Logistics task allocation method and device based on multiple unmanned vehicles

Abstract

The invention discloses a logistics task allocation method and device based on multiple unmanned vehicles. The method comprises the steps of obtaining state information of an unmanned vehicle set; the state information comprises position coordinates, electric quantity, loading capacity, running speed and predicted time for arriving at the next station; the unmanned vehicle set comprises N unmanned vehicles; obtaining a logistics task information set; the logistics task information set comprises M logistics tasks, and each logistics task comprises order quantity, cargo weight, volume, delivery address and expected delivery time; and processing the state information of the unmanned vehicle set and the logistics task information set to obtain a logistics task allocation result. According to the method, the real-time state of the unmanned vehicle and the diversified requirements of the logistics tasks are comprehensively considered, so that more reasonable and efficient task allocation can be realized, the logistics distribution efficiency is improved, and the distribution time and cost are reduced.

Description

Technical Field

[0001] This invention relates to the field of task allocation technology, and in particular to a logistics task allocation method and apparatus based on multiple unmanned vehicles. Background Technology

[0002] With the rapid development of the logistics industry, the demand for efficient and intelligent logistics distribution systems is increasing. Traditional logistics distribution mainly relies on human-driven vehicles, which suffers from problems such as high labor intensity, low delivery efficiency, and errors and delays caused by human factors. In recent years, unmanned vehicle technology has gradually emerged and been applied in the logistics field, providing a new approach to solving these problems.

[0003] However, in logistics delivery scenarios involving multiple autonomous vehicles, the rational allocation of logistics tasks has become a key challenge. Existing task allocation methods often have the following shortcomings: First, they fail to fully consider the real-time status of autonomous vehicles, such as battery level, load capacity, and speed, leading to unreasonable task allocation and impacting delivery efficiency and the utilization efficiency of the autonomous vehicles. Second, they have poor adaptability to complex and ever-changing logistics task demands, struggling to cope with fluctuations in order volume and differences in delivery time requirements. Third, they lack effective global optimization strategies, failing to achieve overall reduction in logistics costs and improvement in delivery service quality. Therefore, a more intelligent and efficient multi-autonomous vehicle-based logistics task allocation method is needed to meet the demands of modern logistics development. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a logistics task allocation method and device based on multiple unmanned vehicles, which can comprehensively consider the real-time status of unmanned vehicles and the diverse needs of logistics tasks, realize efficient and reasonable task allocation, improve logistics delivery efficiency, and reduce logistics costs.

[0005] To address the aforementioned technical problems, a first aspect of this invention discloses a logistics task allocation method based on multiple unmanned vehicles, the method comprising:

[0006] S1, Obtain the status information of the unmanned vehicle set; the status information includes location coordinates, battery level, load capacity, driving speed, and estimated arrival time at the next station; the unmanned vehicle set includes N unmanned vehicles;

[0007] S2, Obtain a set of logistics task information; the set of logistics task information includes M logistics tasks, each logistics task including order quantity, cargo weight, volume, delivery address, and expected delivery time;

[0008] S3, process the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result.

[0009] As an optional implementation, in the first aspect of the present invention, processing the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result includes:

[0010] S31, Process the state information of the unmanned vehicle set and the logistics task information set to obtain a logistics task allocation model;

[0011] S32, Solve the logistics task allocation model to obtain the logistics task allocation result.

[0012] As an optional implementation, in the first aspect of the present invention, processing the state information of the unmanned vehicle set and the logistics task information set to obtain a logistics task allocation model includes:

[0013] S311, Process the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation constraints;

[0014] The expression for the logistics task allocation constraint is as follows:

[0015]

[0016] Where, x ij Let N represent the number of tasks performed by driverless vehicle i, and M represent the number of driverless vehicles.

[0017] S312, Process the constraints of the logistics task allocation to obtain the logistics task allocation model.

[0018] As an optional implementation, in the first aspect of the present invention, the expression for the logistics task allocation model is:

[0019]

[0020] Where f is the logistics task allocation model, d ij t is the distance traveled by the autonomous vehicle i along the planned path for task j. ij The driving time e for autonomous vehicle i to perform the planned path for task j ij The charging price is the cost of planning the route for autonomous vehicle i to perform task j, where α, β, and λ are the weights of driving time, travel distance, and charging price, and α + β + γ = 1, T max and T min D represents the minimum and maximum driving time. max and D min E represents the minimum and maximum travel distances. max and E min V represents the minimum and maximum charging prices. sump is the sum of the values ​​of performing the tasks. ij The probability V of autonomous vehicle i performing task j. j The value function for performing task j,

[0021] As an optional implementation, in the first aspect of the present invention, solving the logistics task allocation model to obtain the logistics task allocation result includes:

[0022] S321, Process the state information of the unmanned vehicle set and the logistics task information set to obtain the first distance matrix, and initialize the iteration number, honey source exploration limit, and population size;

[0023] S322: Randomly generate food sources according to the population size, calculate the objective function value, and set the exploration count for each food source to 0;

[0024] S323, randomly select a univariate operator to perform a neighborhood search on the food source to obtain a first new solution; when the first new solution is greater than a preset first constraint threshold, replace the original solution with the first new solution; when the first new solution is less than or equal to the preset first constraint threshold, increment the number of explorations of the food source by 1.

[0025] S324, randomly select an observation object from the solution set, perform a binary operator operation on the current food source based on the observation object, and obtain a second new solution; when the second new solution is greater than the preset second constraint threshold, replace the original solution with the second new solution; when the second new solution is less than or equal to the preset second constraint threshold, increment the number of explorations of the food source by 1;

[0026] S325, check the number of times each food source has been explored. When the number of times a food source has been explored reaches the limit, use the elite scouting strategy to generate a new food source and reset the number of times the corresponding location has been explored to 0.

[0027] S326, Sort the current population and solution set to obtain the solution set sequence;

[0028] S327, Select the first half of the solutions from the solution set sequence as the updated solution set;

[0029] S328, when the preset maximum number of iterations is reached, the updated solution set is output; the updated solution set is the logistics task allocation result.

[0030] As an optional implementation, in the first aspect of the present invention, the expression for the first distance matrix is:

[0031]

[0032] The starting coordinates of the driverless vehicle are (x i,y i The forward angle is α, the minimum turning radius is r, and the target point's position coordinates are (x, y). t ,y t ), θ=2π-(θ1-θ2), (x p ,y p ) with (x i ,y i Let r be the coordinates of the point of tangency on the original circle with center r and radius r.

[0033] As an optional implementation, in the first aspect of the present invention, the step of sorting the current population and the solution set to obtain a solution set sequence includes:

[0034] S3261, Rank the current population and solution set to obtain the preprocessed population;

[0035] S3262, Process the pre-processed population to obtain the crowding distance index;

[0036] The expression for the congestion distance index is as follows:

[0037]

[0038] Where, P(i+1).f k Let P(i-1).f represent the objective function value of the i-th individual in the sorted population on the k-th objective function. k f represents the objective function value of the (i-1)th individual in the sorted population on the k-th objective function. k Let P(i) be the weight value of the k-th objective. dis Let r be the crowding distance index for the i-th individual, and r be the number of individuals.

[0039] S3263, Sort the current population and solution set according to the crowding distance index to obtain the solution set sequence.

[0040] A second aspect of this invention discloses a logistics task allocation device based on multiple unmanned vehicles, the device comprising:

[0041] The unmanned vehicle information acquisition module is used to acquire the status information of the unmanned vehicle ensemble; the status information includes location coordinates, battery level, load capacity, driving speed, and estimated arrival time at the next station; the unmanned vehicle ensemble includes N unmanned vehicles.

[0042] The logistics task information acquisition module is used to acquire a set of logistics task information; the set of logistics task information includes M logistics tasks, and each logistics task includes order quantity, cargo weight, volume, delivery address, and expected delivery time;

[0043] The logistics task allocation module is used to process the status information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result.

[0044] As an optional implementation, in the second aspect of the present invention, the processing of the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result includes:

[0045] S31, Process the state information of the unmanned vehicle set and the logistics task information set to obtain a logistics task allocation model;

[0046] S32, Solve the logistics task allocation model to obtain the logistics task allocation result.

[0047] As an optional implementation, in the second aspect of the present invention, the processing of the state information of the unmanned vehicle set and the logistics task information set to obtain a logistics task allocation model includes:

[0048] S311, Process the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation constraints;

[0049] The expression for the logistics task allocation constraint is as follows:

[0050]

[0051] Where, x ij Let N represent the number of tasks performed by driverless vehicle i, and M represent the number of driverless vehicles.

[0052] S312, Process the constraints of the logistics task allocation to obtain the logistics task allocation model.

[0053] As an optional implementation, in the second aspect of the present invention, the expression for the logistics task allocation model is:

[0054]

[0055] Where f is the logistics task allocation model, d ij t is the distance traveled by the autonomous vehicle i along the planned path for task j. ij The driving time e for autonomous vehicle i to perform the planned path for task j ij The charging price is the cost of planning the route for autonomous vehicle i to perform task j, where α, β, and λ are the weights of driving time, travel distance, and charging price, and α + β + γ = 1, T max and T min D represents the minimum and maximum driving time. maxand D min E represents the minimum and maximum travel distances. max and E min V represents the minimum and maximum charging prices. sum p is the sum of the values ​​of performing the tasks. ij The probability V of autonomous vehicle i performing task j. j The value function for performing task j,

[0056] As an optional implementation, in the second aspect of the present invention, solving the logistics task allocation model to obtain the logistics task allocation result includes:

[0057] S321, Process the state information of the unmanned vehicle set and the logistics task information set to obtain the first distance matrix, and initialize the iteration number, honey source exploration limit, and population size;

[0058] S322: Randomly generate food sources according to the population size, calculate the objective function value, and set the exploration count for each food source to 0;

[0059] S323, randomly select a univariate operator to perform a neighborhood search on the food source to obtain a first new solution; when the first new solution is greater than a preset first constraint threshold, replace the original solution with the first new solution; when the first new solution is less than or equal to the preset first constraint threshold, increment the number of explorations of the food source by 1.

[0060] S324, randomly select an observation object from the solution set, perform a binary operator operation on the current food source based on the observation object, and obtain a second new solution; when the second new solution is greater than the preset second constraint threshold, replace the original solution with the second new solution; when the second new solution is less than or equal to the preset second constraint threshold, increment the number of explorations of the food source by 1;

[0061] S325, check the number of times each food source has been explored. When the number of times a food source has been explored reaches the limit, use the elite scouting strategy to generate a new food source and reset the number of times the corresponding location has been explored to 0.

[0062] S326, Sort the current population and solution set to obtain the solution set sequence;

[0063] S327, Select the first half of the solutions from the solution set sequence as the updated solution set;

[0064] S328, when the preset maximum number of iterations is reached, the updated solution set is output; the updated solution set is the logistics task allocation result.

[0065] As an optional implementation, in a second aspect of the present invention, the expression for the first distance matrix is:

[0066]

[0067] The starting coordinates of the driverless vehicle are (x i ,y i The forward angle is α, the minimum turning radius is r, and the target point is... Let be the coordinates of the point of tangency on the original radius.

[0068] As an optional implementation, in the second aspect of the present invention, the step of sorting the current population and the solution set to obtain a solution set sequence includes:

[0069] S3261, Rank the current population and solution set to obtain the preprocessed population;

[0070] S3262, Process the pre-processed population to obtain the crowding distance index;

[0071] The expression for the congestion distance index is as follows:

[0072]

[0073] Where, P(i+1).f k Let P(i-1).f represent the objective function value of the i-th individual in the sorted population on the k-th objective function. k f represents the objective function value of the (i-1)th individual in the sorted population on the k-th objective function. k Let P(i) be the weight value of the k-th objective. dis Let r be the crowding distance index for the i-th individual, and r be the number of individuals.

[0074] S3263, Sort the current population and solution set according to the crowding distance index to obtain the solution set sequence.

[0075] A third aspect of the present invention discloses another logistics task allocation device based on multiple unmanned vehicles, the device comprising:

[0076] Memory containing executable program code;

[0077] A processor coupled to the memory;

[0078] The processor calls the executable program code stored in the memory to execute some or all of the steps in the logistics task allocation method based on multiple unmanned vehicles disclosed in the first aspect of the present invention.

[0079] The fourth aspect of the present invention discloses a computer-storable medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the logistics task allocation method based on multiple unmanned vehicles disclosed in the first aspect of the present invention.

[0080] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0081] This invention designs and implements a logistics task allocation method based on multiple unmanned vehicles. By comprehensively considering the real-time status of unmanned vehicles and the diverse needs of logistics tasks, it can achieve more reasonable and efficient task allocation, improve logistics and distribution efficiency, reduce delivery time and costs, and ensure the smooth progress of logistics and distribution. Attached Figure Description

[0082] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0083] Figure 1 This is a flowchart illustrating a logistics task allocation method based on multiple unmanned vehicles disclosed in an embodiment of the present invention;

[0084] Figure 2 This is a schematic diagram of the structure of a logistics task allocation device based on multiple unmanned vehicles disclosed in an embodiment of the present invention;

[0085] Figure 3 This is a schematic diagram of another logistics task allocation device based on multiple unmanned vehicles disclosed in an embodiment of the present invention. Detailed Implementation

[0086] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0087] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0088] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0089] This invention discloses a method and apparatus for logistics task allocation based on multiple unmanned vehicles (UAVs). The method includes acquiring the status information of a set of UAVs, including location coordinates, battery level, load capacity, driving speed, and estimated arrival time at the next station; the set of UAVs includes N UAVs; acquiring a set of logistics task information, including M logistics tasks, each logistics task including order quantity, cargo weight, volume, delivery address, and expected delivery time; and processing the status information of the UAVs and the logistics task information set to obtain a logistics task allocation result. This invention, by comprehensively considering the real-time status of the UAVs and the diverse needs of logistics tasks, can achieve more reasonable and efficient task allocation, improve logistics delivery efficiency, and reduce delivery time and costs. Detailed explanations follow.

[0090] Example 1

[0091] Please see Figure 1 , Figure 1 This is a flowchart illustrating a logistics task allocation method based on multiple unmanned vehicles disclosed in an embodiment of the present invention. Wherein, Figure 1 The described multi-unmanned vehicle-based logistics task allocation method is applied in the field of task allocation technology, and the embodiments of this invention are not limited thereto. Figure 1 As shown, the logistics task allocation method based on multiple unmanned vehicles may include the following operations:

[0092] S1, Obtain the status information of the unmanned vehicle set; the status information includes location coordinates, battery level, load capacity, driving speed, and estimated arrival time at the next station; the unmanned vehicle set includes N unmanned vehicles;

[0093] S2, Obtain a set of logistics task information; the set of logistics task information includes M logistics tasks, each logistics task including order quantity, cargo weight, volume, delivery address, and expected delivery time;

[0094] S3, process the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result.

[0095] Optionally, the process of processing the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result includes:

[0096] S31, Process the state information of the unmanned vehicle set and the logistics task information set to obtain a logistics task allocation model;

[0097] S32, Solve the logistics task allocation model to obtain the logistics task allocation result.

[0098] Optionally, the process of processing the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation model includes:

[0099] S311, Process the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation constraints;

[0100] The expression for the logistics task allocation constraint is as follows:

[0101]

[0102] Where, x ij Let N represent the number of tasks performed by driverless vehicle i, and M represent the number of driverless vehicles. This means that each autonomous vehicle can only perform one logistics task. This means that at least one driverless vehicle will be assigned to perform each logistics task.

[0103] Let C be the total energy consumption of the driverless car traveling on the highway (m, m′). E Introduce an energy consumption coefficient α, where α ∈ (1, 2). The total energy consumption C E for:

[0104] C E =α[C c (m,m′)]+C g (m,m′)+C r (m,m′)+C t (m,m′)+C b (m,m′)

[0105] In the formula: C cC is the potential energy converted from electrical energy; g C is the electrical energy converted from potential energy when the driverless car goes downhill; r The energy consumed due to air resistance and wheel rolling friction; C t C is the energy consumed to accelerate a vehicle to a target speed per unit distance. b The energy recovered by braking the vehicle when encountering a curve.

[0106] The vehicle speed will change from v per unit distance. j Accelerate to target speed v j+1 The energy consumed is:

[0107]

[0108] In the formula: k is the unit path; Δ E denoted as the total energy consumption difference; U represents the total path; j represents any intersection node; and J represents the rated energy capacity of the autonomous vehicle.

[0109] It is concluded that the vehicle is along highway P k (v1,v2,…,v k The total energy consumption for driving is:

[0110]

[0111] Let the current state of charge of the electric vehicle battery be S. soc The remaining battery power C after passing through this section of road j′ for:

[0112]

[0113] The constraint is C j ″>15%J.

[0114] S312, Process the constraints of the logistics task allocation to obtain the logistics task allocation model.

[0115] Optionally, the expression for the logistics task allocation model is:

[0116]

[0117] Where f is the logistics task allocation model, d ij t is the distance traveled by the autonomous vehicle i along the planned path for task j. ij The driving time e for autonomous vehicle i to perform the planned path for task j ij The charging price is the cost of planning the route for autonomous vehicle i to perform task j, where α, β, and λ are the weights of driving time, travel distance, and charging price, and α + β + γ = 1, T max and T minD represents the minimum and maximum driving time. max and D min E represents the minimum and maximum travel distances. max and E min V represents the minimum and maximum charging prices. sum p is the sum of the values ​​of performing the tasks. ij The probability V of autonomous vehicle i performing task j. j The value function for performing task j,

[0118] V j The calculation method is as follows:

[0119]

[0120] r ij The shortest path for autonomous vehicle i to perform task j is d. ij In the horizontal projection, h ij For from d ij towards r ij The length of the perpendicular line drawn;

[0121] Optionally, solving the logistics task allocation model to obtain the logistics task allocation result includes:

[0122] S321, Process the state information of the unmanned vehicle set and the logistics task information set to obtain the first distance matrix, and initialize the iteration number, honey source exploration limit, and population size;

[0123] S322: Randomly generate food sources according to the population size, calculate the objective function value, and set the exploration count for each food source to 0;

[0124] S323, randomly select a univariate operator to perform a neighborhood search on the food source and obtain a first new solution; when the first new solution is greater than a preset first constraint threshold (i.e., the solution that satisfies the condition that the new solution dominates the nectar source), replace the original solution with the first new solution; when the first new solution is less than or equal to the preset first constraint threshold, increment the number of times the food source is explored by 1.

[0125] Unary operators include:

[0126] 1) Single-point sliding operator: This operator randomly selects a logistics task in the allocation sequence and inserts it before another randomly selected logistics task;

[0127] 2) Interval Reversal Operator: This operator randomly selects a task interval of a certain length [x] from the allocation sequence. i ,x i+1 ,…,x i+s ], readjust the interval to [xi+s ,x i+s-1 ,…,x i ];

[0128] 3) Crossover mutation operator: Randomly select two tasks and then swap their assigned targets.

[0129] S324, randomly select an observation object from the solution set, perform a binary operator operation on the current food source based on the observation object, and obtain a second new solution; when the second new solution is greater than the preset second constraint threshold, replace the original solution with the second new solution; when the second new solution is less than or equal to the preset second constraint threshold, increment the number of explorations of the food source by 1;

[0130] Binary operators include:

[0131] 1) Single-point same-position crossover operator: This operator randomly selects a target point and swaps the target points of the two allocation sequences at that point;

[0132] 2) Two-point dislocation crossover operator: randomly select two target points x a and x b , assign the first sequence x a The allocation target at the location and the second allocation sequence x b The allocation targets at one location are swapped, and the other location is processed in the same way.

[0133] 3) Interval Crossover Operator: Randomly select an interval [x a ,x b This swaps the allocation targets within the two allocation sequence intervals.

[0134] S325, check the number of times each food source has been explored. When the number of times a food source has been explored reaches the limit, use the elite scouting strategy to generate a new food source and reset the number of times the corresponding location has been explored to 0.

[0135] S326, Sort the current population and solution set to obtain the solution set sequence;

[0136] S327, Select the first half of the solutions from the solution set sequence as the updated solution set;

[0137] S328, when the preset maximum number of iterations is reached, the updated solution set is output; the updated solution set is the logistics task allocation result.

[0138] This invention uses vector encoding, and the logistics task allocation scheme is saved in the following form:

[0139] x = [x1, x2, ..., x M ]

[0140] Where xi ∈{1,2,…,N}, the vector encoding method is as follows:

[0141] A two-level encoding method is adopted. The first level of encoding is responsible for counting the node information of the binary tree and passing the statistical results to the second level of encoding, thereby avoiding the need for repeated statistics.

[0142] The first-level encoder receives the raw information as input and initializes a dictionary structure, constructing a basic dictionary containing all 255 characters in the ASCII table. Dictionary encoding begins, starting with character number 256, and reads the raw information character by character to form an initial string. This string is then searched within the dictionary. If the string already exists in the dictionary, it is marked as the current string; otherwise, the corresponding encoded string is output, added to the dictionary, and the current string is updated with the most recently read character. This process is repeated until the raw information is completely processed.

[0143] The second-level encoding process begins by receiving information from the previous level's encoding, along with a dictionary. This input includes all characters and entries from the dictionary, used to construct an initial encoding tree. An encoding table is initialized to record the unique code for each character, reducing the size of both the encoding tree and the encoding table. During encoding, the encoding tree and its code values ​​are dynamically updated and adjusted based on the read and matched information to optimize encoding efficiency and reduce required storage space. This process is repeated until encoding is complete, further optimizing information processing and transmission efficiency.

[0144] Optionally, the first distance matrix is ​​expressed as:

[0145]

[0146] The starting coordinates of the driverless vehicle are (x i ,y i The forward angle is α, the minimum turning radius is r, and the target point's position coordinates are (x, y). t ,y t ), θ=2π-(θ1-θ2), (x p ,y p ) with (x i ,y i Let r be the coordinates of the point of tangency on the original circle with center r and radius r.

[0147] Optionally, sorting the current population and solution set to obtain a solution set sequence includes:

[0148] S3261, Rank the current population and solution set to obtain the preprocessed population;

[0149] S3262, Process the pre-processed population to obtain the crowding distance index;

[0150] The expression for the congestion distance index is as follows:

[0151]

[0152] Where, P(i+1).f k Let P(i-1).f represent the objective function value of the i-th individual in the sorted population on the k-th objective function. k f represents the objective function value of the (i-1)th individual in the sorted population on the k-th objective function. k Let P(i) be the weight value of the k-th objective. dis Let r be the crowding distance index for the i-th individual, and r be the number of individuals.

[0153] S3263, Sort the current population and solution set according to the crowding distance index to obtain the solution set sequence.

[0154] As can be seen, the present invention designs and implements a logistics task allocation method based on multiple unmanned vehicles. By comprehensively considering the real-time status of unmanned vehicles and the diverse needs of logistics tasks, it can achieve more reasonable and efficient task allocation, improve logistics and distribution efficiency, reduce delivery time and costs, and ensure the smooth progress of logistics and distribution.

[0155] Example 2

[0156] This embodiment implements a logistics task allocation method based on multiple unmanned vehicles, the steps of which include:

[0157] 1) Data Acquisition and Processing Module:

[0158] The system collects real-time status information for each autonomous vehicle, including battery level, payload capacity, current location, speed, and estimated arrival time at the next station. This data is acquired through sensors, positioning devices, and the onboard control system installed on the autonomous vehicles and transmitted to the task allocation center via wireless communication modules.

[0159] Collect logistics task information, including order quantity, cargo weight, volume, delivery address, and expected delivery time. This information is provided by the logistics order management system and synchronized to the task allocation center.

[0160] 2) Task allocation model construction module:

[0161] Establish a task priority evaluation model. Assign a priority coefficient to each task based on factors such as expected delivery time and urgency. For example, assign a higher priority coefficient to urgent orders with strict time constraints, and a relatively lower priority coefficient to regular orders.

[0162] Construct a matching model between autonomous vehicles and tasks. Taking into account both the state information of the autonomous vehicles and the task requirements, calculate the matching degree of each autonomous vehicle for each task.

[0163] 3) Task allocation and execution module:

[0164] Based on the task priority evaluation model and the autonomous vehicle-task matching model, the Hungarian algorithm or other optimization algorithms are used to assign the most suitable autonomous vehicle to each logistics task. High-priority tasks are prioritized for assignment to autonomous vehicles with high matching degrees to ensure that urgent tasks can be completed on time.

[0165] During mission execution, the status of the autonomous vehicles and the progress of the mission are monitored in real time. If any abnormal situations occur, such as vehicle malfunction or road congestion, the mission allocation plan is adjusted promptly. For example, if an autonomous vehicle malfunctions, its unfinished tasks are reassigned to other available autonomous vehicles, and a new delivery route is planned.

[0166] 4) Task allocation process:

[0167] First, the data acquisition and processing module acquires real-time status information of the unmanned vehicle and logistics task information, and transmits it to the task allocation center.

[0168] The task allocation model construction module calculates a priority coefficient for each task based on factors such as the expected delivery time and the urgency of the goods. For example, for task 1, the priority coefficient is set to 0.8 because the expected delivery time is short and the urgency of the goods is high; for task 4, the priority coefficient is set to 0.3 because the expected delivery time is long and the urgency of the goods is low.

[0169] Using the method described above, the matching degree of all autonomous vehicles for all tasks is calculated, and a matching degree matrix is ​​formed.

[0170] Finally, the task allocation and execution module uses the Hungarian algorithm to assign the most suitable autonomous vehicle to each task based on the matching degree matrix and task priority. For example, task 1 is assigned to autonomous vehicle E because autonomous vehicle E has a high matching degree with task 1 and can meet the load requirements; task 2 is assigned to autonomous vehicle B, and so on.

[0171] Abnormal situation handling: In the execution of the task in Example 1, if the unmanned vehicle C malfunctions on its way to delivery task 5, the system will immediately obtain the information through the data acquisition and processing module.

[0172] After receiving the fault information from driverless car C, the task allocation and execution module removes task 5 from driverless car C's task list and recalculates the matching degree of other available driverless cars (driverless cars A, B, D, and E) with task 5. Based on the new matching degree matrix, the Hungarian algorithm is used to reassign driverless cars to task 5. Assuming that after the reassignment, task 5 is assigned to driverless car A, the system simultaneously replans the route for driverless car A to the delivery address of task 5.

[0173] By using the aforementioned real-time monitoring and dynamic adjustment of task allocation schemes, we ensure that logistics and delivery tasks can still proceed smoothly even in the event of abnormal situations.

[0174] Example 3

[0175] Please see Figure 2 , Figure 2 This is a schematic diagram of a logistics task allocation device based on multiple unmanned vehicles disclosed in an embodiment of the present invention. Figure 2 The described multi-unmanned vehicle-based logistics task allocation device is applied in the field of task allocation technology, and the embodiments of this invention are not limited thereto. Figure 2 As shown, the logistics task allocation device based on multiple unmanned vehicles can include the following operations:

[0176] S301, Unmanned Vehicle Information Acquisition Module, used to acquire the status information of an unmanned vehicle ensemble; the status information includes location coordinates, battery level, load capacity, driving speed, and estimated arrival time at the next station; the unmanned vehicle ensemble includes N unmanned vehicles.

[0177] S302, Logistics task information acquisition module, used to acquire a set of logistics task information; the set of logistics task information includes M logistics tasks, each logistics task including order quantity, cargo weight, volume, delivery address, and expected delivery time;

[0178] S303, Logistics Task Allocation Module, is used to process the status information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result.

[0179] Example 4

[0180] Please see Figure 3 , Figure 3 This is a schematic diagram of another logistics task allocation device based on multiple unmanned vehicles disclosed in an embodiment of the present invention. Figure 3 The described multi-unmanned vehicle-based logistics task allocation device is applied in the field of task allocation technology, and the embodiments of this invention are not limited thereto. Figure 3 As shown, the logistics task allocation device based on multiple unmanned vehicles can include the following operations:

[0181] Memory 401 storing executable program code;

[0182] Processor 402 coupled to memory 401;

[0183] The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the logistics task allocation method based on multiple unmanned vehicles described in Embodiment 1 and Embodiment 2.

[0184] Example 5

[0185] This invention discloses a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program enables a computer to perform the steps in the multi-unmanned vehicle-based logistics task allocation method described in Embodiments 1 and 2.

[0186] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0187] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0188] Finally, it should be noted that the logistics task allocation method based on multiple unmanned vehicles disclosed in the embodiments of the present invention is only a preferred embodiment of the present invention and is only used to illustrate the technical solution of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A logistics task allocation method based on multiple unmanned vehicles, characterized in that, The method includes: S1, Obtain the status information of the unmanned vehicle set; the status information includes location coordinates, battery level, load capacity, driving speed, and estimated arrival time at the next station; the unmanned vehicle set includes N unmanned vehicles; S2, Obtain a set of logistics task information; the set of logistics task information includes M logistics tasks, each logistics task including order quantity, cargo weight, volume, delivery address, and expected delivery time; S3, process the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result.

2. The logistics task allocation method based on multiple unmanned vehicles according to claim 1, characterized in that, The process of processing the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result includes: S31, Process the state information of the unmanned vehicle set and the logistics task information set to obtain a logistics task allocation model; S32, Solve the logistics task allocation model to obtain the logistics task allocation result.

3. The logistics task allocation method based on multiple unmanned vehicles according to claim 2, characterized in that, The process of processing the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation model includes: S311, Process the state information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation constraints; The expression for the logistics task allocation constraint is as follows: Where, x ij Let N represent the number of tasks performed by driverless vehicle i, and M represent the number of driverless vehicles. S312, Process the constraints of the logistics task allocation to obtain the logistics task allocation model.

4. The logistics task allocation method based on multiple unmanned vehicles according to claim 3, characterized in that, The expression for the logistics task allocation model is: Where f is the logistics task allocation model, d ij t is the distance traveled by the autonomous vehicle i along the planned path for task j. ij The driving time e for autonomous vehicle i to perform the planned path for task j ij The charging price is the cost of planning the route for autonomous vehicle i to perform task j, where α, β, and λ are the weights of driving time, travel distance, and charging price, and α + β + γ = 1, T max and T min D represents the minimum and maximum driving time. max and D min E represents the minimum and maximum travel distances. max and E min V represents the minimum and maximum charging prices. sum p is the sum of the values ​​of performing the tasks. ij The probability V of autonomous vehicle i performing task j. j The value function for performing task j, 5. The logistics task allocation method based on multiple unmanned vehicles according to claim 2, characterized in that, Solving the logistics task allocation model to obtain the logistics task allocation result includes: S321, Process the state information of the unmanned vehicle set and the logistics task information set to obtain the first distance matrix, and initialize the iteration number, honey source exploration limit, and population size; S322: Randomly generate food sources according to the population size, calculate the objective function value, and set the exploration count for each food source to 0; S323, randomly select a univariate operator to perform a neighborhood search on the food source to obtain a first new solution; when the first new solution is greater than a preset first constraint threshold, replace the original solution with the first new solution; when the first new solution is less than or equal to the preset first constraint threshold, increment the number of explorations of the food source by 1. S324, randomly select an observation object from the solution set, perform a binary operator operation on the current food source based on the observation object, and obtain a second new solution; when the second new solution is greater than the preset second constraint threshold, replace the original solution with the second new solution; when the second new solution is less than or equal to the preset second constraint threshold, increment the number of explorations of the food source by 1; S325, check the number of times each food source has been explored. When the number of times a food source has been explored reaches the limit, use the elite scouting strategy to generate a new food source and reset the number of times the corresponding location has been explored to 0. S326, Sort the current population and solution set to obtain the solution set sequence; S327, Select the first half of the solutions from the solution set sequence as the updated solution set; S328, when the preset maximum number of iterations is reached, the updated solution set is output; the updated solution set is the logistics task allocation result.

6. The logistics task allocation method based on multiple unmanned vehicles according to claim 5, characterized in that, The expression for the first distance matrix is: The starting coordinates of the driverless vehicle are (x i Given that the forward angle is α, the minimum turning radius is r, and the target point's coordinates are (x, yi), the forward angle is α, the minimum turning radius is r, and the target point's coordinates are (x, yi). t ,y t ), θ=2π-(θ1-θ2), (x p ,y p ) with (x i ,y i Let r be the coordinates of the point of tangency on the original circle with center r and radius r.

7. The logistics task allocation method based on multiple unmanned vehicles according to claim 5, characterized in that, The process of sorting the current population and solution set to obtain a solution set sequence includes: S3261, Rank the current population and solution set to obtain the preprocessed population; S3262, Process the pre-processed population to obtain the crowding distance index; The expression for the congestion distance index is as follows: Where, P(i+1).f k Let P(i-1).f represent the objective function value of the i-th individual in the sorted population on the k-th objective function. k f represents the objective function value of the (i-1)th individual in the sorted population on the k-th objective function. k Let P(i) be the weight value of the k-th objective. dis Let r be the crowding distance index for the i-th individual, and r be the number of individuals. S3263, Sort the current population and solution set according to the crowding distance index to obtain the solution set sequence.

8. A logistics task allocation device based on multiple unmanned vehicles, characterized in that, The device includes: The unmanned vehicle information acquisition module is used to acquire the status information of the unmanned vehicle ensemble; the status information includes location coordinates, battery level, load capacity, driving speed, and estimated arrival time at the next station; the unmanned vehicle ensemble includes N unmanned vehicles. The logistics task information acquisition module is used to acquire a set of logistics task information; the set of logistics task information includes M logistics tasks, and each logistics task includes order quantity, cargo weight, volume, delivery address, and expected delivery time; The logistics task allocation module is used to process the status information of the unmanned vehicle set and the logistics task information set to obtain the logistics task allocation result.

9. A logistics task allocation device based on multiple unmanned vehicles, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the logistics task allocation method based on multiple unmanned vehicles as described in any one of claims 1-7.

10. A computer-storable medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, are used to execute the logistics task allocation method based on multiple unmanned vehicles as described in any one of claims 1-7.

Images