CN113759959B - Unmanned aerial vehicle path planning method and device for emergency material distribution - Google Patents

Unmanned aerial vehicle path planning method and device for emergency material distribution Download PDF

Info

Publication number
CN113759959B
CN113759959B CN202110839626.1A CN202110839626A CN113759959B CN 113759959 B CN113759959 B CN 113759959B CN 202110839626 A CN202110839626 A CN 202110839626A CN 113759959 B CN113759959 B CN 113759959B
Authority
CN
China
Prior art keywords
uav
drone
disaster relief
node
numbered
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110839626.1A
Other languages
Chinese (zh)
Other versions
CN113759959A (en
Inventor
罗贺
靳鹏
张歆悦
朱默宁
王国强
胡笑旋
马华伟
唐奕城
夏维
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei University of Technology
Original Assignee
Hefei University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hefei University of Technology filed Critical Hefei University of Technology
Priority to CN202110839626.1A priority Critical patent/CN113759959B/en
Publication of CN113759959A publication Critical patent/CN113759959A/en
Application granted granted Critical
Publication of CN113759959B publication Critical patent/CN113759959B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明提供一种针对应急物资配送的无人机路径规划方法和装置，涉及路径规划技术领域。本发明通过异构无人机从多个不同的站点出发为救灾点进行物资配送，能有效缩短完成配送任务的总时间。同时增加时间窗限制，对救援任务紧急的救援点进行优先配送，精准确定物资配送路线，使救援路线的安排更加合理。

Figure 202110839626

The invention provides a UAV path planning method and device for emergency material distribution, and relates to the technical field of path planning. The invention uses heterogeneous drones to start from a plurality of different sites to distribute materials for disaster relief points, which can effectively shorten the total time for completing the distribution task. At the same time, increase the time window limit, prioritize the distribution of emergency rescue points, accurately determine the material distribution route, and make the arrangement of the rescue route more reasonable.

Figure 202110839626

Description

针对应急物资配送的无人机路径规划方法和装置UAV path planning method and device for emergency material distribution

技术领域technical field

本发明涉及路径规划技术领域，具体涉及一种针对应急物资配送的无人机路径规划方法和装置。The invention relates to the technical field of path planning, in particular to a UAV path planning method and device for emergency material distribution.

背景技术Background technique

地震等自然灾害会对人民生命造成很大威胁，如何在第一时间将应急物资配送到需要的人手中，关乎人民的生命安全。由于无人机可以不受地形因素的限制，可以对人力难以到达的地震灾后地区进行物资配送，无人机配送已逐渐应用于地震灾后物资配送工作中，可有效解决灾后物资的配送需求。地震灾害发生后，急需应急物资的救灾点较多，而可用于灾后救援物资配送的无人机数量有限，为了能尽早对救灾点进行应急物资发放，需要对无人机的配送路径进行优化，即在续航能力约束下，以最小的飞行时长将应急物资配送到指定地点。Natural disasters such as earthquakes will pose a great threat to people's lives. How to distribute emergency supplies to those who need them as soon as possible is related to the safety of people's lives. Since UAVs are not limited by terrain factors, they can deliver materials to post-earthquake areas that are difficult to reach by manpower. UAV distribution has been gradually applied to post-earthquake material distribution, which can effectively solve the post-disaster material distribution needs. After an earthquake occurs, there are many disaster relief sites that urgently need emergency supplies, and the number of drones that can be used for post-disaster relief supplies distribution is limited. That is, under the constraint of endurance, the emergency supplies will be delivered to the designated location with the minimum flight time.

然而，在现有技术的无人机配送方法中，同构无人机在续航能力约束下，为救灾点进行配送，单一站点在满足大规模需求中存在难度，不合理的任务路径规划方案，导致不能及时的将物资配送到救灾点，即现有技术的无人机配送方法生成的配送路径会导致配送时间过长。However, in the UAV distribution method of the prior art, the homogeneous UAVs are distributed for disaster relief points under the constraint of endurance, and it is difficult for a single site to meet the large-scale demand, and the unreasonable task path planning scheme, As a result, the materials cannot be delivered to the disaster relief point in time, that is, the delivery route generated by the UAV delivery method in the prior art will lead to too long delivery time.

发明内容SUMMARY OF THE INVENTION

(一)解决的技术问题(1) Technical problems solved

针对现有技术的不足，本发明提供了一种针对应急物资配送的无人机路径规划方法和装置，解决了现有技术的无人机配送方法生成的配送路径会导致配送时间过长的技术问题。In view of the deficiencies of the prior art, the present invention provides a UAV path planning method and device for emergency material distribution, which solves the problem that the distribution path generated by the UAV distribution method in the prior art will lead to too long distribution time. question.

(二)技术方案(2) Technical solutions

为实现以上目的，本发明通过以下技术方案予以实现：To achieve the above purpose, the present invention is achieved through the following technical solutions:

第一方面，本发明提供一种针对应急物资配送的无人机路径规划方法，所述方法包括：In a first aspect, the present invention provides a UAV path planning method for emergency material distribution, the method comprising:

S1、获取救灾点信息、多个站点信息和异构无人机信息；S1. Obtain disaster relief site information, multiple site information and heterogeneous UAV information;

S2、基于救灾点信息、多个站点信息和异构无人机信息，以最小化无人机飞行时长为目标构建多站点带时间窗的多无人机配送模型；S2. Based on disaster relief point information, multiple site information and heterogeneous UAV information, a multi-site multi-UAV distribution model with time windows is constructed with the goal of minimizing UAV flight time;

S3、对多站点带时间窗的多无人机配送模型求解，最优任务路径规划方案。S3. Solve the multi-UAV distribution model with time windows at multiple sites, and plan the optimal mission path.

优选的，所述多站点带时间窗的多无人机配送模型包括目标函数，采用公式(1)来表示：Preferably, the multi-site multi-UAV distribution model with time window includes an objective function, which is expressed by formula (1):

Figure GDA0003758896840000021
Figure GDA0003758896840000021

其中，i和j为节点编号，V为所有节点集合；h为无人机编号，H为无人机集合；

Figure GDA0003758896840000022
为编号为h的无人机从节点i到节点j的飞行时长；
Figure GDA0003758896840000023
为决策变量，编号为h的无人机从节点i到达节点j的路径；Among them, i and j are the node numbers, V is the set of all nodes; h is the drone number, and H is the drone set;
Figure GDA0003758896840000022
is the flight time of the drone numbered h from node i to node j;
Figure GDA0003758896840000023
is the decision variable, the path of the UAV numbered h from node i to node j;

编号为h的无人机从节点i到达节点j的飞行时长

Figure GDA0003758896840000024
通过下式计算得到：The flight time of the drone numbered h from node i to node j
Figure GDA0003758896840000024
It is calculated by the following formula:

Figure GDA0003758896840000025
Figure GDA0003758896840000025

其中，vih为编号为h的无人机的飞行速度；xi为节点i的横坐标，yi为节点i的纵坐标；xj为节点j的横坐标，yj为节点j的纵坐标。Among them, vi h is the flight speed of the UAV numbered h; x i is the abscissa of node i, y i is the ordinate of node i; x j is the abscissa of node j, y j is the ordinate of node j coordinate.

3、如权利要求1所述的针对应急物资配送的无人机路径规划方法，其特征在于，所述多站点带时间窗的多无人机配送模型还包括约束条件，采用公式(3)至(11)来表示：3. The UAV path planning method for emergency material distribution according to claim 1, wherein the multi-site multi-UAV distribution model with time windows further includes constraints, using formula (3) to (11) to represent:

Figure GDA0003758896840000031
Figure GDA0003758896840000031

Figure GDA0003758896840000032
Figure GDA0003758896840000032

Figure GDA0003758896840000033
Figure GDA0003758896840000033

Figure GDA0003758896840000034
Figure GDA0003758896840000034

Figure GDA0003758896840000035
Figure GDA0003758896840000035

Figure GDA0003758896840000036
Figure GDA0003758896840000036

Figure GDA0003758896840000037
Figure GDA0003758896840000037

Figure GDA0003758896840000038
Figure GDA0003758896840000038

Figure GDA0003758896840000039
Figure GDA0003758896840000039

其中：in:

公式(3)表示每个灾民点仅被访问一次；Equation (3) indicates that each disaster site is visited only once;

公式(4)表示各灾民点进出平衡约束Equation (4) expresses the balance constraint on the entry and exit of each disaster-stricken point

公式(5)表示每架无人机仅被使用一次Equation (5) means that each UAV is used only once

公式(6)～(7)表示每架无人机到达灾民点时间和灾民点的开始服务时间之间的关系；Formulas (6) to (7) represent the relationship between the time each drone arrives at the disaster victims’ point and the start time of service at the disaster victims’ point;

公式(7)表示无人机必须在灾民点的服务时间窗内提供服务Equation (7) indicates that the UAV must provide service within the service time window of the disaster victims

公式(8)表示无人机必须在灾民点的服务时间窗内提供服务Equation (8) indicates that the drone must provide service within the service time window of the disaster victims

公式(9)～(10)表示消除子路径，确保无人机的飞行时长不能超过无人机的最大续航时长；Formulas (9) to (10) represent the elimination of sub-paths to ensure that the flight time of the UAV cannot exceed the maximum endurance of the UAV;

公式(11)表示决策变量约束；Formula (11) represents the decision variable constraint;

l、i和j为救灾点编号，V为所有节点集合；D为无人机站点集合，N为救灾点集合；h为无人机编号，H为无人机集合；

Figure GDA0003758896840000041
为编号为h的无人机访问救灾点j后已飞行时长，
Figure GDA0003758896840000042
为编号为h的无人机访问救灾点i后已飞行时长，
Figure GDA0003758896840000043
为编号为h的无人机访问救灾点r后已飞行时长，Sh为编号为h的无人机的续航时间；ei为救灾点i的最早开始服务时间；li为救灾点i的最迟开始服务时间；
Figure GDA0003758896840000044
为编号为h的无人机到达救灾点i的时间；
Figure GDA0003758896840000045
为编号为h的无人机到达救灾点j的时间；
Figure GDA0003758896840000046
为编号为h的无人机到达救灾点i的开始服务的时间；sei为无人机到达救灾点i用于完成任务的时间；
Figure GDA0003758896840000047
为决策变量，编号为h的无人机从节点i到达节点j的路径；
Figure GDA0003758896840000048
为决策变量，编号为h的无人机从节点l到达救灾点i的路径；
Figure GDA0003758896840000049
为决策变量，编号为h的无人机从救灾点i到达节点j的路径；
Figure GDA00037588968400000410
为决策变量，编号为h的无人机从节点r到达节点i的路径；
Figure GDA00037588968400000411
为编号为h的无人机从节点i到节点j的飞行时长；M为正整数。l, i and j are the number of disaster relief points, V is the set of all nodes; D is the set of UAV sites, and N is the set of disaster relief points; h is the number of drones, and H is the set of drones;
Figure GDA0003758896840000041
is the flight time of the drone numbered h after visiting the disaster relief point j,
Figure GDA0003758896840000042
The flight time of the drone numbered h after visiting disaster relief point i,
Figure GDA0003758896840000043
is the flight time of the drone numbered h after visiting the disaster relief point r, S h is the endurance time of the drone numbered h; e i is the earliest service time of the disaster relief point i; l i is the time of the disaster relief point i the latest time to start the service;
Figure GDA0003758896840000044
is the time when the drone numbered h arrives at the disaster relief point i;
Figure GDA0003758896840000045
is the time when the drone numbered h arrives at the disaster relief point j;
Figure GDA0003758896840000046
is the time when the drone numbered h arrives at the disaster relief point i and starts to serve; se i is the time when the drone arrives at the disaster relief point i for completing the task;
Figure GDA0003758896840000047
is the decision variable, the path of the UAV numbered h from node i to node j;
Figure GDA0003758896840000048
is the decision variable, the path of the drone numbered h from node l to disaster relief point i;
Figure GDA0003758896840000049
is the decision variable, the path of the UAV numbered h from the disaster relief point i to the node j;
Figure GDA00037588968400000410
is the decision variable, the path of the UAV numbered h from node r to node i;
Figure GDA00037588968400000411
is the flight duration of the UAV numbered h from node i to node j; M is a positive integer.

优选的，所述S3包括：Preferably, the S3 includes:

S301、基于灾点信息、多个站点信息、异构无人机信息和多站点带时间窗的多无人机配送模型获取无人机配送路径的初始任务路径规划方案集合；S301. Obtain a set of initial mission path planning schemes for the UAV distribution path based on disaster point information, multiple site information, heterogeneous UAV information, and a multi-site multi-UAV distribution model with a time window;

S302、对于生成的初始任务路径规划方案集合，通过引入分段交叉算子和动态插入算子的改进遗传算法进行优化，从而获得对于无人机进行一个或多个救灾点配送服务的最优任务路径规划方案。S302. For the generated initial task path planning scheme set, optimize by introducing an improved genetic algorithm of a segmented crossover operator and a dynamic insertion operator, so as to obtain an optimal task for the UAV to perform the delivery service to one or more disaster relief points Path planning scheme.

优选的，所述S301包括：Preferably, the S301 includes:

S301a、设定编码规则；S301a, set encoding rules;

S301b、基于编码规则生成初始任务路径规划方案集合，包括：S301b, generating an initial task path planning scheme set based on the coding rule, including:

步骤1：将救灾点集合N中的救灾点进行随机排列Nr，形成染色体的第一行编码；Step 1: Randomly arrange N r of the disaster relief points in the disaster relief point set N to form the first line of chromosome coding;

步骤2：针对排列Nr中的每一个客户，从集合H中随机选择无人机进行访问，形成染色体的第二行编码；Step 2: For each customer in the arrangement N r , randomly select drones from the set H to visit, forming the second line of chromosome coding;

步骤3：依据无人机编号选出所访问的救灾点，并按照救灾点的时间窗最早开始访问时间非降序排列，从而得到无人机所访问的救灾点序列Rok；Step 3: Select the disaster relief points visited according to the drone number, and arrange them in non-descending order according to the earliest access time of the time window of the disaster relief point, so as to obtain the disaster relief point sequence Ro k visited by the drone;

步骤4：在每架无人机访问救灾点序列的最前面和最后面加入该无人机对应的站点编号，用来表示无人机的起点，得到了每架无人机访问的救灾点序列Rk；Step 4: Add the site number corresponding to the drone at the front and the back of the sequence of disaster relief points visited by each drone to indicate the starting point of the drone, and obtain the sequence of disaster relief points visited by each drone R k ;

步骤5：根据预设的种群规模Np重复步骤1-4，得到初始种群。Step 5: Repeat steps 1-4 according to the preset population size N p to obtain an initial population.

优选的，所述S302包括：Preferably, the S302 includes:

S302a、设置改进遗传算法的执行参数和以公式(12)作为适应度函数，对每一个初始任务路径规划方案的适应度值进行计算，所述执行参数包括最大迭代次数和交叉概率；S302a, setting the execution parameters of the improved genetic algorithm and using formula (12) as the fitness function, calculate the fitness value of each initial task path planning scheme, and the execution parameters include the maximum number of iterations and the crossover probability;

Figure GDA0003758896840000051
Figure GDA0003758896840000051

S302b、通过轮盘赌选择方法从初始任务路径规划方案集合中选择2个不同的路径规划方案使用分段交叉算子根据交叉概率进行交叉操作，得到2个路径规划方案，适应度值越小的方案被选中概率越大，包括：S302b. Select two different path planning schemes from the initial task path planning scheme set by the roulette selection method, and use the segmented cross operator to perform the crossover operation according to the crossover probability to obtain two path planning schemes, the smaller the fitness value is. The greater the probability of the scheme being selected, including:

S302c、对步骤S302b中得到的路径规划方案进行动态插入操作，得到2个新的路径规划方案；S302c, dynamically inserting the path planning schemes obtained in step S302b to obtain two new path planning schemes;

S302d、重复步骤S302b-S302c，直到达到预设的最大迭代次数，从更新的任务路径规划方案集合中，找到适应度函数值最小的任务路径规划方案，获得无人机进行一个或多个救灾点配送服务的最优任务路径规划方案。S302d, repeating steps S302b-S302c until the preset maximum number of iterations is reached, from the updated set of mission path planning schemes, find the mission path planning scheme with the smallest fitness function value, and obtain one or more disaster relief points for the unmanned aerial vehicle Optimal task routing scheme for delivery service.

优选的，所述S302b包括：Preferably, the S302b includes:

步骤1：通过轮盘赌选择方法从初始任务路径规划方案集合进行选择两条染色体作为父代染色体；Step 1: Select two chromosomes as parent chromosomes from the initial task path planning scheme set by the roulette selection method;

步骤2：根据无人机编号对父代染色体进行分段，每一分段染色体表示一架无人机的任务路径规划方案；Step 2: Segment the parent chromosome according to the drone number, and each segmented chromosome represents the mission path planning scheme of a drone;

步骤3：将两条染色体的一个分段进行单点交叉操作；Step 3: Perform a single-point crossover operation on a segment of two chromosomes;

步骤4：根据无人机数量|H|重复步骤3，直到完成所有分段的交叉操作，并依据无人机编号将分段的染色体进行合并，得到子染色体；Step 4: Repeat step 3 according to the number of drones |H| until the crossover operation of all segments is completed, and merge the segmented chromosomes according to the number of drones to obtain sub-chromosomes;

和/或and / or

所述S302c包括：The S302c includes:

步骤1：如果未配送救灾点集合Nvc不为空集，转步骤2；否则，输出任务路径规划方案；Step 1: If the set of undistributed disaster relief points N vc is not an empty set, go to step 2; otherwise, output the task path planning scheme;

步骤2：从无人机集合H中随机选择无人机h；Step 2: Randomly select the drone h from the set H of drones;

步骤3：判断无人机h是否满足续航约束，如果违反约束转步骤2；否则，转步骤4；Step 3: Determine whether the drone h satisfies the endurance constraint, and if it violates the constraint, go to Step 2; otherwise, go to Step 4;

步骤4：利用公式(13)从Nvc中选出救灾点c；Step 4: Use formula (13) to select disaster relief point c from N vc ;

Figure GDA0003758896840000071
Figure GDA0003758896840000071

其中，ec为救灾点c的最早开始服务时间；

Figure GDA0003758896840000072
为编号为h的无人机到达救灾点c的时间，
Figure GDA0003758896840000073
编号为h的无人机从救灾点u到救灾点c时间；Among them, e c is the earliest service time of disaster relief point c;
Figure GDA0003758896840000072
is the time when the drone numbered h arrives at the disaster relief point c,
Figure GDA0003758896840000073
The time of the drone numbered h from disaster relief point u to disaster relief point c;

步骤5：检验插入救灾点c是否满足约束条件，如果满足则将救灾点c插入当前规划路径Rh中，并从集合Nvc中删除救灾点c，转步骤4；否则，转步骤6；Step 5: Check whether the inserted disaster relief point c satisfies the constraint condition, if so, insert the disaster relief point c into the current planning path R h , and delete the disaster relief point c from the set N vc , go to step 4; otherwise, go to step 6;

步骤6：从无人机集合H中删除无人机h，转步骤1。Step 6: Delete the drone h from the drone set H, and go to Step 1.

第二方面，本发明提供一种针对应急物资配送的无人机路径规划装置，所述装置包括：In a second aspect, the present invention provides a UAV path planning device for emergency material distribution, the device comprising:

信息获取模块，用于获取救灾点信息、多个站点信息和异构无人机信息；Information acquisition module, used to acquire disaster relief site information, multiple site information and heterogeneous UAV information;

模型构建模型，用于基于救灾点信息、多个站点信息和异构无人机信息，以最小化无人机飞行时长为目标构建多站点带时间窗的多无人机配送模型；Model building model, which is used to build a multi-site multi-UAV distribution model with time windows based on disaster relief point information, multiple site information and heterogeneous UAV information with the goal of minimizing UAV flight time;

求解模型，用于对多站点带时间窗的多无人机配送模型求解，最优任务路径规划方案。The solution model is used to solve the multi-site multi-UAV distribution model with time window, and the optimal mission path planning scheme.

第三方面，本发明提供一种计算机可读存储介质，其存储用于针对应急物资配送的无人机路径规划的计算机程序，其中，所述计算机程序使得计算机执行如上述所述的针对应急物资配送的无人机路径规划方法。In a third aspect, the present invention provides a computer-readable storage medium storing a computer program for UAV path planning for emergency material distribution, wherein the computer program causes a computer to execute the above-mentioned emergency material distribution UAV path planning method for delivery.

第四方面，本发明提供一种电子设备，包括：In a fourth aspect, the present invention provides an electronic device, comprising:

一个或多个处理器；one or more processors;

存储器；以及memory; and

一个或多个程序，其中所述一个或多个程序被存储在所述存储器中，并且被配置成由所述一个或多个处理器执行，所述程序包括用于执行如上述所述的针对应急物资配送的无人机路径规划方法。One or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, the programs comprising a UAV path planning method for emergency material distribution.

(三)有益效果(3) Beneficial effects

本发明提供了一种针对应急物资配送的无人机路径规划方法和装置。与现有技术相比，具备以下有益效果：The invention provides a UAV path planning method and device for emergency material distribution. Compared with the prior art, it has the following beneficial effects:

本发明通过异构无人机从多个不同的站点出发为救灾点进行物资，能有效缩短完成配送任务的总时间。同时增加时间窗限制，对救援任务紧急的救援点进行优先配送，精准确定物资配送路线，使救援路线的安排更加合理。The present invention uses heterogeneous drones to start from a plurality of different sites to supply materials for disaster relief points, which can effectively shorten the total time for completing the distribution task. At the same time, increase the time window limit, prioritize the distribution of emergency rescue points, accurately determine the material distribution route, and make the arrangement of the rescue route more reasonable.

附图说明Description of drawings

为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

图1本发明实施例一种针对应急物资配送的无人机路径规划方法的框图；1 is a block diagram of a UAV path planning method for emergency material distribution according to an embodiment of the present invention;

图2为染色体形式示意图；Fig. 2 is a schematic diagram of chromosome form;

图3为初始任务路径规划方案生成过程，图3(a)初始任务路径规划方案生成过程染色体的变化过程示意图，图3(b)为图3(a)对应的路径示意图。Figure 3 shows the generation process of the initial task path planning scheme, Figure 3(a) is a schematic diagram of the change process of chromosomes during the generation process of the initial task path planning scheme, and Figure 3(b) is a schematic diagram of the path corresponding to Figure 3(a).

具体实施方式Detailed ways

为使本发明实施例的目的、技术方案和优点更加清楚，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are described clearly and completely. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the implementations. example. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

本申请实施例通过提供一种针对应急物资配送的无人机路径规划方法和装置，解决了现有技术的无人机配送方法生成的配送路径会导致配送时间过长的技术问题，实现异构无人机从多个不同的站点出发为多个救灾点进行配送服务，缩短配送时间。By providing a UAV path planning method and device for emergency material distribution, the embodiments of the present application solve the technical problem that the distribution path generated by the UAV distribution method in the prior art will lead to too long distribution time, and realize heterogeneous distribution. UAVs start from multiple different sites to provide delivery services for multiple disaster relief points, shortening the delivery time.

本申请实施例中的技术方案为解决上述技术问题，总体思路如下：The technical solutions in the embodiments of the present application are to solve the above-mentioned technical problems, and the general idea is as follows:

现有技术无人机配送中，同构无人机在续航能力约束下，为救灾点进行配送，单一站点在满足大规模需求中存在难度，不合理的任务路径规划方案，可能会违反救灾点的时间窗约束，延迟到达救灾点的时间。针对现有技术的问题，本发明实施例提出一种针对应急物资配送的无人机路径规划方法，该方法通过循环多次迭代的改进方法，针对应急物资的配送任务实现了对异构无人机群进行物资配送任务，增加时间窗限制，更精准得确定应急物资配送路线，缩短了完成配送任务的总时间，降低成本，尽可能提升无人机的工作效用。In the UAV distribution of the existing technology, the homogeneous UAVs are distributed for the disaster relief point under the constraint of endurance. It is difficult for a single site to meet the large-scale demand. Unreasonable task path planning may violate the disaster relief point. time window constraints, delay the time to reach the disaster relief point. In view of the problems in the prior art, the embodiment of the present invention proposes a UAV path planning method for emergency material distribution. This method realizes the heterogeneous unmanned aerial vehicle for the distribution task of emergency materials through the improved method of looping and iterating for many times. The aircraft group carries out material distribution tasks, increases the time window limit, and determines the emergency material distribution route more accurately, which shortens the total time to complete the distribution task, reduces costs, and maximizes the working utility of UAVs.

为了更好的理解上述技术方案，下面将结合说明书附图以及具体的实施方式对上述技术方案进行详细的说明。In order to better understand the above technical solutions, the above technical solutions will be described in detail below with reference to the accompanying drawings and specific embodiments.

本发明实施例提供一种针对应急物资配送的无人机路径规划方法，该方法包括以下步骤：An embodiment of the present invention provides a UAV path planning method for emergency material distribution. The method includes the following steps:

S1、获取救灾点信息、多个站点信息和异构无人机信息；S1. Obtain disaster relief site information, multiple site information and heterogeneous UAV information;

S2、基于救灾点信息、多个站点信息和异构无人机信息，以最小化无人机飞行时长为目标构建多站点带时间窗的多无人机配送模型；S2. Based on disaster relief point information, multiple site information and heterogeneous UAV information, a multi-site multi-UAV distribution model with time windows is constructed with the goal of minimizing UAV flight time;

S3、对多站点带时间窗的多无人机配送模型求解，最优任务路径规划方案。S3. Solve the multi-UAV distribution model with time windows at multiple sites, and plan the optimal mission path.

本发明实施例通过异构无人机从多个不同的站点出发为救灾点进行物资，能有效缩短完成配送任务的总时间。同时增加时间窗限制，对救援任务紧急的救援点进行优先配送，精准确定物资配送路线，使救援路线的安排更加合理。In the embodiment of the present invention, heterogeneous drones are used to deliver supplies to disaster relief sites from a plurality of different sites, which can effectively shorten the total time for completing the distribution task. At the same time, increase the time window limit, prioritize the distribution of emergency rescue points, accurately determine the material distribution route, and make the arrangement of the rescue route more reasonable.

下面对本发明实施例的实施过程进行详细说明：The implementation process of the embodiment of the present invention is described in detail below:

在步骤S1中，获取救灾点信息、多个站点信息和异构无人机信息，具体实施过程如下：In step S1, the disaster relief site information, multiple site information and heterogeneous UAV information are obtained, and the specific implementation process is as follows:

计算机获取救灾点信息、多个站点信息和异构无人机信息。The computer obtains disaster relief site information, multiple site information and heterogeneous UAV information.

救灾点信息包括救灾点的需求及坐标。The disaster relief point information includes the needs and coordinates of the disaster relief point.

多个站点信息包括站点编号、站点坐标和站点数量。Multiple site information includes site number, site coordinates, and number of sites.

异构无人机信息包括无人机的编号、无人机飞行速度和无人机续航能力。Heterogeneous drone information includes the number of the drone, the flight speed of the drone, and the endurance of the drone.

在步骤S2中，基于救灾点信息、多个站点信息和异构无人机信息，以最小化无人机飞行时长为目标构建多站点带时间窗的多无人机配送模型，具体实施过程如下：In step S2, based on the disaster relief point information, multiple site information and heterogeneous UAV information, a multi-site multi-UAV distribution model with a time window is constructed with the goal of minimizing the UAV flight duration. The specific implementation process is as follows :

所述多站点带时间窗的多无人机配送模型的目标函数采用公式(1)来表示：The objective function of the multi-site multi-UAV distribution model with time window is expressed by formula (1):

Figure GDA0003758896840000111
Figure GDA0003758896840000111

其中，i和j为节点编号，V为所有节点集合；h为无人机编号，H为无人机集合；

Figure GDA0003758896840000112
为编号为h的无人机从节点i到节点j的飞行时长；
Figure GDA0003758896840000113
为决策变量，编号为h的无人机从节点i到达节点j的路径。Among them, i and j are the node numbers, V is the set of all nodes; h is the drone number, and H is the drone set;
Figure GDA0003758896840000112
is the flight time of the drone numbered h from node i to node j;
Figure GDA0003758896840000113
is the decision variable, the path of the UAV numbered h from node i to node j.

编号为h的无人机从节点i到达节点j的飞行时长

Figure GDA0003758896840000114
通过下式计算得到：The flight time of the drone numbered h from node i to node j
Figure GDA0003758896840000114
It is calculated by the following formula:

Figure GDA0003758896840000115
Figure GDA0003758896840000115

其中，vih为编号为h的无人机的飞行速度；xi为节点i的横坐标，yi为节点i的纵坐标；Among them, vi h is the flight speed of the UAV numbered h; x i is the abscissa of node i, and y i is the ordinate of node i;

xj为节点j的横坐标，yj为节点j的纵坐标。x j is the abscissa of node j, and y j is the ordinate of node j.

所述多站点带时间窗的多无人机配送模型的约束条件采用公式(3)至(11)来表示：The constraints of the multi-site multi-UAV distribution model with time windows are expressed by formulas (3) to (11):

Figure GDA0003758896840000116
Figure GDA0003758896840000116

Figure GDA0003758896840000117
Figure GDA0003758896840000117

Figure GDA0003758896840000118
Figure GDA0003758896840000118

Figure GDA0003758896840000119
Figure GDA0003758896840000119

Figure GDA00037588968400001110
Figure GDA00037588968400001110

Figure GDA00037588968400001111
Figure GDA00037588968400001111

Figure GDA0003758896840000121
Figure GDA0003758896840000121

Figure GDA0003758896840000122
Figure GDA0003758896840000122

Figure GDA0003758896840000123
Figure GDA0003758896840000123

其中：in:

公式(3)表示每个灾民点仅被访问一次；Equation (3) indicates that each disaster site is visited only once;

公式(4)表示各灾民点进出平衡约束Equation (4) expresses the balance constraint on the entry and exit of each disaster-stricken point

公式(5)表示每架无人机仅被使用一次Equation (5) means that each UAV is used only once

公式(6)～(7)表示每架无人机到达灾民点时间和灾民点的开始服务时间之间的关系；Formulas (6) to (7) represent the relationship between the time each drone arrives at the disaster victims’ point and the start time of service at the disaster victims’ point;

公式(7)表示无人机必须在灾民点的服务时间窗内提供服务Equation (7) indicates that the UAV must provide service within the service time window of the disaster victims

公式(8)表示无人机必须在灾民点的服务时间窗内提供服务Equation (8) indicates that the drone must provide service within the service time window of the disaster victims

公式(9)～(10)表示消除子路径，确保无人机的飞行时长不能超过无人机的最大续航时长；Formulas (9) to (10) represent the elimination of sub-paths to ensure that the flight time of the UAV cannot exceed the maximum endurance of the UAV;

公式(11)表示决策变量约束。Equation (11) represents the decision variable constraint.

l、i和j为救灾点编号，V为所有节点集合；D为无人机站点集合，N为救灾点集合；h为无人机编号，H为无人机集合；

Figure GDA0003758896840000124
为编号为h的无人机访问救灾点j后已飞行时长，
Figure GDA0003758896840000125
为编号为h的无人机访问救灾点i后已飞行时长，
Figure GDA0003758896840000126
为编号为h的无人机访问救灾点r后已飞行时长，Sh为编号为h的无人机的续航时间；ei为救灾点i的最早开始服务时间；li为救灾点i的最迟开始服务时间；
Figure GDA0003758896840000127
为编号为h的无人机到达救灾点i的时间；
Figure GDA0003758896840000128
为编号为h的无人机到达救灾点j的时间；
Figure GDA0003758896840000129
为编号为h的无人机到达救灾点i的开始服务的时间；sei为无人机到达救灾点i用于完成任务的时间；
Figure GDA0003758896840000131
为决策变量，编号为h的无人机从节点i到达节点j的路径；
Figure GDA0003758896840000132
为决策变量，编号为h的无人机从节点l到达救灾点i的路径；
Figure GDA0003758896840000133
为决策变量，编号为h的无人机从救灾点i到达节点j的路径；
Figure GDA0003758896840000134
为决策变量，编号为h的无人机从节点r到达节点i的路径；
Figure GDA0003758896840000135
为编号为h的无人机从节点i到节点j的飞行时长；M为一个大的正整数。l, i and j are the numbers of disaster relief points, and V is the set of all nodes; D is the set of UAV sites, and N is the set of disaster relief points; h is the number of drones, and H is the set of drones;
Figure GDA0003758896840000124
is the flight time of the drone numbered h after visiting the disaster relief point j,
Figure GDA0003758896840000125
The flight time of the drone numbered h after visiting disaster relief point i,
Figure GDA0003758896840000126
is the flight time of the drone numbered h after visiting the disaster relief point r, S h is the endurance time of the drone numbered h; e i is the earliest service time of the disaster relief point i; l i is the time of the disaster relief point i the latest time to start the service;
Figure GDA0003758896840000127
is the time when the drone numbered h arrives at the disaster relief point i;
Figure GDA0003758896840000128
is the time when the drone numbered h arrives at the disaster relief point j;
Figure GDA0003758896840000129
is the time when the drone numbered h arrives at the disaster relief point i and starts to serve; se i is the time when the drone arrives at the disaster relief point i for completing the task;
Figure GDA0003758896840000131
is the decision variable, the path of the UAV numbered h from node i to node j;
Figure GDA0003758896840000132
is the decision variable, the path of the drone numbered h from node l to disaster relief point i;
Figure GDA0003758896840000133
is the decision variable, the path of the UAV numbered h from the disaster relief point i to the node j;
Figure GDA0003758896840000134
is the decision variable, the path of the UAV numbered h from node r to node i;
Figure GDA0003758896840000135
is the flight duration of the drone numbered h from node i to node j; M is a large positive integer.

在步骤S3中，对多站点带时间窗的多无人机配送模型求解，最优任务路径规划方案，具体实施过程如下：In step S3, the multi-site multi-UAV distribution model with time windows is solved, and the optimal task path planning scheme is implemented. The specific implementation process is as follows:

S301、基于灾点信息、多个站点信息、异构无人机信息和多站点带时间窗的多无人机配送模型获取无人机配送路径的初始任务路径规划方案集合。具体为：S301 , based on disaster point information, multiple site information, heterogeneous UAV information, and a multi-site multi-UAV distribution model with a time window to obtain a set of initial mission path planning schemes for UAV distribution paths. Specifically:

S301a、设定编码规则，如下：S301a, set encoding rules, as follows:

一条染色体表示一个初始任务路径规划方案，染色体采用一种整数编码方式，由两行构成，无人机访问的救灾点构成染色体第一行，无人机编号构成染色体的第二行。染色体形式如图2所示：A chromosome represents an initial mission path planning scheme. The chromosome adopts an integer coding method and consists of two lines. The disaster relief point visited by the drone constitutes the first row of the chromosome, and the drone number constitutes the second row of the chromosome. The chromosome form is shown in Figure 2:

图1所示染色体表示：编号为1的无人机访问救灾点3、救灾点4、救灾点5、救灾点6和救灾点7；编号为2的无人机访问救灾点1、救灾点2、救灾点8和救灾点9。The chromosomes shown in Figure 1 represent: the drone numbered 1 visits disaster relief point 3, disaster relief point 4, disaster relief point 5, disaster relief point 6 and disaster relief point 7; the drone numbered 2 visits disaster relief point 1 and disaster relief point 2 , Disaster Relief Point 8 and Disaster Relief Point 9.

S301b、根据编码规则生成初始任务路径规划方案集合，包括：S301b, generate an initial task path planning scheme set according to the coding rule, including:

步骤1：将救灾点集合N中的救灾点进行随机排列Nr，形成染色体的第一行编码；Step 1: Randomly arrange N r of the disaster relief points in the disaster relief point set N to form the first line of chromosome coding;

步骤2：针对排列Nr中的每一个客户，从集合H中随机选择无人机进行访问，形成染色体的第二行编码；Step 2: For each customer in the arrangement N r , randomly select drones from the set H to visit, forming the second line of chromosome coding;

步骤3：依据无人机编号选出所访问的救灾点，并按照救灾点的时间窗最早开始访问时间非降序排列，从而得到无人机所访问的救灾点序列Rok；Step 3: Select the disaster relief points visited according to the drone number, and arrange them in non-descending order according to the earliest access time of the time window of the disaster relief point, so as to obtain the disaster relief point sequence Ro k visited by the drone;

步骤4：在每架无人机访问救灾点序列的最前面和最后面加入该无人机对应的站点编号，用来表示无人机的起点，得到了每架无人机访问的救灾点序列Rk；Step 4: Add the site number corresponding to the drone at the front and the back of the sequence of disaster relief points visited by each drone to indicate the starting point of the drone, and obtain the sequence of disaster relief points visited by each drone R k ;

步骤5：根据预设的种群规模Np重复步骤1-4，初始任务路径规划方案集合。Step 5: Repeat steps 1-4 according to the preset population size Np , and set the initial task path planning scheme.

初始任务路径规划方案生成过程如图3所示：The generation process of the initial task path planning scheme is shown in Figure 3:

图3(a)所示染色体表示：编号为1的无人机访问救灾点3、救灾点4、救灾点5、救灾点6和救灾点7；编号为2的无人机访问救灾点1、救灾点2、救灾点8和救灾点9。依据救灾点的时间窗最早开始访问时间非降序排列对救灾点顺序进行调整，则编号为1的无人机依次访问救灾点6、救灾点5、救灾点4、救灾点3和救灾点7，编号为2的无人机依次访问救灾点8、救灾点1、救灾点9和救灾点2。在任务序列的最前面和最后面加入该无人机对应的站点编号得到完整的初始任务路径规划方案，则编号为1的无人机从编号为10的站点出发，依次完成救灾点6、救灾点5、救灾点4、救灾点3和救灾点7的配送任务，最后返回编号为10的站点，编号为2的无人机从编号为11的站点出发，依次完成救灾点8、救灾点1、救灾点9和救灾点2的配送任务，最后返回编号为11的站点。路径示意图如图3(b)所示。The chromosomes shown in Figure 3(a) represent: the drone numbered 1 visits disaster relief point 3, disaster relief point 4, disaster relief point 5, disaster relief point 6 and disaster relief point 7; the drone numbered 2 visits disaster relief point 1, Disaster Relief Point 2, Disaster Relief Point 8 and Disaster Relief Point 9. Adjust the order of the disaster relief points according to the earliest access time of the disaster relief point in a non-descending order, and the drone numbered 1 will visit the disaster relief point 6, the disaster relief point 5, the disaster relief point 4, the disaster relief point 3 and the disaster relief point 7 in turn. The drone numbered 2 visits disaster relief point 8, disaster relief point 1, disaster relief point 9 and disaster relief point 2 in turn. Add the site number corresponding to the drone at the front and back of the task sequence to obtain a complete initial mission path planning scheme, then the drone numbered 1 will start from the site numbered 10 and complete disaster relief point 6 and disaster relief in turn. The distribution tasks of point 5, disaster relief point 4, disaster relief point 3 and disaster relief point 7, and finally return to the station numbered 10. The drone numbered 2 departs from the station numbered 11 and completes disaster relief point 8 and disaster relief point 1 in turn. , Disaster Relief Point 9 and Disaster Relief Point 2, and finally return to the station numbered 11. The schematic diagram of the path is shown in Figure 3(b).

在具体实施过程中，初始任务路径规划方案集合中的规划方案并不一定都满足多站点带时间窗的多无人机配送模型的约束条件，所以有必要对初始任务路径规划方案集合中的每条染色体进行约束检查，并对不满足约束条件的染色体进行删除。In the specific implementation process, the planning schemes in the initial mission path planning scheme set do not necessarily meet the constraints of the multi-site multi-UAV delivery model with time windows, so it is necessary to analyze the initial mission path planning scheme set. Constraints are checked on chromosomes, and chromosomes that do not meet the constraints are deleted.

S302、对于生成的初始任务路径规划方案集合，通过引入分段交叉算子和动态插入算子的改进遗传算法进行优化，从而获得对于无人机进行一个或多个救灾点配送服务的最优任务路径规划方案，包括：S302. For the generated initial task path planning scheme set, optimize by introducing an improved genetic algorithm of a segmented crossover operator and a dynamic insertion operator, so as to obtain an optimal task for the UAV to perform the delivery service to one or more disaster relief points Path planning scheme, including:

S302a、设置遗传算法的执行参数，如最大迭代次数、交叉概率等；以公式(12)作为适应度函数，对每一个初始任务路径规划方案的适应度值进行计算，；S302a, setting the execution parameters of the genetic algorithm, such as the maximum number of iterations, the crossover probability, etc.; using the formula (12) as the fitness function, calculate the fitness value of each initial task path planning scheme,

Figure GDA0003758896840000151
Figure GDA0003758896840000151

S302b、通过轮盘赌选择方法从初始任务路径规划方案集合中选择2个不同的路径规划方案使用分段交叉算子根据交叉概率进行交叉操作，得到2个路径规划方案，适应度值越小的方案被选中概率越大，包括：S302b. Select two different path planning schemes from the initial task path planning scheme set by the roulette selection method, and use the segmented cross operator to perform the crossover operation according to the crossover probability to obtain two path planning schemes, the smaller the fitness value is. The greater the probability of the scheme being selected, including:

步骤1：通过轮盘赌选择方法从初始任务路径规划方案集合进行选择两条染色体作为父代染色体；Step 1: Select two chromosomes as parent chromosomes from the initial task path planning scheme set by the roulette selection method;

步骤2：根据无人机编号对父代染色体进行分段，每一分段染色体表示一架无人机的任务路径规划方案；Step 2: Segment the parent chromosome according to the drone number, and each segmented chromosome represents the mission path planning scheme of a drone;

步骤3：将两条染色体的一个分段进行单点交叉操作；Step 3: Perform a single-point crossover operation on a segment of two chromosomes;

步骤4：根据无人机数量|H|重复步骤3，直到完成所有分段的交叉操作，并依据无人机编号将分段的染色体进行合并，得到子染色体。Step 4: Repeat step 3 according to the number of drones |H| until the crossover operation of all segments is completed, and merge the segmented chromosomes according to the number of drones to obtain sub-chromosomes.

S302c、对步骤S302b中得到的路径规划方案进行动态插入操作，得到2个新的路径规划方案；S302c, dynamically inserting the path planning schemes obtained in step S302b to obtain two new path planning schemes;

步骤1：如果未配送救灾点集合Nvc不为空集，转步骤2；否则，输出任务路径规划方案；Step 1: If the set of undistributed disaster relief points N vc is not an empty set, go to step 2; otherwise, output the task path planning scheme;

步骤2：从无人机集合H中随机选择无人机h；Step 2: Randomly select the drone h from the set H of drones;

步骤3：判断无人机h是否满足续航约束，如果违反约束转步骤2；否则，转步骤4；Step 3: Determine whether the drone h satisfies the endurance constraint, and if it violates the constraint, go to Step 2; otherwise, go to Step 4;

步骤4：利用公式(13)从Nvc中选出救灾点c；Step 4: Use formula (13) to select disaster relief point c from N vc ;

Figure GDA0003758896840000161
Figure GDA0003758896840000161

其中，ec为救灾点c的最早开始服务时间；

Figure GDA0003758896840000162
为编号为h的无人机到达救灾点c的时间，
Figure GDA0003758896840000163
编号为h的无人机从救灾点u到救灾点c时间；Among them, e c is the earliest service time of disaster relief point c;
Figure GDA0003758896840000162
is the time when the drone numbered h arrives at the disaster relief point c,
Figure GDA0003758896840000163
The time of the drone numbered h from disaster relief point u to disaster relief point c;

步骤5：检验插入救灾点c是否满足约束条件，如果满足则将救灾点c插入当前规划路径Rh中，并从集合Nvc中删除救灾点c，转步骤4；否则，转步骤6；Step 5: Check whether the inserted disaster relief point c satisfies the constraint condition, if so, insert the disaster relief point c into the current planning path R h , and delete the disaster relief point c from the set N vc , go to step 4; otherwise, go to step 6;

步骤6：从无人机集合H中删除无人机h，转步骤1。Step 6: Delete the drone h from the drone set H, and go to Step 1.

S302d、重复步骤S302b-S302c，直到达到预设的最大迭代次数，从更新的任务路径规划方案集合中，找到适应度函数值最小的任务路径规划方案，获得无人机进行一个或多个救灾点配送服务的最优任务路径规划方案。S302d, repeating steps S302b-S302c until the preset maximum number of iterations is reached, from the updated set of mission path planning schemes, find the mission path planning scheme with the smallest fitness function value, and obtain one or more disaster relief points for the unmanned aerial vehicle Optimal task routing scheme for delivery service.

本发明实施例还提供一种针对应急物资配送的无人机路径规划装置，所述装置包括：An embodiment of the present invention also provides a UAV path planning device for emergency material distribution, the device comprising:

信息获取模块，用于获取救灾点信息、多个站点信息和异构无人机信息；Information acquisition module, used to acquire disaster relief site information, multiple site information and heterogeneous UAV information;

模型构建模型，用于基于救灾点信息、多个站点信息和异构无人机信息，以最小化无人机飞行时长为目标构建多站点带时间窗的多无人机配送模型；Model building model, which is used to build a multi-site multi-UAV distribution model with time windows based on disaster relief point information, multiple site information and heterogeneous UAV information with the goal of minimizing UAV flight time;

求解模型，用于对多站点带时间窗的多无人机配送模型求解，最优任务路径规划方案。The solution model is used to solve the multi-site multi-UAV distribution model with time window, and the optimal mission path planning scheme.

可理解的是，本发明实施例提供的针对应急物资配送的无人机路径规划装置与上述针对应急物资配送的无人机路径规划方法相对应，其有关内容的解释、举例、有益效果等部分可以参考针对应急物资配送的无人机路径规划方法中的相应内容，此处不再赘述。It can be understood that the UAV path planning device for emergency material distribution provided by the embodiment of the present invention corresponds to the above-mentioned UAV path planning method for emergency material distribution, and the explanations, examples, beneficial effects and other parts of the relevant content are included. You can refer to the corresponding content in the UAV path planning method for emergency material distribution, which will not be repeated here.

本发明实施例还提供一种计算机可读存储介质，其存储用于针对应急物资配送的无人机路径规划的计算机程序，其中，所述计算机程序使得计算机执行如上述所述的针对应急物资配送的无人机路径规划方法。Embodiments of the present invention further provide a computer-readable storage medium, which stores a computer program for UAV path planning for emergency material distribution, wherein the computer program enables a computer to execute the above-mentioned emergency material distribution for emergency material distribution. UAV path planning method.

本发明实施例还提供一种电子设备，包括：An embodiment of the present invention also provides an electronic device, including:

一个或多个处理器；one or more processors;

存储器；以及memory; and

一个或多个程序，其中所述一个或多个程序被存储在所述存储器中，并且被配置成由所述一个或多个处理器执行，所述程序包括用于执行如上述所述的针对应急物资配送的无人机路径规划方法。One or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, the programs comprising a UAV path planning method for emergency material distribution.

综上所述，与现有技术相比，具备以下有益效果：To sum up, compared with the prior art, it has the following beneficial effects:

本发明实施例通过异构无人机从多个不同的站点出发为救灾点进行物资，能有效缩短完成配送任务的总时间。同时增加时间窗限制，对救援任务紧急的救援点进行优先配送，精准确定物资配送路线，使救援路线的安排更加合理。In the embodiment of the present invention, heterogeneous drones are used to deliver supplies to disaster relief sites from a plurality of different sites, which can effectively shorten the total time for completing the distribution task. At the same time, increase the time window limit, prioritize the distribution of emergency rescue points, accurately determine the material distribution route, and make the arrangement of the rescue route more reasonable.

需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。It should be noted that, in this document, 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 relationship between these entities or operations. any such actual relationship or sequence exists. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。The above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; 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: The recorded technical solutions are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (8)

1.一种针对应急物资配送的无人机路径规划方法，其特征在于，所述方法包括：1. A UAV path planning method for emergency material distribution, characterized in that the method comprises: S1、获取救灾点信息、多个站点信息和异构无人机信息；S1. Obtain disaster relief site information, multiple site information and heterogeneous UAV information; S2、基于救灾点信息、多个站点信息和异构无人机信息，以最小化无人机飞行时长为目标构建多站点带时间窗的多无人机配送模型；S2. Based on disaster relief point information, multiple site information and heterogeneous UAV information, a multi-site multi-UAV distribution model with time windows is constructed with the goal of minimizing UAV flight time; S3、对多站点带时间窗的多无人机配送模型求解，最优任务路径规划方案；S3. Solve the multi-site multi-UAV distribution model with time window, and the optimal mission path planning scheme; 其中，所述多站点带时间窗的多无人机配送模型包括目标函数和约束条件；Wherein, the multi-site multi-UAV distribution model with time window includes an objective function and constraints; 目标函数采用公式(1)来表示：The objective function is expressed by formula (1):
Figure FDA0003758896830000011
Figure FDA0003758896830000011
 其中，i和j为节点编号，V为所有节点集合；h为无人机编号，H为无人机集合；
Figure FDA0003758896830000012
为编号为h的无人机从节点i到节点j的飞行时长；
Figure FDA0003758896830000013
为决策变量，编号为h的无人机从节点i到达节点j的路径；Among them, i and j are the node numbers, V is the set of all nodes; h is the drone number, and H is the drone set;
Figure FDA0003758896830000012
is the flight time of the drone numbered h from node i to node j;
Figure FDA0003758896830000013
is the decision variable, the path of the UAV numbered h from node i to node j; 编号为h的无人机从节点i到达节点j的飞行时长
Figure FDA0003758896830000015
通过下式计算得到：The flight time of the drone numbered h from node i to node j
Figure FDA0003758896830000015
It is calculated by the following formula:
Figure FDA0003758896830000014
Figure FDA0003758896830000014
 其中，vih为编号为h的无人机的飞行速度；xi为节点i的横坐标，yi为节点i的纵坐标；xj为节点j的横坐标，yj为节点j的纵坐标；Among them, vi h is the flight speed of the UAV numbered h; x i is the abscissa of node i, y i is the ordinate of node i; x j is the abscissa of node j, y j is the ordinate of node j coordinate; 约束条件采用公式(3)至(11)来表示：The constraints are expressed by formulas (3) to (11):
Figure FDA0003758896830000021
Figure FDA0003758896830000021
Figure FDA0003758896830000022
Figure FDA0003758896830000022
Figure FDA0003758896830000023
Figure FDA0003758896830000023
Figure FDA0003758896830000024
Figure FDA0003758896830000024
Figure FDA0003758896830000025
Figure FDA0003758896830000025
Figure FDA0003758896830000026
Figure FDA0003758896830000026
Figure FDA0003758896830000027
Figure FDA0003758896830000027
Figure FDA0003758896830000028
Figure FDA0003758896830000028
Figure FDA0003758896830000029
Figure FDA0003758896830000029
 其中：in: 公式(3)表示每个灾民点仅被访问一次；Formula (3) indicates that each disaster site is visited only once; 公式(4)表示各灾民点进出平衡约束Equation (4) expresses the balance constraint on the entry and exit of each disaster-stricken point 公式(5)表示每架无人机仅被使用一次Equation (5) means that each UAV is used only once 公式(6)～(7)表示每架无人机到达灾民点时间和灾民点的开始服务时间之间的关系；Formulas (6) to (7) represent the relationship between the time each drone arrives at the disaster victims’ point and the start time of service at the disaster victims’ point; 公式(7)表示无人机必须在灾民点的服务时间窗内提供服务Equation (7) indicates that the UAV must provide service within the service time window of the disaster victims 公式(8)表示无人机必须在灾民点的服务时间窗内提供服务Equation (8) indicates that the drone must provide service within the service time window of the disaster victims 公式(9)～(10)表示消除子路径，确保无人机的飞行时长不能超过无人机的最大续航时长；Formulas (9) to (10) represent the elimination of sub-paths to ensure that the flight time of the UAV cannot exceed the maximum endurance of the UAV; 公式(11)表示决策变量约束；Formula (11) represents the decision variable constraint; l、i和j为救灾点编号，V为所有节点集合；D为无人机站点集合，N为救灾点集合；h为无人机编号，H为无人机集合；
Figure FDA0003758896830000031
为编号为h的无人机访问救灾点j后已飞行时长，
Figure FDA0003758896830000032
为编号为h的无人机访问救灾点i后已飞行时长，
Figure FDA0003758896830000033
为编号为h的无人机访问救灾点r后已飞行时长，Sh为编号为h的无人机的续航时间；ei为救灾点i的最早开始服务时间；li为救灾点i的最迟开始服务时间；
Figure FDA0003758896830000034
为编号为h的无人机到达救灾点i的时间；
Figure FDA0003758896830000035
为编号为h的无人机到达救灾点j的时间；
Figure FDA0003758896830000036
为编号为h的无人机到达救灾点i的开始服务的时间；sei为无人机到达救灾点i用于完成任务的时间；
Figure FDA0003758896830000037
为决策变量，编号为h的无人机从节点i到达节点j的路径；
Figure FDA0003758896830000038
为决策变量，编号为h的无人机从节点l到达救灾点i的路径；
Figure FDA0003758896830000039
为决策变量，编号为h的无人机从救灾点i到达节点j的路径；
Figure FDA00037588968300000310
为决策变量，编号为h的无人机从节点r到达节点i的路径；
Figure FDA00037588968300000311
为编号为h的无人机从节点i到节点j的飞行时长；M为正整数。l, i and j are the numbers of disaster relief points, and V is the set of all nodes; D is the set of UAV sites, and N is the set of disaster relief points; h is the number of drones, and H is the set of drones;
Figure FDA0003758896830000031
is the flight time of the drone numbered h after visiting the disaster relief point j,
Figure FDA0003758896830000032
The flight time of the drone numbered h after visiting disaster relief point i,
Figure FDA0003758896830000033
is the flight time of the drone numbered h after visiting the disaster relief point r, S h is the endurance time of the drone numbered h; e i is the earliest service time of the disaster relief point i; l i is the time of the disaster relief point i the latest time to start the service;
Figure FDA0003758896830000034
is the time when the drone numbered h arrives at the disaster relief point i;
Figure FDA0003758896830000035
is the time when the drone numbered h arrives at the disaster relief point j;
Figure FDA0003758896830000036
is the time when the drone numbered h arrives at the disaster relief point i and starts to serve; se i is the time when the drone arrives at the disaster relief point i for completing the task;
Figure FDA0003758896830000037
is the decision variable, the path of the UAV numbered h from node i to node j;
Figure FDA0003758896830000038
is the decision variable, the path of the drone numbered h from node l to disaster relief point i;
Figure FDA0003758896830000039
is the decision variable, the path of the UAV numbered h from the disaster relief point i to the node j;
Figure FDA00037588968300000310
is the decision variable, the path of the UAV numbered h from node r to node i;
Figure FDA00037588968300000311
is the flight duration of the UAV numbered h from node i to node j; M is a positive integer. 2.如权利要求1所述的针对应急物资配送的无人机路径规划方法，其特征在于，所述S3包括：2. The UAV path planning method for emergency material distribution according to claim 1, wherein the S3 comprises: S301、基于灾点信息、多个站点信息、异构无人机信息和多站点带时间窗的多无人机配送模型获取无人机配送路径的初始任务路径规划方案集合；S301. Obtain a set of initial mission path planning schemes for the UAV distribution path based on disaster point information, multiple site information, heterogeneous UAV information, and a multi-site multi-UAV distribution model with a time window; S302、对于生成的初始任务路径规划方案集合，通过引入分段交叉算子和动态插入算子的改进遗传算法进行优化，从而获得对于无人机进行一个或多个救灾点配送服务的最优任务路径规划方案。S302. For the generated initial task path planning scheme set, optimize by introducing an improved genetic algorithm of a segmented cross operator and a dynamic insertion operator, so as to obtain an optimal task for the UAV to perform the delivery service for one or more disaster relief points Path planning scheme. 3.如权利要求2所述的针对应急物资配送的无人机路径规划方法，其特征在于，所述S301包括：3. The UAV path planning method for emergency material distribution according to claim 2, wherein the S301 comprises: S301a、设定编码规则；S301a, set encoding rules; S301b、基于编码规则生成初始任务路径规划方案集合，包括：S301b, generating an initial task path planning scheme set based on the coding rule, including: 步骤1：将救灾点集合N中的救灾点进行随机排列Nr，形成染色体的第一行编码；Step 1: Randomly arrange N r of the disaster relief points in the disaster relief point set N to form the first line of chromosome coding; 步骤2：针对排列Nr中的每一个客户，从集合H中随机选择无人机进行访问，形成染色体的第二行编码；Step 2: For each customer in the arrangement N r , randomly select drones from the set H to visit, forming the second line of chromosome coding; 步骤3：依据无人机编号选出所访问的救灾点，并按照救灾点的时间窗最早开始访问时间非降序排列，从而得到无人机所访问的救灾点序列Rok；Step 3: Select the disaster relief points visited according to the drone number, and arrange them in non-descending order according to the earliest access time of the time window of the disaster relief point, so as to obtain the disaster relief point sequence Ro k visited by the drone; 步骤4：在每架无人机访问救灾点序列的最前面和最后面加入该无人机对应的站点编号，用来表示无人机的起点，得到了每架无人机访问的救灾点序列Rk；Step 4: Add the site number corresponding to the drone at the front and the back of the sequence of disaster relief points visited by each drone to indicate the starting point of the drone, and obtain the sequence of disaster relief points visited by each drone R k ; 步骤5：根据预设的种群规模Np重复步骤1-4，得到初始种群。Step 5: Repeat steps 1-4 according to the preset population size N p to obtain an initial population. 4.如权利要求2所述的针对应急物资配送的无人机路径规划方法，其特征在于，所述S302包括：4. The UAV path planning method for emergency material distribution according to claim 2, wherein the S302 comprises: S302a、设置改进遗传算法的执行参数和以公式(12)作为适应度函数，对每一个初始任务路径规划方案的适应度值进行计算，所述执行参数包括最大迭代次数和交叉概率；S302a, setting the execution parameters of the improved genetic algorithm and using formula (12) as the fitness function, calculate the fitness value of each initial task path planning scheme, and the execution parameters include the maximum number of iterations and the crossover probability;
Figure FDA0003758896830000041
Figure FDA0003758896830000041
 S302b、通过轮盘赌选择方法从初始任务路径规划方案集合中选择2个不同的路径规划方案使用分段交叉算子根据交叉概率进行交叉操作，得到2个路径规划方案，适应度值越小的方案被选中概率越大，包括：S302b. Select two different path planning schemes from the initial task path planning scheme set by the roulette selection method, and use the segmented cross operator to perform the crossover operation according to the crossover probability to obtain two path planning schemes, the smaller the fitness value is. The greater the probability of the scheme being selected, including: S302c、对步骤S302b中得到的路径规划方案进行动态插入操作，得到2个新的路径规划方案；S302c, dynamically inserting the path planning schemes obtained in step S302b to obtain two new path planning schemes; S302d、重复步骤S302b-S302c，直到达到预设的最大迭代次数，从更新的任务路径规划方案集合中，找到适应度函数值最小的任务路径规划方案，获得无人机进行一个或多个救灾点配送服务的最优任务路径规划方案。S302d, repeating steps S302b-S302c until the preset maximum number of iterations is reached, from the updated set of mission path planning schemes, find the mission path planning scheme with the smallest fitness function value, and obtain one or more disaster relief points for the unmanned aerial vehicle Optimal task routing scheme for delivery service. 5.如权利要求2所述的针对应急物资配送的无人机路径规划方法，其特征在于，所述S302b包括：5. The UAV path planning method for emergency material distribution according to claim 2, wherein the S302b comprises: 步骤1：通过轮盘赌选择方法从初始任务路径规划方案集合进行选择两条染色体作为父代染色体；Step 1: Select two chromosomes as parent chromosomes from the initial task path planning scheme set by the roulette selection method; 步骤2：根据无人机编号对父代染色体进行分段，每一分段染色体表示一架无人机的任务路径规划方案；Step 2: Segment the parent chromosome according to the drone number, and each segmented chromosome represents the mission path planning scheme of a drone; 步骤3：将两条染色体的一个分段进行单点交叉操作；Step 3: Perform a single-point crossover operation on a segment of two chromosomes; 步骤4：根据无人机数量|H|重复步骤3，直到完成所有分段的交叉操作，并依据无人机编号将分段的染色体进行合并，得到子染色体；Step 4: Repeat step 3 according to the number of drones |H| until the crossover operation of all segments is completed, and merge the segmented chromosomes according to the number of drones to obtain sub-chromosomes; 和/或and / or 所述S302c包括：The S302c includes: 步骤1：如果未配送救灾点集合Nvc不为空集，转步骤2；否则，输出任务路径规划方案；Step 1: If the set of undistributed disaster relief points N vc is not an empty set, go to step 2; otherwise, output the task path planning scheme; 步骤2：从无人机集合H中随机选择无人机h；Step 2: Randomly select the drone h from the set H of drones; 步骤3：判断无人机h是否满足续航约束，如果违反约束转步骤2；否则，转步骤4；Step 3: Determine whether the drone h satisfies the endurance constraint, and if it violates the constraint, go to Step 2; otherwise, go to Step 4; 步骤4：利用公式(13)从Nvc中选出救灾点c；Step 4: Use formula (13) to select disaster relief point c from N vc ;
Figure FDA0003758896830000061
Figure FDA0003758896830000061
 其中，ec为救灾点c的最早开始服务时间；
Figure FDA0003758896830000062
为编号为h的无人机到达救灾点c的时间，
Figure FDA0003758896830000063
编号为h的无人机从救灾点u到救灾点c时间；Among them, e c is the earliest service time of disaster relief point c;
Figure FDA0003758896830000062
is the time when the drone numbered h arrives at the disaster relief point c,
Figure FDA0003758896830000063
The time of the drone numbered h from disaster relief point u to disaster relief point c; 步骤5：检验插入救灾点c是否满足约束条件，如果满足则将救灾点c插入当前规划路径Rh中，并从集合Nvc中删除救灾点c，转步骤4；否则，转步骤6；Step 5: Check whether the inserted disaster relief point c satisfies the constraint condition, if so, insert the disaster relief point c into the current planning path R h , and delete the disaster relief point c from the set N vc , go to step 4; otherwise, go to step 6; 步骤6：从无人机集合H中删除无人机h，转步骤1。Step 6: Delete the drone h from the drone set H, and go to Step 1. 6.一种针对应急物资配送的无人机路径规划装置，其特征在于，所述装置包括：6. A UAV path planning device for emergency material distribution, characterized in that the device comprises: 信息获取模块，用于获取救灾点信息、多个站点信息和异构无人机信息；Information acquisition module, used to acquire disaster relief site information, multiple site information and heterogeneous UAV information; 模型构建模型，用于基于救灾点信息、多个站点信息和异构无人机信息，以最小化无人机飞行时长为目标构建多站点带时间窗的多无人机配送模型；Model building model, which is used to build a multi-site multi-UAV distribution model with time windows based on disaster relief point information, multiple site information and heterogeneous UAV information with the goal of minimizing UAV flight time; 求解模型，用于对多站点带时间窗的多无人机配送模型求解，最优任务路径规划方案；The solution model is used to solve the multi-UAV distribution model with time windows at multiple sites, and the optimal mission path planning scheme; 其中，所述多站点带时间窗的多无人机配送模型包括目标函数和约束条件；Wherein, the multi-site multi-UAV distribution model with time window includes an objective function and constraints; 目标函数采用公式(1)来表示：The objective function is expressed by formula (1):
Figure FDA0003758896830000071
Figure FDA0003758896830000071
 其中，i和j为节点编号，V为所有节点集合；h为无人机编号，H为无人机集合；
Figure FDA0003758896830000072
为编号为h的无人机从节点i到节点j的飞行时长；
Figure FDA0003758896830000073
为决策变量，编号为h的无人机从节点i到达节点j的路径；Among them, i and j are the node numbers, V is the set of all nodes; h is the drone number, and H is the drone set;
Figure FDA0003758896830000072
is the flight time of the drone numbered h from node i to node j;
Figure FDA0003758896830000073
is the decision variable, the path of the UAV numbered h from node i to node j; 编号为h的无人机从节点i到达节点j的飞行时长
Figure FDA0003758896830000074
通过下式计算得到：The flight time of the drone numbered h from node i to node j
Figure FDA0003758896830000074
It is calculated by the following formula:
Figure FDA0003758896830000075
Figure FDA0003758896830000075
 其中，vih为编号为h的无人机的飞行速度；xi为节点i的横坐标，yi为节点i的纵坐标；xj为节点j的横坐标，yj为节点j的纵坐标；Among them, vi h is the flight speed of the UAV numbered h; x i is the abscissa of node i, y i is the ordinate of node i; x j is the abscissa of node j, y j is the ordinate of node j coordinate; 约束条件采用公式(3)至(11)来表示：The constraints are expressed by formulas (3) to (11):
Figure FDA0003758896830000076
Figure FDA0003758896830000076
Figure FDA0003758896830000077
Figure FDA0003758896830000077
Figure FDA0003758896830000078
Figure FDA0003758896830000078
Figure FDA0003758896830000079
Figure FDA0003758896830000079
Figure FDA00037588968300000710
Figure FDA00037588968300000710
Figure FDA00037588968300000711
Figure FDA00037588968300000711
Figure FDA00037588968300000712
Figure FDA00037588968300000712
Figure FDA00037588968300000713
Figure FDA00037588968300000713
Figure FDA00037588968300000714
Figure FDA00037588968300000714
 其中：in: 公式(3)表示每个灾民点仅被访问一次；Equation (3) indicates that each disaster site is visited only once; 公式(4)表示各灾民点进出平衡约束Equation (4) expresses the balance constraint on the entry and exit of each disaster-stricken point 公式(5)表示每架无人机仅被使用一次Equation (5) means that each UAV is used only once 公式(6)～(7)表示每架无人机到达灾民点时间和灾民点的开始服务时间之间的关系；Formulas (6) to (7) represent the relationship between the time each drone arrives at the disaster victims’ point and the start time of service at the disaster victims’ point; 公式(7)表示无人机必须在灾民点的服务时间窗内提供服务Equation (7) indicates that the UAV must provide service within the service time window of the disaster victims 公式(8)表示无人机必须在灾民点的服务时间窗内提供服务Equation (8) indicates that the drone must provide service within the service time window of the disaster victims 公式(9)～(10)表示消除子路径，确保无人机的飞行时长不能超过无人机的最大续航时长；Formulas (9) to (10) represent the elimination of sub-paths to ensure that the flight time of the UAV cannot exceed the maximum endurance of the UAV; 公式(11)表示决策变量约束；Formula (11) represents the decision variable constraint; l、i和j为救灾点编号，V为所有节点集合；D为无人机站点集合，N为救灾点集合；h为无人机编号，H为无人机集合；
Figure FDA0003758896830000081
为编号为h的无人机访问救灾点j后已飞行时长，
Figure FDA0003758896830000082
为编号为h的无人机访问救灾点i后已飞行时长，
Figure FDA0003758896830000083
为编号为h的无人机访问救灾点r后已飞行时长，Sh为编号为h的无人机的续航时间；ei为救灾点i的最早开始服务时间；li为救灾点i的最迟开始服务时间；
Figure FDA0003758896830000084
为编号为h的无人机到达救灾点i的时间；
Figure FDA0003758896830000085
为编号为h的无人机到达救灾点j的时间；
Figure FDA0003758896830000086
为编号为h的无人机到达救灾点i的开始服务的时间；sei为无人机到达救灾点i用于完成任务的时间；
Figure FDA0003758896830000087
为决策变量，编号为h的无人机从节点i到达节点j的路径；
Figure FDA0003758896830000088
为决策变量，编号为h的无人机从节点l到达救灾点i的路径；
Figure FDA0003758896830000089
为决策变量，编号为h的无人机从救灾点i到达节点j的路径；
Figure FDA00037588968300000810
为决策变量，编号为h的无人机从节点r到达节点i的路径；
Figure FDA00037588968300000811
为编号为h的无人机从节点i到节点j的飞行时长；M为正整数。l, i and j are the number of disaster relief points, V is the set of all nodes; D is the set of UAV sites, and N is the set of disaster relief points; h is the number of drones, and H is the set of drones;
Figure FDA0003758896830000081
is the flight time of the drone numbered h after visiting the disaster relief point j,
Figure FDA0003758896830000082
The flight time of the drone numbered h after visiting disaster relief point i,
Figure FDA0003758896830000083
is the flight time of the drone numbered h after visiting the disaster relief point r, S h is the endurance time of the drone numbered h; e i is the earliest service time of the disaster relief point i; l i is the time of the disaster relief point i the latest time to start the service;
Figure FDA0003758896830000084
is the time when the drone numbered h arrives at the disaster relief point i;
Figure FDA0003758896830000085
is the time when the drone numbered h arrives at the disaster relief point j;
Figure FDA0003758896830000086
is the time when the drone numbered h arrives at the disaster relief point i and starts to serve; se i is the time when the drone arrives at the disaster relief point i for completing the task;
Figure FDA0003758896830000087
is the decision variable, the path of the UAV numbered h from node i to node j;
Figure FDA0003758896830000088
is the decision variable, the path of the drone numbered h from node l to disaster relief point i;
Figure FDA0003758896830000089
is the decision variable, the path of the drone numbered h from the disaster relief point i to the node j;
Figure FDA00037588968300000810
is the decision variable, the path of the drone numbered h from node r to node i;
Figure FDA00037588968300000811
is the flight time of the UAV numbered h from node i to node j; M is a positive integer. 7.一种计算机可读存储介质，其特征在于，其存储用于针对应急物资配送的无人机路径规划的计算机程序，其中，所述计算机程序使得计算机执行如权利要求1～5任一所述的针对应急物资配送的无人机路径规划方法。7. A computer-readable storage medium, characterized in that it stores a computer program for UAV path planning for emergency material distribution, wherein the computer program causes a computer to execute any one of claims 1 to 5. The described UAV path planning method for emergency material distribution. 8.一种电子设备，其特征在于，包括：8. An electronic device, characterized in that, comprising: 一个或多个处理器；one or more processors; 存储器；以及memory; and 一个或多个程序，其中所述一个或多个程序被存储在所述存储器中，并且被配置成由所述一个或多个处理器执行，所述程序包括用于执行如权利要求1～5任一所述的针对应急物资配送的无人机路径规划方法。One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising means for performing the functions of claims 1-5 Any of the UAV path planning methods for emergency material distribution.
CN202110839626.1A 2021-07-23 2021-07-23 Unmanned aerial vehicle path planning method and device for emergency material distribution Active CN113759959B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110839626.1A CN113759959B (en) 2021-07-23 2021-07-23 Unmanned aerial vehicle path planning method and device for emergency material distribution

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110839626.1A CN113759959B (en) 2021-07-23 2021-07-23 Unmanned aerial vehicle path planning method and device for emergency material distribution

Publications (2)

Publication Number Publication Date
CN113759959A CN113759959A (en) 2021-12-07
CN113759959B true CN113759959B (en) 2022-10-11

Family

ID=78787888

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110839626.1A Active CN113759959B (en) 2021-07-23 2021-07-23 Unmanned aerial vehicle path planning method and device for emergency material distribution

Country Status (1)

Country Link
CN (1) CN113759959B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118674345A (en) * 2024-05-30 2024-09-20 秦皇岛刘刚物流有限公司 Logistics management system based on Internet of things

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1835370A2 (en) * 2006-03-17 2007-09-19 Thales Automatic trajectory planner
CN108229719A (en) * 2017-11-29 2018-06-29 合肥工业大学 Unmanned plane formation task distributes the Multipurpose Optimal Method and device with trajectory planning
CN110825104A (en) * 2019-09-20 2020-02-21 合肥工业大学 A two-stage optimization method for mobile platform path planning and UAV task assignment
CN111242454A (en) * 2020-01-07 2020-06-05 杭州电子科技大学 Chemical accident multi-target two-stage emergency rescue material scheduling method
CN111352417A (en) * 2020-02-10 2020-06-30 合肥工业大学 Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11242143B2 (en) * 2016-06-13 2022-02-08 Skydio, Inc. Unmanned aerial vehicle beyond visual line of sight control

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1835370A2 (en) * 2006-03-17 2007-09-19 Thales Automatic trajectory planner
CN108229719A (en) * 2017-11-29 2018-06-29 合肥工业大学 Unmanned plane formation task distributes the Multipurpose Optimal Method and device with trajectory planning
CN110825104A (en) * 2019-09-20 2020-02-21 合肥工业大学 A two-stage optimization method for mobile platform path planning and UAV task assignment
CN111242454A (en) * 2020-01-07 2020-06-05 杭州电子科技大学 Chemical accident multi-target two-stage emergency rescue material scheduling method
CN111352417A (en) * 2020-02-10 2020-06-30 合肥工业大学 Rapid generation method of heterogeneous multi-unmanned aerial vehicle cooperative path

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Research on Computing Task Allocation Method Based on Multi-UAVs Collaboration;He Dong 等;《2020 IEEE International Conference on Smart Internet of Things (SmartIoT)》;20200910;全文 *
基于改进蚁群算法的无人机集群任务规划;宋霏羽 等;《舰船电子工程》;20210620(第6期);全文 *
面向异构任务的巡逻车辆与无人机协同路径规划问题研究;张鹏;《《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》》;20210215(第2期);全文 *

Also Published As

Publication number Publication date
CN113759959A (en) 2021-12-07

Similar Documents

Publication Publication Date Title
CN106600147B (en) Towards the multiple no-manned plane method for allocating tasks and device of decomposable asymmetric choice net task
Masuda et al. Heterogeneous voter models
CN113762593B (en) Unmanned aerial vehicle emergency material distribution method and device after earthquake disaster
CN113762594B (en) Route planning method and device for vehicle-machine collaborative distribution post-disaster rescue materials
CN105447568B (en) Power telecom network failure analysis methods based on BP neural network
CN107809322A (en) The distribution method and device of work order
CN111132009B (en) Mobile edge computing method, device and system for Internet of Things
CN109872033B (en) Airport position allocation method
WO2022087962A1 (en) Simulation-based closed-loop aps scheduling optimization method and system, and storage medium
CN113759959B (en) Unmanned aerial vehicle path planning method and device for emergency material distribution
CN107886158A (en) A kind of bat optimized algorithm based on Iterated Local Search and Stochastic inertia weight
CN112631612B (en) Optimization method for kubernetes cloud platform configuration based on genetic algorithm
Najafi et al. Location and distribution management of relief centers: A genetic algorithm approach
Li et al. ChatTwin: toward automated digital twin generation for data center via large language models
CN112003734A (en) Improved structure entropy based key node identification method for information physical system
CN107453786B (en) A method and device for establishing a power communication network model
Huo et al. [Retracted] Research on Solving Postdisaster Material Distribution and Scheduling with Improved NSGA‐II Algorithm
Zhang et al. Recursive weighted treelike networks
EP4089980B1 (en) Sequenced capacity deployment for wan and datacenter networks
A Konstantinidou et al. A multi-objective network design model for post-disaster transportation network management
Zheng et al. A stairs evacuation model considering the pedestrian merging flows
CN114691370A (en) Task allocation method and device based on genetic algorithm
Cai et al. A Braess’s paradox inspired method for enhancing the robustness of air traffic networks
CN108429640B (en) Display method and device for nodes of network equipment
Bui et al. A survivable design of last mile communication networks using multi-objective genetic algorithms

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant