Distribution method, system and equipment for multiple unmanned vehicles, and medium

Abstract

The invention provides a distribution method, system and device for multiple unmanned vehicles, and a medium, and the method comprises the steps: obtaining a global map of a distribution task, and generating a path queue of distribution points; determining a target starting point of the unmanned vehicle in the path queue; dividing the path queue into target paths according to the target starting point, and configuring a target delivery task of the unmanned vehicle according to the target paths; and 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.

Description

Technical Field

[0001] The present invention relates to the field of intelligent distribution technology, and in particular to a distribution method, system, equipment and medium for multiple unmanned vehicles. Background Art

[0002] In recent years, in the field of autonomous delivery by unmanned vehicles, unmanned vehicles, as an intelligent delivery tool, are gradually replacing the traditional human delivery model, especially showing unique advantages in complex, dynamic and large-scale urban environments. Autonomous delivery systems of unmanned vehicles usually rely on core technologies such as high-precision maps, sensor data fusion, path planning and task scheduling to efficiently, accurately and safely transport goods from the delivery point to the destination.

[0003] However, the existing path planning and task allocation algorithms lack dynamic adjustment capabilities in collaborative tasks involving multiple unmanned vehicles, making it difficult to cope with complex urban distribution environments. In addition, collaborative technologies are limited by communication and computing capabilities, and cannot achieve truly efficient collaboration and optimal resource allocation.

[0004] Therefore, a multi-unmanned vehicle delivery method is urgently needed to solve the problem of uneven distribution resource load due to the lack of dynamic adjustment capability of unmanned vehicles in collaborative tasks. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention proposes a delivery method, system, equipment and medium for multiple unmanned vehicles.

[0006] The first aspect of the present invention discloses a delivery method of multiple unmanned vehicles, comprising:

[0007] Get the global map of the delivery task and generate the route queue of the delivery point;

[0008] Determine the target starting point where the unmanned vehicle is located in the path queue;

[0009] Dividing the path queue into target paths according to the target starting point, and configuring the target delivery task of the unmanned vehicle according to the target path;

[0010] The target path is re-segmented according to the status feedback of the target delivery task, and the target delivery task is dynamically updated according to the re-segmented path.

[0011] As an optional implementation manner, the obtaining of the global map of the delivery task includes:

[0012] According to the delivery task, the vehicle set of N unmanned vehicles in the distribution center is determined, and the target point set of M delivery points outside the distribution center is determined, where the vehicle set is represented by L car ={c1,c2,...,c n}, the target point set is represented by L site ={s1,s2,...,s m}, the locations of the distribution center, distribution point and unmanned vehicle are obtained according to the distribution task.

[0013] As an optional implementation, the generating of the route queue of the delivery point includes:

[0014] Construct the first delivery point S in the target point set j1 and the second delivery point S j2 The distance cost and commuting cost, the distance cost is represented by C dis (s j1 ,s j2 )=NavLength(s j1 ,s j2 ), where NavLength(s j1 ,s j2 ) represents the first delivery point S j1 and the second delivery point S j2 The cost of generating a non-shortest path through global map navigation, the commuting cost is represented by C tra (s j1 ,s j2 )=traffic(s j1 ,s j2 ), where traffic(s j1 ,s j2 ) represents the first delivery point S j1 and the second delivery point S j2 The cost of being on a global map navigation path affected by commuting;

[0015] Assign the weight α1 of the distance cost and the weight α2 of the commuting cost, and define the first delivery point S j1 and the second delivery point S j2 The TSP cost is expressed as:

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

[0017] According to the TSP cost, a cost matrix is ​​constructed to solve the path problem of the distribution points, determine the order of the distribution points on the path and the shortest distance between the distribution points, and output a path queue that forms a closed loop around the distribution center. The path queue is expressed as Represents the path sequence of the i-th delivery point.

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

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

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

[0021] Evenly dividing the path between two adjacent target starting points in the path queue to generate a target sub-path for the target unmanned vehicle starting from the target starting point;

[0022] 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 from the target starting point along the target sub-path to the split point to perform the sub-delivery task;

[0023] A task list for the unmanned vehicle is generated according to the sub-delivery tasks and the task group, and a target delivery task for the unmanned vehicle is configured according to the target sub-path and the task list.

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

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

[0026] Determine 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 evenly divided points and the state information;

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

[0028] The dynamic threshold is compared with the progress difference between 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 to be re-segmented.

[0029] As an optional implementation manner, dynamically updating the target delivery task according to the re-segmented path includes:

[0030] If the current task group needs to be re-split, the unfinished value of the target sub-path in the task group is obtained and the unfinished value is weighted averaged to determine the re-splitting point of the task group;

[0031] Re-determine the target sub-paths of the first unmanned vehicle and the second unmanned vehicle in the task group according to the re-segmentation point, and update the target delivery task according to the target sub-paths;

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

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

[0034] The path solving module is used to obtain the global map of the delivery task and generate the path queue of the delivery point;

[0035] A starting point search module, used to determine the target starting point of the unmanned vehicle in the path queue;

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

[0037] The dynamic adjustment module is used to re-segment the target path according to the status feedback of the target delivery task, and dynamically update the target delivery task according to the re-segmented path.

[0038] As an optional implementation, the step of obtaining a global map of the delivery task in the path solving module includes:

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

[0040] As an optional implementation, the path queue for generating the delivery points in the path solving module includes:

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

[0042] Assign the weight α1 of the distance cost and the weight α2 of the commuting cost, and define the first delivery point S j1 and the second delivery point S j2 The TSP cost is expressed 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, determine the order of the distribution points on the path and the shortest distance between the distribution points, and output a path queue that forms a closed loop around the distribution center. The path queue is expressed as Represents the path sequence of the i-th delivery point.

[0045] As an optional implementation, the step of determining the target starting point where the unmanned vehicle is located in the path queue in the starting point search module includes:

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

[0047] As an optional implementation, the task allocation module divides the path queue into target paths according to the target starting point, and configures the target delivery task of the unmanned vehicle according to the target path, including:

[0048] Evenly dividing the path between two adjacent target starting points in the path queue to generate a target sub-path for the target unmanned vehicle starting from the target starting point;

[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 from the target starting point along the target sub-path to the split point to perform the sub-delivery task;

[0050] A task list for the unmanned vehicle is generated according to the sub-delivery tasks and the task group, and a target delivery task for the unmanned vehicle is configured according to the target sub-path and the task list.

[0051] As an optional implementation, the re-segmentation of the target path according to the state feedback of the target delivery task in the dynamic adjustment module includes:

[0052] In response to the status information returned by the unmanned vehicle, traverse the task status and motion status of each unmanned vehicle in the task group;

[0053] Determine 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 evenly divided points and the state information;

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

[0055] The dynamic threshold is compared with the progress difference between 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 to be re-segmented.

[0056] As an optional implementation, the dynamically adjusting module dynamically updating the target delivery task according to the re-segmented path includes:

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

[0058] Re-determine the target sub-paths of the first unmanned vehicle and the second unmanned vehicle in the task group according to the re-segmentation point, and update the target delivery task according to the target sub-paths;

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

[0060] The third aspect of the present invention discloses a delivery device for multiple unmanned vehicles, comprising:

[0061] at least one processor, and

[0062] a memory communicatively connected to the at least one processor; wherein,

[0063] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the delivery method of multiple unmanned vehicles as described in any one of the first aspects of the present invention.

[0064] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the delivery method of multiple unmanned vehicles as described in any one of the first aspect of the present invention.

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

[0066] The present invention proposes a method, system, equipment and medium for the distribution of multiple unmanned vehicles, the method comprising: obtaining a global map of the distribution task, generating a path queue of the distribution point; determining the target starting point of the unmanned vehicle in the path queue; dividing the path queue into target paths according to the target starting point, configuring the target distribution task of the unmanned vehicle according to the target path; re-segmenting the target path according to the state feedback of the target distribution task, and dynamically updating the target distribution task according to the re-segmented path. The present invention obtains a closed-loop path point queue by solving the traveling salesman problem in the path generation of the global map, uses a search algorithm to query the path point closest to the path center for the path queue, and preliminarily groups all the path points according to the number of unmanned vehicles, and introduces a re-segmentation scheme to dynamically adjust the task volume of the unmanned vehicle, ensuring the balance and efficiency of task allocation during the execution process, not only improving the calculation efficiency of path planning, but also enhancing the flexibility of allocating collaborative tasks, solving the problem of uneven distribution resource load due to the lack of dynamic adjustment capability of unmanned vehicles in collaborative tasks, and having great application value in the field of unmanned vehicle distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0068] Figure 1It is a flow chart of the delivery method of multiple unmanned vehicles of the present invention;

[0069] Figure 2 Schematic diagram of a delivery system of multiple unmanned vehicles according to the present invention. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0071] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0072] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0073] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0074] Example 1

[0075] See also Figure 1 The embodiment of the present invention discloses a delivery method of multiple unmanned vehicles, including:

[0076] 101. Obtain a global map of the delivery task and generate a route queue for the delivery point;

[0077] It should be noted that the delivery task refers to the process in which unmanned vehicles transport items (such as express delivery, express transportation, fresh food, medicine and fast-moving consumer goods, etc.) to all delivery points (such as parks, campuses, residential areas, warehouses) along the planned route within the area with the distribution center as the center. Autonomous delivery by unmanned vehicles usually needs to rely on high-precision maps, multi-sensor data fusion, unmanned vehicle path planning and unmanned vehicle task scheduling. Specifically, the distribution center will receive various delivery requirements related to the distribution point, and the distribution center will generate the corresponding delivery tasks. The location of the distribution center as the regional center and the location of the distribution point can provide accurate road information and location references through high-precision maps. Next, it is necessary to generate optional paths for unmanned vehicles to perform delivery tasks.

[0078] Specifically, when generating the task path of the unmanned vehicle, it is necessary to consider a variety of influencing factors. For example, if the unmanned vehicle starts from the distribution center, it is necessary to consider the shortest total distance that each unmanned vehicle needs to move. 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. A reasonable allocation plan can enable the unmanned vehicle to efficiently complete all delivery tasks. The path selection and task allocation of the unmanned vehicle are the problems that need to be solved at present. Before determining the path selection and task allocation, it is necessary to obtain the corresponding parameters as data support. The subsequent implementation method will further describe how to complete the path selection and task allocation of the unmanned vehicle.

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

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

[0081] Specifically, when communication is feasible, the distribution center receives delivery tasks issued according to the delivery points, where the number of unit delivery tasks and the number of delivery points correspond to each other and are recorded as M. The M delivery points are set as the target points (task end points) of the delivery tasks, and the number of optional unmanned vehicles that can perform the delivery tasks is recorded as N. The location information of the delivery points can be confirmed based on the received address information, and the location of the unmanned vehicle can be confirmed through multiple sensors, vehicle networks and high-precision maps. It can be known that the road conditions and environment of the delivery point area can be queried on the high-precision map through the address information, and the factors affecting the travel efficiency of the unmanned vehicle (such as traffic congestion, poor road conditions, weather effects, etc.) can be obtained through the sensors of the unmanned vehicle. Environmental information is then integrated with the high-precision map information to determine the degree of impact on the delivery efficiency of the unmanned vehicle in the actual scenario.

[0082] As an optional implementation, the generating of the route queue of the delivery point includes:

[0083] Construct the first delivery point S in the target point set j1 and the second delivery point S j2 The distance cost and commuting cost, the distance cost is represented by C dis (s j1 ,s j2 )=NavLength(sj1 ,s j2 ), where NavLength(s j1 ,s j2 ) represents the first delivery point S j1 and the second delivery point S j2 The cost of generating a non-shortest path through global map navigation, the commuting cost is represented by C tra (s j1 ,s j2 )=traffic(s j1 ,s j2 ), where traffic(s j1 ,s j2 ) represents the first delivery point S j1 and the second delivery point S j2 The cost of being on a global map navigation path affected by commuting;

[0084] Specifically, in order to obtain a path that takes the shortest time as possible, the unmanned vehicle can start from the distribution center to the farthest distribution point, and then travel to the next distribution point in turn until the distribution points form a closed loop around the distribution center to achieve the highest distribution efficiency. Therefore, the TSP model is introduced in this implementation, and the path planning of each distribution point can be converted into a traveling salesman problem. In this embodiment, the solution to the path queue can be understood as the shortest path problem in which the unmanned vehicle starts from the starting distribution point, visits each distribution point only once, and finally returns to the starting distribution point. However, unlike the traditional traveling salesman problem, there is more than one unmanned vehicle as a traveling salesman, and the shortest path and task allocation problem of each unmanned vehicle need to be considered. Therefore, the initial closed-loop path queue is generated here.

[0085] Furthermore, in order to improve the accuracy of generating path queues, two factors that affect delivery efficiency: path distance and commuting time are taken as issues that need to be considered when generating paths. The two factors are constructed as TSP costs in the TSP model, where the path distance cost can be queried by using a high-precision map to inquire about the distance between the delivery starting point and the delivery end point before executing the delivery task, or it can be queried through the navigation path. In addition to the path distance, the commuting time problem also needs to consider factors that affect the actual commuting time, such as weather factors, road conditions, and traffic congestion factors during the actual travel process. The constructed commuting cost further improves the probability of generating the shortest path queue, avoids some influencing factors causing the actual path time to be too high, and makes the path between two adjacent delivery points in the generated closed-loop path queue the shortest.

[0086] Assign the weight α1 of the distance cost and the weight α2 of the commuting cost, and define the first delivery point S j1 and the second delivery point S j2The TSP cost is expressed as:

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

[0088] According to the TSP cost, a cost matrix is ​​constructed to solve the path problem of the distribution points, determine the order of the distribution points on the path and the shortest distance between the distribution points, and output a path queue that forms a closed loop around the distribution center. The path queue is expressed as Represents the path sequence of the i-th delivery point.

[0089] Specifically, after assigning weights to different TSP costs, a cost matrix is ​​constructed to solve the path queue. To ensure that the distance of each path is the shortest, the cost matrix includes all possible paths generated by all distribution points. Therefore, when constructing the TSP cost, any two distribution points S j1 and S j2 It is built on the basis of ensuring that any possible shortest path can be traversed when generating the path queue. Can record from delivery point i The order of the departure paths.

[0090] 102. Determine the target starting point where the unmanned vehicle is located 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 the corresponding delivery task, it is necessary to further confirm the starting point of the unmanned vehicle in the delivery task. Since the path queue has a path sequence and is a closed-loop path, configuring two unmanned vehicles at the same starting point and performing delivery tasks in opposite directions can reduce the resource consumption of subsequent computing task allocation and path allocation, which is especially important in collaborative tasks with real-time requirements, and can quickly deploy unmanned vehicles to deliver tasks.

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

[0093] According to the initial position of the target unmanned vehicle in the vehicle set at the distribution center, the adjacent points of each unmanned vehicle relative to the N distribution points are determined, and the adjacent point farthest from the target unmanned vehicle among the adjacent points is selected as the target starting point of the target unmanned vehicle, and the number of the target starting points is at least N / 2.

[0094] Specifically, taking 4 unmanned vehicles as an example, the delivery points in the path queue are continuously searched and the farthest delivery point is selected as the starting point based on 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 then it returns to the distribution center from the final delivery point. Selecting the farthest delivery point as the starting point can reduce the commuting time consumed by the unmanned vehicle in traveling to and from the distribution center. When 4 unmanned vehicles perform delivery tasks, two delivery points are taken as the starting point. The unmanned vehicle only needs to complete each 1 / 4 arc of the closed-loop path queue from the starting point in turn, so as to average the actual commuting time of each unmanned vehicle as much as possible, which can improve the efficiency of the distribution center in completing batch delivery tasks per unit time.

[0095] 103. Divide the path queue into target paths according to the target starting point, and configure the target delivery task of the unmanned vehicle according to the target path;

[0096] As an optional implementation, dividing the path queue into target paths according to the target starting point, and configuring the target delivery task of the unmanned vehicle according to the target path, includes:

[0097] Evenly dividing the path between two adjacent target starting points in the path queue to generate a target sub-path for the target unmanned vehicle starting from the target starting point;

[0098] 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 from the target starting point along the target sub-path to the split point to perform the sub-delivery task;

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

[0100] Specifically, in order to evenly divide the path between each adjacent starting point, it can be evenly divided according to distance factors, road conditions factors, traffic factors and weather factors, so as to ensure that two unmanned vehicles traveling in opposite directions at adjacent delivery points can reach the task end at the same time to complete the delivery task at the same time, where the target delivery task is the sub-delivery task that needs to be completed for the corresponding N delivery points, and the target sub-path is the delivery task that each unmanned vehicle needs to complete independently.

[0101] 104. Re-segment the target path according to the status feedback of the target delivery task, and dynamically update the target delivery task according to the re-segmented path.

[0102] As an optional implementation manner, the re-segmenting the target path according to the state feedback of the target delivery task includes:

[0103] In response to the status information returned by the unmanned vehicle, traverse the task status and motion status of each unmanned vehicle in the task group;

[0104] Determine 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 evenly divided points and the state information;

[0105] The dynamic threshold is updated in real time according to the road environment information and the travel information of the progress value obtained in the state information, and the dynamic threshold is configured as the adjustment condition for re-segmenting the target path;

[0106] The dynamic threshold is compared with the progress difference between 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 to be re-segmented.

[0107] Specifically, for two unmanned vehicles traveling towards each other between adjacent delivery points, there is a problem of unreasonable delivery tasks. For example, in the actual delivery process, the unmanned vehicle c1 has a good road condition and completes the delivery task quickly, while the unmanned vehicle c2 has a slow delivery task due to traffic jams. In this case, it is necessary to make real-time adjustments to the above situation. Assuming that the dynamic threshold is 2, the first progress value of the i-th unmanned vehicle (the first unmanned vehicle) is length(l ci ), the second progress value of the jth unmanned vehicle (the second unmanned vehicle) is length(l cj ), you can use length(l ci )-length(l cj )>2, the judgment result is used to select whether to re-segment. Since the process of obtaining the progress value has been confirmed based on the status information returned by the unmanned vehicle, the data that causes the unreasonable delivery task parsed from the status information can also be reused in the subsequent adjustment of the re-segmentation point, reducing the computing loss of the distribution center.

[0108] As an optional implementation manner, dynamically updating the target delivery task according to the re-segmented path includes:

[0109] If the current task group needs to be re-split, the unfinished value of the target sub-path in the task group is obtained and the unfinished value is weighted averaged to determine the re-splitting point of the task group;

[0110] Re-determine the target sub-paths of the first unmanned vehicle and the second unmanned vehicle in the task group according to the re-segmentation point, and update the target delivery task according to the target sub-paths;

[0111] The target delivery task is continuously updated until the unmanned vehicle completes all tasks.

[0112] It should be noted that for the delivery tasks being executed, the unmanned vehicles that have not completed the sub-delivery tasks can be repeatedly tested, and the task volume of each unmanned vehicle can be adjusted in real time according to the actual operation status of the unmanned vehicle, thereby improving the overall efficiency of the unmanned vehicle in completing the target delivery task.

[0113] The present invention proposes a method for distributing multiple unmanned vehicles, including: obtaining a global map of distribution tasks, generating a path queue of distribution points; determining the target starting point of the unmanned vehicle in the path queue; dividing the path queue into target paths according to the target starting point, configuring the target distribution task of the unmanned vehicle according to the target path; re-segmenting the target path according to the state feedback of the target distribution task, and dynamically updating the target distribution task according to the re-segmented path. The present invention obtains a closed-loop path point queue by solving the traveling salesman problem in the path generation of the global map, uses a search algorithm to query the path point closest to the path center for the path queue, and preliminarily groups all the path points according to the number of unmanned vehicles, and introduces a re-segmentation scheme to dynamically adjust the task volume of the unmanned vehicle, ensuring the balance and efficiency of task allocation during the execution process, not only improving the calculation efficiency of path planning, but also enhancing the flexibility of task allocation, solving the problem of uneven distribution resource load due to the lack of dynamic adjustment capability of unmanned vehicles in collaborative tasks, and having great application value in the field of unmanned vehicle distribution.

[0114] like Figure 2 As shown, the second aspect of the present invention discloses a delivery system of multiple unmanned vehicles, the system comprising:

[0115] The path solving module is used to obtain the global map of the delivery task and generate the path queue of the delivery point;

[0116] A starting point search module, used to determine the target starting point of the unmanned vehicle in the path queue;

[0117] A task allocation module, used to divide the path queue into target paths according to the target starting point, and configure the target delivery task of the unmanned vehicle according to the target path;

[0118] The dynamic adjustment module is used to re-segment the target path according to the status 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 step of obtaining a global map of the delivery task in the path solving module includes:

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

[0121] As an optional implementation, the path queue for generating the delivery points in the path solving module includes:

[0122] Construct the first delivery point S in the target point set j1 and the second delivery point S j2 The distance cost and commuting cost, the distance cost is represented by C dis (s j1 ,s j2 )=NavLength(s j1 ,s j2 ), where NavLength(s j1 ,s j2 ) represents the first delivery point S j1 and the second delivery point S j2 The cost of generating a non-shortest path through global map navigation, the commuting cost is represented by C tra (s j1 ,s j2 )=traffic(s j1 ,s j2 ), where traffic(s j1 ,s j2 ) represents the first delivery point S j1 and the second delivery point S j2 The cost of being on a global map navigation path affected by commuting;

[0123] Assign the weight α1 of the distance cost and the weight α2 of the commuting cost, and define the first delivery point S j1 and the second delivery point S j2 The TSP cost is expressed as:

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

[0125] According to the TSP cost, a cost matrix is ​​constructed to solve the path problem of the distribution points, determine the order of the distribution points on the path and the shortest distance between the distribution points, and output a path queue that forms a closed loop around the distribution center. The path queue is expressed as Represents the path sequence of the i-th delivery point.

[0126] As an optional implementation, the step of determining the target starting point where the unmanned vehicle is located in the path queue in the starting point search module includes:

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

[0128] As an optional implementation, the task allocation module divides the path queue into target paths according to the target starting point, and configures the target delivery task of the unmanned vehicle according to the target path, including:

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

[0130] 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 from the target starting point along the target sub-path to the split point to perform the sub-delivery task;

[0131] A task list for the unmanned vehicle is generated according to the sub-delivery tasks and the task group, and a target delivery task for the unmanned vehicle is configured according to the target sub-path and the task list.

[0132] As an optional implementation, the re-segmentation of the target path according to the state feedback of the target delivery task in the dynamic adjustment module includes:

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

[0134] Determine 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 evenly divided points and the state information;

[0135] The dynamic threshold is updated in real time according to the road environment information and the travel information of the progress value obtained in the state information, and the dynamic threshold is configured as the adjustment condition for re-segmenting the target path;

[0136] The dynamic threshold is compared with the progress difference between 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 to be re-segmented.

[0137] As an optional implementation, the dynamically adjusting module dynamically updating the target delivery task according to the re-segmented path includes:

[0138] If the current task group needs to be re-split, the unfinished value of the target sub-path in the task group is obtained and the unfinished value is weighted averaged to determine the re-splitting point of the task group;

[0139] Re-determine the target sub-paths of the first unmanned vehicle and the second unmanned vehicle in the task group according to the re-segmentation point, and update the target delivery task according to the target sub-paths;

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

[0141] The third aspect of the present invention discloses a delivery device for multiple unmanned vehicles, comprising:

[0142] at least one processor, and

[0143] a memory communicatively connected to the at least one processor; wherein,

[0144] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the delivery method of multiple unmanned vehicles as described in any one of the first aspects of the present invention.

[0145] The computer device may be a terminal, and the computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes 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 operation of 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 an external terminal through a network connection. When the computer program is executed by the processor, a delivery method of multiple unmanned vehicles is implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0146] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the delivery method of multiple unmanned vehicles as described in any one of the first aspect of the present invention.

[0147] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the above-mentioned embodiments of the delivery method by multiple unmanned vehicles. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), 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, if the above modules of the present invention are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, RAM, ROM, magnetic disks or optical disks.

[0149] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A delivery method using multiple unmanned vehicles, characterized in that: The method comprises: Get the global map of the delivery task and generate the route queue of the delivery point; Determine the target starting point where the unmanned vehicle is located in the path queue; Dividing the path queue into target paths according to the target starting point, and configuring the target delivery task of the unmanned vehicle according to the target path; The target path is re-segmented according to the status feedback of the target delivery task, and the target delivery task is dynamically updated according to the re-segmented path.

2. The delivery method of multiple unmanned vehicles according to claim 1, characterized in that: The obtaining of the global map of the delivery task includes: According to the delivery task, the vehicle set of N unmanned vehicles in the distribution center is determined, and the target point set of M delivery points outside the distribution center is determined, where the vehicle set is represented by L car ={c1,c2,...,c n }, the target point set is represented by L site ={s1,s2,...,s m }, the locations of the distribution center, distribution point and unmanned vehicle are obtained according to the distribution task.

3. The delivery method of multiple unmanned vehicles according to claim 2, characterized in that: The generating of the path queue of the delivery point comprises: Construct the first delivery point S in the target point set j1 and the second delivery point S j2 The distance cost and commuting cost, the distance cost is represented by C dis (s j1 ,s j2 )=NavLength(s j1 ,s j2 ), where NavLength(s j1 ,s j2 ) represents the first delivery point S j1 and the second delivery point S j2 The cost of generating a non-shortest path through global map navigation, the commuting cost is represented by C tra (s j1 ,s j2 )=traffic(s j1 ,s j2 ), where traffic(s j1 ,s j2 ) represents the first delivery point S j1 and the second delivery point S j2 The cost of being on a global map navigation path affected by commuting; Assign the weight α1 of the distance cost and the weight α2 of the commuting cost, and define the first delivery point S j1 and the second delivery point S j2 The TSP cost is expressed as: C(s j1 ,s j2 )=α1C dis (s j1 ,s j2 )+α2C tra (s j1 ,s j2 ); According to the TSP cost, a cost matrix is ​​constructed to solve the path problem of the distribution points, determine the order of the distribution points on the path and the shortest distance between the distribution points, and output a path queue that forms a closed loop around the distribution center. The path queue is expressed as Represents the path sequence of the i-th delivery point.

4. The delivery method using multiple unmanned vehicles according to claim 3, characterized in that: The step of determining that the unmanned vehicle is located at a target starting point in the path queue includes: According to the initial position of the target unmanned vehicle in the vehicle set at the distribution center, the adjacent points of each unmanned vehicle relative to N distribution points are determined, and the adjacent point farthest from the target unmanned vehicle among the adjacent points is selected as the target starting point of the target unmanned vehicle, and the number of the target starting points is at least N / 2.

5. The delivery method using multiple unmanned vehicles according to claim 1, characterized in that: The step of dividing the path queue into target paths according to the target starting point and configuring the target delivery task of the unmanned vehicle according to the target path includes: Evenly dividing the path between two adjacent target starting points in the path queue to generate a target sub-path for the target unmanned vehicle starting from the target starting point; 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 from the target starting point along the target sub-path to the split point to perform the sub-delivery task; A task list for the unmanned vehicle is generated according to the sub-delivery tasks and the task group, and a target delivery task for the unmanned vehicle is configured according to the target sub-path and the task list.

6. The delivery method using multiple unmanned vehicles according to claim 5, characterized in that: The re-segmenting the target path according to the status feedback of the target delivery task includes: In response to the status information returned by the unmanned vehicle, traverse the task status and motion status of each unmanned vehicle in the task group; Determine 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 evenly divided points and the state information; The dynamic threshold is updated in real time according to the road environment information and the travel information of the progress value obtained in the state information, and the dynamic threshold is configured as the adjustment condition for re-segmenting the target path; The dynamic threshold is compared with the progress difference between 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 to be re-segmented.

7. The delivery method using multiple unmanned vehicles according to claim 6, characterized in that: The dynamically updating the target delivery task according to the re-segmented path includes: If the current task group needs to be re-split, the unfinished value of the target sub-path in the task group is obtained and the unfinished value is weighted averaged to determine the re-splitting point of the task group; Re-determine the target sub-paths of the first unmanned vehicle and the second unmanned vehicle in the task group according to the re-segmentation point, and update the target delivery task according to the target sub-paths; The target delivery task is continuously updated until the unmanned vehicle completes all tasks.

8. A delivery system with multiple unmanned vehicles, characterized in that: The system comprises: The path solving module is used to obtain the global map of the delivery task and generate the path queue of the delivery point; A starting point search module, used to determine the target starting point of the unmanned vehicle in the path queue; A task allocation module, used to divide the path queue into target paths according to the target starting point, and configure the target delivery task of the unmanned vehicle according to the target path; The dynamic adjustment module is used to re-segment the target path according to the status feedback of the target delivery task, and dynamically update the target delivery task according to the re-segmented path.

9. A delivery device with multiple unmanned vehicles, characterized in that: include: at least one processor, and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the delivery method of multiple unmanned vehicles as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the delivery method of multiple unmanned vehicles as described in any one of claims 1 to 7.

Images