Multi-unmanned vehicle distribution method, system, device and medium

Abstract

The application provides a multi-unmanned vehicle distribution method, system, device and medium. The method comprises the following steps: acquiring a global map of a distribution task, and generating a path queue of a distribution point; determining a target starting point of an unmanned vehicle in the path queue; dividing the path queue into a target path according to the target starting point, and configuring a target distribution task of the unmanned vehicle according to the target path; re-dividing the target path according to the state feedback of the target distribution task, and dynamically updating the target distribution task according to the re-divided path.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent distribution, in particular to a multi-unmanned vehicle distribution method, system, device and medium. BACKGROUND

[0002] In recent years, in the field of multi-unmanned vehicle autonomous distribution, unmanned vehicles, as an intelligent distribution tool, are gradually replacing traditional human distribution modes, especially in complex, dynamic and large-scale urban environments, and exhibit unique advantages. The autonomous distribution system of unmanned vehicles usually relies on high-precision maps, sensor data fusion, path planning and task scheduling, and other core technologies to efficiently, accurately and safely transport goods from distribution points to destinations.

[0003] Then, the existing path planning and task allocation algorithm lacks dynamic adjustment capability in the cooperative task of multiple unmanned vehicles, and is difficult to cope with complex urban distribution environments, and the cooperative technology is limited by communication and computing power, and cannot realize real efficient cooperation and optimal allocation of resources.

[0004] Therefore, there is an urgent need for a multi-unmanned vehicle distribution method to solve the problem of uneven distribution of resources caused by the lack of dynamic adjustment capability in the cooperative task of unmanned vehicles. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides a multi-unmanned vehicle distribution method, system, device and medium.

[0006] The first aspect of the present application discloses a multi-unmanned vehicle distribution method, comprising:

[0007] obtaining a global map of a distribution task, and generating a path queue of a distribution point;

[0008] determining a target starting point of an unmanned vehicle in the path queue;

[0009] dividing the path queue into a target path according to the target starting point, and configuring a target distribution task of the unmanned vehicle according to the target path;

[0010] re-dividing the target path according to the state feedback of the target distribution task, and dynamically updating the target distribution task according to the re-divided path.

[0011] As an optional implementation, the obtaining of the global map of the distribution task comprises:

[0012] determining a vehicle set of N unmanned vehicles in a distribution center according to the distribution task, and determining a target point set of M distribution points outside the distribution center, wherein the vehicle set is represented as L car ={c1,c2,...,c n}, the target point set is represented as L site = {s1, s2,..., s m N}, the location of the distribution center, the distribution point and the unmanned vehicle is obtained according to the distribution task.

[0013] As an optional implementation, the path queue of the distribution point is generated, including:

[0014] The distance cost and the commuting cost of the first distribution point S j1 and the second distribution point S j2 in the target point set are constructed, the distance cost is represented as C dis (s j1 ,s j2 ) = NavLength (s j1 ,s j2 ), wherein NavLength (s j1 ,s j2 ) represents the cost of the non-shortest path generated by global map navigation between the first distribution point S j1 and the second distribution point S j2 , and the commuting cost is represented as C tra (s j1 ,s j2 ) = traffic (s j1 ,s j2 ), wherein traffic (s j1 ,s j2 ) represents the cost of the commuting affected by the global map navigation path between the first distribution point S j1 and the second distribution point S j2 .

[0015] The weight α1 of the distance cost and the weight α2 of the commuting cost are assigned, and the TSP cost of the first distribution point S j1 and the second distribution point S j2 is defined, wherein the TSP cost is represented as:

[0016] C (s j1 ,s j2 ) = α1C dis (s j1 ,s j2 ) + α2C tra (s j1 ,s j2 ).

[0017] The cost matrix is constructed according to the TSP cost to solve the path problem of the distribution point, the order of the distribution point on the path and the shortest distance between the distribution points are determined, and the path queue forming a closed loop around the distribution center is output, and the path queue is represented as indicates the path order of the i-th delivery point.

[0018] As an optional implementation, the determining of the target starting point of the unmanned vehicle in the path queue includes:

[0019] According to the initial position of the target unmanned vehicle in the delivery center in the vehicle set, the proximity points of each unmanned vehicle relative to the N delivery points are determined, and the proximity point farthest from the target unmanned vehicle is selected as the target starting point of the target unmanned vehicle, and the number of target starting points is at least N / 2.

[0020] As an optional implementation, the dividing of the path queue into target paths according to the target starting points, and the configuring of the target delivery task of the unmanned vehicle according to the target path, includes:

[0021] The path between two adjacent target starting points in the path queue is uniformly divided to generate a target sub-path of the target unmanned vehicle starting from the target starting point;

[0022] The two target unmanned vehicles adjacent to the target starting point are configured as a task group, and the target unmanned vehicles in the task group move along the target sub-path from the target starting point to the division point to perform a sub-delivery task;

[0023] The task list of the unmanned vehicle is generated according to the sub-delivery task and the task group, and the target delivery task of the unmanned vehicle is configured according to the target sub-path and the task list.

[0024] As an optional implementation, the re-dividing of the target path according to the state feedback of the target delivery task, includes:

[0025] In response to the state information returned by the unmanned vehicle, the task state and the motion state of the unmanned vehicle in each task group are traversed;

[0026] The first progress value of the first unmanned vehicle and the second progress value of the second unmanned vehicle in the task group are determined according to the uniform division point and the state information;

[0027] The dynamic threshold value is updated in real time according to the road condition environment information obtained from the state information and the travel information of the progress value, and the dynamic threshold value is configured as an adjustment condition for the re-dividing of the target path;

[0028] The dynamic threshold value is compared according to the progress difference value of the first progress value and the second progress value obtained in real time to determine whether the first unmanned vehicle and the second unmanned vehicle in the current task group are re-divided.

[0029] As an optional implementation, the dynamic updating of the target delivery task according to the re-divided path, includes:

[0030] If the current task group needs to be re-divided, an unfinished value of a target sub-path in the task group is obtained, and a weighted average of the unfinished value is determined to determine a re-division point of the task group;

[0031] According to the re-division point, a target sub-path of a first unmanned vehicle and a second unmanned vehicle in the task group is re-determined, and the target delivery task is updated according to the target sub-path;

[0032] The target delivery task is continuously updated until the unmanned vehicles complete all tasks.

[0033] The second aspect of the present application discloses a delivery system of multiple unmanned vehicles, the system comprising:

[0034] A path solving module is configured to obtain a global map of a delivery task, and generate a path queue of delivery points.

[0035] A starting point searching module is configured to determine a target starting point of an unmanned vehicle in the path queue.

[0036] A task allocation module is configured to divide the path queue into target paths according to the target starting point, and configure a target delivery task of the unmanned vehicle according to the target paths.

[0037] A dynamic adjustment module is configured to re-divide the target paths according to a state feedback of the target delivery task, and dynamically update the target delivery task according to the re-divided paths.

[0038] As an optional implementation, the path solving module comprises:

[0039] According to the delivery task, a vehicle set of N unmanned vehicles in a delivery center and a target point set of M delivery points outside the delivery center are determined, wherein the vehicle set is represented as L car ={c1,c2,...,c n}, the target point set is represented as L site ={s1,s2,...,s m}, and the positions of the delivery center, the delivery points and the unmanned vehicles are obtained according to the delivery task.

[0040] As an optional implementation, the path solving module comprises:

[0041] The distance cost and the commuting cost of a first delivery point S j1 and a second delivery point S j2 in the target point set are constructed, the distance cost is represented as C dis (s j1 ,s j2 )=NavLength(sj1 j2 ), wherein NavLength(s j1 j2 ) represents the first distribution point S j1 and the second distribution point S j2 The cost of generating a non-shortest path through global map navigation is represented as C tra (s j1 , s j2 ) = traffic(s j1 , s j2 ), wherein traffic(s j1 , s j2 ) represents the cost of the first distribution point S j1 and the second distribution point S j2 affected by traffic on the global map navigation path;

[0042] The weight of the distance cost α1and the weight of the traffic cost α2are assigned to define the TSP cost of the first distribution point S j1 and the second distribution point S j2 , wherein the TSP cost is represented as:

[0043] C(s j1 , s j2 ) = α1C dis (s j1 , s j2 ) + α2C tra (s j1 , s j2 );

[0044] According to the TSP cost, a cost matrix is constructed to solve the path problem of the distribution points, to determine the order of the distribution points on the path and the shortest distance between the distribution points, and to output a path queue forming a closed loop around the distribution center, which is represented as represents the path order of the i-th distribution point.

[0045] As an optional implementation, the target starting point of the unmanned vehicle in the path queue is determined in the starting point searching module, comprising:

[0046] According to the initial position of the target unmanned vehicle in the distribution center in the vehicle set, the adjacent points of each unmanned vehicle relative to the distance of N distribution points are determined, and the adjacent point farthest from the target unmanned vehicle in the adjacent points is selected as the target starting point of the target unmanned vehicle, and the number of target starting points is at least N / 2.

[0047] ​​As an optional implementation, the task allocation module, wherein the path queue is divided into target paths according to the target starting points, and the target delivery tasks of the unmanned vehicles are configured according to the target paths, comprises:

[0048] The path between two adjacent target starting points in the path queue is evenly divided to generate a target sub-path of the target starting point from which the target unmanned vehicle departs;

[0049] Two target unmanned vehicles adjacent to the target starting point are configured as a task group, and the target unmanned vehicles in the task group move along the target sub-path from the target starting point to the division point to perform a sub-delivery task;

[0050] A task list of the unmanned vehicles is generated according to the sub-delivery tasks and the task group, and the target delivery tasks of the unmanned vehicles are configured according to the target sub-path and the task list.

[0051] As an optional implementation, the dynamic adjustment module, wherein the target path is re-divided according to the state feedback of the target delivery task, comprises:

[0052] In response to the state information returned by the unmanned vehicles, the task state and the motion state of the unmanned vehicles in each task group are traversed;

[0053] The first progress value of the first unmanned vehicle and the second progress value of the second unmanned vehicle in the task group are determined according to the uniform division point and the state information;

[0054] The dynamic threshold value is updated in real time according to the road condition environment information obtained from the state information and the travel information of the progress value, and the dynamic threshold value is configured as an adjustment condition for re-dividing the target path;

[0055] The dynamic threshold value is compared with the progress difference value of the first progress value and the second progress value obtained in real time to determine whether the first unmanned vehicle and the second unmanned vehicle in the current task group need to be re-divided.

[0056] As an optional implementation, the dynamic adjustment module, wherein the target delivery task is dynamically updated according to the re-divided path, comprises:

[0057] If the current task group needs to be re-divided, the unfinished value of the target sub-path in the task group is obtained, and the unfinished value is weighted and averaged to determine the re-division point of the task group;

[0058] The target sub-paths of the first unmanned vehicle and the second unmanned vehicle in the task group are re-determined according to the re-division point, and the target delivery task is updated according to the target sub-paths;

[0059] The target delivery task is continuously updated until the unmanned vehicles complete all tasks.

[0060] The third aspect of the present application discloses a multi-unmanned vehicle distribution device, comprising:

[0061] at least one processor, and

[0062] a memory in communication connection with the at least one processor; wherein

[0063] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the multi-unmanned vehicle distribution method according to any one of the first aspect of the present application.

[0064] The fourth aspect of the present application discloses a computer readable storage medium, which stores computer executable instructions for causing a computer to execute the multi-unmanned vehicle distribution method according to any one of the first aspect of the present application.

[0065] Compared with the prior art, the present application has the following advantages:

[0066] The present application provides a multi-unmanned vehicle distribution method, system, device and medium, the method comprising: obtaining a global map of a distribution task, generating a path queue of a distribution point; determining that the unmanned vehicle is located at a target starting point in the path queue; according to the target starting point, the path queue is divided into a target path, and the target distribution task of the unmanned vehicle is configured according to the target path; according to the state feedback of the target distribution task, the target path is re-divided, and the target distribution task is dynamically updated according to the re-divided path. The present application solves the traveling salesman problem by path generation in the global map to obtain a closed-loop path point queue, uses a search algorithm to query the path point closest to the path center from the path queue, and preliminarily groups all path points according to the number of unmanned vehicles, while introducing a re-division scheme to dynamically adjust the task amount of the unmanned vehicle, ensuring the balance and efficiency of task allocation in the execution process, not only improving the calculation efficiency of path planning, but also enhancing the flexibility of collaborative task allocation, solving the problem of uneven distribution of resources caused by lack of dynamic adjustment capability in the collaborative task of unmanned vehicles, and having great application value in the field of unmanned vehicle distribution. BRIEF DESCRIPTION OF DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0068] Figure 1A flow chart of the multi-unmanned vehicle delivery method of the present application;

[0069] Figure 2 A schematic diagram of the multi-unmanned vehicle delivery system of the present application. DETAILED DESCRIPTION

[0070] For the purpose of the present application, technical solutions and advantages, the following will be described and explained in conjunction with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application, and are not intended to limit the present application. Based on the examples provided in the present application, all other examples obtained by those of ordinary skill in the art without making creative efforts fall within the scope of the present application.

[0071] Obviously, the drawings described in the following are only some examples or embodiments of the present application, and for those of ordinary skill in the art, the present application can be applied to other similar scenarios without making creative efforts based on these drawings. In addition, it can be understood that although the efforts made in the development process can be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacture or production changes based on the technical content disclosed in the present application are only routine technical means, and should not be understood as insufficient disclosure of the content disclosed in the present application.

[0072] In the present application, the phrase "embodiment" means that the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in the present application can be combined with other embodiments without conflict.

[0073] Unless otherwise defined, technical terms and scientific terms used in the present application shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terms "a", "an", "one", "this", and similar referents in the context of describing the application are to be construed to be open-ended, referring to one or more than one, unless otherwise noted. The terms "including", "comprising", "having" and variations thereof in this application are meant to encompass the possibility of non-exclusive inclusion, such that processes, methods, systems, products, or apparatuses that comprise a list of steps or elements are not limited to only those steps or elements but can include other steps or elements not expressly listed or inherent to such processes, methods, systems, products, or apparatuses. The terms "connected", "coupled", and similar referents in the context of this application are to be construed as beading in a manner that permits the causal agent or signal to act upon the object or another causative agent. The term "plurality" means two or more. The term "and / or" describes association between or among multiple options, and indicates that when there are multiple options present (for example, "A and / or B"), that the associated object or method can be either A or B or both. The character " / " is used to represent "and / or" in some instances. The terms "first", "second", "third", and the like are used to describe various objects and do not necessarily indicate a specific order or sequence.

[0074] Embodiment 1

[0075] Referring to Figure 1 In some embodiments, the present application discloses a multi-unmanned vehicle delivery method, comprising:

[0076] 101. Obtain a global map of a delivery task, and generate a path queue of delivery points;

[0077] It should be noted that the delivery task refers to the process of transporting goods (such as express delivery, express delivery, fresh food, medicine, and fast-moving goods, etc.) to all delivery points (such as parks, campuses, residential areas, warehouses) along the planned path by unmanned vehicles in the area with the delivery center as the center. Unmanned vehicle autonomous delivery usually needs to rely on high-precision maps, multi-sensor data fusion, unmanned vehicle path planning, and unmanned vehicle task scheduling, etc. to achieve together. Specifically, the delivery center will receive various delivery requirements related to the delivery point, and then the delivery center will generate a corresponding delivery task. The position of the delivery center as the regional center and the position of the delivery point can provide accurate road information and location reference through the high-precision map. Next, it is necessary to generate a selectable path for the unmanned vehicle to execute the delivery task.

[0078] Specifically, when generating the task path of the unmanned vehicle, various influencing factors need to be considered, for example, if the unmanned vehicle departs from the distribution center, the total distance that each unmanned vehicle needs to move to reach the shortest distance needs to be considered, and the shortest moving path will improve the work efficiency of the distribution center, and how to reasonably allocate the distribution task to each independent unmanned vehicle also needs to be considered, and a reasonable allocation scheme can enable the unmanned vehicle to efficiently complete all distribution tasks, so the path selection and task allocation of the unmanned vehicle are currently problems to be solved. Before determining the path selection and task allocation, the corresponding parameters need to be obtained as data support, and the subsequent implementation manner will further describe how to complete the path selection and task allocation of the unmanned vehicle.

[0079] As an optional implementation manner, the obtaining the global map of the distribution task comprises:

[0080] According to the distribution task, a vehicle set of N unmanned vehicles in the distribution center is determined, and a target point set of M distribution points outside the distribution center is determined, wherein the vehicle set is represented as L car ={c1,c2,...,c n}, and the target point set is represented as L site ={s1,s2,...,s m}, and the positions of the distribution center, the distribution point and the unmanned vehicle are obtained according to the distribution task.

[0081] Specifically, in the case of communication, the distribution center receives the distribution task issued according to the distribution point, wherein the number of unit distribution tasks and the number of distribution points are one-to-one corresponding and recorded as M, the M distribution points are set as the target points (task end points) of the distribution task, and the number of optional unmanned vehicles for executing the distribution task is recorded as N, wherein the position information of the distribution point can be confirmed according to the received address information, and the position of the unmanned vehicle can be confirmed through multiple sensors, Internet of Vehicles and high-precision maps. It can be known that the road conditions and environment of the distribution point area can be queried on the high-precision map through the address information, and the influencing factors (such as traffic congestion, poor road conditions, weather influence, etc.) affecting the travel efficiency of the unmanned vehicle can obtain environmental information through the sensors of the unmanned vehicle and then fuse with the high-precision map information, so as to determine the influence degree of the unmanned vehicle distribution efficiency in the actual scene.

[0082] As an optional implementation manner, the generating the path queue of the distribution point comprises:

[0083] The distance cost and commuting cost of a first distribution point S j1 and a second distribution point S j2 in the target point set are constructed, the distance cost is represented as C dis (s j1 ,s j2 )=NavLength(sj1 j2 ), wherein NavLength(s j1 j2 ) represents a non-shortest path cost generated by global map navigation between the first delivery point S j1 and the second delivery point S j2 , and the commuting cost is represented as C tra (s j1 , s j2 ) = traffic(s j1 , s j2 ), wherein traffic(s j1 , s j2 ) represents a cost affected by commuting between the first delivery point S j1 and the second delivery point S j2 on the global map navigation path;

[0084] Specifically, in order to obtain a path with shorter time consumption as much as possible, the unmanned vehicle can start from the distribution center to the farthest delivery point, and then travel to the next delivery point in turn until the delivery points form a closed loop around the distribution center to achieve the highest delivery efficiency. Therefore, in this embodiment, a TSP model is introduced, and the path planning of each delivery point can be converted into a traveling salesman problem. In this embodiment, the solution of the path queue can be understood as the shortest path problem of the unmanned vehicle starting from the starting delivery point, visiting each delivery point only once, and finally returning to the starting delivery point. However, unlike the traditional traveling salesman problem, there is not only one traveling salesman, but also the problem of assigning tasks to each unmanned vehicle. Therefore, an initial closed loop path queue is generated first.

[0085] Further, in order to improve the accuracy of generating the path queue, two factors that affect the delivery efficiency, path distance and commuting time consumption, are considered as problems that need to be considered in generating the path. The two factors are constructed as TSP costs in the TSP model. The path distance cost can be queried by the high-precision map between the delivery starting point and the delivery ending point before performing the delivery task, or it can be queried by the navigation path. In addition to the path distance, the commuting time consumption problem also needs to consider the weather factor, road condition factor and traffic congestion factor and other influencing factors that affect the actual commuting time. By constructing the commuting cost, the probability of generating the shortest path queue is further improved, and the actual path time consumption caused by some influencing factors is avoided, so that the path between two adjacent delivery points in the generated closed loop path queue is the shortest.

[0086] The weight α1 of the distance cost and the weight α2 of the commuting cost are assigned, and the first delivery point S j1 and the second delivery point S j2 ​​TSP cost, wherein the TSP cost is expressed as:

[0087] C(s j1 ,s j2 )=α1C dis (s j1 ,s j2 )+α2C tra (s j1 ,s j2 );

[0088] constructing a cost matrix according to the TSP cost to solve a path problem of the distribution points, determining an order of the distribution points on the path and a shortest distance between the distribution points, and outputting a path queue forming a closed loop around the distribution center, the path queue being expressed as denotes an order of the i-th distribution point.

[0089] Specifically, for different TSP costs, weights are assigned to construct a cost matrix to solve the path queue. To ensure that the distance of each path is the shortest, the cost matrix includes all possible path generation conditions of the distribution points. Therefore, when constructing the TSP cost, any two distribution points S j1 and S j2 are taken as the basis to ensure that any possible shortest path solution can be traversed when generating the path queue, and the path queue can record the path order starting from the distribution point s i .

[0090] 102. determining a target starting point of the unmanned vehicle in the path queue;

[0091] Specifically, after generating the path queue, in order to further plan the path that each unmanned vehicle needs to travel and further confirm the starting point of the unmanned vehicle in the distribution task, since the path queue has a path order and is a closed loop path, configuring two unmanned vehicles at the same starting point and performing distribution tasks in opposite directions can reduce the resource consumption of subsequent task allocation and path allocation, especially in cooperative tasks with real-time requirements, which is particularly important for quickly deploying unmanned vehicles into distribution tasks.

[0092] As an optional implementation, the determining of the target starting point of the unmanned vehicle in the path queue includes:

[0093] determining a proximity point of each unmanned vehicle relative to the N distribution points according to the initial position of the target unmanned vehicle in the vehicle set, and screening the proximity point farthest from the target unmanned vehicle as the target starting point of the target unmanned vehicle, the number of target starting points being at least N / 2. ​

[0094] Specifically, taking four unmanned vehicles as an example, the delivery points in the continuous search path queue are searched and the farthest delivery point is selected as the starting point according to the actual distance. Since the unmanned vehicle moves from the distribution center to the first delivery point to complete the first delivery task, the first delivery task is taken as the starting point, and the farthest delivery point is selected as the starting point for the subsequent return of the unmanned vehicle from the final delivery point to the distribution center, which can reduce the commuting time consumed by the unmanned vehicle in the round trip to the distribution center. In the case of four unmanned vehicles performing delivery tasks, two delivery points are taken as the starting points, and then the unmanned vehicle can complete the path of each 1 / 4 circular arc of the closed loop path queue in turn, so as to average the actual commuting time of each unmanned vehicle as much as possible, thereby improving the efficiency of the distribution center in completing batch delivery tasks within a unit time.

[0095] 103. According to the target starting point, the path queue is divided into a target path, and the target delivery task of the unmanned vehicle is configured according to the target path;

[0096] As an optional implementation, the path queue is divided into a target path according to the target starting point, and the target delivery task of the unmanned vehicle is configured according to the target path, comprising:

[0097] The path between the two adjacent target starting points in the path queue is uniformly divided to generate a target sub-path of the target unmanned vehicle starting from the target starting point;

[0098] The two target unmanned vehicles adjacent to the target starting point are configured as a task group, and the target unmanned vehicles in the task group move along the target sub-path to the division point to perform a sub-delivery task from the target starting point;

[0099] According to the sub-delivery task and the task group, a task list of the unmanned vehicle is generated, and the target delivery task of the unmanned vehicle is configured according to the target sub-path and the task list.

[0100] Specifically, in order to uniformly divide the path between each adjacent starting point, the path can be uniformly divided according to factors such as distance, road conditions, traffic, and weather, so as to ensure that the two unmanned vehicles moving towards each other from adjacent delivery points can reach the task end point at the same time to complete the delivery task. The target delivery task is a sub-delivery task required to be completed for N delivery points, and the target sub-path is a delivery task that each unmanned vehicle needs to complete independently.

[0101] 104. According to the state feedback of the target delivery task, the target path is re-divided, and the target delivery task is dynamically updated according to the re-divided path.

[0102] As an optional implementation, the target path is re-divided according to the state feedback of the target delivery task, comprising:

[0103] In response to the state information returned by the unmanned vehicles, the task state and the motion state of the unmanned vehicles in each task group are traversed;

[0104] According to the uniform segmentation point and the state information, a first progress value of a first unmanned vehicle and a second progress value of a second unmanned vehicle in the task group are determined;

[0105] According to the road condition environment information obtained from the state information and the travel information of the progress values, a dynamic threshold is updated in real time, and the dynamic threshold is configured as an adjustment condition for re-segmentation of the target path;

[0106] According to the progress difference between the first progress value and the second progress value obtained in real time, it is judged whether the first unmanned vehicle and the second unmanned vehicle in the current task group perform re-segmentation according to the dynamic threshold.

[0107] Specifically, for two unmanned vehicles moving towards each other between adjacent distribution points, there is a problem of unreasonable distribution tasks, for example, in the actual distribution process, the unmanned vehicle c1 completes the distribution task quickly because of good road conditions, while the unmanned vehicle c2 is slow in the distribution task progress due to traffic congestion, so real-time adjustment is needed for the above situation. Assuming that the dynamic threshold is 2, let the first progress value of the i-th unmanned vehicle (the first unmanned vehicle) be length(l ci ), and the second progress value of the j-th unmanned vehicle (the second unmanned vehicle) be length(l cj ), then whether to perform re-segmentation can be selected by the determination result of length(l ci )-length(l cj )>2. Since the process of obtaining the progress value has been confirmed according to the state information returned by the unmanned vehicle, the data causing unreasonable distribution tasks analyzed from the state information can also be reused in the subsequent process of adjusting the re-segmentation point, reducing the calculation loss of the distribution center.

[0108] As an optional implementation, the dynamic updating of the target distribution task according to the re-segmented path comprises:

[0109] If the current task group needs to be re-segmented, the uncompleted value of the target sub-path in the task group is obtained, and a weighted average of the uncompleted value is determined to determine the re-segmentation point of the task group;

[0110] According to the re-segmentation point, the target sub-path of the first unmanned vehicle and the second unmanned vehicle in the task group is re-determined, and the target distribution task is updated according to the target sub-path;

[0111] The target distribution task is continuously updated until the unmanned vehicles complete all tasks.

[0112] It needs to be explained that for the ongoing delivery task, the unmanned vehicles of the unfinished sub-delivery task can be repeatedly detected continuously, and the task amount of each unmanned vehicle is adjusted in real time according to the actual operation of the unmanned vehicle, so that the efficiency of the unmanned vehicle to complete the target delivery task as a whole is improved.

[0113] The application discloses a multi-unmanned vehicle delivery method, which comprises the following steps: acquiring a global map of a delivery task, generating a path queue of a delivery point, determining a target starting point of the unmanned vehicle in the path queue, segmenting the path queue into a target path according to the target starting point, configuring a target delivery task of the unmanned vehicle according to the target path, re-segmenting the target path according to a state feedback of the target delivery task, and dynamically updating the target delivery task according to the re-segmented path.

[0114] As shown in Figure 2 The application discloses a multi-unmanned vehicle delivery system, which comprises the following steps:

[0115] A path solving module is configured to acquire a global map of a delivery task and generate a path queue of a delivery point.

[0116] A starting point searching module is configured to determine a target starting point of the unmanned vehicle in the path queue.

[0117] A task allocation module is configured to segment the path queue into a target path according to the target starting point, and configure a target delivery task of the unmanned vehicle according to the target path.

[0118] A dynamic adjustment module is configured to re-segment the target path according to a state feedback of the target delivery task, and dynamically update the target delivery task according to the re-segmented path.

[0119] As an optional implementation, the path solving module is configured to acquire the global map of the delivery task, which comprises the following steps:

[0120] According to the delivery task, a vehicle set of N unmanned vehicles in a delivery center is determined, and a target point set of M delivery points outside the delivery center is determined, wherein the vehicle set is represented as L car ={c1,c2,...,c n}, the target point set is represented as L site = {s1, s2,..., s m N}, the location of the distribution center, the distribution point and the unmanned vehicle is obtained according to the distribution task.

[0121] As an optional implementation, the path solving module generates a path queue of the distribution point, including:

[0122] The distance cost and the commuting cost of the first distribution point S j1 and the second distribution point S j2 in the target point set are constructed, the distance cost is represented as C dis (s j1 ,s j2 ) = NavLength(s j1 ,s j2 ), wherein NavLength(s j1 ,s j2 ) represents the cost of the first distribution point S j1 and the second distribution point S j2 to generate a non-shortest path through the global map navigation, and the commuting cost is represented as C tra (s j1 ,s j2 ) = traffic(s j1 ,s j2 ), wherein traffic(s j1 ,s j2 ) represents the cost of the first distribution point S j1 and the second distribution point S j2 to be affected by the commuting on the global map navigation path.

[0123] The weight α1 of the distance cost and the weight α2 of the commuting cost are assigned, and the TSP cost of the first distribution point S j1 and the second distribution point S j2 is defined, wherein the TSP cost is represented as:

[0124] C(s j1 ,s j2 ) = α1C dis (s j1 ,s j2 ) + α2C tra (s j1 ,s j2 );

[0125] The cost matrix is constructed according to the TSP cost to solve the path problem of the distribution point, determine the order of the distribution point on the path and the shortest distance between the distribution points, and output the path queue forming a closed loop around the distribution center, the path queue is represented as indicates the path order of the i-th delivery point.

[0126] As an optional implementation, the determining, by the starting point searching module, of the target starting point of the unmanned vehicle in the path queue includes:

[0127] According to the initial position of the target unmanned vehicle in the set of vehicles at the distribution center, the proximity points of each unmanned vehicle relative to the N delivery points are determined, and the proximity point farthest from the target unmanned vehicle among the proximity points is selected as the target starting point of the target unmanned vehicle, and the number of target starting points is at least N / 2.

[0128] As an optional implementation, the task allocation module includes:

[0129] uniformly dividing the path between two adjacent target starting points in the path queue to generate a target sub-path of the target unmanned vehicle starting from the target starting point;

[0130] configuring two target unmanned vehicles adjacent to the target starting point as a task group, and the target unmanned vehicles in the task group move from the target starting point to the division point along the target sub-path to perform a sub-delivery task;

[0131] generating a task list of the unmanned vehicle according to the sub-delivery task and the task group, and configuring a target delivery task of the unmanned vehicle according to the target sub-path and the task list.

[0132] As an optional implementation, the dynamic adjustment module includes:

[0133] in response to the state information returned by the unmanned vehicle, traversing the task state and motion state of the unmanned vehicle in each task group;

[0134] determining a first progress value of a first unmanned vehicle and a second progress value of a second unmanned vehicle in the task group according to the uniform division point and the state information;

[0135] updating the dynamic threshold value in real time according to the road condition environment information obtained from the state information and the travel information of the progress value, and configuring the dynamic threshold value as an adjustment condition for the re-division of the target path;

[0136] comparing the progress difference value of the first progress value and the second progress value obtained in real time to the dynamic threshold value to determine whether the first unmanned vehicle and the second unmanned vehicle in the current task group are re-divided.

[0137] As an optional implementation, the dynamic adjustment module dynamically updates the target distribution task according to the resegmentation path, and the method comprises the following steps of:

[0138] If the current task group needs to be resegmented, the uncompleted value of the target sub-path in the task group is obtained, and the uncompleted value is weighted and averaged to determine the resegmentation point of the task group;

[0139] The target sub-path of the first unmanned vehicle and the second unmanned vehicle in the task group is re-determined according to the resegmentation point, and the target distribution task is updated according to the target sub-path;

[0140] The target distribution task is continuously updated until the unmanned vehicle completes all tasks.

[0141] The third aspect of the present application discloses a multi-unmanned vehicle distribution device, which comprises:

[0142] at least one processor, and

[0143] a memory in communication connection with the at least one processor; wherein

[0144] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any one of the multi-unmanned vehicle distribution methods disclosed in the first aspect of the present application.

[0145] The computer device can be a terminal, and the computer device comprises a processor, a memory, a network interface, a display screen and an input device connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement the multi-unmanned vehicle distribution method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0146] The fourth aspect of the present application discloses a computer readable storage medium, which stores computer executable instructions for causing a computer to execute the multi-unmanned vehicle distribution method disclosed in any one of the first aspect of the present application.

[0147] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments of the delivery method through multiple unmanned vehicles. Any reference to memory, storage, database, or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0148] Alternatively, the above-mentioned modules of the present application, if realized in the form of software function modules and sold or used as independent products, can also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, terminal, or network device, etc.) to execute all or part of the embodiments of the present application. The above-mentioned storage medium includes mobile storage devices, RAM, ROM, magnetic or optical disks, and various media that can store program codes.

[0149] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A multi-unmanned vehicle delivery method, characterized by, The method comprises: acquiring a global map of a delivery task, generating a path queue of a delivery point; determining a target starting point of an unmanned vehicle in the path queue; segmenting the path queue into a target path according to the target starting point, and configuring a target delivery task of the unmanned vehicle according to the target path; re-segmenting the target path according to the state feedback of the target delivery task, and dynamically updating the target delivery task according to the re-segmented path; the target path according to the target starting point, and the target delivery task of the unmanned vehicle according to the target path, comprises: uniformly segmenting the path between two adjacent target starting points in the path queue to generate a target sub-path of the target unmanned vehicle starting from the target starting point; configuring two target unmanned vehicles adjacent to the target starting point as a task group, and the target unmanned vehicles in the task group move along the target sub-path to a segmentation point to perform a sub-delivery task from the target starting point; generating a task list of the unmanned vehicle according to the sub-delivery task and the task group, and configuring the target delivery task of the unmanned vehicle according to the target sub-path and the task list; the re-segmenting the target path according to the state feedback of the target delivery task, comprises: in response to the state information returned by the unmanned vehicle, traversing the task state and motion state of the unmanned vehicle in each task group; determining a first progress value of a first unmanned vehicle and a second progress value of a second unmanned vehicle in the task group according to the uniform segmentation point and the state information; real-time updating a dynamic threshold value according to the road environment information obtained from the state information and the travel information of the progress value, and configuring the dynamic threshold value as an adjustment condition for re-segmenting the target path; comparing the dynamic threshold value according to the progress difference value of the first progress value and the second progress value to determine whether the first unmanned vehicle and the second unmanned vehicle in the current task group need to be re-segmented; the dynamic updating of the target delivery task according to the re-segmented path, comprises: if the current task group needs to be re-segmented, obtaining an unfinished value of the target sub-path in the task group and determining a re-segmentation point of the task group by weighted average of the unfinished value; redetermining the target sub-path of the first unmanned vehicle and the second unmanned vehicle in the task group according to the re-segmentation point, and updating the target delivery task according to the target sub-path; continuously updating the target delivery task until the unmanned vehicle completes all tasks.

2. The multi-unmanned vehicle delivery method according to claim 1, wherein the acquiring a global map of a delivery task, comprises: According to the distribution task, a vehicle set of N unmanned vehicles in the distribution center is determined, and a target point set of M distribution points outside the distribution center is determined, wherein the vehicle set is represented as , the target point set is represented as , and the positions of the distribution center, the distribution points, and the unmanned vehicles are obtained according to the distribution task.

3. The multi-unmanned vehicle delivery method according to claim 2, wherein the generating a path queue of a delivery point, comprises: constructing a distance cost for a first delivery point and a second delivery point in the set of target points, the distance cost being represented as wherein denotes a first delivery point and a second delivery point a non-shortest path cost generated by global map navigation, the commute cost being represented as wherein denotes a first delivery point and a second delivery point a cost affected by commute located on a global map navigation path; a weight of the distance cost and a weight of the commute cost defining a TSP cost of the first distribution point and the second distribution point wherein the TSP cost is expressed as: ； A cost matrix is constructed according to a TSP cost to solve a path problem of distribution points, an order of the distribution points located on a path is determined, and a shortest distance between the distribution points is determined, and a path queue formed in a closed loop around the distribution center is output, the path queue being represented as , represents a path order of the i-th distribution point.

4. The multi-unmanned vehicle delivery method according to claim 3, wherein, the determining a target starting point of an unmanned vehicle in the path queue, comprises: According to the initial position of the target unmanned vehicle in the distribution center in the vehicle set, a nearby point of each unmanned vehicle relative to any distribution point is determined, and the nearby point farthest from the target unmanned vehicle in the nearby points is selected as a target starting point of the target unmanned vehicle, and the number of target starting points is at least .

5. A multi-unmanned vehicle delivery system, characterized by, the system comprises: a path solving module for acquiring a global map of a delivery task, and generating a path queue of a delivery point; a starting point searching module for determining a target starting point of an unmanned vehicle in the path queue; a task allocation module for segmenting the path queue into a target path according to the target starting point, and configuring a target delivery task of the unmanned vehicle according to the target path; a dynamic adjustment module for re-segmenting the target path according to the state feedback of the target delivery task, and dynamically updating the target delivery task according to the re-segmented path; The method comprises the following steps: The path queue is divided into target paths according to the target starting points, and target delivery tasks of unmanned vehicles are configured according to the target paths; The paths between two adjacent target starting points in the path queue are uniformly divided to generate target sub-paths of target unmanned vehicles starting from the target starting points; Two target unmanned vehicles adjacent to the target starting points are configured as a task group, and the target unmanned vehicles in the task group move along the target sub-paths from the target starting points to the division points to perform sub-delivery tasks; A task list of the unmanned vehicles is generated according to the sub-delivery tasks and the task group, and target delivery tasks of the unmanned vehicles are configured according to the target sub-paths and the task list; The target paths are re-divided according to the state feedback of the target delivery tasks, which comprises the following steps: In response to the state information returned by the unmanned vehicles, the task states and motion states of the unmanned vehicles in each task group are traversed; First progress values of first unmanned vehicles and second progress values of second unmanned vehicles in the task groups are determined according to the uniform division points and the state information; A dynamic threshold is updated in real time according to the road condition environment information obtained from the state information and the travel information of the progress values, and the dynamic threshold is configured as an adjustment condition for re-dividing the target paths; Whether the first unmanned vehicles and the second unmanned vehicles in the current task group need to be re-divided is determined by comparing the dynamic threshold according to the progress difference values of the first progress values and the second progress values obtained in real time; The target delivery tasks are dynamically updated according to the re-divided paths, which comprises the following steps: If the current task group needs to be re-divided, an unfinished value of the target sub-paths in the task group is obtained, and the unfinished value is weighted and averaged to determine a re-division point of the task group; The target sub-paths of the first unmanned vehicles and the second unmanned vehicles in the task group are re-determined according to the re-division point, and the target delivery tasks are updated according to the target sub-paths; 6. A multi-unmanned vehicle delivery apparatus, characterized by, The target delivery tasks are continuously updated until the unmanned vehicles complete all tasks. The method comprises the following steps: at least one processor, and a memory connected to the at least one processor in communication; 7. A computer-readable storage medium, characterized in that, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the delivery method of the multiple unmanned vehicles according to any one of claims 1 to 4. The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the delivery method of the multiple unmanned vehicles according to any one of claims 1 to 4.

Images