Vehicle-machine collaborative delivery route optimization method and system

Abstract

The present invention provides a method and system for optimizing the path of vehicle-machine collaborative pickup and delivery, and relates to the field of path optimization technology. The present invention obtains the pickup and delivery task data of multiple drones and vehicles in collaboration; based on the pickup and delivery task data, a vehicle-machine collaborative pickup and delivery model is constructed with the goal of minimizing the transportation distance of all vehicles and drones in the delivery process and the pickup process; based on the pickup and delivery task data, the vehicle-machine collaborative pickup and delivery model is solved to obtain the drone path and the vehicle driving path. The present invention considers using the vehicle-machine collaborative method to pick up and deliver goods, and when planning the logistics distribution route, it also considers recycling the goods or their packaging to reduce the reverse logistics cost and the pickup and delivery cost.

Description

Technical Field

[0001] The present invention relates to the technical field of route optimization, and in particular to a method and system for optimizing a route for vehicle-machine collaborative pickup and delivery. Background Art

[0002] As drone technology continues to mature, in the field of terminal delivery, many logistics companies and technology companies have completed preliminary experiments on using drones for terminal delivery. Due to the limitations of drone load and flight distance, drones can only deliver goods of specific specifications to customers within a certain range. Therefore, the use of pure drone delivery still has great limitations in terms of battery life and load. Combining vehicles with drones for delivery can effectively solve the problem of drone battery life and load.

[0003] The current logistics problem of vehicle-machine collaboration generally considers optimizing the delivery route with the goal of minimizing delivery time or shortest delivery route.

[0004] However, the existing methods do not take the problem of reverse logistics into consideration, resulting in a low utilization rate of the optimized path in terms of reverse logistics, which makes the entire pickup and delivery logistics transportation cost higher. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] In view of the deficiencies in the prior art, the present invention provides a method and system for optimizing the path of vehicle-machine collaborative pickup and delivery, which solves the technical problem that the prior vehicle-machine collaborative path optimization method does not take reverse logistics into consideration.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] In a first aspect, the present invention provides a method for optimizing a vehicle-machine collaborative pickup and delivery route, comprising the following steps:

[0010] S1, obtain the data of the delivery task coordinated by multiple drones and vehicles;

[0011] S2. Based on the delivery task data, a vehicle-machine collaborative delivery model is constructed with the goal of minimizing the transportation distance of all vehicles and drones during the delivery and pickup processes;

[0012] S3. Solve the vehicle-machine collaborative delivery model based on the delivery task data to obtain the drone path and vehicle driving path.

[0013] Preferably, the method of solving the vehicle-machine collaborative pickup and delivery model in S3 includes solving the vehicle-machine collaborative pickup and delivery model by a greedy algorithm and a saving algorithm.

[0014] Preferably, the vehicle-machine collaborative delivery model includes an objective function, such as formula (1):

[0015] in:

[0016] represents the distance traveled by vehicle k from i to j;

[0017] represents the distance traveled by drone k′ from i to j;

[0018]

[0019]

[0020] V a represents the anchor node set, V a =(1,2,3...a), V a =V s ∪V f , V s represents the set of drone launch nodes, V f Represents the set of drone landing nodes;

[0021] V0 represents the warehouse node;

[0022] K t represents the vehicle set;

[0023] K d Represents a drone set.

[0024] Preferably, the vehicle-machine collaborative delivery model includes constraints, such as formulas (2) to (14):

[0025]

[0026]

[0027]

[0028]

[0029]

[0030]

[0031]

[0032]

[0033]

[0034]

[0035]

[0036]

[0037]

[0038] in:

[0039] V a represents the anchor node set, V a =(1,2,3...a), V a =V s ∪V f , V s represents the set of drone launch nodes, V f Represents the set of drone landing nodes;

[0040] V0 represents the warehouse node;

[0041] K t represents the vehicle set;

[0042] K d represents the set of drones;

[0043] C represents the customer node set, C = (1.2.3...n), C = C d ∪C p , C d =(1.2.3...n) represents the set of delivery customer nodes, C p =(1.2.3...n) represents the set of pickup customer nodes;

[0044] Ca represents the volume of vehicle k;

[0045] Ba represents the endurance of UAV k′;

[0046] D i represents the demand of node i;

[0047] represents the load of vehicle k after leaving point i;

[0048] represents the battery usage of drone k′ after passing point i;

[0049] T i k represents the arrival time of vehicle k at node i;

[0050] represents the arrival time of UAV k′ at node i;

[0051] The vehicle k passes through the arc<i,j> The driving time;

[0052] Indicates the arc of UAV k<i,j> The driving time;

[0053] Formula (2) represents the flow balance constraint of vehicles entering and leaving the warehouse. Any vehicle leaving the warehouse must return to the warehouse;

[0054] Formula (3) means ensuring the flow balance of any vehicle at any node;

[0055] Formula (4) indicates that any customer point is visited by a certain drone and only once, and the drone visits the customer uniquely;

[0056] Formula (5) means that for drone k′ visiting customer j, all arcs arriving at point j are added together, and all arcs leaving point j are added together, and they are made equal to ensure the flow balance of drones at the customer point.

[0057] Formula (6) represents the flow balance of drone take-off and landing points. This constraint is an originality constraint, which uses the order of accessing nodes to constrain that there will be no conflict between drone sorties;

[0058] Formula (7) is an originality constraint. Since the number of drone cargo units is limited, the order of accessing nodes is used to constrain any flight to prevent the situation where the first pick-up and the last delivery are not allowed.

[0059] Formula (8) and Formula (9) are originality constraints. Due to the limited number of cargo units carried by drones, based on the existing flight constraints, any flight is allowed to deliver goods once and pick up goods once at most, that is, any flight is allowed to have the situation of delivering first and picking up later or picking up one by one and delivering one by one;

[0060] Formula (10) and Formula (11) indicate that the demand of each customer is within the range of the drone’s cargo capacity;

[0061] Formula (12) represents the constraints of the vehicle's real-time load, and the large M constraint ensures the feasibility of the formula;

[0062] Formula (13) indicates that the UAV flight endurance constraint is completed on the basis of the existing flight constraint;

[0063] Formula (14) indicates that when a UAV carried by any vehicle returns to this point, the vehicle must arrive there before that point.

[0064] Preferably, S3 specifically includes:

[0065] S301, importing the delivery task data, and calculating the Euclidean distance between each node;

[0066] S302, store all anchor points in a linked list A<>, randomly select an anchor point a as the starting point, and delete the point after selection; and determine whether the anchor point linked list A<> is empty, if not, proceed to the next step; if empty, proceed to S312;

[0067] S303, finding the delivery point D with the shortest distance from the anchor point a;

[0068] S304, determine whether the time spent between two points meets the endurance of the drone; determine whether the vehicle's load in this round is less than the vehicle's volume; if both are met, proceed to the next step; if any one is not met, proceed to S309;

[0069] S305, each anchor point a corresponds to a circle number r, and it is determined whether the circle number is less than the maximum circle number. If not, it returns to the second step; if so, the circle number is increased by 1, and the delivery point Cir[a][r][1]=D is stored in the circle;

[0070] S306, finding a pickup point P that is the shortest distance from the delivery point D;

[0071] S307, determine whether the accumulated time of the lap meets the endurance of the drone; determine whether the vehicle's load in the lap is less than the vehicle's volume; if both are satisfied, proceed to the next step; if any one is not satisfied, proceed to S303;

[0072] S308, the pickup point Cir[a][r][2]=P is stored in the round, and the process returns to S302;

[0073] S309, finding a pickup point P that is the shortest distance from the anchor point a;

[0074] S310, determine whether the time spent between two points meets the endurance of the drone; determine whether the vehicle's load in this round is less than the vehicle's volume; if both are met, proceed to the next step; if any one is not met, proceed to S302;

[0075] S311, the number of rounds + 1, the round stores the pickup point Cir[a][r][1] = P, and determines whether the number of rounds is less than the maximum number of rounds, if not, return to S302; if so, return to S309;

[0076] S312, storing the anchor points whose number of turns is greater than 0 in a new linked list An<>;

[0077] S313, calculating the saved mileage between the anchor points, and sorting and storing them in the linked list CW<>, where the attributes include anchor point a1, anchor point a2, and saved mileage;

[0078] S314, access the mileage saving table CW<> according to the idea of ​​the serial mileage saving algorithm; and determine whether the access is completed. If the access is completed, then it is completed and the vehicle path and the drone path are output; otherwise, go to the next step;

[0079] S315, judging whether the accumulated initial load of the vehicle in the warehouse and the real-time load at each anchor point meet the vehicle volume constraint, if so, proceeding to the next step, otherwise, returning to S314;

[0080] S316, storing the anchor point in the corresponding vehicle path; and returning to S314.

[0081] Preferably, the method of solving the vehicle-machine collaborative pickup and delivery model in S3 includes solving the vehicle-machine collaborative pickup and delivery model by means of a genetic algorithm.

[0082] Preferably, solving the vehicle-machine collaborative pickup and delivery model by genetic algorithm includes:

[0083] Step 1: Initial population number P_num, maximum number of evolutions I_num, initial temperature S_tem, cooling coefficient T_tem; Generate P_num solutions through the initial solution heuristic rule to form the initial population Pop_List; Design the optimal individual in the current Pop_List as the global optimal solution GlobalBest, and initialize the number of evolutions i = 0;

[0084] Step 2: Determine whether the current evolution number i is less than or equal to the maximum evolution number I_num. If so, proceed to the next step. If not, end the evolution and output the global optimal solution, that is, output the vehicle path and the drone path;

[0085] Step 3: Take the inverse of the objective function as the fitness value and calculate the fitness value of each individual;

[0086] Step 4: Select the population Select_Pop that participates in this round of evolution from Pop_List;

[0087] Step 5: In Select_Pop, select individuals as parent 1 and parent 2 for crossover and mutation operations to obtain new offspring individuals as neighborhood solutions, with i=i+1;

[0088] Step 6: Check whether the obtained neighborhood solution is a feasible solution through constraint conditions to adjust the solution of the combined path and update the current temperature coefficient;

[0089] Step 7: Determine whether the fitness value of the neighborhood solution is greater than or equal to the global optimal solution. If so, proceed to the next step; if not, proceed to Step 9;

[0090] Step8: Update the global optimal solution;

[0091] Step 9: Determine whether the neighborhood solution is greater than or equal to the current optimal solution. If so, proceed to Step 11; otherwise, proceed to Step 10;

[0092] Step 10: Use the Metroplis rule to accept the inferior solution. The probability expression of acceptance is: Where Δf = cost(New_In)-cost(Select_Pop[j]), T refers to the current annealing temperature;

[0093] Step 11: Update the next generation population; return to Step 2.

[0094] In a second aspect, the present invention provides a vehicle-machine collaborative pickup and delivery route optimization system, comprising:

[0095] Data acquisition module, which acquires the data of pick-up and delivery tasks coordinated by multiple drones and vehicles;

[0096] A model building module, based on the delivery task data, builds a vehicle-machine collaborative delivery model with the goal of minimizing the transportation distance of all vehicles and drones during the delivery process and the pickup process;

[0097] The path acquisition module solves the vehicle-machine collaborative delivery model based on the delivery task data to obtain the drone path and the vehicle driving path.

[0098] In a third aspect, the present invention provides a computer-readable storage medium storing a computer program for optimizing a route for collaborative pickup and delivery of goods between a vehicle and a computer, wherein the computer program enables a computer to execute the above-mentioned method for optimizing a route for collaborative pickup and delivery of goods between a vehicle and a computer.

[0099] In a fourth aspect, the present invention provides an electronic device, comprising:

[0100] one or more processors;

[0101] Memory; and

[0102] 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, and the programs include programs for executing the vehicle-machine collaborative pick-up and delivery path optimization method as described above.

[0103] (III) Beneficial effects

[0104] The present invention provides a method and system for optimizing the path of vehicle-machine collaborative pickup and delivery. Compared with the prior art, it has the following beneficial effects:

[0105] The present invention obtains the task data of multiple drones and vehicles to pick up and deliver goods; based on the task data, a vehicle-machine collaborative pickup and delivery model is constructed with the goal of minimizing the transportation distance of all vehicles and drones during the delivery process and the pickup process; the vehicle-machine collaborative pickup and delivery model is solved based on the task data to obtain the drone path and the vehicle driving path. The present invention considers using the vehicle-machine collaborative method to pick up and deliver goods, and when planning the logistics distribution route, it also considers recycling the goods or their packaging to reduce the reverse logistics cost and the pickup and delivery cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0106] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0107] Figure 1 A block diagram of a method for optimizing a vehicle-machine collaborative pickup and delivery route in an embodiment of the present invention. DETAILED DESCRIPTION

[0108] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0109] The embodiments of the present application provide a method and system for optimizing the path for vehicle-machine collaborative pickup and delivery, thereby solving the technical problem that the existing vehicle-machine collaborative path optimization method does not take reverse logistics into consideration, thereby improving the utilization rate of the optimized path in reverse logistics and reducing the cost of reverse logistics.

[0110] The technical solution in the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0111] A method for optimizing the path of vehicle-machine collaborative pickup and delivery in an embodiment of the present invention mainly includes two parts: one is to establish a vehicle-machine collaborative pickup and delivery model based on multiple vehicles and multiple drones; the other is to propose a heuristic rule algorithm based on the characteristics of the problem. The heuristic rule is a solution based on 2E-VRP, combining the ideas of the greedy algorithm and the mileage saving algorithm, using anchor points as entry points to obtain feasible solutions for vehicle-drone routes. This model can describe the problem of multiple drone takeoffs during vehicle-machine collaborative delivery, and takes into account the endurance constraints of each drone and the load problem of each vehicle, which is more in line with the actual operation process of vehicle-machine collaboration. Based on the vehicle-machine collaborative pickup and delivery model, an embodiment of the present invention proposes a heuristic-based path planning algorithm. With the support of this algorithm, the efficiency of vehicle-machine collaborative pickup and delivery can be further improved, reducing the cost of reverse logistics.

[0112] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0113] The embodiment of the present invention provides a method for optimizing a vehicle-machine collaborative pickup and delivery route. Figure 1 As shown, the method comprises the following steps:

[0114] S1, obtain the data of the delivery task coordinated by multiple drones and vehicles;

[0115] S2. Based on the delivery task data, a vehicle-machine collaborative delivery model is constructed with the goal of minimizing the transportation distance of all vehicles and drones during the delivery and pickup processes;

[0116] S3. Solve the vehicle-machine collaborative delivery model based on the delivery task data to obtain the drone path and vehicle driving path.

[0117] The embodiment of the present invention considers using a vehicle-machine collaborative method to pick up and deliver goods. When planning a logistics distribution route, it also considers recycling the goods or their packaging to reduce reverse logistics costs and reduce pickup and delivery costs.

[0118] The following is a detailed description of each step:

[0119] In step S1, the data of the delivery task coordinated by multiple drones and vehicles is obtained. The specific implementation process is as follows:

[0120] Get delivery task data: distribution network data, transportation tool data, demand-related data and decision variables.

[0121] in,

[0122] The distribution network data includes the distribution network directed graph G = <V, E>, V = {0, 1, ..., n + 1} node set, the node set includes: V0 warehouse node; customer node set C = (1.2.3 ... n), C = C d ∪C p ,

[0123] C d =(1.2.3...n) represents the set of delivery customer nodes, C p =(1.2.3...n) represents the set of customer nodes for picking up goods; the anchor node set V a =(1,2,3...a), V a =V s ∪V f , V s represents the set of drone launch nodes, V f represents the set of nodes where the drone lands; E = {(i, j) | i, j∈V, i≠j} means that there is an arc between nodes i and j, that is, the vehicle can travel from node i to node j; the distance that vehicle k travels from i to j is the distance that drone k′ travels from i to j It should be noted that in the embodiment of the present invention, the vehicle carrying the drone departs from the warehouse node V0 and arrives at the designated anchor point V a The drone takes off from this anchor point to pick up and deliver the goods, and then lands back at the anchor point. The vehicle is not responsible for picking up and delivering the goods, but only serves as a mobile base station to shorten the limited flight range of the drone.

[0124] The transportation tool data includes: transportation tool set K = K t ∪K d , K t =(1.2.3...k) represents the vehicle set, K d =(1.2.3...k′) represents the set of drones; the volume Ca of vehicle k and the endurance Ba of drone k′.

[0125] Demand-related data include: demand D of node i i ; The load of vehicle k after leaving point i Battery usage of drone k′ after passing point i The arrival time T of vehicle k at node i i k ; Arrival time of drone k′ at node i Vehicle k arc<i,j> Driving time Drone K Warp Arc<i,j> Driving time Drone launch time SL and drone recovery time SR.

[0126] The decision variables include:

[0127] and

[0128] In step S2, based on the delivery task data, a vehicle-machine collaborative delivery model is constructed with the goal of minimizing the transportation distance of all vehicles and drones during the delivery and pickup processes. The specific implementation process is as follows:

[0129] The vehicle-machine collaborative delivery model includes an objective function and constraints. The objective function is as shown in formula (1):

[0130]

[0131] The constraints include formulas (2) to (14):

[0132]

[0133]

[0134]

[0135]

[0136]

[0137]

[0138]

[0139]

[0140]

[0141]

[0142]

[0143]

[0144]

[0145] in:

[0146] Formula (2) represents the flow balance constraint of vehicles entering and leaving the warehouse. Any vehicle leaving the warehouse must return to the warehouse;

[0147] Formula (3) means ensuring the flow balance of any vehicle at any node;

[0148] Formula (4) indicates that any customer point is visited by a certain drone and only once, and the drone visits the customer uniquely;

[0149] Formula (5) means that for drone k′ visiting customer j, all arcs arriving at point j are added together, and all arcs leaving point j are added together, and they are made equal to ensure the flow balance of drones at the customer point.

[0150] Formula (6) represents the flow balance of drone take-off and landing points. This constraint is an originality constraint, which uses the order of accessing nodes to constrain that there will be no conflict between drone sorties;

[0151] Formula (7) is an originality constraint. Since the number of drone cargo units is limited, the order of accessing nodes is used to constrain any flight to prevent the situation where the first pick-up and the last delivery are not allowed.

[0152] Formula (8) and Formula (9) are originality constraints. Due to the limited number of cargo units carried by drones, based on the existing flight constraints, any flight is allowed to deliver goods once and pick up goods once at most, that is, any flight is allowed to have the situation of delivering first and picking up later or picking up one by one and delivering one by one;

[0153] Formula (10) and Formula (11) indicate that the demand of each customer is within the range of the drone’s cargo capacity;

[0154] Formula (12) represents the constraint condition of the vehicle's real-time load. The large M constraint guarantees the feasibility of the formula; that is, a large M constraint is constructed so that the inequality still holds when the vehicle does not pass through route i to j. M is an infinite positive number.

[0155] Formula (13) indicates that the UAV flight endurance constraint is completed on the basis of the existing flight constraint;

[0156] Formula (14) indicates that when a UAV carried by any vehicle returns to this point, the vehicle must arrive there before that point.

[0157] In step S3, the vehicle-machine collaborative delivery model is solved based on the delivery task data to obtain the drone path and vehicle driving path. The specific implementation process is as follows:

[0158] It should be noted that, in the embodiment of the present invention, the vehicle-machine collaborative pickup and delivery model can be solved by a genetic algorithm or other heuristic algorithms. In the embodiment of the present invention, a genetic algorithm is briefly introduced, and a solution based on 2E-VRP is specifically introduced, combining the ideas of the greedy algorithm and the mileage saving algorithm to solve the vehicle-machine collaborative pickup and delivery model.

[0159] The process of solving the vehicle-machine collaborative pickup and delivery model through genetic algorithm is as follows:

[0160] Step 1: Initial population number P_num, maximum number of evolutions I_num, initial temperature S_tem, cooling coefficient T_tem; Generate P_num solutions through the initial solution heuristic rule to form the initial population Pop_List; Design the optimal individual in the current Pop_List as the global optimal solution, and initialize the number of evolutions i=0;

[0161] Step 2: Determine whether the current evolution number i is less than or equal to the maximum evolution number I_num. If so, proceed to the next step. If not, end the evolution and output the global optimal solution, that is, output the vehicle path and the drone path;

[0162] Step 3: Take the inverse of the objective function as the fitness value and calculate the fitness value of each individual;

[0163] Step 4: Use the roulette wheel selection strategy to select the population Select_Pop participating in this round of evolution from Pop_List;

[0164] Step 5: In Select_Pop, select individuals as parent 1 and parent 2 for crossover and mutation operations to obtain new offspring individuals as neighborhood solutions, with i=i+1;

[0165] Step 6: Check whether the obtained neighborhood solution is a feasible solution through constraint conditions to adjust the solution of the combined path and update the current temperature coefficient;

[0166] Step 7: Determine whether the fitness value of the neighborhood solution is greater than or equal to the global optimal solution. If so, proceed to the next step; if not, proceed to Step 9;

[0167] Step8: Update the global optimal solution;

[0168] Step 9: Determine whether the neighborhood solution is greater than or equal to the current optimal solution. If so, proceed to Step 11; otherwise, proceed to Step 10;

[0169] Step 10: Use the Metroplis rule to accept the inferior solution. The probability expression of acceptance is: Where Δf = cost(New_In)-cost(Select_Pop[j]), T refers to the current annealing temperature;

[0170] Step 11: Update the next generation population; return to Step 2.

[0171] Based on the 2E-VRP solution, combined with the ideas of the greedy algorithm and the mileage saving algorithm, the specific process of solving the vehicle-machine collaborative pickup and delivery model is as follows:

[0172] S301, importing the delivery task data, and calculating the Euclidean distance between each node;

[0173] S302, store all anchor points in a linked list A<>, randomly select an anchor point a as the starting point, and delete the point after selection; and determine whether the anchor point linked list A<> is empty, if not, proceed to the next step; if empty, proceed to S312;

[0174] S303, finding the delivery point D with the shortest distance from the anchor point a;

[0175] S304, determine whether the time spent between two points meets the endurance of the drone; determine whether the vehicle's load in this round is less than the vehicle's volume; if both are met, proceed to the next step; if any one is not met, proceed to S309;

[0176] S305, each anchor point a corresponds to a circle number r, and it is determined whether the circle number is less than the maximum circle number. If not, it returns to the second step; if so, the circle number is increased by 1, and the delivery point Cir[a][r][1]=D is stored in the circle;

[0177] S306, finding a pickup point P that is the shortest distance from the delivery point D;

[0178] S307, determine whether the accumulated time of the lap meets the endurance of the drone; determine whether the vehicle's load in the lap is less than the vehicle's volume; if both are satisfied, proceed to the next step; if any one is not satisfied, proceed to S303;

[0179] S308, the pickup point Cir[a][r][2]=P is stored in the round, and the process returns to S302;

[0180] S309, finding a pickup point P that is the shortest distance from the anchor point a;

[0181] S310, determine whether the time spent between two points meets the endurance of the drone; determine whether the vehicle's load in this round is less than the vehicle's volume; if both are met, proceed to the next step; if any one is not met, proceed to S302;

[0182] S311, the number of rounds + 1, the round stores the pickup point Cir[a][r][1] = P, and determines whether the number of rounds is less than the maximum number of rounds, if not, return to S302; if so, return to S309;

[0183] S312, storing the anchor points whose number of turns is greater than 0 in a new linked list An<>;

[0184] S313, calculating the saved mileage between the anchor points, and sorting and storing them in the linked list CW<>, where the attributes include anchor point a1, anchor point a2, and saved mileage;

[0185] S314, access the mileage saving table CW<> according to the idea of ​​the serial mileage saving algorithm; and determine whether the access is completed. If the access is completed, it ends and outputs the vehicle path and the drone path; if the access is not completed, proceed to the next step;

[0186] S315: Determine whether the accumulated initial load of the vehicle in the warehouse and the real-time load at each anchor point meet the vehicle volume constraint. If so, proceed to the next step; if not, return to S314;

[0187] S316: Store the anchor point in the corresponding vehicle path, and then return to S314.

[0188] The embodiment of the present invention further provides a vehicle-machine collaborative pickup and delivery route optimization system, comprising:

[0189] Data acquisition module, which acquires the data of pick-up and delivery tasks coordinated by multiple drones and vehicles;

[0190] A model building module, based on the delivery task data, builds a vehicle-machine collaborative delivery model with the goal of minimizing the transportation distance of all vehicles and drones during the delivery process and the pickup process;

[0191] The path acquisition module solves the vehicle-machine collaborative delivery model based on the delivery task data to obtain the drone path and the vehicle driving path.

[0192] It can be understood that the vehicle-machine collaborative pickup and delivery path optimization system provided in an embodiment of the present invention corresponds to the above-mentioned vehicle-machine collaborative pickup and delivery path optimization method, and the explanations, examples, beneficial effects and other parts of its relevant contents can refer to the corresponding contents in the vehicle-machine collaborative pickup and delivery path optimization method, and will not be repeated here.

[0193] An embodiment of the present invention also provides a computer-readable storage medium storing a computer program for optimizing the path for collaborative pickup and delivery between vehicle and computer, wherein the computer program enables a computer to execute the method for optimizing the path for collaborative pickup and delivery between vehicle and computer as described above.

[0194] An embodiment of the present invention further provides an electronic device, including:

[0195] one or more processors;

[0196] Memory; and

[0197] 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, and the programs include programs for executing the vehicle-machine collaborative pick-up and delivery path optimization method as described above.

[0198] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0199] 1. The embodiment of the present invention considers using a vehicle-machine collaborative method to pick up and deliver goods. When planning the logistics distribution route, it also considers recycling the goods or their packaging to reduce reverse logistics costs and reduce the cost of picking up and delivering goods.

[0200] 2. The vehicle-machine collaborative pickup and delivery model proposed in the embodiment of the present invention can describe the problem of multiple drone takeoffs during the vehicle-machine collaborative delivery process, and take into account the endurance constraints of each drone and the load capacity of each vehicle, which is more in line with the actual operation process of vehicle-machine collaboration, and facilitates the subsequent deriving of vehicle paths and drone paths that conform to the actual operation process based on the model, thereby reducing the cost of pickup and delivery.

[0201] 3. The embodiment of the present invention proposes a heuristic rule algorithm based on the characteristics of the vehicle-machine collaborative pickup and delivery model. The heuristic rule is a solution based on 2E-VRP, combining the ideas of the greedy algorithm and the mileage-saving algorithm, and using the anchor point as the entry point to obtain the optimal solution for the vehicle-drone route, further improving the efficiency of vehicle-machine collaborative pickup and delivery and reducing the cost of reverse logistics.

[0202] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0203] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the route of picking up and delivering goods in collaboration with a vehicle and a machine, characterized in that: The following steps are involved: S1, obtain the data of the delivery task coordinated by multiple drones and vehicles; S2. Based on the delivery task data, a vehicle-machine collaborative delivery model is constructed with the goal of minimizing the transportation distance of all vehicles and drones during the delivery and pickup processes; S3, solving the vehicle-machine collaborative delivery model based on the delivery task data to obtain the drone path and vehicle driving path; The vehicle-machine collaborative delivery model includes an objective function, such as formula (1): in: represents the distance traveled by vehicle k from i to j; represents the distance traveled by drone k′ from i to j; V a represents the anchor node set, V a =(1,2,3...a), V a =V s ∪V f , V s represents the set of drone launch nodes, V f Represents the set of drone landing nodes; V0 represents the warehouse node; K t represents the vehicle set; K d represents the set of drones; The vehicle-machine collaborative delivery model includes constraints, such as formulas (2) to (14): in: V a represents the anchor node set, V a =(1,2,3...a), V a =V s ∪V f , V s represents the set of drone launch nodes, V f Represents the set of drone landing nodes; V0 represents the warehouse node; K t represents the vehicle set; K d represents the set of drones; C represents the customer node set, C = (1.2.3...n), C = C d ∪C p , C d =(1.2.3...n) represents the set of delivery customer nodes, C p =(1.2.3...n) represents the set of pickup customer nodes; Ca represents the volume of vehicle k; Ba represents the endurance of UAV k′; D i represents the demand of node i; represents the load of vehicle k after leaving point i; represents the battery usage of drone k′ after passing point i; represents the arrival time of vehicle k at node i; represents the arrival time of UAV k′ at node i; The vehicle k passes through the arc<i,j> The driving time; Indicates the arc of UAV k<i,j> The driving time; Formula (2) represents the flow balance constraint of vehicles entering and leaving the warehouse. Any vehicle leaving the warehouse must return to the warehouse; Formula (3) means ensuring the flow balance of any vehicle at any node; Formula (4) indicates that any customer point is visited by a certain drone and only once, and the drone visits the customer uniquely; Formula (5) means that for drone k′ visiting customer j, all arcs arriving at point j are added together, and all arcs leaving point j are added together, and they are made equal to ensure the flow balance of drones at the customer point. Formula (6) represents the flow balance of drone take-off and landing points. This constraint is an originality constraint, which uses the order of accessing nodes to constrain that there will be no conflict between drone sorties; Formula (7) is an originality constraint. Since the number of cargo units carried by drones is limited, the order of accessing nodes is used to constrain any flight to prevent the situation where the first pick-up and the last delivery are not allowed; Formula (8) and Formula (9) are originality constraints. Due to the limited number of cargo units carried by drones, based on the existing flight constraints, any flight is allowed to deliver goods once and pick up goods once at most, that is, any flight is allowed to have the situation of delivering first and picking up later or picking up one by one and delivering one by one; Formula (10) and Formula (11) indicate that the demand of each customer is within the range of the drone’s cargo capacity; Formula (12) represents the constraints of the vehicle's real-time load, and the large M constraint ensures the feasibility of the formula; Formula (13) indicates that the UAV flight endurance constraint is completed on the basis of the existing flight constraint; Formula (14) indicates that when a UAV carried by any vehicle returns to this point, the vehicle must arrive there before that point.

2. The vehicle-machine collaborative delivery route optimization method according to claim 1, characterized in that: The method of solving the vehicle-machine collaborative pickup and delivery model in S3 includes solving the vehicle-machine collaborative pickup and delivery model through a greedy algorithm and a saving algorithm.

3. The vehicle-machine collaborative delivery route optimization method according to any one of claims 1 to 2, characterized in that: The S3 specifically includes: S301, importing the delivery task data, and calculating the Euclidean distance between each node; S302, store all anchor points in a linked list A<>, randomly select an anchor point a as the starting point, and delete the point after selection; and determine whether the anchor point linked list A<> is empty, if not, proceed to the next step; if empty, proceed to S312; S303, finding the delivery point D with the shortest distance from the anchor point a; S304, determine whether the time spent between two points meets the endurance of the drone; determine whether the vehicle's load in this round is less than the vehicle's volume; if both are met, proceed to the next step; if any one is not met, proceed to S309; S305, each anchor point a corresponds to a circle number r, and it is determined whether the circle number is less than the maximum circle number. If not, it returns to the second step; if so, the circle number is increased by 1, and the delivery point Cir[a][r][1]=D is stored in the circle; S306, finding a pickup point P that is the shortest distance from the delivery point D; S307, determine whether the accumulated time of the lap meets the endurance of the drone; determine whether the vehicle's load in the lap is less than the vehicle's volume; if both are satisfied, proceed to the next step; if any one is not satisfied, proceed to S303; S308, the pickup point Cir[a][r][2]=P is stored in the round, and the process returns to S302; S309, finding a pickup point P that is the shortest distance from the anchor point a; S310, determine whether the time spent between two points meets the endurance of the drone; determine whether the vehicle's load in this round is less than the vehicle's volume; if both are met, proceed to the next step; if any one is not met, proceed to S302; S311, the number of rounds + 1, the round stores the pickup point Cir[a][r][1] = P, and determines whether the number of rounds is less than the maximum number of rounds, if not, return to S302; if so, return to S309; S312, storing the anchor points whose number of turns is greater than 0 in a new linked list An<>; S313, calculating the saved mileage between the anchor points, and sorting and storing them in the linked list CW<>, where the attributes include anchor point a1, anchor point a2, and saved mileage; S314, access the mileage saving table CW<> according to the idea of ​​the serial mileage saving algorithm; and determine whether the access is completed. If the access is completed, then it is completed and the vehicle path and the drone path are output; otherwise, go to the next step; S315, judging whether the accumulated initial load of the vehicle in the warehouse and the real-time load at each anchor point meet the vehicle volume constraint, if so, proceeding to the next step, otherwise, returning to S314; S316, storing the anchor point in the corresponding vehicle path; and returning to S314.

4. The vehicle-machine collaborative delivery route optimization method according to claim 1, characterized in that: The method of solving the vehicle-machine collaborative pickup and delivery model in S3 includes solving the vehicle-machine collaborative pickup and delivery model through a genetic algorithm.

5. The vehicle-machine collaborative delivery route optimization method as claimed in claim 4, characterized in that: The method of solving the vehicle-machine collaborative delivery model by using a genetic algorithm includes: Step 1: Initial population number P_num, maximum number of evolutions I_num, initial temperature S_tem, cooling coefficient T_tem; Generate P_num solutions through the initial solution heuristic rule to form the initial population Pop_List; Design the optimal individual in the current Pop_List as the global optimal solution, and initialize the number of evolutions i=0; Step 2: Determine whether the current evolution number i is less than or equal to the maximum evolution number I_num. If so, proceed to the next step. If not, end the evolution and output the global optimal solution, that is, output the vehicle path and the drone path; Step 3: Take the inverse of the objective function as the fitness value and calculate the fitness value of each individual; Step 4: Select the population Select_Pop that participates in this round of evolution from Pop_List; Step 5: In Select_Pop, select individuals as parent 1 and parent 2 for crossover and mutation operations to obtain new offspring individuals as neighborhood solutions, with i=i+1; Step 6: Check whether the obtained neighborhood solution is a feasible solution through constraint conditions to adjust the solution of the combined path and update the current temperature coefficient; Step 7: Determine whether the fitness value of the neighborhood solution is greater than or equal to the global optimal solution. If so, proceed to the next step; if not, proceed to Step 9; Step8: Update the global optimal solution; Step 9: Determine whether the fitness value of the neighborhood solution is greater than or equal to the current optimal solution. If so, proceed to step 11; otherwise, proceed to step 10; Step 10: Use the Metroplis rule to accept the inferior solution. The probability expression of acceptance is: Where Δf = cost(New_In)-cost(Select_Pop[j]), T refers to the current annealing temperature; Step 11: Update the next generation population; return to Step 2.

6. A vehicle-machine collaborative delivery route optimization system, characterized in that: include: Data acquisition module, which acquires the data of pick-up and delivery tasks coordinated by multiple drones and vehicles; A model building module, based on the delivery task data, builds a vehicle-machine collaborative delivery model with the goal of minimizing the transportation distance of all vehicles and drones during the delivery process and the pickup process; A path acquisition module solves the vehicle-machine collaborative delivery model based on the delivery task data to obtain the drone path and vehicle driving path; The vehicle-machine collaborative delivery model includes an objective function, such as formula (1): in: represents the distance traveled by vehicle k from i to j; represents the distance traveled by drone k′ from i to j; V a represents the anchor node set, V a =(1,2,3...a), V a =V s ∪V f , V s represents the set of drone launch nodes, V f Represents the set of drone landing nodes; V0 represents the warehouse node; K t represents the vehicle set; K d represents the set of drones; The vehicle-machine collaborative delivery model includes constraints, such as formulas (2) to (14): in: V a represents the anchor node set, V a =(1,2,3...a), V a =V s ∪V f , V s represents the set of drone launch nodes, V f Represents the set of drone landing nodes; V0 represents the warehouse node; K t represents the vehicle set; K d represents the set of drones; C represents the customer node set, C = (1.2.3...n), C = C d ∪C p , C d =(1.2.3...n) represents the set of delivery customer nodes, C p =(1.2.3...n) represents the set of pickup customer nodes; Ca represents the volume of vehicle k; Ba represents the endurance of UAV k′; D i represents the demand of node i; represents the load of vehicle k after leaving point i; represents the battery usage of drone k′ after passing point i; represents the arrival time of vehicle k at node i; represents the arrival time of UAV k′ at node i; The vehicle k passes through the arc<i,j> The driving time; Indicates the arc of UAV k<i,j> The driving time; Formula (2) represents the flow balance constraint of vehicles entering and leaving the warehouse. Any vehicle leaving the warehouse must return to the warehouse; Formula (3) means ensuring the flow balance of any vehicle at any node; Formula (4) indicates that any customer point is visited by a certain drone and only once, and the drone visits the customer uniquely; Formula (5) means that for drone k′ visiting customer j, all arcs arriving at point j are added together, and all arcs leaving point j are added together, and they are made equal to ensure the flow balance of drones at the customer point. Formula (6) represents the flow balance of drone take-off and landing points. This constraint is an originality constraint, which uses the order of accessing nodes to constrain that there will be no conflict between drone sorties; Formula (7) is an originality constraint. Since the number of cargo units carried by drones is limited, the order of accessing nodes is used to constrain any flight to prevent the situation where the first pick-up and the last delivery are not allowed; Formula (8) and Formula (9) are originality constraints. Due to the limited number of cargo units carried by drones, based on the existing flight constraints, any flight is allowed to deliver goods once and pick up goods once at most, that is, any flight is allowed to have the situation of delivering first and picking up later or picking up one by one and delivering one by one; Formula (10) and Formula (11) indicate that the demand of each customer is within the range of the drone’s cargo capacity; Formula (12) represents the constraints of the vehicle's real-time load, and the large M constraint ensures the feasibility of the formula; Formula (13) indicates that the UAV flight endurance constraint is completed on the basis of the existing flight constraint; Formula (14) indicates that when a UAV carried by any vehicle returns to this point, the vehicle must arrive there before that point.

7. A computer-readable storage medium, characterized in that: It stores a computer program for optimizing the path of vehicle-machine collaborative pickup and delivery, wherein the computer program enables the computer to execute the method for optimizing the path of vehicle-machine collaborative pickup and delivery as described in any one of claims 1 to 5.

8. An electronic device, characterized in that: include: one or more processors; Memory; as well as 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, and the programs include programs for executing the vehicle-machine collaborative pick-up and delivery path optimization method as described in any one of claims 1 to 5.

Images