Unmanned vehicle collaborative delivery path planning method, device and computer-readable storage medium

Abstract

The present application provides a method, device and computer-readable storage medium for collaborative delivery of unmanned vehicles. A large unmanned vehicle is loaded with one or more small unmanned vehicles. When the current small unmanned vehicle is transferred and unloaded, the pre-stored correspondence between the sub-area and the small unmanned vehicle is called to obtain the sub-area corresponding to the current small unmanned vehicle; each of the sub-areas includes several delivery locations; the target delivery location is determined in the sub-area corresponding to the current small unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information; the current small unmanned vehicle uses the target delivery location as the starting point of the cargo delivery task to implement the intra-domain path planning operation in the current sub-area. The present application improves the delivery efficiency of goods.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a method, device and computer-readable storage medium for unmanned vehicle collaborative delivery path planning. Background Art

[0002] With the advancement of technology, unmanned vehicles have gradually entered people's daily lives. On the one hand, unmanned vehicles are widely used in the modern logistics industry. During the process of logistics distribution or goods delivery, unmanned vehicles need to constantly determine their current location and constantly plan their driving paths in order to efficiently and accurately determine the destination, and ultimately ensure that the goods are delivered to the destination.

[0003] However, research has found that unmanned vehicles in existing technologies are often delivered by a single unmanned vehicle, which results in low operating efficiency. A single unmanned vehicle control strategy is also not suitable for scenarios where large and small unmanned vehicles collaborate to deliver goods. Researchers have found that in the above specific scenarios, it is particularly important to select the optimal target delivery address from a large number of delivery locations for collaborative delivery between large and small unmanned vehicles, and there is still no better solution. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, device and computer-readable storage medium for planning a route for collaborative delivery by an unmanned vehicle to solve the technical defect of not being able to obtain the optimal target delivery location. The specific technical solution is as follows:

[0005] The present application provides a method for planning a route for collaborative delivery of unmanned vehicles, including:

[0006] The large unmanned vehicle loads one or more small unmanned vehicles. When the current small unmanned vehicle is transferred and unloaded, the pre-stored correspondence between the sub-area and the small unmanned vehicle is called to obtain the sub-area corresponding to the current small unmanned vehicle; each of the sub-areas includes several delivery locations;

[0007] Determine the target delivery location in the sub-area corresponding to the current unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information;

[0008] The large unmanned vehicle drives to the target delivery location and unloads the current small unmanned vehicle at the target delivery location;

[0009] The current unmanned vehicle uses the target delivery location as the starting point of the cargo delivery task and implements intra-domain path planning operations in the current sub-area.

[0010] Preferably, as an implementable method, the step of determining the target delivery location in the sub-area corresponding to the current small unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information includes:

[0011] Construct a target evaluation result output function for the distribution location based on the distribution point attribute information; calculate the target evaluation result output value of all distribution locations in the current sub-area based on the target evaluation result output function for the distribution location;

[0012] Calculate the demand value of small unmanned vehicles in the current sub-area based on the service capability attribute information of the delivery vehicle;

[0013] The delivery location is determined according to the output value of the target evaluation result and the demand value of the small unmanned vehicle in the current sub-area to obtain the target delivery location.

[0014] Preferably, as an implementable solution, the distribution point attribute information includes the distribution time span, the express delivery and receiving volume of the distribution location over the distribution time span, and the distance between the distribution locations.

[0015] Preferably, as an implementable solution, a target evaluation result output function of a delivery location is constructed according to the delivery point attribute information, including:

[0016] The target evaluation result output function of the delivery location is constructed based on the delivery time span, the express delivery and receiving volume of the delivery location, and the distance between the delivery locations;

[0017] The formula of the target evaluation result output function of the distribution location is as follows:

[0018]

[0019] Among them, α 1 , α 2 are all pre-set coefficients. Represents the target evaluation result output value of the delivery location; Indicates the delivery location within the delivery time span starting from the current time t The volume of express delivery and receipt;

[0020] Indicates the delivery location Delivery location The distance between

[0021] Delivery Location represents the i-th delivery location in the q-th sub-region;

[0022] Delivery Location represents the jth delivery location in the qth sub-region;

[0023] The sub-region is denoted as q, q∈{1,2,3,…}.

[0024] Preferably, as an implementable solution, the delivery vehicle service capability attribute information includes the express delivery and receiving volume at the delivery location and the cargo carrying capacity of the small unmanned vehicle.

[0025] Preferably, as an implementable solution, the demand value of the small unmanned vehicle in the current sub-area is calculated based on the service capability attribute information of the delivery vehicle, specifically including:

[0026] Calculate the demand value of unmanned vehicles in the current sub-area based on the express delivery and receiving volume of the delivery location and the cargo carrying capacity of unmanned vehicles;

[0027] The formula for the demand value of the small unmanned vehicle is as follows:

[0028]

[0029] Among them, N q Indicates the demand value of small unmanned vehicles in the sub-area; Indicates the delivery location within the delivery time span starting from the current time t The express delivery volume; w represents the cargo carrying capacity of each small unmanned vehicle.

[0030] Preferably, as an implementable solution, the delivery location is determined according to the output value of the target evaluation result and the demand value of the small unmanned vehicle in the current sub-area to obtain the target delivery location, which specifically includes the following steps:

[0031] Get the target evaluation result output value of all distribution locations in the current sub-region, and output the target evaluation result value of all distribution locations Sorting to obtain a delivery location evaluation ranking list; the delivery location evaluation ranking list is arranged in descending order of value;

[0032] The delivery locations with the target quantity threshold number that are ranked at the top are selected from the delivery location evaluation ranking list as the target delivery locations; the value of the target quantity threshold number is equal to the small unmanned vehicle demand value of the current sub-area.

[0033] Preferably, as an implementable method, when the current unmanned vehicle performs the intra-domain path planning operation in the current sub-region with the target delivery location as the starting point of the cargo delivery task, if there are multiple unmanned vehicles in the current sub-region, the delivery task allocation operation is performed on the unmanned vehicles in the current sub-region, and then the intra-domain path planning operation is performed;

[0034] The distribution task allocation operation includes:

[0035] Search for small unmanned vehicles in the current sub-area and determine the current position of each small unmanned vehicle in the current sub-area;

[0036] Get the current delivery location of the goods;

[0037] According to the current delivery location of the goods and the current location of each unmanned vehicle in the current sub-area, the distance between the goods and the vehicle is calculated. Among them, the distance between the cargo and the vehicle target In Indicates the current position of the small unmanned vehicle; d k represents the delivery location of the kth item;

[0038] The target distance between the current position of each unmanned vehicle in the current sub-area and the current delivery position of the goods is calculated. Sorting is performed to obtain a distance sorting list; the distance sorting list is sorted in a direction from small to large values;

[0039] Get the small unmanned vehicle with the smallest value in the distance sorting list as the target small unmanned vehicle:

[0040] Assign the current cargo delivery task to the target unmanned vehicle.

[0041] Preferably, as an implementable solution, when it is detected that the delivery task of the target small unmanned vehicle is multiple tasks, the intra-domain path planning operation is performed:

[0042] Determine the current location of the target small unmanned vehicle and the delivery locations of all delivery tasks that the target small unmanned vehicle needs to complete;

[0043] Generate an optimal driving path for the target small unmanned vehicle through path planning, where the optimal driving path starts from the current position of the target small unmanned vehicle and passes through the delivery locations of all delivery tasks that the target small unmanned vehicle needs to complete;

[0044] Send the optimal driving path to the target small unmanned vehicle.

[0045] The present invention provides a route planning device for unmanned vehicle collaborative delivery, the device comprising: a call processing module, a target determination module, an unloading control processing module, and an intra-domain planning module, wherein;

[0046] A calling processing module is used to load one or more small unmanned vehicles. When the current small unmanned vehicle is transferred and unloaded, the pre-stored correspondence between the sub-area and the small unmanned vehicle is called to obtain the sub-area corresponding to the current small unmanned vehicle; each of the sub-areas includes a number of delivery locations;

[0047] A target determination module is used to determine the target delivery location in the sub-area corresponding to the current small unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information;

[0048] An unloading control processing module is used to control the large unmanned vehicle to drive to a target delivery location and unload the current small unmanned vehicle at the target delivery location;

[0049] The intra-domain planning module is used to control the current unmanned vehicle to implement intra-domain path planning operations in the current sub-area with the target delivery location as the starting point of the cargo delivery task.

[0050] In a third aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method execution steps of the above-mentioned unmanned vehicle collaborative delivery path planning are implemented.

[0051] Beneficial effects of the embodiments of the present application:

[0052] The large unmanned vehicle is loaded with one or more small unmanned vehicles. When transferring and unloading the current small unmanned vehicle, the corresponding relationship is called to obtain the sub-area corresponding to the current small unmanned vehicle. When determining the delivery location within the sub-area, it is necessary to determine the target delivery location in the current sub-area based on the delivery point attribute information and the delivery vehicle service capability attribute information;

[0053] In the above specific implementation process, since each sub-area includes several delivery locations, the large unmanned vehicle in the technical solution of the present application finally determines the target delivery location in the sub-area corresponding to the current small unmanned vehicle based on two reference factors: the attribute information of the delivery point and the attribute information of the service capability of the delivery vehicle; through the design of the above two reference factors, the actual situation of the attribute information of the delivery point and the attribute information of the service capability of the delivery vehicle is fully considered to the greatest extent, and the target delivery location is obtained, which is used to transfer the small unmanned vehicle to the target delivery location by the large unmanned vehicle to unload the current small unmanned vehicle (thereby providing more efficient and reasonable transit delivery location processing, and then the current small unmanned vehicle uses the target delivery location as the starting point of the cargo delivery task to implement the intra-domain path planning operation in the current sub-area), thereby improving the efficiency of goods delivery;

[0054] By determining the target delivery location processing operation in the current sub-area based on the delivery point attribute information and the delivery vehicle service capability attribute information, a technical basis is provided for the subsequent small unmanned vehicle to carry out delivery task allocation operations.

[0055] Of course, implementing any product or method of the present application does not necessarily require achieving all of the above advantages at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0057] Figure 1 A main flow chart of a method for unmanned vehicle collaborative path navigation and delivery provided in an embodiment of the present application;

[0058] Figure 2 A specific flow chart of step S20 in a method for unmanned vehicle collaborative path navigation and delivery provided in an embodiment of the present application;

[0059] Figure 3 A specific flow chart of step S201 in a method for unmanned vehicle collaborative path navigation and delivery provided in an embodiment of the present application;

[0060] Figure 4 A specific flow chart of step S202 in a method for unmanned vehicle collaborative path navigation and delivery provided in an embodiment of the present application;

[0061] Figure 5 A specific flow chart of step S203 in a method for unmanned vehicle collaborative path navigation and delivery provided in an embodiment of the present application;

[0062] Figure 6 A specific flow chart of step S40 in a method for unmanned vehicle collaborative path navigation and delivery provided in an embodiment of the present application;

[0063] Figure 7 A specific flow chart of the intra-domain path planning operation in a method for unmanned vehicle collaborative path navigation and delivery provided in an embodiment of the present application;

[0064] Figure 8 A schematic diagram of the structure of an unmanned vehicle collaborative delivery path planning device provided in an embodiment of the present application;

[0065] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0067] like Figure 1 As shown, an unmanned vehicle collaborative delivery path planning method provided in an embodiment of the present application has the following specific steps:

[0068] S10, the large unmanned vehicle loads one or more small unmanned vehicles, and when the current small unmanned vehicle is transferred and unloaded, the pre-stored correspondence between the sub-area and the small unmanned vehicle is called to obtain the sub-area corresponding to the current small unmanned vehicle; each of the sub-areas includes a number of delivery locations; that is, the control system of the large unmanned vehicle (or other control systems) divides the target area formed by the area to be delivered into multiple sub-areas in advance, and when the current small unmanned vehicle needs to be transferred, the correspondence can be directly called to obtain the sub-area to be delivered corresponding to the current small unmanned vehicle;

[0069] S20, determining a target delivery location in the sub-area corresponding to the current small unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information;

[0070] S30, the large unmanned vehicle drives to the target delivery location and unloads the current small unmanned vehicle at the target delivery location;

[0071] S40, the current unmanned vehicle uses the target delivery location as the starting point of the cargo delivery task to implement a path planning operation within the current sub-area;

[0072] The large unmanned vehicle is loaded with one or more small unmanned vehicles. When the current small unmanned vehicle is transferred and unloaded, the corresponding relationship is called to obtain the sub-area corresponding to the current small unmanned vehicle. In the subsequent execution process, the current small unmanned vehicle needs to be unloaded into the current sub-area according to the transfer. The researchers found that since multiple delivery locations are set up in each sub-area, when each small unmanned vehicle performs the cargo delivery task in the current sub-area, the first problem to be solved is how to determine the target delivery location of the small unmanned vehicle (that is, the selection and determination of the unloading location of the large unmanned vehicle for the small unmanned vehicle).

[0073] During the preprocessing operation, it is necessary to divide the area formed by the area to be delivered into multiple sub-areas in advance; the correspondence between each sub-area and the small unmanned vehicle performing the cargo delivery task is pre-stored; that is, for each sub-area, a small unmanned vehicle used to perform the cargo delivery task in the sub-area is pre-determined, and the correspondence between the sub-area and the small unmanned vehicle is stored in the control system of the large unmanned vehicle, so that the control system knows which sub-area each small unmanned vehicle is responsible for the cargo delivery work, and then can control the small unmanned vehicle to perform the unloading process of the small unmanned vehicle in the corresponding sub-area); wherein each sub-area includes several delivery locations; then based on the delivery point attribute information and the delivery vehicle service capability attribute information, the target delivery location is determined in the sub-area corresponding to the current small unmanned vehicle; the large unmanned vehicle drives to the target delivery location and unloads the current small unmanned vehicle at the target delivery location;

[0074] Finally, after completing the unloading of the current small unmanned vehicle and reaching the target delivery location, the current small unmanned vehicle is controlled to implement the intra-domain path planning operation in the current sub-area with the target delivery location as the starting point of the cargo delivery task.

[0075] like Figure 2 As shown, during the execution of step S20, the target delivery location is determined in the sub-area corresponding to the current unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information, including:

[0076] S201, constructing a target evaluation result output function for a delivery location based on the attribute information of the delivery point; calculating the target evaluation result output values ​​of all delivery locations in the current sub-region based on the target evaluation result output function for the delivery location;

[0077] S202, calculating the demand value of the small unmanned vehicle in the current sub-area based on the service capability attribute information of the delivery vehicle;

[0078] S203, determining the delivery location according to the output value of the target evaluation result and the demand value of the small unmanned vehicle in the current sub-area to obtain the target delivery location.

[0079] In the above embodiment, when selecting the target delivery location in the current sub-region, firstly, the target evaluation result output function of the delivery location is constructed according to the attribute information of the delivery point; then, the target evaluation result output value of all the delivery locations in the current sub-region is calculated according to the target evaluation result output function of the delivery location (the target evaluation result output values ​​of all the delivery locations in the current sub-region constitute an initial delivery location set, and then the small unmanned vehicle demand value of the current sub-region is calculated based on the service capability attribute information of the delivery vehicle, and finally the target delivery location is determined according to the target evaluation result output value and the small unmanned vehicle demand value of the current sub-region, that is, the initial delivery location set is optimized and selected, and finally a delivery location set is obtained);

[0080] In the above technical solution, the actual demand in each sub-region needs to be considered. In the specific implementation, the demand value of the small unmanned vehicle in the current sub-region is calculated based on the service capability attribute information of the delivery vehicle; the delivery location is determined according to the output value of the target evaluation result and the demand value of the small unmanned vehicle in the current sub-region, and the target delivery location is obtained (that is, the number of target delivery locations can be one or more). Through the above analysis, it can be seen that the execution process combines the two reference factors of the output value of the target evaluation result and the demand value of the small unmanned vehicle in the current sub-region, and finally calculates the target delivery location.

[0081] The above technical solution is mainly based on the following research findings: the larger the output value of the target evaluation result of the above delivery location, the more suitable the delivery location is as a target delivery location; at the same time, the demand for small unmanned vehicles in each current sub-area also determines how many screened target delivery locations should be determined. For this, it is necessary to combine the demand value of small unmanned vehicles in the current sub-area to finally calculate the delivery location set.

[0082] During the execution of step S201, a target evaluation result output function of the delivery location is constructed according to the delivery point attribute information; wherein the delivery point attribute information includes the delivery time span, the express delivery and receiving volume of the delivery location over the delivery time span, and the distance between the delivery locations.

[0083] See also Figure 3 During the execution of step S201, a target evaluation result output function of the delivery location is constructed according to the delivery point attribute information, which specifically includes the following operations:

[0084] Step S2011, constructing a target evaluation result output function (hereinafter referred to as evaluation function) of the delivery location based on the delivery time span, the express delivery and receiving volume of the delivery location, and the distance between the delivery locations;

[0085] The formula of the target evaluation result output function of the distribution location is as follows:

[0086]

[0087] Among them, α 1 , α 2 are all pre-set coefficients. Represents the target evaluation result output value of the delivery location;

[0088] in, Indicates the delivery location within the delivery time span starting from the current time t The volume of express delivery and receipt;

[0089] Indicates the delivery location Delivery location The distance between

[0090] Delivery Location represents the i-th delivery location in the q-th sub-region;

[0091] Delivery Location represents the jth delivery location in the qth sub-region; the above delivery location Delivery location This can be the associated delivery location;

[0092] The sub-region is denoted as q, q∈{1,2,3}.

[0093] It should be noted that when constructing the evaluation function, a target evaluation result output function of the delivery location is constructed based on the delivery time span, the express delivery and receiving volume of the delivery location, and the distance between the delivery locations (i.e., the distance between the two associated delivery locations mentioned above) (the target evaluation result output function of the delivery location mentioned above is used to calculate and output the target evaluation result output value of the delivery location); the larger the value of the target evaluation result output value of the delivery location mentioned above, the more suitable the delivery location is as the target delivery location; since each sub-area contains several delivery locations, it is crucial to select which delivery location as the target delivery location of the small unmanned vehicle (i.e., the location where the current small unmanned vehicle is unloaded). The embodiment of the present application performs the optimal evaluation and determines the target evaluation result output value of the delivery location through the above method;

[0094] This embodiment takes into account three factors (i.e., the attribute information of the delivery point includes the first factor, the second factor, and the third factor); the first factor includes the express delivery volume of the delivery location: research has found that the greater the delivery volume of the delivery location, the greater the benefit of selecting the delivery location as the target location; the second factor includes the distance between the delivery locations; that is, the farther a delivery location is from other delivery locations, the more inclined it is not to select the delivery location as the target delivery location. The third factor includes the delivery time span; t represents the current date, such as January 26, 2022 is recorded as 20220126; T represents the preset time span size, which is set to 7 days in this solution; It represents the delivery location within the time span from t-7 to t-1 The volume of express delivery and receipt;

[0095] The target evaluation result output function of the delivery location combines the above three factors in order to select a more ideal target delivery location.

[0096] During the execution of step S202, the demand value of the small unmanned vehicle in the current sub-area is calculated based on the delivery vehicle service capacity attribute information; wherein the delivery vehicle service capacity attribute information includes the express delivery and receiving volume at the delivery location and the cargo carrying capacity of the small unmanned vehicle.

[0097] See also Figure 4 During the execution of step S202, the demand value of the small unmanned vehicle in the current sub-area is calculated based on the service capability attribute information of the delivery vehicle, which specifically includes the following operation steps:

[0098] Step S2021, calculating the demand value of the small unmanned vehicle in the current sub-area based on the express delivery and receiving volume of the delivery location and the cargo carrying capacity of the small unmanned vehicle;

[0099] The formula for the demand value of small unmanned vehicles is as follows:

[0100]

[0101] Among them, N q Indicates the demand value of small unmanned vehicles in the sub-area;

[0102] in, Indicates the delivery location within the delivery time span starting from the current time t The volume of express delivery and receipt;

[0103] Among them, w represents the cargo load of each small unmanned vehicle.

[0104] See also Figure 5 During the execution of step S203, the delivery location is determined according to the output value of the target evaluation result and the demand value of the small unmanned vehicle in the current sub-area to obtain the target delivery location, which specifically includes the following operation steps:

[0105] Step S2031: Obtain the target evaluation result output values ​​of all delivery locations in the current sub-region, and output the target evaluation result values ​​of all delivery locations. Sorting to obtain a delivery location evaluation ranking list; the delivery location evaluation ranking list is arranged in descending order of value;

[0106] Step S2032, selecting a delivery location with a target quantity threshold number that is ranked at the top from the delivery location evaluation ranking list as the target delivery location; the value of the target quantity threshold number is equal to the small unmanned vehicle demand value of the current sub-area;

[0107] It should be noted that when the target delivery location of the current sub-region is determined, the target evaluation result output values ​​of all delivery locations are first obtained, and the target evaluation result output values ​​of all delivery locations are calculated. Sorting is performed to obtain a delivery location evaluation ranking list (i.e., thereby forming an initial delivery location set); the delivery location evaluation ranking list is arranged in descending order of value; then, based on the delivery location evaluation ranking list, the delivery locations with the target quantity threshold number that are ranked at the top are selected as the selected delivery locations, i.e., the target delivery locations, and are summarized to form a delivery location set;

[0108] The target quantity threshold is the demand value N of the small unmanned vehicle in the current sub-area. q That is, the value of the target number threshold is related to the demand value of small unmanned vehicles in the sub-area, that is, N q Indicates the demand value of small unmanned vehicles in the sub-area;

[0109] It should be noted that in the specific technical solution of the embodiment of the present application, the target delivery location selection process is: Arrange in descending order and select the first N in the delivery location evaluation sorting list qThe delivery locations are selected as the selected delivery locations to form a delivery location set (i.e., the delivery locations with the target quantity threshold number that are ranked high in the initial delivery location set are finally optimized, i.e., the delivery location set formed by one or more target delivery locations). The above delivery location set contains one or more target delivery locations.

[0110] In a specific implementation, the area to be delivered is divided into three sub-areas, and a total of four target delivery locations are set up for unloading or loading small unmanned vehicles; each sub-area may have one or more delivery locations. However, as to how to select the target delivery location within the sub-area, the above-mentioned unmanned vehicle collaborative delivery path planning method can be referred to for processing.

[0111]

[0112] See also Figure 6 During the execution of step S40, when the current unmanned vehicle performs the intra-domain path planning operation in the current sub-region with the target delivery location as the starting point of the cargo delivery task, if there are multiple unmanned vehicles in the current sub-region, the delivery task allocation operation is performed on the unmanned vehicles in the current sub-region, and then the intra-domain path planning operation is performed;

[0113] The distribution task allocation operation includes:

[0114] S401, searching for small unmanned vehicles in the current sub-area, and determining the current position of each small unmanned vehicle in the current sub-area;

[0115] S402, obtaining the current delivery location of the goods;

[0116] S403, based on the current delivery location of the goods and the current location of each unmanned vehicle in the current sub-area, calculate the distance between the goods and the vehicle target.

[0117] Among them, the distance between the cargo and the vehicle target In Indicates the current position of the small unmanned vehicle; d k represents the delivery location of the kth item;

[0118] S404: Calculate the target distance between the current position of each unmanned vehicle in the current sub-area and the current delivery position of the goods. Sorting is performed to obtain a distance sorting list; the distance sorting list is sorted in the direction from small to large values;

[0119] S405, obtaining the small unmanned vehicle with the smallest value in the distance sorting list as the target small unmanned vehicle:

[0120] S406, assigning the current cargo delivery task to the target small unmanned vehicle.

[0121] It should be noted that when multiple small unmanned vehicles jointly complete the cargo delivery task in a sub-area, the distribution of the delivery task is also involved. The task distribution is performed through steps S401-S406. During the specific execution, it is necessary to calculate the cargo and vehicle target distance between the delivery location of the cargo and the current location of each small unmanned vehicle in the current sub-area. in, represents the current position of the small unmanned vehicle; where d k Indicates the delivery location of the kth item; when calculating the distance between the two Then, a distance sorting list is established; finally, the small unmanned vehicle with the smallest value in the distance sorting list is taken as the target small unmanned vehicle, and the delivery task is assigned to the target small unmanned vehicle with the shortest distance (after determining the target small unmanned vehicle, path planning operations need to be implemented for multiple task deliveries, see subsequent technical content for details).

[0122] See also Figure 7 , when it is detected that the delivery task of the target unmanned vehicle is multiple tasks, the path planning operation within the domain is performed:

[0123] S501, determining the current location of the target small unmanned vehicle and the delivery locations of all delivery tasks that the target small unmanned vehicle needs to complete;

[0124] S502, generating an optimal driving path for the target small unmanned vehicle through path planning, wherein the optimal driving path starts from the current position of the target small unmanned vehicle and passes through the delivery locations of all delivery tasks that the target small unmanned vehicle needs to complete;

[0125] The above-mentioned optimal driving path of the target small unmanned vehicle is generated by path planning, and the following scheme is adopted: first, the current position of the target small unmanned vehicle is obtained to form a directed graph of path planning to each target delivery location in the delivery location set in the delivery area; wherein the target small unmanned vehicle is the small unmanned vehicle with the smallest value in the distance sorting list;

[0126] The directed graph of path planning includes a vertex set (i.e., the current location of the small unmanned vehicle + the set of all delivery locations) and an edge set;

[0127] The vertex set is denoted as V = {1, 2, ..., N}; E is the edge set; according to the calculated distance d between each vertex ij (known), and Define x ij :

[0128]

[0129] Linear programming is performed on the mathematical model of the directed graph of path planning, and the target Hamilton path of the directed graph is obtained by solving the first constraint, the second constraint, and the third constraint:

[0130]

[0131]

[0132] Where |K| is the number of vertices in set K and satisfies 2≤|K|≤|V|-1;

[0133] The first constraint is used to constrain each vertex to have only one incoming edge; the second constraint is used to constrain each vertex to have only one outgoing edge; the third constraint is used to constrain each vertex to not generate any sub-circuits; the Hamilton path is the optimal driving planning path that goes through all vertices without repetition and then returns to the starting point (the mathematical model of the directed graph for path planning will not be repeated here);

[0134] The control system of the large unmanned vehicle sends the optimal driving planning path to the target small unmanned vehicle;

[0135] The target small unmanned vehicle drives within the sub-area according to the optimal driving planning path to complete the cargo delivery task.

[0136] In summary, the unmanned vehicle collaborative delivery path planning method provided in the embodiment of the present application not only determines the target delivery location (i.e., the delivery location set), but can also further reasonably allocate delivery tasks for the optimal delivery location set and perform path planning operations.

[0137] On the second hand, based on the same technical concept, such as Figure 8 As shown, the embodiment of the present application also provides a device for planning a route for collaborative delivery of unmanned vehicles, the device comprising: a calling processing module 10, a target determination module 20, an unloading control processing module 30, and an intra-domain planning processing module 40, wherein;

[0138] The calling processing module 10 is used to load one or more small unmanned vehicles. When the current small unmanned vehicle is transferred and unloaded, the pre-stored correspondence between the sub-area and the small unmanned vehicle is called to obtain the sub-area corresponding to the current small unmanned vehicle; each of the sub-areas includes a number of delivery locations;

[0139] A target determination module 20, for determining a target delivery location in a sub-area corresponding to the current small unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information;

[0140] The unloading control processing module 30 is used to control the large unmanned vehicle to travel to the target delivery location and unload the current small unmanned vehicle at the target delivery location;

[0141] The intra-domain planning processing module 40 is used to control the current small unmanned vehicle to implement intra-domain path planning operations in the current sub-area with the target delivery location as the starting point of the cargo delivery task.

[0142] An embodiment of the present application provides an unmanned vehicle collaborative delivery path planning device, which applies the above-mentioned unmanned vehicle collaborative delivery path planning method, and can be applied to robots for finding target delivery locations, task allocation, and path planning processing.

[0143] At the distribution center, the carriage of the large unmanned vehicle can carry one or more small unmanned vehicles. The large unmanned vehicle loads the small unmanned vehicle and then calls its corresponding sub-area. According to the situation of the sub-area and related attribute information, the target delivery location within the corresponding sub-area is determined. After driving to the target delivery location, the control system controls the large unmanned vehicle to unload the small unmanned vehicle; the small unmanned vehicle gets off at the target location and starts driving independently in order to complete cargo delivery tasks (such as express delivery and receipt) and path planning operations in the current sub-area.

[0144] It is understandable that the above main control is completed by the control system of the large unmanned vehicle. Of course, the small unmanned vehicle also has a control system, and the control system records the relevant information of the cargo delivery task, so that the small unmanned vehicle can independently complete the corresponding cargo delivery task. After completing the cargo delivery task, the small unmanned vehicle can return to the target delivery location where it originally got off, and send a task completion signal to the large unmanned vehicle so that the large unmanned vehicle can pick it up. Finally, the large unmanned vehicle loads the small unmanned vehicle and returns to the distribution center.

[0145] At present, when delivering goods, the embodiment of the present application also provides a method for unmanned vehicle collaborative delivery path planning, which utilizes a large unmanned vehicle and a small unmanned vehicle to collaboratively complete the cargo delivery task, so as to minimize the delivery cost and maximize the delivery efficiency.

[0146] In the specific technical solution, the target determination module includes a function construction submodule, a demand calculation submodule and a target delivery determination submodule:

[0147] The function construction submodule is used to construct a target evaluation result output function of the distribution location according to the distribution point attribute information; and calculate the target evaluation result output value of all distribution locations in the current sub-area according to the target evaluation result output function of the distribution location;

[0148] The demand calculation submodule is used to calculate the demand value of the small unmanned vehicle in the current sub-area based on the service capability attribute information of the delivery vehicle;

[0149] The target delivery determination submodule is used to determine the delivery location according to the output value of the target evaluation result and the demand value of the small unmanned vehicle in the current sub-area to obtain the target delivery location.

[0150] In the specific technical solution, the function construction submodule is used to construct a target evaluation result output function (i.e., evaluation function for short) of the delivery location based on the delivery time span, the express delivery and receiving volume of the delivery location, and the distance between the delivery locations;

[0151] The formula of the target evaluation result output function of the distribution location is as follows:

[0152]

[0153] Among them, α 1 , α 2 are all pre-set coefficients. Represents the target evaluation result output value of the delivery location;

[0154] in, Indicates the delivery location within the delivery time span starting from the current time t The volume of express delivery and receipt; Indicates the delivery location Delivery location The distance between

[0155] Delivery Location represents the i-th delivery location in the q-th sub-region; delivery location represents the jth delivery location in the qth sub-region; delivery location For delivery location The associated delivery location of ; the sub-region is denoted by q, q∈{1,2,3}.

[0156] In the specific technical solution, the function construction submodule is used to calculate the demand value of the small unmanned vehicle in the current sub-area based on the service capability attribute information of the delivery vehicle, specifically including: calculating the demand value of the small unmanned vehicle in the current sub-area based on the express delivery and receiving volume of the delivery location and the cargo carrying capacity of the small unmanned vehicle; the formula for the demand value of the small unmanned vehicle is as follows:

[0157]

[0158] Among them, N q Indicates the demand value of small unmanned vehicles in the sub-area;

[0159] in, Indicates the delivery location within the delivery time span starting from the current time t The volume of express delivery and receipt;

[0160] Among them, w represents the cargo load of each small unmanned vehicle.

[0161] In a specific technical solution, the target delivery determination submodule includes a first calculation submodule and a second calculation submodule;

[0162] The first calculation submodule is used to obtain the target evaluation result output value of all delivery locations, and calculate the target evaluation result output value of all delivery locations. Sorting to obtain a delivery location evaluation ranking list; the delivery location evaluation ranking list is arranged in descending order of value;

[0163] The first calculation submodule is used to select the delivery locations with the target quantity threshold number that are ranked at the top from the delivery location evaluation ranking list as the target delivery locations; the value of the target quantity threshold number is equal to the small unmanned vehicle demand value of the current sub-area;

[0164] In the specific technical solution, the intra-domain planning processing module includes a distribution task allocation submodule;

[0165] The distribution task allocation submodule is used to search for small unmanned vehicles in the current sub-area, determine the current position of each small unmanned vehicle in the current sub-area, obtain the current delivery location of the goods, and calculate the distance between the goods and the vehicle according to the current delivery location of the goods and the current position of each small unmanned vehicle in the current sub-area. Calculate the target distance between the current location of each unmanned vehicle in the current sub-area and the current delivery location of the goods. Sort the distance sorting list; sort the distance sorting list from small to large; take the unmanned vehicle with the smallest value in the distance sorting list as the target unmanned vehicle: assign the current cargo delivery task to the target unmanned vehicle. In Indicates the current position of the small unmanned vehicle; d k represents the delivery location of the kth item;

[0166] In the specific technical solution, the intra-domain planning processing module also includes an intra-domain path planning processing submodule;

[0167] The intra-domain path planning processing submodule is used to determine the current position of the target small unmanned vehicle and the delivery location of all delivery tasks that the target small unmanned vehicle needs to complete; the optimal driving path of the target small unmanned vehicle is generated through path planning, and the optimal driving path starts from the current position of the target small unmanned vehicle and passes through the delivery location of all delivery tasks that the target small unmanned vehicle needs to complete.

[0168] According to another aspect of the embodiments of the present application, the present application provides an electronic device, such as Fig. 9As shown, it includes a memory 103, a processor 101, a communication interface 102 and a communication bus 104. The memory 103 stores a computer program that can be run on the processor 101. The memory 103 and the processor 101 communicate through the communication interface 102 and the communication bus 104. When the processor 101 executes the computer program, the steps of the above method are implemented.

[0169] The memory and processor in the above electronic device communicate through the communication bus and the communication interface. The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0170] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0171] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0172] The present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of a method for planning a path for collaborative delivery of unmanned vehicles are implemented.

[0173] According to another aspect of the embodiment of the present application, a computer-readable medium having a non-volatile program code executable by a processor is provided. In the embodiment of the present application, the computer-readable medium is configured to store a program code for the processor to execute the above method.

[0174] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in the present application, or a combination thereof.

[0175] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0176] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0177] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0178] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0179] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0180] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0181] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk. It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without more constraints, an element defined by the phrase "comprising a..." does not exclude the existence of other identical elements in the process, method, article or apparatus comprising the element.

[0182] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A method for unmanned vehicle collaborative delivery path planning, It is characterized in that The method comprises: The large unmanned vehicle loads one or more small unmanned vehicles. When the current small unmanned vehicle is transferred and unloaded, the pre-stored correspondence between the sub-area and the small unmanned vehicle is called to obtain the sub-area corresponding to the current small unmanned vehicle; each of the sub-areas includes several delivery locations; Determine the target delivery location in the sub-area corresponding to the current unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information; The large unmanned vehicle drives to the target delivery location and unloads the current small unmanned vehicle at the target delivery location; The current unmanned vehicle uses the target delivery location as the starting point of the cargo delivery task and implements the intra-domain path planning operation in the current sub-area; The method of determining the target delivery location in the sub-area corresponding to the current small unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information includes: Construct a target evaluation result output function for the distribution location based on the distribution point attribute information; calculate the target evaluation result output value of all distribution locations in the current sub-area based on the target evaluation result output function for the distribution location; Calculate the demand value of small unmanned vehicles in the current sub-area based on the service capability attribute information of the delivery vehicle; Determine the delivery location according to the output value of the target evaluation result and the demand value of the small unmanned vehicle in the current sub-area to obtain the target delivery location; The target evaluation result output function of the distribution location is constructed according to the distribution point attribute information, including: The target evaluation result output function of the delivery location is constructed based on the delivery time span, the express delivery and receiving volume of the delivery location, and the distance between the delivery locations; The formula of the target evaluation result output function of the distribution location is as follows: Among them, α 1 , α 2 are all pre-set coefficients. Represents the target evaluation result output value of the delivery location; Indicates the delivery location within the delivery time span starting from the current time t The volume of express delivery and receipt; Indicates the delivery location Delivery location The distance between Delivery Location represents the i-th delivery location in the q-th sub-region; Delivery Location represents the jth delivery location in the qth sub-region; The sub-region is denoted as q, q∈{1,2,3,…}; The delivery vehicle service capability attribute information includes the express delivery and receiving volume at the delivery location and the cargo carrying capacity of the small unmanned vehicle; The demand value of the small unmanned vehicle in the current sub-area is calculated based on the service capability attribute information of the delivery vehicle, including: Calculate the demand value of unmanned vehicles in the current sub-area based on the express delivery and receiving volume of the delivery location and the cargo carrying capacity of unmanned vehicles; The formula for the demand value of the small unmanned vehicle is as follows: Among them, N q Indicates the demand value of small unmanned vehicles in the sub-area; Indicates the delivery location within the delivery time span starting from the current time t The express delivery volume; w represents the cargo carrying capacity of each small unmanned vehicle; The delivery location is determined according to the output value of the target evaluation result and the demand value of the small unmanned vehicle in the current sub-area to obtain the target delivery location, which specifically includes the following steps: Get the target evaluation result output value of all distribution locations in the current sub-region, and output the target evaluation result value of all distribution locations Sorting to obtain a delivery location evaluation ranking list; the delivery location evaluation ranking list is arranged in descending order of value; Selecting a delivery location with a target quantity threshold number that is ranked at the top from the delivery location evaluation ranking list as the target delivery location; the value of the target quantity threshold number is equal to the small unmanned vehicle demand value of the current sub-area; When the current unmanned vehicle uses the target delivery location as the starting point of the cargo delivery task to implement the intra-domain path planning operation in the current sub-region, if there are multiple unmanned vehicles in the current sub-region, the delivery task allocation operation is performed on the unmanned vehicles in the current sub-region, and then the intra-domain path planning operation is performed; The distribution task allocation operation includes: Search for small unmanned vehicles in the current sub-area and determine the current position of each small unmanned vehicle in the current sub-area; Get the current delivery location of the goods; According to the current delivery location of the goods and the current location of each unmanned vehicle in the current sub-area, the distance between the goods and the vehicle is calculated. Among them, the distance between the cargo and the vehicle target In Indicates the current position of the small unmanned vehicle; d k represents the delivery location of the kth item; The target distance between the current position of each unmanned vehicle in the current sub-area and the current delivery position of the goods is calculated. Sorting is performed to obtain a distance sorting list; the distance sorting list is sorted in a direction from small to large values; Get the small unmanned vehicle with the smallest value in the distance sorting list as the target small unmanned vehicle: Assign the current cargo delivery task to the target unmanned vehicle; When it is detected that the delivery task of the target unmanned vehicle is multiple tasks, the path planning operation in the domain is performed: Determine the current location of the target small unmanned vehicle and the delivery locations of all delivery tasks that the target small unmanned vehicle needs to complete; Generate an optimal driving path for the target small unmanned vehicle through path planning, where the optimal driving path starts from the current position of the target small unmanned vehicle and passes through the delivery locations of all delivery tasks that the target small unmanned vehicle needs to complete; Send the optimal driving path to the target small unmanned vehicle.

2. The method according to claim 1, It is characterized in that The distribution point attribute information includes the distribution time span, the express delivery and receiving volume of the distribution location within the distribution time span, and the distance between the distribution locations.

3. A unmanned vehicle collaborative delivery path planning device, It is characterized in that It uses the unmanned vehicle collaborative delivery path planning method as claimed in claim 1 to implement processing, and the device includes: a call processing module, a target determination module, an unloading control processing module, and an intra-domain planning processing module, wherein; A calling processing module is used to load one or more small unmanned vehicles. When the current small unmanned vehicle is transferred and unloaded, the pre-stored correspondence between the sub-area and the small unmanned vehicle is called to obtain the sub-area corresponding to the current small unmanned vehicle; each of the sub-areas includes a number of delivery locations; A target determination module is used to determine the target delivery location in the sub-area corresponding to the current small unmanned vehicle based on the delivery point attribute information and the delivery vehicle service capability attribute information; An unloading control processing module is used to control the large unmanned vehicle to drive to a target delivery location and unload the current small unmanned vehicle at the target delivery location; The intra-domain planning processing module is used to control the current unmanned vehicle to implement intra-domain path planning operations in the current sub-area with the target delivery location as the starting point of the cargo delivery task.

4. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 2 are implemented.

Images