Unmanned vehicle intra-field scheduling method and device, electronic equipment and storage medium

Abstract

The invention discloses an in-field scheduling method and device of an unmanned vehicle, electronic equipment and a storage medium. The scheduling method comprises the steps of obtaining a current vehicle state of the unmanned vehicle in a target area; judging whether an unmanned vehicle of which the vehicle state is the return buffer area and the departure buffer area exists at the same time or not; if yes, based on a weight model, calculating a first weight of the target unmanned vehicle in the return buffer area and a second weight of the target unmanned vehicle in the go buffer area; and switching the vehicle state of the target unmanned vehicle in the return buffer area or the departure buffer area to the coordination area based on the values of the first weight and the second weight. According to the method, three scheduling algorithms of the unmanned vehicle can be realized based on the logic region division of the business scene and the organic state machine, the method can be suitable for different scenes, the scheduling problem when a single channel exists in a site can be effectively solved, and the working efficiency of the unmanned vehicle is greatly improved.

Description

Technical Field

[0001] The present application belongs to the technical field of unmanned vehicles, and specifically relates to an on-site dispatching method and device, electronic equipment and storage medium for unmanned vehicles. Background Art

[0002] Most of today's logistics transfer sites are operated on-site, that is, automated express sorting is carried out in a limited indoor space. In order to achieve the highest transportation efficiency in a limited space, it is necessary to efficiently dispatch unmanned vehicles in the site. Due to different sites, the problems faced by the unmanned vehicle dispatch process are also different. The existing unmanned vehicle dispatch method can only dispatch unmanned vehicles based on specific sites and cannot meet the needs of different sites.

[0003] Therefore, for the application of unmanned vehicles in logistics scenarios, it is urgent to abstract a set of general models to ensure that unmanned vehicles can achieve the highest transportation efficiency in a limited space. Summary of the invention

[0004] The purpose of the present invention is to provide an on-site dispatching method and device, electronic device and storage medium for unmanned vehicles, so as to solve the technical problem that the unmanned vehicle dispatching method existing in the prior art can only dispatch unmanned vehicles based on a specific site and cannot meet the needs of different sites.

[0005] In order to achieve the above purpose, a technical solution adopted in this application is:

[0006] A method for dispatching an unmanned vehicle on site is provided, comprising:

[0007] Acquire the current vehicle state of the unmanned vehicle in the target area, the vehicle state including a return buffer area, a coordination area, and an outbound buffer area, and the vehicle state of the unmanned vehicle can be controlled to switch from the return buffer area to the coordination area, and from the outbound buffer area to the coordination area;

[0008] Determine whether there are unmanned vehicles whose vehicle status is the return buffer zone and the outbound buffer zone at the same time;

[0009] If so, based on the weight model, calculate the first weight of the target unmanned vehicle in the return buffer and the second weight of the target unmanned vehicle in the outbound buffer, wherein the weight factors in the weight model include at least one of a parking space vacancy weight, a site distance weight, a busy / idle time weight, a user role weight, and an area weight, the parking space vacancy weight is used to describe the loading demand intensity of the unmanned vehicle in the target area, the site distance weight is used to describe the distance between the unmanned vehicle and the target delivery site, and the busy / idle time weight is used to describe the delivery demand intensity of the unmanned vehicle in the target area;

[0010] Based on the values ​​of the first weight and the second weight, the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer is switched to the coordination zone.

[0011] In one embodiment, the vehicle state further includes a loading parking area; and the method for calculating the parking space vacancy weight includes:

[0012] Obtain the number of unmanned vehicles in the loading parking area with a vehicle status of the unmanned vehicle, and obtain the current number of free parking spaces;

[0013] Based on the current number of free parking spaces, the parking space free weight is determined.

[0014] In one embodiment, the step of calculating the first weight of the target unmanned vehicle in the return buffer zone includes:

[0015] Obtain a first reference weight of the target unmanned vehicle in the return buffer and an average number of loads of the unmanned vehicle in a specified period to calculate the first weight, wherein the first reference weight includes at least one of a parking space vacancy weight and an area weight.

[0016] In one embodiment, the step of calculating the second weight of the target unmanned vehicle in the outbound buffer zone includes:

[0017] Obtain a second reference weight and an actual number of loads of the target unmanned vehicle in the outbound buffer to calculate the second weight, wherein the second reference weight includes at least one of a site distance weight, a busy / off-peak weight, a user role weight, and an area weight.

[0018] In one embodiment, the target unmanned vehicle in the return buffer is the first unmanned vehicle in the return buffer, and the target unmanned vehicle in the outbound buffer is the first unmanned vehicle in the outbound buffer;

[0019] The step of switching the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer to the coordination zone based on the values ​​of the first weight and the second weight is specifically:

[0020] The vehicle state of the target unmanned vehicle with a larger weight is switched to the coordination area.

[0021] In one embodiment, the target unmanned vehicle in the return buffer is the unmanned vehicle queue in the return buffer, and the target unmanned vehicle in the outbound buffer is the unmanned vehicle queue in the outbound buffer;

[0022] The step of switching the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer to the coordination zone based on the values ​​of the first weight and the second weight includes:

[0023] Comparing the sum of the first weights of the unmanned vehicle queue in the return buffer and the sum of the second weights of the unmanned vehicle queue in the outbound buffer;

[0024] The vehicle states of the unmanned vehicle queue with larger weight are switched to the coordination area in sequence.

[0025] In one embodiment, the step of calculating the first weight of the target unmanned vehicle in the return buffer and the second weight of the target unmanned vehicle in the outbound buffer based on the weight model also includes:

[0026] Get the current time and determine whether it is the peak period;

[0027] If not, the vehicle states of the unmanned vehicle in the return buffer zone and the unmanned vehicle in the outbound buffer zone are switched to the coordination zone in sequence.

[0028] In one embodiment, the vehicle status also includes an off-site waiting area;

[0029] When there is only an unmanned vehicle whose vehicle status is the outbound buffer zone, the method further includes:

[0030] Determine whether there is an unmanned vehicle in the off-site waiting area;

[0031] If so, based on the weight model, calculate the second weight of the target unmanned vehicle in the outbound buffer zone and the third weight of the target unmanned vehicle in the off-site waiting zone;

[0032] Based on the values ​​of the second weight and the third weight, the vehicle state of the target unmanned vehicle in the outbound buffer area or the off-site waiting area is switched to the coordination area.

[0033] In one embodiment, the step of calculating the third weight of the target unmanned vehicle in the off-site waiting area includes:

[0034] Obtain a third reference weight of the target unmanned vehicle in the off-site waiting area and an average number of loads of the unmanned vehicle in a specified period to calculate the third weight, wherein the third reference weight includes at least one of a parking space vacancy weight and an area weight.

[0035] In order to achieve the above purpose, another technical solution adopted by this application is:

[0036] Provided is an on-site dispatching device for an unmanned vehicle, comprising:

[0037] A state acquisition module, used to acquire the current vehicle state of the unmanned vehicle in the target area, wherein the vehicle state includes a return buffer zone, a coordination zone, and an outbound buffer zone, and the vehicle state of the unmanned vehicle can be controlled to switch from the return buffer zone to the coordination zone, and from the outbound buffer zone to the coordination zone;

[0038] A judgment module, used for judging whether there are unmanned vehicles whose vehicle status is the return buffer zone and the outbound buffer zone at the same time;

[0039] A weight calculation module, for calculating, based on a weight model, a first weight of a target unmanned vehicle in the return buffer and a second weight of a target unmanned vehicle in the outbound buffer when there are unmanned vehicles whose vehicle states are both in the return buffer and the outbound buffer, wherein the weight factors in the weight model include at least one of a parking space vacancy weight, a site distance weight, a busy / idle time weight, a user role weight, and an area weight, wherein the parking space vacancy weight is used to describe the loading demand intensity of the unmanned vehicle in the target area, the site distance weight is used to describe the distance between the unmanned vehicle and the target delivery site, and the busy / idle time weight is used to describe the delivery demand intensity of the unmanned vehicle in the target area;

[0040] A scheduling module is used to switch the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer to the coordination area based on the values ​​of the first weight and the second weight.

[0041] In order to achieve the above purpose, another technical solution adopted by this application is:

[0042] An electronic device is provided, comprising:

[0043] at least one processor; and

[0044] A memory storing instructions, which, when executed by the at least one processor, enables the at least one processor to execute the on-site dispatching method for unmanned vehicles as described in any of the above embodiments.

[0045] In order to achieve the above purpose, another technical solution adopted by this application is:

[0046] A machine-readable storage medium is provided, which stores executable instructions. When the instructions are executed, the machine executes the on-site dispatching method of the unmanned vehicle as described in any of the above embodiments.

[0047] Different from the prior art, the beneficial effects of this application are:

[0048] The on-site dispatching method for unmanned vehicles of the present application is based on the logical area division of business scenarios and the organic state machine, and can implement three dispatching algorithms for unmanned vehicles. It can be applied to different scenarios and can effectively solve the dispatching problem when there is a single channel in the venue, greatly improving the working efficiency of unmanned vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] 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 prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 It is a flowchart of an implementation method of an on-site dispatching method for unmanned vehicles of the present application;

[0051] Figure 2 is a schematic diagram of an implementation method of a logical area of ​​a target area of ​​the present application;

[0052] Figure 3 It is a flow chart of another implementation method of the on-site dispatching method of the unmanned vehicle of the present application;

[0053] Figure 4 It is a flow chart of another implementation method of the on-site dispatching method of the unmanned vehicle of the present application;

[0054] Figure 5 It is a structural schematic diagram of an implementation method of an on-site dispatching device for an unmanned vehicle of the present application;

[0055] Figure 6 It is a schematic structural diagram of an embodiment of an electronic device of the present application. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0057] At present, in order to improve operating efficiency, logistics transfer stations mostly use automated express sorting and unmanned vehicles for loading and delivery. In order to achieve the highest transportation efficiency in a limited space, it is necessary to efficiently dispatch unmanned vehicles in the field. However, due to the different sites of different transfer stations, the problems faced in the dispatch process of unmanned vehicles are also different. As a result, there is no unmanned vehicle dispatch method that can be used in different sites in the industry, which cannot meet the needs of different sites.

[0058] In order to solve the above problems, the applicant has developed a new on-site dispatching method for unmanned vehicles. This dispatching method divides the on-site site into logical areas, realizes seamless switching of unmanned vehicles between various areas based on a finite state machine, and combines a weight algorithm to realize the most favorable unmanned vehicle dispatching method in the current state, which helps to achieve the optimal solution for unmanned vehicle transportation, that is, when an unmanned vehicle transfers goods and leaves, another idle vehicle can immediately fill its place.

[0059] Specifically, an exemplary system architecture for implementing the on-site dispatching method of the unmanned vehicle of the present application may include an unmanned vehicle, a network, and a server. The network is used to provide a communication link between the unmanned vehicle and the server, and may include various connection types, such as a wired communication link, a wireless communication link, or an optical fiber cable, etc.

[0060] The server can obtain parameters such as the location and number of loads from the unmanned vehicle based on the network, and send scheduling instructions to the unmanned vehicle based on the on-site scheduling method to achieve efficient scheduling of the unmanned vehicles on the site.

[0061] The server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it may be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module. No specific limitation is made here.

[0062] The following is a detailed description of the on-site dispatching method for the unmanned vehicle in this application. Figure 1 , Figure 1 It is a flow chart of an implementation method of the on-site dispatching method of the unmanned vehicle of the present application.

[0063] like Figure 1 As shown, the on-site scheduling method includes:

[0064] S100: Obtain the current vehicle status of the unmanned vehicle in the target area.

[0065] Among them, the target area can be a logistics transfer site or other preset unmanned vehicle operation scene areas.

[0066] The vehicle state of the unmanned vehicle can be obtained based on the location of the unmanned vehicle. Specifically, the target area can be divided into multiple logical areas, and the vehicle state of the unmanned vehicle in a logical area is defined as the logical area based on a finite state machine.

[0067] In one embodiment, the vehicle state of the unmanned vehicle may include a return buffer zone, a coordination zone, and an outbound buffer zone, and the vehicle state of the unmanned vehicle may be controllably switched from the return buffer zone to the coordination zone, and from the outbound buffer zone to the coordination zone.

[0068] Among them, the return buffer can be a buffer for entering the loading area within the yard, the outbound buffer can be a buffer for leaving the loading area within the yard for delivery after loading, and the coordination area can be a single channel that only allows vehicles in one direction to enter at the same time.

[0069] Of course, the vehicle state of the unmanned vehicle may not be limited to the above state. For example, please refer to Figure 2 , Figure 2 It is a schematic diagram of an implementation method of a logical area of ​​a target area of ​​the present application.

[0070] like Figure 2 As shown, the vehicle status can also include an off-site waiting area, a loading parking area, and a virtual parking area. Among them, the off-site waiting area can include a decision-making area and a sentinel area located outside the site, which can be divided into sections using a high-precision map and used to place unmanned vehicles in a non-operating state; the loading parking area can be used to place unmanned vehicles in a loading state; the virtual parking area can be a buffer queue entering the loading parking area, which can enter the loading parking area as quickly as possible for loading.

[0071] It should be understood that in other implementations, the target area may also be divided into other logical areas, which will not be described in detail herein.

[0072] S200: Determine whether there are unmanned vehicles whose vehicle status is both in the return buffer zone and the outbound buffer zone.

[0073] It should be understood that in one embodiment, when the coordination zone is a single channel, the unmanned vehicles in the return buffer and the outbound buffer cannot enter the coordination zone at the same time, so it is necessary to determine whether there are unmanned vehicles whose vehicle status is the return buffer and the outbound buffer at the same time.

[0074] S300: If yes, based on the weight model, calculate the first weight of the target unmanned vehicle in the return buffer and the second weight of the target unmanned vehicle in the outbound buffer.

[0075] If there are unmanned vehicles whose vehicle status is both in the return buffer and the outbound buffer, the first weight of the target unmanned vehicle in the return buffer and the second weight of the target unmanned vehicle in the outbound buffer can be calculated based on the weight model, so that the unmanned vehicle scheduling can be further realized based on the weight, and the unmanned vehicles in the return buffer or the outbound buffer can be controlled to enter the coordination area.

[0076] Specifically, in one embodiment, the weight factor in the weight model may be at least one of a parking space vacancy weight, a station distance weight, a busy / idle time weight, a user role weight, and an area weight.

[0077] Among them, the parking space vacancy weight can be used to describe the loading demand intensity of unmanned vehicles in the target area. It is understandable that when the current loading demand intensity of unmanned vehicles is high, in order to improve operating efficiency, the unmanned vehicles in the return buffer zone should be given priority to enter the coordination zone, thereby increasing the number of unmanned vehicles in the loading parking area and improving loading efficiency.

[0078] In one embodiment, the method for calculating the parking space vacancy weight may be:

[0079] Get the number of unmanned vehicles in the loading parking area and the current number of free parking spaces;

[0080] Based on the current number of free parking spaces, the parking space free weight is determined.

[0081] The number of unmanned vehicles in the loading parking area represents the current loading demand intensity. When the number of unmanned vehicles in the loading parking area is small, there are many vacant parking spaces in the loading parking area, and unmanned vehicles need to be quickly added to the loading parking area. Therefore, the vacant parking space weight is higher.

[0082] For example, when the current number of free parking spaces is 1 to 2, the weight parameter may be 1.43, and the parking space free weight may be 1.43*the current number of free parking spaces; when the current number of free parking spaces is 3 to 4, the weight parameter may be 1.76, and the parking space free weight may be 1.76*the current number of free parking spaces; when the current number of free parking spaces is 5 to 6, the weight parameter may be 1.95, and the parking space free weight may be 1.95*the current number of free parking spaces.

[0083] The site distance weight is used to describe the distance between the unmanned vehicle and the target delivery site. In an application scenario, due to the limited number of unmanned vehicles, in order to ensure maximum transportation efficiency, priority should be given to delivering to target sites that are closer. The weight of an unmanned vehicle that is closer to the target site can be higher than that of an unmanned vehicle that is farther away from the target site.

[0084] Exemplarily, when the target site distance is less than 3 kilometers, the site distance weight may be 1.46; when the target site distance is greater than 3 kilometers, the site distance weight may be 1.15.

[0085] The busy and off-peak weights are used to describe the intensity of the delivery demand for unmanned vehicles in the target area. In an application scenario, during peak hours, more cargo is usually delivered and more unmanned vehicles are required. Therefore, the outbound weight is higher than the return weight. During off-peak hours, the outbound weight can be equal to the return weight, or slightly higher than the return weight.

[0086] For example, the busy / off-peak weight of the outbound unmanned vehicle during peak hours can be 1.37, the busy / off-peak weight of the outbound unmanned vehicle during off-peak hours can be 1.03, and the busy / off-peak weight of the return unmanned vehicle during high and off-peak hours can be 1.

[0087] User role weights are used to divide different delivery users. For example, in one embodiment, higher user role weights can be assigned to important users, enterprise-level users, or users who have strict requirements on delivery time. Of course, in other embodiments, weights can also be assigned to different user roles based on specific scenarios.

[0088] For example, in the outbound unmanned vehicle, the user role weight of the enterprise-level user can be 1.47, and the user role weight of the ordinary user can be 1.03; the user role weight of the return unmanned vehicle can be 1.

[0089] The regional weight is used to assign different weights to autonomous vehicles in different vehicle states, for example Figure 2 In the logical area shown, the area weight of the unmanned vehicles in the decision area and the sentinel area can be smaller than that of the unmanned vehicles in the return buffer area, so that the unmanned vehicles in the return buffer area have priority to enter the coordination area.

[0090] Exemplarily, the regional weights of the outbound buffer zone and the return buffer zone may be 1.2, the regional weight of the sentinel zone may be 0.24, and the regional weight of the decision zone may be 0.23.

[0091] In one embodiment, the step of calculating the first weight of the target unmanned vehicle in the return buffer may include:

[0092] The first reference weight of the target unmanned vehicle in the return buffer and the average number of loads of the unmanned vehicle in a specified period are obtained to calculate the first weight.

[0093] Among them, the specified period can be a preset period such as 1 day, 1 week, 1 month, etc. By recording the number of loads of each unmanned vehicle in the specified period, the average number of loads can be obtained; the first reference weight can include at least one of the parking space vacancy weight and the area weight.

[0094] In one embodiment, the step of calculating the second weight of the target unmanned vehicle in the outbound buffer zone may include:

[0095] The second reference weight and the actual number of loads of the target unmanned vehicle in the outbound buffer zone are obtained to calculate the second weight.

[0096] The second reference weight may include at least one of a site distance weight, a busy / idle time weight, a user role weight, and a region weight.

[0097] In one embodiment, the first weight may be the product of the first reference weight and the mean number of carriers, and correspondingly, the second weight may be the product of the second reference weight and the actual number of carriers; in other embodiments, the first weight and the second weight may also be calculated using other methods, as long as the calculation method of the first weight and the second weight is the same.

[0098] In one embodiment, the first reference weight may be the sum of the parking space vacancy weight and the area weight, and the second reference weight may be the sum of the site distance weight, the busy / idle time weight, the user role weight and the area weight.

[0099] The calculation method of the first weight can be: (current number of free parking spaces * weight parameter + regional weight) * average number of loads; the calculation method of the second weight can be: (site distance weight + busy and idle time weight + user role weight + regional weight) * actual number of loads.

[0100] In another embodiment, a basic site distance weight, a basic busy / idle time weight, and a basic user role weight may also be set for the target unmanned vehicle in the return buffer zone, and the first reference weight may be the sum of the parking space vacancy weight, the regional weight, the basic site distance weight, the basic busy / idle time weight, and the basic user role weight; correspondingly, a basic parking space vacancy weight may be set for the target unmanned vehicle in the outbound buffer zone, and the second reference weight may be the sum of the basic parking space vacancy weight, the site distance weight, the busy / idle time weight, the user role weight, and the regional weight.

[0101] The calculation method of the first weight can be: (current number of free parking spaces * weight parameter + regional weight + basic site distance weight + basic busy and idle time weight + basic user role weight) * average number of loads; the calculation method of the second weight can be: (site distance weight + busy and idle time weight + user role weight + regional weight + basic parking space free weight) * actual number of loads.

[0102] S400: Based on the values ​​of the first weight and the second weight, the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer is switched to the coordination zone.

[0103] It can be understood that by comparing the weight of the unmanned vehicle in the return buffer zone with the weight of the unmanned vehicle in the outbound buffer zone, corresponding scheduling can be performed to control the target unmanned vehicle in the return buffer zone or the outbound buffer zone to enter the coordination zone.

[0104] In one embodiment, the target unmanned vehicle in the return buffer zone may be the first unmanned vehicle in the return buffer zone, and the target unmanned vehicle in the outbound buffer zone may be the first unmanned vehicle in the outbound buffer zone.

[0105] At this time, the first weight and the second weight can be directly compared, and the vehicle state of the target unmanned vehicle with a larger weight can be switched to the coordination area. The scheduling method can be to send a coordination area event to the target unmanned vehicle with a larger weight to control its vehicle state to switch to the coordination area.

[0106] Based on the scheduling method of this embodiment, the weights of the unmanned vehicles at the head of the return buffer queue and the head of the outbound buffer queue can be compared at each moment, and the first unmanned vehicle with a larger weight can be controlled to enter the coordination area to achieve the most efficient loading and delivery operations.

[0107] Since the scheduling method of the above implementation needs to interact with the vehicles at the head of the two queues at every moment, there is a problem of too many interactions when there are many vehicles, which may cause increased message delays or even packet loss due to network conditions.

[0108] In order to reduce the number of interactions with vehicles, in another embodiment, the target unmanned vehicle in the return buffer can be the unmanned vehicle queue in the return buffer, and correspondingly, the target unmanned vehicle in the outbound buffer can be the unmanned vehicle queue in the outbound buffer.

[0109] Based on the values ​​of the first weight and the second weight, the step of switching the vehicle state of the target unmanned vehicle in the return buffer zone or the outbound buffer zone to the coordination zone may include:

[0110] Compare the sum of the first weights of the unmanned vehicle queue in the return buffer and the sum of the second weights of the unmanned vehicle queue in the outbound buffer;

[0111] The vehicle states of the unmanned vehicle fleet with larger weights are switched to the coordination area in sequence.

[0112] Specifically, the method of controlling the vehicle state of the unmanned vehicle queue to switch to the coordination area can be to set traffic lights at both ends of the coordination area, and set the traffic lights corresponding to the unmanned vehicle queue with a larger weight to green lights, so as to control the unmanned vehicle queue to enter the coordination area in sequence. Correspondingly, the traffic lights of the unmanned vehicle queue with a smaller weight are set to red lights to put them in a waiting state.

[0113] Among them, the duration of the green light can be adjusted based on the weight of the unmanned vehicle queue. For example, based on the ratio of the weights of the two unmanned vehicle queues, the ratio of the green light duration of the traffic lights at both ends can be controlled to control the unmanned vehicle queues on both sides to enter the coordination area in sequence.

[0114] Based on the scheduling method of the above implementation, after comparing the weights of all unmanned vehicles in the return buffer queue and the outbound buffer queue, the queue with a larger weight can be controlled to enter the coordination area, thereby reducing the frequency of message communication with the unmanned vehicle, and at the same time ensuring that multiple vehicles enter the coordination area at the same time.

[0115] Of course, the scheduling method in the above embodiment is not limited to scheduling the unmanned vehicles in the return buffer and the outbound buffer to enter the coordination area. Figure 2 In the scenario where there is no unmanned vehicle in the return buffer area, unmanned vehicles in the off-site waiting area and the outbound buffer area can also be dispatched.

[0116] Specifically, see Figure 3 , Figure 3 It is a flow chart of another implementation method of the on-site dispatching method of the unmanned vehicle of the present application.

[0117] like Figure 3 As shown, when there is only an unmanned vehicle in the outbound buffer zone, the on-site dispatching method further includes:

[0118] S300a, determine whether there is an unmanned vehicle in the off-site waiting area.

[0119] S400a: If yes, based on the weight model, calculate the second weight of the target unmanned vehicle in the outbound buffer zone and the third weight of the target unmanned vehicle in the off-site waiting zone.

[0120] S500a. Based on the values ​​of the second weight and the third weight, the vehicle state of the target unmanned vehicle in the outbound buffer area or the off-site waiting area is switched to the coordination area.

[0121] It can be understood that by calculating the weights of the target unmanned vehicles in the outbound buffer area and the off-site waiting area, the target unmanned vehicles in the outbound buffer area or the off-site waiting area can be scheduled to switch to the coordination area.

[0122] The calculation method of the second weight value may be the same as that in S300 , and the calculation method of the third weight value may be the same as that of the first weight value in S300 .

[0123] Specifically, the method for calculating the third weight may be:

[0124] The third reference weight of the target unmanned vehicle in the off-site waiting area and the average number of loads of the unmanned vehicle in a specified period are obtained to calculate the third weight.

[0125] In one embodiment, the third weight may be the product of the first reference weight and the average number of carriers, and correspondingly, the second weight may be the product of the second reference weight and the actual number of carriers.

[0126] In one embodiment, the third reference weight may be the sum of the parking space vacancy weight and the area weight, and the second reference weight may be the sum of the site distance weight, the busy / idle time weight, the user role weight and the area weight.

[0127] In another embodiment, a basic site distance weight, a basic busy / idle time weight, and a basic user role weight may also be set for the target unmanned vehicle in the off-site waiting area, and the third reference weight may be the sum of the parking space availability weight, the area weight, the basic site distance weight, the basic busy / idle time weight, and the basic user role weight; accordingly, a basic parking space availability weight may be set for the target unmanned vehicle in the outbound buffer area, and the second reference weight may be the sum of the basic parking space availability weight, the site distance weight, the busy / idle time weight, the user role weight, and the area weight.

[0128] It can be understood that, similar to S500, the target unmanned vehicle in the off-site waiting area can be the unmanned vehicle at the head of the queue or all the unmanned vehicles in the queue; the target unmanned vehicle in the outbound buffer area can be the unmanned vehicle at the head of the queue or all the unmanned vehicles in the queue.

[0129] Correspondingly, the second weight and the third weight of the first vehicle in the queue can be directly compared, and based on the comparison result, the unmanned vehicle in the first vehicle in the queue with a larger weight can be controlled to switch to the coordination area; or the sum of the second weights and the sum of the third weights of the unmanned vehicles in the queue can be compared, and based on the comparison result, the unmanned vehicles in the queue with a larger weight can be controlled to switch to the coordination area in batches.

[0130] The above-mentioned implementation methods schedule the status of unmanned vehicles based on the weight of unmanned vehicles, which can be applied to the scheduling of unmanned vehicles during peak and off-peak periods in different venues. However, in some scenarios, such as off-peak periods, in order to reduce the amount of data calculation and the number of interactions with vehicles, the scheduling method of unmanned vehicles can also adopt a fair polling algorithm.

[0131] Specifically, see Figure 4 , Figure 4 It is a flow chart of another implementation method of the on-site dispatching method of the unmanned vehicle of the present application.

[0132] like Figure 4 As shown, the synchronization with S300 also includes:

[0133] S300b. Obtain the current time and determine whether the current time is a peak period.

[0134] S400b: If not, the vehicle states of the unmanned vehicles in the return buffer and the unmanned vehicles in the outbound buffer are switched to the coordination zone in sequence.

[0135] Specifically, when the current time is an off-peak period, the unmanned vehicles in the return buffer and the outbound buffer can be controlled to alternately enter the coordination area. At this time, a completely fair algorithm is used to ensure that each level of buffer is stable and there will not be excessive backlog.

[0136] It should be understood that this embodiment is not limited to use during off-peak hours, nor is it limited to dispatching unmanned vehicles in the return buffer and the outbound buffer. Unmanned vehicles in other areas can also be dispatched into the coordination area, such as dispatching unmanned vehicles in the decision area and the virtual parking area into the coordination area.

[0137] Based on the unmanned vehicle scheduling method of the above-mentioned implementation modes, three scheduling algorithms for unmanned vehicles can be implemented based on the logical division of business scenarios and finite state machine technology. It can be applied to different scenarios and can effectively solve the scheduling problem when there is a single channel in the site, greatly improving the work efficiency of unmanned vehicles.

[0138] This application also provides an on-site dispatching device for unmanned vehicles, see Figure 5 , Figure 5 It is a structural schematic diagram of an implementation method of an on-site dispatching device for an unmanned vehicle of the present application.

[0139] like Figure 5 As shown, the on-site scheduling device includes a state acquisition module 21, a judgment module 22, a weight calculation module 23 and a scheduling module 24.

[0140] The state acquisition module 21 is used to acquire the current vehicle state of the unmanned vehicle in the target area. The vehicle state includes a return buffer zone, a coordination zone, and an outbound buffer zone. The vehicle state of the unmanned vehicle can be controlled to switch from the return buffer zone to the coordination zone, and from the outbound buffer zone to the coordination zone.

[0141] The judgment module 22 is used to judge whether there are unmanned vehicles whose vehicle status is both the return buffer and the outbound buffer;

[0142] The weight calculation module 23 is used to calculate the first weight of the target unmanned vehicle in the return buffer and the second weight of the target unmanned vehicle in the outbound buffer based on the weight model when there are unmanned vehicles whose vehicle states are the return buffer and the outbound buffer at the same time, wherein the weight factors in the weight model include at least one of the parking space vacancy weight, the site distance weight, the busy and idle time weight, the user role weight and the area weight, the parking space vacancy weight is used to describe the loading demand intensity of the unmanned vehicle in the target area, the site distance weight is used to describe the distance between the unmanned vehicle and the target delivery site, and the busy and idle time weight is used to describe the delivery demand intensity of the unmanned vehicle in the target area;

[0143] The scheduling module 24 is used to switch the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer to the coordination zone based on the values ​​of the first weight and the second weight.

[0144] In one embodiment, the vehicle state also includes a loading parking area, and the weight calculation module 23 is further used to obtain the number of unmanned vehicles whose vehicle state is a loading parking area, and obtain the current number of free parking spaces; based on the current number of free parking spaces, determine the parking space free weight;

[0145] In one embodiment, the weight calculation module 23 is also used to obtain the first reference weight of the target unmanned vehicle in the return buffer and the average number of loads of the unmanned vehicle in a specified period to calculate the first weight, wherein the first reference weight includes at least one of a parking space vacancy weight and an area weight.

[0146] In one embodiment, the weight calculation module 23 is also used to obtain the second reference weight and the actual number of loads of the target unmanned vehicle in the outbound buffer to calculate the second weight, wherein the second reference weight includes at least one of the site distance weight, the busy and idle time weight, the user role weight and the area weight.

[0147] In one embodiment, the target unmanned vehicle in the return buffer is the first unmanned vehicle in the return buffer, and the target unmanned vehicle in the outbound buffer is the first unmanned vehicle in the outbound buffer. The scheduling module 24 is also used to compare the sum of the first weights of the unmanned vehicle queue in the return buffer with the sum of the second weights of the unmanned vehicle queue in the outbound buffer; and the vehicle states of the unmanned vehicle queues with larger weights are switched to the coordination area in sequence.

[0148] In one embodiment, it also includes a polling scheduling module 25, which is used to obtain the current time and determine whether the current time is a peak period; and when the current time is not a peak period, the vehicle states of the unmanned vehicles in the return buffer and the unmanned vehicles in the outbound buffer are switched alternately to the coordination area in sequence.

[0149] In one embodiment, when there is only an unmanned vehicle whose vehicle status is the outbound buffer area, the judgment module 22 is also used to determine whether there is an unmanned vehicle whose vehicle status is the off-site waiting area. When there is an unmanned vehicle whose vehicle status is the off-site waiting area, the weight calculation module 23 is also used to calculate the second weight of the target unmanned vehicle in the outbound buffer area and the third weight of the target unmanned vehicle in the off-site waiting area based on the weight model. The scheduling module 24 is also used to switch the vehicle status of the target unmanned vehicle in the outbound buffer area or the off-site waiting area to the coordination area based on the values ​​of the second weight and the third weight.

[0150] In one embodiment, the weight calculation module 23 is also used to obtain a third reference weight of the target unmanned vehicle in the off-site waiting area and the average number of loads of the unmanned vehicle in a specified period to calculate a third weight, wherein the third reference weight includes at least one of a parking space vacancy weight and an area weight.

[0151] As above Figures 1 to 4 , the method for dispatching an unmanned vehicle on a field according to an embodiment of this specification is described. The details mentioned in the above description of the method embodiment are also applicable to the unmanned vehicle on-field dispatching device of the embodiment of this specification. The above unmanned vehicle on-field dispatching device can be implemented by hardware, or by software, or by a combination of hardware and software.

[0152] This application also provides an electronic device, see Figure 6 , Figure 6 Schematic diagram of the structure of an electronic device of the present application. Figure 6 As shown, the electronic device 30 may include at least one processor 31, a memory 32 (e.g., a non-volatile memory), a memory 33, and a communication interface 34, and the at least one processor 31, the memory 32, the memory 33, and the communication interface 34 are connected together via a bus 35. At least one processor 31 executes at least one computer-readable instruction stored or encoded in the memory 32.

[0153] It should be understood that the computer executable instructions stored in the memory 32, when executed, cause at least one processor 31 to perform the above combined operations in various embodiments of the present specification. Figure 1-Figure 4 Describes the various operations and functions.

[0154] In the embodiments of the present specification, the electronic device 30 may include, but is not limited to, personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile electronic devices, smart phones, tablet computers, cellular phones, personal digital assistants (PDAs), handheld devices, messaging devices, wearable electronic devices, consumer electronic devices, and the like.

[0155] According to one embodiment, a program product such as a machine-readable medium is provided. The machine-readable medium may have instructions (i.e., the above-mentioned elements implemented in the form of software), which, when executed by a machine, causes the machine to perform the above-mentioned combination of various embodiments of this specification. Figure 1-Figure 4 Specifically, a system or device equipped with a readable storage medium may be provided, on which a software program code implementing the functions of any of the above-mentioned embodiments is stored, and a computer or processor of the system or device reads and executes the instructions stored in the readable storage medium.

[0156] In this case, the program code itself read from the machine-readable medium can realize the function of any one of the above embodiments, and thus the machine-readable code and the machine-readable storage medium storing the machine-readable code constitute part of this specification.

[0157] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or a cloud via a communication network.

[0158] Those skilled in the art should understand that the various embodiments disclosed above can be modified and altered in various ways without departing from the essence of the invention. Therefore, the protection scope of this specification should be defined by the appended claims.

[0159] It should be noted that not all steps and units in the above-mentioned processes and system structure diagrams are necessary, and some steps or units can be ignored according to actual needs. The execution order of each step is not fixed and can be determined as needed. The device structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some units may be implemented by the same physical client, or some units may be implemented by multiple physical clients, or some components in multiple independent devices may be implemented together.

[0160] In the above embodiments, the hardware unit or module can be realized by mechanical or electrical means. For example, a hardware unit, module or processor can include permanent dedicated circuit or logic (such as special processor, FPGA or ASIC) to complete the corresponding operation. The hardware unit or processor can also include programmable logic or circuit (such as general-purpose processor or other programmable processor), which can be temporarily set by software to complete the corresponding operation. Specific implementation (mechanical method or dedicated permanent circuit or temporary circuit) can be determined based on cost and time consideration.

[0161] The specific embodiments described above in conjunction with the accompanying drawings describe exemplary embodiments, but do not represent all embodiments that can be implemented or fall within the scope of protection of the claims. The term "exemplary" used throughout this specification means "used as an example, instance or illustration" and does not mean "preferred" or "having advantages" over other embodiments. For the purpose of providing an understanding of the described technology, the specific embodiments include specific details. However, these technologies can be implemented without these specific details. In some instances, in order to avoid making the concepts of the described embodiments difficult to understand, well-known structures and devices are shown in block diagram form.

[0162] The above description of the present disclosure is provided to enable any person of ordinary skill in the art to implement or use the present disclosure. Various modifications to the present disclosure will be apparent to those of ordinary skill in the art, and the general principles corresponding to the present disclosure may be applied to other variations without departing from the scope of protection of the present disclosure. Therefore, the present disclosure is not limited to the examples and designs described herein, but is consistent with the widest range of principles and novel features disclosed herein.

Claims

1. A method for dispatching unmanned vehicles on site, characterized in that: include: Acquire the current vehicle state of the unmanned vehicle in the target area, the vehicle state including a return buffer area, a coordination area, and an outbound buffer area, and the vehicle state of the unmanned vehicle can be controlled to switch from the return buffer area to the coordination area, and from the outbound buffer area to the coordination area; Determine whether there are unmanned vehicles whose vehicle status is the return buffer zone and the outbound buffer zone at the same time; If so, based on the weight model, calculate the first weight of the target unmanned vehicle in the return buffer and the second weight of the target unmanned vehicle in the outbound buffer, wherein the weight factors in the weight model include at least one of a parking space vacancy weight, a site distance weight, a busy / idle time weight, a user role weight, and an area weight, the parking space vacancy weight is used to describe the loading demand intensity of the unmanned vehicle in the target area, the site distance weight is used to describe the distance between the unmanned vehicle and the target delivery site, and the busy / idle time weight is used to describe the delivery demand intensity of the unmanned vehicle in the target area; Based on the values ​​of the first weight and the second weight, the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer is switched to the coordination zone.

2. The on-site dispatching method according to claim 1, characterized in that: The vehicle state also includes a loading parking area; the method for calculating the parking space vacancy weight includes: Obtain the number of unmanned vehicles in the loading parking area with a vehicle status of the unmanned vehicle, and obtain the current number of free parking spaces; Based on the current number of free parking spaces, the parking space free weight is determined.

3. The on-site dispatching method according to claim 1, characterized in that: The step of calculating the first weight of the target unmanned vehicle in the return buffer zone comprises: Obtain a first reference weight of the target unmanned vehicle in the return buffer and an average number of loads of the unmanned vehicle in a specified period to calculate the first weight, wherein the first reference weight includes at least one of a parking space vacancy weight and an area weight.

4. The on-site dispatching method according to claim 1, characterized in that: The step of calculating the second weight of the target unmanned vehicle in the outbound buffer zone comprises: Obtain a second reference weight and an actual number of loads of the target unmanned vehicle in the outbound buffer to calculate the second weight, wherein the second reference weight includes at least one of a site distance weight, a busy / off-peak weight, a user role weight, and an area weight.

5. The on-site dispatching method according to claim 1, characterized in that: The target unmanned vehicle in the return buffer is the first unmanned vehicle in the return buffer, and the target unmanned vehicle in the outbound buffer is the first unmanned vehicle in the outbound buffer; The step of switching the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer to the coordination zone based on the values ​​of the first weight and the second weight is specifically: The vehicle state of the target unmanned vehicle with a larger weight is switched to the coordination area.

6. The on-site dispatching method according to claim 1, characterized in that: The target unmanned vehicle in the return buffer is the unmanned vehicle queue in the return buffer, and the target unmanned vehicle in the outbound buffer is the unmanned vehicle queue in the outbound buffer; The step of switching the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer to the coordination zone based on the values ​​of the first weight and the second weight includes: Comparing the sum of the first weights of the unmanned vehicle queue in the return buffer and the sum of the second weights of the unmanned vehicle queue in the outbound buffer; The vehicle states of the unmanned vehicle queue with larger weight are switched to the coordination area in sequence.

7. The on-site dispatching method according to claim 1, characterized in that: The step of calculating the first weight of the target unmanned vehicle in the return buffer and the second weight of the target unmanned vehicle in the outbound buffer based on the weight model also includes: Get the current time and determine whether it is the peak period; If not, the vehicle states of the unmanned vehicle in the return buffer zone and the unmanned vehicle in the outbound buffer zone are switched to the coordination zone in sequence.

8. The on-site dispatching method according to claim 1, characterized in that: The vehicle status also includes an off-site waiting area; When there is only an unmanned vehicle whose vehicle status is the outbound buffer zone, the method further includes: Determine whether there is an unmanned vehicle in the off-site waiting area; If so, based on the weight model, calculate the second weight of the target unmanned vehicle in the outbound buffer zone and the third weight of the target unmanned vehicle in the off-site waiting zone; Based on the values ​​of the second weight and the third weight, the vehicle state of the target unmanned vehicle in the outbound buffer area or the off-site waiting area is switched to the coordination area.

9. The on-site dispatching method according to claim 8, characterized in that: The step of calculating the third weight of the target unmanned vehicle in the off-site waiting area includes: Obtain a third reference weight of the target unmanned vehicle in the off-site waiting area and an average number of loads of the unmanned vehicle in a specified period to calculate the third weight, wherein the third reference weight includes at least one of a parking space vacancy weight and an area weight.

10. An on-site dispatching device for unmanned vehicles, characterized in that: include: A state acquisition module, used to acquire the current vehicle state of the unmanned vehicle in the target area, wherein the vehicle state includes a return buffer zone, a coordination zone, and an outbound buffer zone, and the vehicle state of the unmanned vehicle can be controlled to switch from the return buffer zone to the coordination zone, and from the outbound buffer zone to the coordination zone; A judgment module, used for judging whether there are unmanned vehicles whose vehicle status is the return buffer zone and the outbound buffer zone at the same time; A weight calculation module, for calculating, based on a weight model, a first weight of a target unmanned vehicle in the return buffer and a second weight of a target unmanned vehicle in the outbound buffer when there are unmanned vehicles whose vehicle states are both in the return buffer and the outbound buffer, wherein the weight factors in the weight model include at least one of a parking space vacancy weight, a site distance weight, a busy / idle time weight, a user role weight, and an area weight, wherein the parking space vacancy weight is used to describe the loading demand intensity of the unmanned vehicle in the target area, the site distance weight is used to describe the distance between the unmanned vehicle and the target delivery site, and the busy / idle time weight is used to describe the delivery demand intensity of the unmanned vehicle in the target area; A scheduling module is used to switch the vehicle state of the target unmanned vehicle in the return buffer or the outbound buffer to the coordination area based on the values ​​of the first weight and the second weight.

11. An electronic device, comprising: at least one processor; as well as A memory storing instructions, which, when executed by the at least one processor, enables the at least one processor to execute the on-site dispatching method for an unmanned vehicle as described in any one of claims 1 to 9.

12. A machine-readable storage medium storing executable instructions, which, when executed, enable the machine to execute the on-site dispatching method for unmanned vehicles as described in any one of claims 1 to 9.

Images