect of the embodiments of the present application, for the time point If there exists a time point Such that Then create a flight arc And Between, where Indicates the flight time of the UAV from To To ; Represents the starting logistics cabinet, Represents the ending logistics cabinet, , , Is the set of logistics cabinets;

[0014] The path planning network satisfies the expression: Where Is the path planning network, Represents the set of nodes, Represents the set of arcs, And Respectively represent the sets of holding arcs and flight arcs.

[0015] According to the first aspect of the embodiments of the present application, the completion times of multiple task groups include the take-off action preparation time and the landing action preparation time of the UAV; when the number of flight arcs configured from the starting logistics cabinet to the ending logistics cabinet is greater than or equal to the number of tasks in the task group, it is determined that all tasks can be executed;

[0016] The target constraint satisfies the expression: Where Represents the longest time required for all UAVs to complete their assigned tasks;

[0017] The time constraint satisfies the expression:

[0018]

[0019] In the formula, Is the tail node of the arc , For a node at the corresponding time point and used to represent the UAV at the node where the corresponding logistics cabinet completes the landing time, is a binary variable, indicating the preparation time required to complete a flight operation, corresponding to the flight arc to represent the UAV performing the corresponding flight operation; the time constraint ensures is at least as long as the completion time of any selected flight arc .

[0020] According to the first aspect of the embodiments of the present application, the path constraints include the first path constraint, the second path constraint, the third path constraint, and the fourth path constraint;

[0021] The first path constraint satisfies the expression:

[0022]

[0023] In the formula, represents a node, and represents the UAV starting node, , represents the index of the UAV, represents the logistics cabinet where the UAV initially docks, is the set of UAVs, represents all the arcs flowing out of the node ; the first path constraint is used to ensure that each UAV starts to execute the task with the logistics cabinet where it initially docks as the starting node;

[0024] The second path constraint satisfies the expression:

[0025]

[0026] In the formula, represents the set of arcs flowing into the node , , represents the set of intermediate nodes except the source node and the precipitation node ; the second path constraint is used to ensure that for each intermediate node , the number of arcs flowing into it must be equal to the number of arcs flowing out, that is, the UAV must leave after arriving at an intermediate node, ensuring the conservation of the number of UAVs; , its inflowing arc number must be equal to the outflow arc number, that is, the UAV must leave after arriving at an intermediate node, ensuring the conservation of the number of UAVs;

[0027] The third path constraint satisfies the expression:

[0028]

[0029] The third path constraint is used to ensure that for each intermediate node , at most one incoming arc is selected, ensuring that the UAV can only select one path to execute at any intermediate node, avoiding multiple paths to ensure the uniqueness and certainty of the path;

[0030] The fourth path constraint satisfies the expression:

[0031]

[0032] The fourth path constraint is used to ensure that the UAV finally flows into the sedimentation node and ends its flight action, and ensures that the number of all arcs flowing into the sedimentation node must be equal to the total number of UAVs, and enables each UAV to be effectively scheduled.

[0033] According to the first aspect of the embodiments of the present application, the variable constraint is used to define the value range of the variable and satisfies the expression:

[0034]

[0035]

[0036] Among them, , , are all binary variables, represents an arc, represents a set of arcs, corresponds to the hold arc to represent that the UAV stays on the corresponding logistics cabinet for a period of time;

[0037] The task constraint satisfies the expression:

[0038]

[0039] In the formula, represents a task group, represents the task group corresponding arc set, represents the set of all task groups, represents the number of tasks in the task group; the task constraint is used to ensure that the number of selected flight arcs in each task group is at least equal to the number of tasks in each task group to ensure that all tasks are executed.

[0040] According to the first aspect of the embodiments of the present application, the take-off and landing constraints include a first take-off and landing constraint and a second take-off and landing constraint; wherein, the first take-off and landing constraint is used to determine that if a flight arc is selected, an additional holding arc must be selected to ensure that the take-off and landing actions must be carried out together with the execution of the flight segment; the first take-off and landing constraint satisfies the expression:

[0041]

[0042]

[0043]

[0044] In the formula, , and are binary variables, indicating that they are equal to 1 if the holding arc is selected, otherwise equal to 0; is the set of holding arcs connected to the head node of the flight arc, is the set of holding arcs connected to the tail node of the flight arc; and are used to distinguish the flight arc and the holding arc, and indicate that if the UAV flies, it must be accompanied by take-off and landing actions, is used to distinguish the type of arc, and respectively represent belongs to and ;

[0045] The second take-off and landing constraint is used to determine that at most one preparation action can be carried out on the same holding arc, and the UAV cannot take off and land at the same time to ensure that the model can correctly arrange the take-off and landing sequence of the UAV on the logistics cabinet and avoid docking conflicts, so as to ensure the sequential execution of operations;

[0046] The second take-off and landing constraint satisfies the expression:

[0047] 。

[0048] In the second aspect, the embodiments of the present application provide a UAV path planning system based on an intelligent logistics cabinet. The UAV path planning system includes: an acquisition module, a grouping module, a constraint configuration module, a construction module, and a solution module; wherein,

[0049] The acquisition module is used to acquire a distribution task set and calculate the total travel time corresponding to all distribution tasks in the distribution task set to determine the scheduling time range;

[0050] The grouping module is used to group the distribution task set to obtain multiple task groups, and the starting logistics cabinet and the ending logistics cabinet of the distribution tasks in the same task group are the same;

[0051] The constraint configuration module is used to configure the constraint conditions for modeling. The constraint conditions include objective constraints representing completion time, time constraints, path constraints, task constraints, variable constraints, and takeoff and landing constraints;

[0052] The construction module aims to minimize the completion time, introduce binary variables, and use the time-expanded network method to introduce the time dimension to construct a goal programming model, so as to transform the UAV task scheduling process into an arc selection process in the time-expanded network;

[0053] The solving module is used to solve the goal programming model through a preset solver to obtain multiple flight arcs and holding arcs, so as to determine the path planning network for the UAV to perform distribution tasks among multiple intelligent logistics cabinets.

[0054] In a third aspect, an embodiment of the present application provides an electronic device, which includes: a processor, a memory, and a program stored on the memory and executable on the processor. When the program is executed by the processor, it implements the UAV path planning method based on intelligent logistics cabinets in the foregoing first aspect.

[0055] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by the processor, it implements the UAV path planning method based on intelligent logistics cabinets in the foregoing first aspect.

[0056] The present application provides a UAV path planning method and system based on intelligent logistics cabinets. Compared with the prior art, it has the following beneficial effects:

[0057] The present application analyzes with the goal of minimizing the completion time, introduces binary variables, and uses the time-expanded network method to introduce the time dimension to construct a goal programming model, transforms the task scheduling of the UAV into an arc selection problem in the time-expanded network, and performs task planning based on nodes and arcs without using task UAV indexes or task indexes; by discretizing time, the present application transforms the dynamic problem into a static network problem, making the problem more intuitive and easy to understand and analyze. The goal programming model is easy to expand and can transform problems that are difficult to model with continuous time models into problems that can be modeled, realizing the modeling and solution of complex problems. Description of the Drawings

[0058] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0059] Figure 1 It is a schematic flowchart of a method for unmanned aerial vehicle path planning based on an intelligent logistics cabinet provided by an embodiment of the present application;

[0060] Figure 2 It is a schematic diagram of collaborative distribution between a logistics cabinet and an unmanned aerial vehicle provided by an embodiment of the present application;

[0061] Figure 3 It is a schematic diagram of a time-expanded network provided by an embodiment of the present application;

[0062] Figure 4 It is a schematic structural diagram of a system for unmanned aerial vehicle path planning based on an intelligent logistics cabinet provided by an embodiment of the present application;

[0063] Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0064] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0065] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or sequence between these entities or operations. Moreover, the term "comprising", "including", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article, or device. Without further limitations, the element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or device including the element.

[0066] The embodiments of the present application provide a method and system for path planning of drones based on intelligent lockers, which solve the problem that it is difficult to model and solve complex problems when planning the path of collaborative distribution between lockers and drones.

[0067] To better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0068] First, a method for path planning of drones based on intelligent lockers provided by the embodiments of the present application will be introduced below.

[0069] The flow chart of a method for path planning of drones based on intelligent lockers provided by the embodiments of the present application is shown as Figure 1 shown, and the drone path planning method may include the following steps S110 - S150.

[0070] S110. Obtain a distribution task set, and calculate the total travel time corresponding to all distribution tasks in the distribution task set to determine the scheduling time range. It can be understood that the scheduling time range is , where is the total travel time.

[0071] S120. Group the distribution task set to obtain multiple task groups, and the starting lockers and ending lockers of the distribution tasks in the same task group are the same.

[0072] S130. Configure the constraint conditions for modeling. The constraint conditions include objective constraints, time constraints, path constraints, task constraints, variable constraints, and takeoff and landing constraints that characterize the completion time.

[0073] S140. With the goal of minimizing the completion time, introduce binary variables and use the time - extended network method to introduce the time dimension to construct a goal programming model, so as to transform the drone task scheduling process into an arc selection process in the time - extended network.

[0074] S150. Solve the goal programming model through a preset solver to obtain multiple flight arcs and holding arcs, so as to determine the path planning network for the drone to perform distribution tasks among multiple intelligent lockers.

[0075] The above is the specific implementation manner of a UAV path planning method based on an intelligent logistics cabinet provided by the embodiments of the present application. It should be noted that the time-expanded network is a mathematical tool for modeling and analyzing dynamic networks; by introducing the time dimension, the time-expanded network transforms the changes in the dynamic network into the form of a static network, thus facilitating the application of traditional graph theory methods for analysis and processing. The present application assumes that the UAVs are homogeneous and there is no time window restriction for the tasks, so the construction of the model can be carried out without adding UAV and task indexes.

[0076] It can be understood that the present application analyzes with the goal of minimizing the completion time, introduces binary variables and uses the time-expanded network method to introduce the time dimension to construct a goal programming model, transforms the task scheduling of the UAVs into an arc selection problem in the time-expanded network, and conducts task planning based on nodes and arcs without using task UAV indexes or task indexes; creates a suitable scheduling plan for the UAVs to ensure that all tasks are completed and there is no UAV docking conflict on each logistics cabinet. The goal programming model is a time-expanded network model. By discretizing time, the dynamic problem is transformed into a static network problem, making the problem more intuitive and easier to understand and analyze.

[0077] The present application uses the time-expanded network method to model the UAV path planning based on the intelligent logistics cabinet, which can create a suitable scheduling plan for the UAVs, ensure that all tasks can be executed, and improve the distribution efficiency. The goal programming model is easy to expand. Although the time-expanded network will increase the use of computing resources compared with the continuous time model, the time-expanded network can transform problems that are difficult to model in the continuous time model into problems that can be modeled.

[0078] It should be noted that after establishing the mathematical model of the goal programming model, a solver can be directly used for solving, such as: IBM ILOG CPLEX, Gurobi, OR-Tools, etc. Exemplarily, the present invention can use the IBM PLUG CPLEX software for solving, adopt the Java programming language, and run on a personal computer equipped with an i9-13900k CPU, 64 GB of RAM, and a Windows 10 Professional operating system. Experimental verification shows that the CPLEX solver can find the optimal solution on a certain scale of uniform instances, and the optimal objective values of these instances range from 21 minutes to 91 minutes, with an average of 41 minutes. It proves that the time-expanded network model proposed by the present invention is feasible.

[0079] In an example, the path planning network satisfies the expression:

[0080] , where is the path planning network, represents a set of nodes, represents a set of arcs, and represent the set of holding arcs and the set of flying arcs respectively. It can be understood that the present application transforms the problem of logistics UAV task scheduling into an arc selection problem in a time-expanded network, and the flight path of the UAV between logistics cabinets can be represented by a series of arcs in the network.

[0081] In another example, use to represent a task group, to represent the set of task groups; use and to represent the starting logistics cabinet and the ending logistics cabinet of the task group respectively. If the number of flying arcs from the starting logistics cabinet to the ending logistics cabinet obtained by solving is greater than or equal to the number of tasks in the task group , it means that all tasks can be executed; by using this method, it is not necessary to assign a specific UAV to execute a specified task, and it is only necessary to ensure that the number of arcs obtained by solving meets the task quantity requirement.

[0082] In some embodiments, with the goal of minimizing the completion time, binary variables are introduced and the time-expanded network method is used to introduce the time dimension to construct a goal programming model, so as to transform the UAV task scheduling process into an arc selection process in the time-expanded network. That is, the aforementioned S140 may specifically include the following steps:

[0083] S210. Discretize the scheduling time range into multiple time points with a small enough and equal interval;

[0084] S220. Create nodes based on each logistics cabinet and each time point to obtain multiple nodes connected by arcs;

[0085] S230. For each time point, create a holding arc for each logistics cabinet and create a flying arc between one logistics cabinet and another to represent the flight path of the UAV from one logistics cabinet to another; both the flying arc and the holding arc correspond to a head node and a tail node;

[0086] S240. Introduce binary variables to represent whether each arc is selected. When the introduced binary variable is , it means that the arc represents the index of the arc, is the set of all arcs. When is , it means that the arc

[0087] is not selected. and time point , create a node ; for each time point , for each logistics cabinet create a holding arc ; if this holding arc is subsequently selected, it represents the stay (takeoff or landing) time of the drone above the corresponding logistics cabinet. This application also creates a flight arc between the logistics cabinet and another logistics cabinet .

[0088] In an example, for the time point , if there exists a time point such that , then create a flight arc and between the nodes, where , represents the flight time of the drone from to ; represents the starting logistics cabinet, represents the ending logistics cabinet, , , is the set of logistics cabinets. It can be understood that the flight arc is used to represent the flight path of the drone from one logistics cabinet to another, and so on, to construct the task distribution network.

[0089] Based on this, this application starts from the time-expanded network, creates a series of nodes and arcs, and characterizes the flight path of the drone between the logistics cabinets as a selection problem of a series of nodes and arcs, providing a practical solution to the problem of collaborative distribution between the logistics cabinets and the drone.

[0090] In some embodiments, the completion times of multiple task groups include the preparation time for the takeoff action and the preparation time for the landing action of the drone; when the number of flight arcs configured from the starting logistics cabinet to the ending logistics cabinet is greater than or equal to the number of tasks in the task group, it is determined that all tasks can be executed.

[0091] In the embodiments of this application, it can be understood that since the model objective is to minimize the completion time, the preparation time required for the takeoff and landing actions of the drone must be added to the completion time of the task. Each takeoff or landing requires a preparation time, and this preparation time is set to ; therefore, if the flight arc is selected, then a series of preceding holding arcs connected to the head node of the arc , and a series of subsequent holding arcs connected to the tail node of the arc must be selected.

[0092] In some embodiments, the foregoing target planning model is solved by a preset solver to obtain multiple flight arcs and holding arcs, so as to determine a path planning network for the UAV to perform distribution tasks among multiple intelligent lockers, that is, the foregoing S150 may specifically include the following steps:

[0093] In the case of selecting a flight arc , based on a preset first strategy and second strategy, map the holding arcs to each flight arc, and select multiple preceding holding arcs connected to the head node of the flight arc , and multiple subsequent holding arcs connected to the tail node of the arc ; Let be a set of flight arcs, representing the index of the arc;

[0094] Specifically, the first strategy includes: for the flight arc , append a set of preceding holding arcs , and in the case of selecting the arc , determine the corresponding holding arc from to represent that the UAV performs a take-off action on the corresponding locker.

[0095] The second strategy includes: append a set of subsequent holding arcs to , and in the case of selecting the arc , determine the corresponding holding arc from to represent that the UAV performs a landing action on the corresponding locker.

[0096] In the embodiments of the present application, please refer to Figure 2 and Figure 3 together. It can be understood that in the first strategy, for the flight arc , append a set of preceding holding arcs ;

[0097] ; ;

[0098] If the arc is selected, then the arc in should be selected, indicating that the UAV performs a take-off action on the corresponding locker; represents the head node of the arc , represents the tail node of the arc , and respectively represent the locker and time point at the node .

[0099] In the second strategy, append a set of subsequent holding arcs to :

[0100] ; If an arc is selected , then the arc in should be selected, indicating that the UAV performs a landing action on the corresponding logistics cabinet.

[0101] In some embodiments, the target constraint satisfies the expression: , where represents the longest time required for all UAVs to complete their assigned tasks. It can be understood that the objective of this application is to find a task allocation and scheduling method such that is as small as possible.

[0102] In some embodiments, the aforementioned time constraint satisfies the expression:

[0103]

[0104] In the formula, is the tail node of arc , is the time point corresponding to node and is used to represent the time when the UAV completes landing on the corresponding logistics cabinet , is a binary variable, represents the preparation time required to complete a flight action. In other words, represents the preparation time required for a takeoff action and a landing action of the UAV. corresponds to the flight arc to represent the UAV performing the corresponding flight action; the time constraint ensures that is at least as long as the completion time of any selected flight arc .

[0105] In the embodiments of this application, it can be understood that when , it means that the flight arc is not selected. At this time, is greater than or equal to the preparation time because the holding arc has been created. Even if there is no UAV performing a flight action on the corresponding logistics cabinet, the preparation time always exists. It is only when the flight arc is selected that its corresponding pre-holding arc and post-holding arc need to be selected to represent the takeoff time before the UAV performs the flight task and the landing time after completing a task, respectively.

[0106] In addition, if the flight arc is selected , then the flight arc corresponding to the UAV​ The tail node In the logistics cabinet The time to complete the landing Plus the preparation time Must be less than or equal to the total completion time .

[0107] In some embodiments, the path constraints include a first path constraint, a second path constraint, a third path constraint, and a fourth path constraint;

[0108] The first path constraint satisfies the expression:

[0109]

[0110] Wherein, Represents a node, And represents the drone The starting node of, , Represents the index of the drone, Represents the logistics cabinet where the drone initially docks, Is the set of drones, Represents all out-flow nodes The arc set of; The first path constraint is used to ensure that each drone starts to execute the task with the logistics cabinet where it initially docks as the starting node;

[0111] The second path constraint satisfies the expression:

[0112]

[0113] Wherein, Represents the arc set of the in-flow node Of, , Represents the set of intermediate nodes except the source node And the precipitation node Outside of, Represents the total number of nodes; The second path constraint is used to ensure that for each intermediate node , the number of in-flowing arcs must be equal to the number of out-flowing arcs, that is, the drone must leave after arriving at an intermediate node, ensuring the conservation of the number of drones;

[0114] The third path constraint satisfies the expression:

[0115]

[0116] The third path constraint is used to ensure that for each intermediate node , at most one incoming arc is selected to ensure that the drone can only select one path to execute at any intermediate node, avoiding multiple paths to ensure the uniqueness and certainty of the path;

[0117] The fourth path constraint satisfies the expression:

[0118]

[0119] The fourth path constraint is used to ensure that the drone finally flows into the sedimentation node and ends its flight action, and ensures that the number of all arcs flowing into the sedimentation node must be equal to the total number of drones, and enables each drone to be effectively scheduled.

[0120] In some embodiments, the variable constraint is used to define the value range of the variable and satisfies the expression:

[0121]

[0122]

[0123] Wherein, , , are all binary variables, represents an arc, represents a set of arcs, corresponds to the hold arc to represent that the drone stays on the corresponding logistics cabinet for a period of time.

[0124] The task constraint satisfies the expression:

[0125]

[0126] In the formula, represents a task group, represents the task group corresponding arc set, represents the set of all task groups, represents the number of tasks in the task group; the task constraint is used to ensure that the number of selected flight arcs in each task group is at least equal to the number of tasks in each task group to ensure that all tasks are executed.

[0127] In some embodiments, the takeoff and landing constraint includes a first takeoff and landing constraint and a second takeoff and landing constraint; wherein, the first takeoff and landing constraint is used to determine that if a flight arc is selected, an additional hold arc must be selected to ensure that the takeoff and landing actions must be carried out together with the execution of the flight segment; the first takeoff and landing constraint satisfies the expression:

[0128]

[0129]

[0130]

[0131] Wherein, , and are binary variables, which are equal to 1 if the holding arc is selected, and equal to 0 otherwise; is the set of holding arcs connected to the head node of the flight arc, is the set of holding arcs connected to the tail node of the flight arc; and are used to distinguish the flight arc and the holding arc, and mean that if the UAV flies, it must be accompanied by take-off and landing actions, is used to distinguish the type of arc, and respectively represent belongs to and .

[0132] It can be understood that represents the set of holding arcs before take-off, represents the set of holding arcs after landing. For each flight arc , if it is selected, i.e., , then all the holding arcs related to the flight arc must also be selected, i.e., or , ensuring that the UAV must make necessary stops on the corresponding logistics cabinet before and after performing the task to complete the take-off and landing preparation actions.

[0133] In some embodiments, the second take-off and landing constraint is used to determine that at most one preparation action can be performed on the same holding arc, and the UAV cannot take off and land simultaneously to ensure that the model can correctly arrange the take-off and landing sequence of the UAV on the logistics cabinet, avoid docking conflicts, and thus ensure the sequential operation; the second take-off and landing constraint satisfies the expression: 。

[0134] In some embodiments, the present application provides a UAV path planning system 300 based on an intelligent logistics cabinet. As Figure 4 shown, the UAV path planning system 300 may include the following modules:

[0135] An acquisition module 310, configured to acquire a set of delivery tasks, and calculate the total travel time corresponding to all the delivery tasks in the set of delivery tasks, so as to determine a scheduling time range;

[0136] A grouping module 320, configured to group the set of delivery tasks to obtain a plurality of task groups, where the starting logistics cabinet and the ending logistics cabinet of the delivery tasks in the same task group are the same;

[0137] A constraint configuration module 330, configured to configure constraint conditions for modeling, where the constraint conditions include an objective constraint representing the completion time, a time constraint, a path constraint, a task constraint, a variable constraint, and a takeoff and landing constraint;

[0138] A construction module 340, configured to take minimizing the completion time as an objective, introduce binary variables, and use the time-expanded network method to introduce a time dimension to construct a goal programming model, so as to transform the UAV task scheduling process into an arc selection process in the time-expanded network;

[0139] A solving module 350, configured to solve the goal programming model through a preset solver to obtain a plurality of flight arcs and holding arcs, so as to determine a path planning network for the UAV to perform delivery tasks among a plurality of intelligent logistics cabinets.

[0140] According to an embodiment of the present application, any plurality of the acquisition module 310, the grouping module 320, the constraint configuration module 330, the construction module 340, and the solving module 350 may be combined and implemented in one module, or any one of the modules may be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module.

[0141] In some embodiments, the construction module 340 may specifically be configured to:

[0142] Discretize the scheduling time range into a plurality of time points with a small enough and equal interval;

[0143] Create nodes based on each logistics cabinet and each time point to obtain a plurality of nodes connected by arcs;

[0144] For each time point, create a holding arc for each logistics cabinet, and create a flight arc between one logistics cabinet and another logistics cabinet to represent the flight path of the UAV from one logistics cabinet to another logistics cabinet; both the flight arc and the holding arc correspond to a head node and a tail node;

[0145] Introduce binary variables to represent whether each arc is selected. When the introduced binary variable is, it means that the arc is selected. When is, it means that the arc Not selected.

[0146] In some embodiments, the solving module 350 may specifically be configured to:

[0147] When selecting a flight arc , based on a preset first strategy and second strategy, map the holding arcs to each flight arc, and select multiple preceding holding arcs connected to the head node of the flight arc , and multiple subsequent holding arcs connected to the arc tail node;

[0148] The first strategy includes: for the flight arc , attach a set of preceding holding arcs , and when selecting the arc , determine the corresponding holding arc from to represent that the unmanned aerial vehicle performs a take-off action on the corresponding logistics cabinet;

[0149] The second strategy includes: for , attach a set of subsequent holding arcs , and when selecting the arc , determine the corresponding holding arc from to represent that the unmanned aerial vehicle performs a landing action on the corresponding logistics cabinet.

[0150] Figure 4 Each module in the system shown in

[0151] In some embodiments, the present application provides an electronic device, and the structural schematic diagram of the electronic device is as shown in Figure 5 .

[0152] The electronic device may include a processor 410 and a memory 420 storing computer program instructions.

[0153] Specifically, the above-mentioned processor 410 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0154] The memory 420 may include a mass storage for data or instructions. By way of example and not limitation, the memory 420 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 420 may include removable or non-removable (or fixed) media. Where appropriate, the memory 420 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, the memory 420 is a non-volatile solid-state memory.

[0155] The memory 420 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory 420 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any of the above embodiments of the UAV path planning method based on an intelligent logistics cabinet.

[0156] The processor 410 reads and executes the computer program instructions stored in the memory 420 to implement any of the above embodiments of the UAV path planning method based on an intelligent logistics cabinet.

[0157] In one example, the electronic device may further include a communication interface 430 and a bus 400. Among them, as Figure 5 shown, the processor 410, the memory 420, and the communication interface 430 are connected through the bus 400 and complete communication with each other.

[0158] The communication interface 430 is mainly used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present application.

[0159] The bus 400 includes hardware, software, or both, and couples the components of the online data flow metering device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, the bus 400 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0160] In addition, in combination with the above-described method for path planning of an unmanned aerial vehicle based on an intelligent logistics cabinet in the embodiments, an embodiment of the present application can provide a computer storage medium for implementation. Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by a processor, any one of the above-described methods for path planning of an unmanned aerial vehicle based on an intelligent logistics cabinet is implemented.

[0161] It should be clear that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0162] The functional blocks shown in the above block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave on a transmission medium or a communication link. A "machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, Erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0163] It should also be noted that in the exemplary embodiments mentioned in this application, some methods or systems are described based on a series of steps or devices. However, this application is not limited to the order of the above steps. That is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0164] As described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block in the flowchart and / or block diagram, and the combination of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more blocks of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It is also understood that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can also be implemented by dedicated hardware that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0165] In summary, compared with the prior art, this application has the following beneficial effects:

[0166] 1. This application analyzes with the goal of minimizing the completion time, introduces binary variables and uses the time-expanded network method to introduce the time dimension to construct a goal programming model, transforms the task scheduling of unmanned aerial vehicles (UAVs) into an arc selection problem in the time-expanded network, and conducts task planning based on nodes and arcs without using task UAV indexes or task indexes; creates a suitable scheduling plan for UAVs to ensure that all tasks are completed and there are no UAV docking conflicts on each logistics cabinet.

[0167] 2. The goal programming model is a time-expanded network model. By discretizing time, it transforms the dynamic problem into a static network problem, making the problem more intuitive and easy to understand and analyze. The goal programming model is easy to expand, can adjust the time granularity or add new constraint conditions according to actual needs, and can transform problems that are difficult to model with a continuous-time model into problems that can be modeled, realizing the modeling and solution of complex problems.

[0168] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A drone path planning method based on an intelligent logistics cabinet, characterized in that: include: Obtain a delivery task set, and calculate the total travel time corresponding to all delivery tasks in the delivery task set to determine the scheduling time range; The delivery task set is grouped to obtain a plurality of task groups, wherein the starting point logistics cabinet and the end point logistics cabinet of the delivery tasks in the same task group are the same; configuring constraints for modeling, wherein the constraints include target constraints representing completion time, time constraints, path constraints, task constraints, variable constraints, and takeoff and landing constraints; With the goal of minimizing the completion time, binary variables are introduced and the time dimension is introduced using the time-extended network method to construct a goal programming model, so as to transform the UAV task scheduling process into an arc selection process in the time-extended network. The target planning model is solved by a preset solver to obtain a plurality of flight arcs and holding arcs to determine a path planning network for the drone to perform a delivery task between a plurality of smart logistics cabinets; The path constraints include a first path constraint, a second path constraint, a third path constraint and a fourth path constraint; The first path constraint satisfies the expression: In the formula, Represents a node, And it means drone The starting node of , represents the index of the drone, Indicates the logistics cabinet where the drone initially stops. It is a collection of drones. Represents all outgoing nodes The first path constraint is used to ensure that each drone starts to perform the task with the logistics cabinet where it initially stops as the starting node; The second path constraint satisfies the expression: In the formula, Indicates the inflow node The arc set of , Indicates that except for the source node and precipitation nodes The set of intermediate nodes other than Represents the total number of nodes; the second path constraint is used to ensure that for each intermediate node ,The number of its inflow arcs must be equal to the number of outflow arcs, i.e. the drone must leave after reaching an intermediate node to ensure the conservation of the number of drones; The third path constraint satisfies the expression: The third path constraint is used to ensure that for each intermediate node , at most one arc flowing into it is selected to ensure that the UAV can only choose one path to execute at any intermediate node, avoiding multiple paths to ensure the uniqueness and certainty of the path; The fourth path constraint satisfies the expression: The fourth path constraint is used to ensure that the drone eventually flows into the settling node and ends its flight action, and ensures that the number of arcs flowing into the settling node must be equal to the total number of drones, and that each drone can be effectively scheduled; The variable constraint is used to define the value range of the variable and satisfies the expression: in, , , are binary variables, represents an arc, represents a collection of arcs, The corresponding holding arc indicates that the drone stays on the corresponding logistics cabinet for a period of time; The task constraints satisfy the expression: In the formula, Represents a task group, Represents the task group The corresponding arc set, represents the set of all task groups, Represents the number of tasks in a task group; the task constraint is used to ensure that each task group The number of selected flight arcs is at least equal to the number of each task group The number of tasks to ensure that all tasks are executed; The takeoff and landing constraints include a first takeoff and landing constraint and a second takeoff and landing constraint; wherein the first takeoff and landing constraint is used to determine that if a flight arc is selected, an additional holding arc must be selected to ensure that the takeoff and landing actions must be performed together with the execution flight segment; the first takeoff and landing constraint satisfies the expression: In the formula, , and is a binary variable, indicating that if the arc is maintained If selected, it is equal to 1, otherwise it is equal to 0; is the set of holding arcs connected to the flying arc head node, is the set of holding arcs connected to the tail node of the flight arc; and Used to distinguish between flying arc and holding arc, and This means that if a drone flies, it must take off and land. Used to distinguish the types of arcs, and Respectively belong and ; The second takeoff and landing constraint is used to determine that at most one preparation action can be performed on the same holding arc, and the drone cannot take off and land at the same time to ensure that the model can correctly arrange the takeoff and landing sequence of the drone on the logistics cabinet to avoid docking conflicts, thereby ensuring the order of operations; The second takeoff and landing constraint satisfies the expression: 。 2. The drone path planning method based on the intelligent logistics cabinet according to claim 1 is characterized in that: The goal of minimizing the completion time is to introduce binary variables and use the time extension network method to introduce the time dimension to build a target programming model, including: Discretizing the scheduling time range into a plurality of time points with sufficiently small intervals and equal intervals; Creating a node based on each logistics cabinet and each time point to obtain a plurality of nodes connected by arcs; For each time point, a holding arc is created for each logistics cabinet, and a flight arc is created from one logistics cabinet to another logistics cabinet to represent the flight path of the drone from one logistics cabinet to another logistics cabinet; the flight arc and the holding arc both correspond to a head node and a tail node; Introduce binary variables to represent whether each arc is selected. When Be chosen, represents the index of the arc, is the set of all arcs, when When Not selected.

3. The drone path planning method based on the intelligent logistics cabinet according to claim 1 is characterized in that: The target planning model is solved by a preset solver to obtain a plurality of flight arcs and holding arcs to determine a path planning network for the drone to perform a delivery task between a plurality of smart logistics cabinets, including: When selecting a flight arc In the case of, based on the preset first strategy and second strategy, the holding arc is mapped to each flight arc, and the arc connected to the flight arc is selected. Multiple preceding holding arcs of the head node, and connected to the arcs Multiple subsequent holding arcs of the tail node; is the flight arc set, Represents the index of the arc; The first strategy includes: for the flight arc , add a set of preceding holding arcs , in the selection arc In the case of The corresponding holding arc is determined in order to represent the take-off action of the UAV on the corresponding logistics cabinet; The second strategy includes: Append a set of subsequent hold arcs , in the selection arc In the case of The corresponding holding arc is determined in order to characterize the landing action of the UAV on the corresponding logistics cabinet.

4. The drone path planning method based on the intelligent logistics cabinet according to claim 3 is characterized in that: For time point , if there is a time point , so that , then at the node and Create a flight arc between ,in, Indicates that the drone arrive Flight time; Indicates the starting point logistics cabinet, Indicates the destination logistics cabinet. , , Assemble for logistics cabinets; The path planning network satisfies the expression: ,in, planning a network for the path, Represents a collection of nodes. represents a collection of arcs, and Represent the collection of holding arcs and flying arcs respectively.

5. The drone path planning method based on the intelligent logistics cabinet according to claim 2 is characterized in that: The completion time of the multiple task groups includes the take-off action preparation time and the landing action preparation time of the drone; when the number of configured flight arcs from the starting logistics cabinet to the end logistics cabinet is greater than or equal to the number of tasks in the task group, it is determined that all tasks can be executed; The target constraint satisfies the expression: ,in, represents the maximum time required for all drones to complete their assigned tasks; The time constraint satisfies the expression: In the formula, It is an arc The tail node of For Node The corresponding time point is used to indicate that the drone is at the node Corresponding logistics cabinet The time to complete the landing, is a binary variable, Indicates the preparation time required to complete a flight action. The corresponding flight arc represents the UAV performing the corresponding flight action; the time constraint guarantees At least with any selected flight arc The completion time is the same.

6. A drone path planning system based on intelligent logistics cabinet, characterized in that: include: An acquisition module is used to acquire a delivery task set and calculate the total travel time corresponding to all delivery tasks in the delivery task set to determine a scheduling time range; A grouping module, used for grouping the delivery task set to obtain a plurality of task groups, wherein the starting point logistics cabinet and the end point logistics cabinet of the delivery tasks in the same task group are the same; A constraint configuration module, used to configure constraint conditions for modeling, wherein the constraint conditions include target constraints representing completion time, time constraints, path constraints, task constraints, variable constraints, and takeoff and landing constraints; A building module is used to introduce binary variables and the time dimension using the time-extended network method to construct a goal planning model with the goal of minimizing the completion time, so as to transform the UAV task scheduling process into an arc selection process in the time-extended network; A solving module, used to solve the target planning model through a preset solver to obtain multiple flight arcs and holding arcs to determine a path planning network for the drone to perform a delivery task between multiple smart logistics cabinets; The path constraints include a first path constraint, a second path constraint, a third path constraint and a fourth path constraint; The first path constraint satisfies the expression: In the formula, Represents a node, And it means drone The starting node of , represents the index of the drone, Indicates the logistics cabinet where the drone initially stops. It is a collection of drones. Represents all outgoing nodes The first path constraint is used to ensure that each drone starts to perform the task with the logistics cabinet where it initially stops as the starting node; The second path constraint satisfies the expression: In the formula, Indicates the inflow node The arc set of , Indicates that except for the source node and precipitation nodes The set of intermediate nodes other than Represents the total number of nodes; the second path constraint is used to ensure that for each intermediate node ,The number of its inflow arcs must be equal to the number of outflow arcs, i.e. the drone must leave after reaching an intermediate node to ensure the conservation of the number of drones; The third path constraint satisfies the expression: The third path constraint is used to ensure that for each intermediate node , at most one arc flowing into it is selected to ensure that the UAV can only choose one path to execute at any intermediate node, avoiding multiple paths to ensure the uniqueness and certainty of the path; The fourth path constraint satisfies the expression: The fourth path constraint is used to ensure that the drone eventually flows into the settling node and ends its flight action, and ensures that the number of arcs flowing into the settling node must be equal to the total number of drones, and that each drone can be effectively scheduled; The variable constraint is used to define the value range of the variable and satisfies the expression: in, , , are binary variables, represents an arc, represents a collection of arcs, The corresponding holding arc indicates that the drone stays on the corresponding logistics cabinet for a period of time; The task constraints satisfy the expression: In the formula, Represents a task group, Represents the task group The corresponding arc set, represents the set of all task groups, Represents the number of tasks in a task group; the task constraint is used to ensure that each task group The number of selected flight arcs is at least equal to the number of each task group The number of tasks to ensure that all tasks are executed; The takeoff and landing constraints include a first takeoff and landing constraint and a second takeoff and landing constraint; wherein the first takeoff and landing constraint is used to determine that if a flight arc is selected, an additional holding arc must be selected to ensure that the takeoff and landing actions must be performed together with the execution flight segment; the first takeoff and landing constraint satisfies the expression: In the formula, , and is a binary variable, indicating that if the arc is maintained If selected, it is equal to 1, otherwise it is equal to 0; is the set of holding arcs connected to the flying arc head node, is the set of holding arcs connected to the tail node of the flight arc; and Used to distinguish between flying arc and holding arc, and This means that if a drone flies, it must take off and land. Used to distinguish the types of arcs, and Respectively belong and ; The second takeoff and landing constraint is used to determine that at most one preparation action can be performed on the same holding arc, and the drone cannot take off and land at the same time to ensure that the model can correctly arrange the takeoff and landing sequence of the drone on the logistics cabinet to avoid docking conflicts, thereby ensuring the order of operations; The second takeoff and landing constraint satisfies the expression: 。 7. An electronic device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the method for drone path planning based on a smart logistics cabinet as described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the drone path planning method based on the smart logistics cabinet as described in any one of claims 1 to 5 is implemented.

Images