A method for planning a cooperative delivery path of a UAV vehicle considering dynamic requests

Abstract

This invention discloses a drone-vehicle collaborative delivery route planning method considering dynamic requests. It employs a two-stage solution process based on clustering-based scenario prediction, comprising: Stage 1: Generating initial delivery routes for predetermined static demands, and then delivering goods according to these routes; Stage 2: Continuously monitoring for newly generated demands during the delivery process. For new demands, the current drone and truck positions are evaluated, and the demands are inserted into unexecuted routes using an insertion algorithm. This process continues until the end of the work cycle, forming the final delivery plan. This invention can solve collaborative path planning for trucks and drones in dynamic scenarios, thereby improving overall delivery efficiency and reducing overall delivery distance.

Description

Technical Field

[0001] This invention belongs to the field of path optimization, specifically a method for planning collaborative delivery routes for unmanned aerial vehicles that takes into account dynamic requests. Background Technology

[0002] With the rapid development of e-commerce and on-demand delivery services, logistics and distribution systems, especially the last-mile delivery segment, face continuous challenges in terms of operational efficiency and service costs.

[0003] Traditional vehicle routing models and their optimization methods are mainly designed for delivery scenarios with a single vehicle type. When dealing with highly dynamic urban logistics demands, they have limitations in model structure and are difficult to achieve efficient resource allocation in complex delivery environments.

[0004] To improve the adaptability and economy of last-mile delivery, drone delivery has been gradually introduced. Drone delivery, with its spatial mobility, can, to some extent, circumvent ground traffic constraints and achieve rapid, direct delivery. Building on this, a truck-drone collaborative delivery model has been further proposed, integrating the combined advantages of truck carrying capacity and drone flexibility.

[0005] Although the truck-drone collaborative delivery model has shown optimization potential, existing research has mainly focused on static scenarios, and its synergistic effects in dynamic scenarios have not yet been systematically explored. Summary of the Invention

[0006] The present invention addresses the shortcomings of the existing technology by proposing a method for collaborative delivery path planning of unmanned aerial vehicles (UAVs) that considers dynamic requests. This method aims to solve collaborative path schemes between trucks and UAVs in dynamic scenarios, thereby improving overall delivery efficiency and reducing overall delivery distance.

[0007] To achieve the above-mentioned objectives, the present invention adopts the following technical solution: The present invention provides a drone-vehicle collaborative delivery route planning method that considers dynamic requests. This method is applied to a scenario where a single delivery center receives an initial order set from N potential customer locations and assigns it to a truck and its equipped drone. The truck departs fully loaded from the delivery center, completes the initial order and any subsequent new orders, and then returns to the delivery center. The drone-vehicle collaborative delivery route planning method includes the following steps: Step 1: For the initial order, generate the initial delivery route for the truck and its equipped drone. and initialize the current planned route. ; Step 2: The truck and its equipped drone execute the currently planned route. During the process, the distribution center received new dynamic orders. At that time, an improved insertion algorithm is applied to... insert In this process, a delivery route with the shortest total driving distance is obtained. and will Assign to Then, return to step 2 and execute sequentially until... Continue until completion.

[0008] The method for collaborative delivery route planning of unmanned aerial vehicles (UAVs) considering dynamic requests, as described in this invention, is characterized in that step 1 includes: Step 1.1 Denote the initial order set as ={ },in, Indicates the first One initial order, and The customer's point number is recorded as , The demand is denoted as ;Will The set of potential customer points corresponding to the above is denoted as . ; Define and initialize a known order set. ; Define and initialize an initial order probability table generated from N potential customer locations. ={ },in, Indicates the first The probability of generating an initial order from a potential customer point, and And the expected number of initial orders; ; ; Step 1.2 If any known order ,make Corresponding potential customer point number Probability of generated intermediate orders 1. Otherwise, let Thus, the probability table of intermediate orders is obtained. ; ;in, Indicates the first The probability of an intermediate order from a potential customer point; Step 1.3 Use equation (1) to obtain the first... Probability of final orders generated by potential customer locations Thus, the final order probability table is obtained. : = (1) In equation (1), This represents the set of numbers for N potential customer locations; express The set consisting of the IDs of all potential customer locations corresponding to all known orders; Indicates the first The initial order probability of a potential customer point Indicates the first The probability of an intermediate order generated by a potential customer point; Step 1.4 Apply the kmem++ algorithm to... Clustering potential customer points by distance yields... Clustering results { … … } and its cluster centers { … , ..., };in, Indicates the first The set of IDs for potential customer points corresponding to each cluster; for Cluster centers ; Step 1.5 Based on Calculate the first according to formula (2) The probability of orders generated by each cluster This allows us to obtain a probability table for each cluster to generate orders. = { }; = (2) In equation (2), Indicates belonging to the first Each cluster represents the set of all customer point IDs. Indicates the first The probability of a final order generated by a potential customer point; Step 1.6 Traversal ,against , producing the first A random number between (0, 1) ,like ,Will Use it as the virtual customer point's ID and add it to the set of virtual customer point IDs. If the condition is met, then it is not included, thus obtaining the final result. ; Step 1.7 and After merging, we obtain the set of customer point numbers currently pending processing. ; Initialize truck path This indicates that the trucks' routes all start from and return to the distribution center; Step 1.8 will For each customer point, try inserting it into the second-to-last position of the truck path. Then calculate the distance increase after insertion and select the customer point with the smallest distance increase for insertion to obtain the new truck path. Then, remove the inserted customer points from the... Remove from the middle; Step 1.9 Process the new truck route as in Step 1.8 until... Until the set is empty, the final truck path is obtained and denoted as . ; Step 1.10 Initialize the drone path It is an empty set; Step 1.11 from The process begins by traversing the first non-distribution center customer point in the list. If the current customer point is a virtual customer point, the traversal continues; otherwise, the corresponding customer point is removed from the list. Remove and insert In the process, it checks whether the inserted drone path meets the drone's load and endurance constraints. If it does, the inserted drone path is retained; otherwise, the original drone path is retained, until the drone is traversed to the next node. The updated truck route is obtained by stopping at the last non-distribution center customer point in the route. and the final drone path And form a truck-drone collaborative delivery route. .

[0009] Furthermore, step 2 includes: Step 2.1 Define and initialize the current time. ; Define and initialize exist Execution status under ,in, Indicates in Disembarkation route The path point number reached in the process, exist Drone path The path point number reached in the process; Step 2.2 When there is a new dynamic order Upon arrival, ,in, express The arrival time; Get exist Execution status under ; Step 2.3 Inspection Does the cluster center of the corresponding customer point belong to... If it belongs to the category, proceed to step 2.4; otherwise, proceed to step 3. The cluster center of the corresponding customer point is used as the virtual customer point's ID and added to the set of virtual customer point IDs. In, and from medium-sized truck route The Starting from each path point, traverse backwards in the manner that minimizes the distance increased. The corresponding cluster center is inserted into the truck path. Then proceed to step 2.4; Step 2.4 From respectively medium-sized truck route The Each waypoint and the drone path The Starting from the path points, traverse backwards to determine the path. Corresponding customer points The nearest truck waypoint a and drone waypoint b; Step 2.5 Based on the truck route The type of truck waypoint 'a' and the drone path The type of drone path point b in the data will be determined by the following: Insert the nearest neighbor customer point neighborhood of a and the nearest neighbor customer point neighborhood of b respectively to obtain the truck-drone collaborative delivery route for each type; Step 2.6 Select delivery routes that meet the drone load and range constraints from the truck-drone collaborative delivery routes under each type, calculate the total driving distance of each selected delivery route, and choose the delivery route with the shortest total driving distance. .

[0010] Furthermore, there are five types of truck waypoint a in step 2.5, including: The first type is where point 'a' is neither the launch point nor the recovery point of the drone, but when the truck arrives at truck path point 'a', the drone has already been launched and is no longer on the truck. Therefore, Insert the truck waypoint preceding or following truck waypoint a; The second type is where point a is neither the launch point nor the recovery point of the drone, and the drone remains on the truck when the truck reaches point a on its path. In this case, Insert the element before or after truck waypoint 'a'; or Build for services A new drone flight mission, with launch point 'a' and the next truck path point after 'a' as the return point, will be inserted into the drone's path. In, or, build for services A new drone flight mission with 'a' as the recovery point and the preceding truck path point as the launch point, and inserts the drone path... middle; The third type is where 'a' is the launch point but not the recovery point, then... Insert the truck waypoint preceding or following 'a', or construct a path for the service. A new drone flight mission with 'a' as the recovery point and the preceding truck path point as the launch point, and inserts the drone path... In, or, will Insert drone path In the UAV flight mission with launch point a; The fourth type is where 'a' is a recovery point but not a launch point, then... Insert the truck waypoint preceding or following 'a', or, build the service... A new drone flight mission is initiated from point 'a', with the next truck path point after 'a' as the return point, and the drone path is inserted into the launch path. In, or, will Insert into drone path In the drone flight mission with point a as the recovery point.

[0011] The fifth type is where 'a' is both a recovery point and a launch point, then... Insert the truck waypoint preceding or following 'a', or... Insert into drone path In a UAV flight mission with launch point 'a', or, Insert into drone path In the drone flight mission with point a as the recovery point; The type of drone waypoint b is only the type of customer served by the drone, and will Insert as drone path The path point of the drone preceding or following drone in the middle b.

[0012] The present invention provides an electronic device, including a memory and a processor, characterized in that the memory is used to store a program supporting the processor to execute the unmanned vehicle collaborative delivery route planning method considering dynamic requests, and the processor is configured to execute the program stored in the memory.

[0013] The present invention discloses a computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, performs the unmanned aerial vehicle collaborative delivery route planning method that takes into account dynamic requests.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention constructs a delivery solution for dynamic logistics delivery scenarios by adopting a dynamic truck-drone route. The collaborative delivery of drones and trucks allows the advantages of the two modes of transportation to complement each other, effectively handling dynamic orders added during the delivery process, improving the overall efficiency of last-mile delivery, and reducing logistics operating costs.

[0015] 2. In collaborative path planning, this invention innovatively applies the probability of potential customers generating orders to the solution algorithm, and proposes a two-stage cluster-based scenario prediction construction algorithm, which effectively predicts dynamic orders, thereby reducing the overall delivery distance. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the problem scenario of the present invention; Figure 2 This is a schematic diagram of the truck-drone route of the present invention; Figure 3 This is a schematic diagram of the neighborhood structure of the insertion algorithm of this invention. Detailed Implementation

[0017] In this embodiment, a drone-vehicle collaborative delivery route planning method considering dynamic requests is characterized by its application to a scenario where a delivery center receives an initial order set from N potential customer locations and assigns it to a truck and its equipped drone. The truck departs fully loaded from the delivery center, completes the initial orders and subsequent new orders, and then returns to the delivery center. Specifically, as follows... Figure 1 As shown, Figure 1 (a) shows the initial moment, including the truck-drone path with all static orders. Each truck departs from and eventually returns to the distribution center, coordinating the mission by launching and recovering drones along the way. Figure 1 (b) shows the dynamic truck-drone path at a decision point within the work cycle, where the solid line indicates that the path has been executed, and the surrounding triangles represent newly arriving dynamic orders. Figure 1 (c) shows the dynamic truck-drone path after a decision at a certain moment within the work cycle, where triangles represent dynamic orders that, if accepted, will be inserted into paths that have not yet been executed. This drone-vehicle collaborative delivery path planning method includes the following steps: Step 1: For the initial order, generate the initial delivery route for the truck and its equipped drone. and initialize the current planned route. ; Step 1.1 Denote the initial order set as ={ },in, Indicates the first One initial order, and The customer's point number is recorded as , The demand is denoted as ;Will The set of potential customer points corresponding to the above is denoted as . ; Define and initialize a known order set. ; Define and initialize an initial order probability table generated from N potential customer locations. ={ },in, Indicates the first The probability of generating an initial order from a potential customer point, and And the expected number of initial orders; ; .

[0018] Step 1.2 If any known order ,Will Corresponding potential customer point number Probability of generated intermediate orders 1. Otherwise, Thus, the probability table of intermediate orders is obtained. ; ;in, Indicates the first The initial order probability of a potential customer point.

[0019] Step 1.3 Use equation (1) to obtain the first... Probability of final orders generated by potential customer locations Thus, the final order probability table is obtained. : = (1) In equation (1), This represents the set of numbers for N potential customer locations; express The set consisting of the IDs of all potential customer locations corresponding to all known orders; Indicates the first The initial order probability of a potential customer point Indicates the first The probability of an intermediate order generated by a potential customer point.

[0020] Step 1.4 Apply the kmem++ algorithm to... Clustering potential customer points by distance yields... Clustering results { … … } and its cluster centers { … , ..., };in, Indicates the first The set of IDs for potential customer points corresponding to each cluster; for Cluster centers ; Step 1.5 Based on Calculate the first according to formula (2) The probability of orders generated by each cluster This allows us to obtain a probability table for each cluster to generate orders. = { }; = (2) In equation (2), Indicates the first The probability of generating a final order from a potential customer point.

[0021] Step 1.6 generates the first A random number between 0 and 1 ,like ,Will Use it as the virtual customer point's ID and add it to the set of virtual customer point IDs. If the condition is met, then it is not included, thus obtaining the final result. ; Step 1.7 and After merging, we obtain the set of customer point numbers currently pending processing. ; Initialize truck path This indicates that the trucks' routes all start from and return to the distribution center.

[0022] Step 1.8 will For each customer point, try inserting it into the second-to-last position of the truck path. Then calculate the distance increase after insertion and select the customer point with the smallest distance increase for insertion to obtain the new truck path. Then, remove the inserted customer points from the... Remove from the middle; Step 1.9 Process the new truck route as in Step 1.8 until... Let the empty set be the location, and the final truck path be denoted as . .

[0023] Step 1.10 Initialize the drone path It is an empty set; Step 1.11 from The process begins by traversing the first non-distribution center customer point in the list. If the current customer point is a virtual customer point, the traversal continues; otherwise, the corresponding customer point is removed from the list. Remove and insert In the process, it checks whether the inserted drone path meets the drone's load and endurance constraints. If it does, the inserted drone path is retained; otherwise, the original drone path is retained, until the drone is traversed to the next node. The updated truck route is obtained by stopping at the last non-distribution center customer point in the route. and the final drone path And form a truck-drone collaborative delivery route. .

[0024] Specific truck-drone route example Figure 2 As shown, Figure 2 The truck path represents the route taken by the truck starting from distribution center 0, following the path: Distribution Center 0 → Customer Point 3 → Customer Point 7 → Customer Point 5 → Customer Point 6 → Cluster Center 1 (-1001) → Customer Point 11 → Customer Point 14 → Customer Point 9 → Cluster Center 3 (-1003) → Customer Point 15 → Customer Point 12 → Customer Point 8 → Customer Point 10 → Customer Point 16 → Distribution Center 0, finally returning to the distribution center. The cluster centers represent virtual customers with no actual order demand. The drone path represents the route taken from the distribution center... The process involves three drone flight segments: launch drone from point 0 to customer point 2, then to customer point 1, and finally to customer point 3; launch drone from customer point 11 to customer point 4, then to customer point 9; and launch drone from customer point 8 to customer point 13, then to customer point 10. A value of -1 indicates the end of each segment. The current path status flag indicates that the first seven waypoints of the truck and drone's paths are fixed at the current moment. The only feasible insertion point for a newly arriving order is after the seventh waypoint in either the truck's or drone's path.

[0025] Step 2: The truck and its equipped drone execute the currently planned route. During the process, the distribution center received new dynamic orders. At that time, an improved insertion algorithm is applied to... insert In this process, a new delivery route with the optimal total driving distance is obtained. and will Assign to Then, return to step 2 and execute sequentially until... Until completion.

[0026] Step 2.1 Define and initialize the current time. ; Define and initialize exist Execution status under ,in, Indicates in Disembarkation route The path point number reached in the process, exist Drone path The path point number reached in the process; Step 2.2 When there is a new dynamic order Upon arrival, ,in, express The arrival time; Get exist Execution status under .

[0027] Step 2.3 Inspection Does the cluster center of the corresponding customer point belong to... If it belongs to the category, proceed to step 2.4; otherwise, proceed to step 3. The cluster center of the corresponding customer point is used as the virtual customer point's ID and added to the set of virtual customer point IDs. In, and from medium-sized truck route The Starting from each path point, traverse backwards in the manner that minimizes the distance increased. The corresponding cluster center is inserted into the truck path. Then proceed to step 2.4; Step 2.4 From respectively medium-sized truck route The Each waypoint and the drone path The Starting from the path points, traverse backwards to determine the path. Corresponding customer points The nearest truck waypoint a and drone waypoint b.

[0028] Step 2.5 Based on the truck route The type of truck waypoint 'a' and the drone path The type of drone path point b in the data will be determined by the following: Insert the nearest neighbor customer point neighborhood of a and the nearest neighbor customer point neighborhood of b respectively to obtain the truck-drone collaborative delivery route for each type; Step 2.6 Select delivery routes that meet the drone load and range constraints from the truck-drone collaborative delivery routes under each type, calculate the total driving distance of each selected delivery route, and choose the delivery route with the shortest total driving distance. .

[0029] Specific types such as Figure 3 As shown, the red dashed line represents an existing drone mission, the black dashed line represents a truck path, the green dashed line represents a newly created drone mission, the green circle represents the found path point a or b, and the green square represents the possible insertion position.

[0030] There are 5 types of points a on the truck path.

[0031] The first type, such as Figure 3 As shown in (b), a is neither the launch point nor the recovery point of the drone, but when the truck arrives at truck path point a, the drone has already been launched and is no longer on the truck. Therefore, Insert the truck waypoint preceding or following truck waypoint a; The second type, such as Figure 3 As shown in (c), a is neither the launch point nor the recovery point of the drone, and when the truck arrives at truck path point a, the drone has not been launched and is still on the truck. Therefore, Insert the position before or after truck waypoint 'a'; or construct a service. A new drone flight mission, with launch point 'a' and the next truck path point after 'a' as the return point, will be inserted into the drone's path. In, or, build for services A new drone flight mission with 'a' as the recovery point and the preceding truck path point as the launch point, and inserts the drone path... middle; The third type, such as Figure 3 As shown in (d), a is the launch point but not the recovery point, then... Insert the truck waypoint preceding or following 'a', or construct a path for the service. A new drone flight mission with 'a' as the recovery point and the preceding truck path point as the launch point, and inserts the drone path... In, or, will Insert drone path In the UAV flight mission with launch point a; The fourth type, such as Figure 3 As shown in (e), a is the recovery point but not the launch point, then... Insert the truck waypoint preceding or following 'a', or, build the service... A new drone flight mission is initiated from point 'a', with the next truck path point after 'a' as the return point, and the drone path is inserted into the launch path. In, or, will Insert into drone path In the drone flight mission with point a as the recovery point.

[0032] The fifth type, such as Figure 3 As shown in (f), a is both the recovery point and the launch point, then... Insert the truck waypoint preceding or following 'a', or... Insert into drone path In a UAV flight mission with launch point 'a', or, Insert into drone path In the drone flight mission with point a as the recovery point.

[0033] like Figure 3 As shown in (a), the type of drone waypoint b is only the type of customer served by the drone, and will Insert as drone path The path point of the drone preceding or following drone in the middle b.

[0034] Step 2.6 Select delivery routes that meet the drone's payload and range constraints from all delivery options under each type, and calculate the total travel distance for each delivery route to select the delivery option with the shortest total travel distance. As the current solution .

[0035] An electronic device includes a memory and a processor, the memory for storing a program that supports the processor in executing the aforementioned drone vehicle collaborative delivery route planning method that takes into account dynamic requests, the processor being configured to execute the program stored in the memory.

[0036] A computer-readable storage medium on which a computer program is stored, which, when executed by a processor, performs the aforementioned method for collaborative delivery route planning of unmanned aerial vehicles that takes into account dynamic requests.

Claims

1. A method for collaborative delivery route planning of unmanned aerial vehicles (UAVs) considering dynamic requests, characterized in that, This method is applied to a scenario where a single distribution center receives an initial order set from N potential customer locations and assigns it to a truck and its equipped drone. The truck departs fully loaded from the distribution center, completes the initial orders and any subsequent new orders, and then returns to the distribution center. The drone-vehicle collaborative delivery path planning method includes the following steps: Step 1: For the initial order, generate the initial delivery route for the truck and its equipped drone. and initialize the current planned route. ; Step 2: The truck and its equipped drone execute the currently planned route. During the process, the distribution center received new dynamic orders. At that time, an improved insertion algorithm is applied to... insert In this process, a delivery route with the shortest total driving distance is obtained. and will Assign to Then, return to step 2 and execute sequentially until... Continue until completion.

2. The method for collaborative delivery route planning of unmanned aerial vehicles (UAVs) considering dynamic requests according to claim 1, characterized in that, Step 1 includes: Step 1.1 Denote the initial order set as ={ },in, Indicates the first One initial order, and The customer's point number is recorded as , The demand is denoted as ;Will The set of potential customer points corresponding to the above is denoted as . ; Define and initialize a known order set. ; Define and initialize an initial order probability table generated from N potential customer locations. ={ },in, Indicates the first The probability of generating an initial order from a potential customer point, and And the expected number of initial orders; ; ; Step 1.2 If any known order ,make Corresponding potential customer point number Probability of generated intermediate orders 1. Otherwise, let Thus, the probability table of intermediate orders is obtained. ; ;in, Indicates the first The probability of an intermediate order from a potential customer point; Step 1.3 Use equation (1) to obtain the first... Probability of final orders generated by potential customer locations Thus, the final order probability table is obtained. : = (1) In equation (1), This represents the set of numbers for N potential customer locations; express The set consisting of the IDs of all potential customer locations corresponding to all known orders; Indicates the first The initial order probability of a potential customer point Indicates the first The probability of an intermediate order generated by a potential customer point; Step 1.4 Apply the kmem++ algorithm to... Clustering potential customer points by distance yields... Clustering results { … … } and its cluster centers { … , ..., };in, Indicates the first The set of IDs for potential customer points corresponding to each cluster; for Cluster centers ; Step 1.5 Based on Calculate the first according to formula (2) The probability of orders generated by each cluster This allows us to obtain a probability table for each cluster to generate orders. = { }; = (2) In equation (2), Indicates belonging to the first Each cluster represents the set of all customer point IDs. Indicates the first The probability of a final order generated by a potential customer point; Step 1.6 Traversal ,against , producing the first A random number between (0, 1) ,like ,Will Use it as the virtual customer point's ID and add it to the set of virtual customer point IDs. If not, then do not join, thus obtaining the final result. ; Step 1.7 and After merging, we obtain the current set of customer point numbers to be processed. ; Initialize truck path This indicates that the trucks' routes all start from and return to the distribution center; Step 1.8 will For each customer point, try inserting it into the second-to-last position of the truck path. Then calculate the distance increase after insertion and select the customer point with the smallest distance increase for insertion to obtain the new truck path. Then, remove the inserted customer points from the... Remove from middle; Step 1.9 Process the new truck route as in Step 1.8 until... Until the set is empty, the final truck path is obtained and denoted as . ; Step 1.10 Initialize the drone path It is an empty set; Step 1.11 from The process begins by traversing the first non-distribution center customer point in the list. If the current customer point is a virtual customer point, the traversal continues; otherwise, the corresponding customer point is removed from the list. Remove and insert In the process, it checks whether the inserted drone path meets the drone's load and endurance constraints. If it does, the inserted drone path is retained; otherwise, the original drone path is retained, until the drone is traversed to the next node. The updated truck route is obtained by stopping at the last non-distribution center customer point in the route. and the final drone path And form a truck-drone collaborative delivery route. .

3. The method for collaborative delivery route planning of unmanned aerial vehicles considering dynamic requests according to claim 2, characterized in that, Step 2 includes: Step 2.1 Define and initialize the current time. ; Define and initialize exist Execution status under ,in, Indicates in Disembarkation route The path point number reached in the process, exist Drone path The path point number reached in the process; Step 2.2 When there is a new dynamic order Upon arrival, ,in, express The arrival time; Get exist Execution status under ; Step 2.3 Inspection Does the cluster center of the cluster to which the corresponding customer point belongs belong to? If it belongs to the category, proceed to step 2.4; otherwise, proceed to step 3. The cluster center of the corresponding customer point is used as the virtual customer point's ID and added to the set of virtual customer point IDs. In, and from medium-sized truck route The Starting from each path point, traverse backwards to minimize the distance increased. The corresponding cluster center is inserted into the truck path. Then proceed to step 2.4; Step 2.4 From respectively medium-sized truck route The Each waypoint and the drone path The Starting from the path points, traverse backwards to determine the path. Corresponding customer points The nearest truck waypoint a and drone waypoint b; Step 2.5 Based on the truck route The type of truck waypoint 'a' and the drone path The type of drone path point b in the data will be determined by the following: Insert the nearest neighbor customer point neighborhood of a and the nearest neighbor customer point neighborhood of b respectively to obtain the truck-drone collaborative delivery route for each type; Step 2.6 Select delivery routes that meet the drone load and range constraints from the truck-drone collaborative delivery routes under each type, calculate the total driving distance of each selected delivery route, and choose the delivery route with the shortest total driving distance. .

4. The method for collaborative delivery route planning of unmanned aerial vehicles considering dynamic requests according to claim 3, characterized in that, There are five types of truck waypoint a in step 2.5, including: The first type is where point 'a' is neither the launch point nor the recovery point of the drone, but when the truck arrives at truck path point 'a', the drone has already been launched and is no longer on the truck. Therefore, Insert the truck waypoint before or after truck waypoint a; The second type is where point 'a' is neither the launch point nor the recovery point of the drone, and the drone remains on the truck when the truck reaches point 'a' on its path. Insert the element before or after truck waypoint 'a'; or Build for services A new drone flight mission, with launch point 'a' and the next truck path point after 'a' as the return point, will be inserted into the drone's path. In, or, build for services A new drone flight mission with 'a' as the recovery point and the preceding truck path point as the launch point, and inserts the drone path... middle; The third type is where 'a' is the launch point but not the recovery point, then... Insert the truck waypoint preceding or following 'a', or construct a path for the service. A new drone flight mission with 'a' as the recovery point and the preceding truck path point as the launch point, and inserts the drone path... In, or, will Insert drone path In the UAV flight mission with launch point a; The fourth type is where 'a' is a recovery point but not a launch point, then... Insert the truck waypoint preceding or following 'a', or, build the service... A new drone flight mission is initiated from point a, with the next truck path point after point a as the return point, and the drone path is inserted into the launch path. In, or, will Insert into drone path In the drone flight mission with point a as the recovery point. The fifth type is where 'a' is both a recovery point and a launch point, then... Insert the truck waypoint preceding or following 'a', or... Insert into drone path In a UAV flight mission with launch point 'a', or... Insert into drone path In the drone flight mission with point a as the recovery point; The type of drone waypoint b is only the type of customer served by the drone, and will Insert as drone path The previous or next drone waypoint in the middle b.

5. An electronic device, comprising a memory and a processor, characterized in that, The memory is used to store programs that support the processor in executing the drone vehicle collaborative delivery route planning method considering dynamic requests as described in any of claims 1-4, and the processor is configured to execute the programs stored in the memory.

6. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program is executed by the processor to perform the drone vehicle collaborative delivery route planning method that takes into account dynamic requests as described in any of claims 1-4.

Images